{ "schema": "ddc-token-boundary-ledger/1", "runner_id": "THINK_B_2EP_SIX_ARMS_RUNNER_V3", "bindings": { "config_sha256": "3f2dccc79ebaff962851b13c3bfad37d248bc2da8c44418520ccf30eb828f097", "runner_code_sha256": "fd6d1c6403810acc4460e2ce0fb5f4418881387b11f4bd21f7cd21067faa3a0a", "config_schema_sha256": "d6d13eeee42bf04cf34fc68b2fa7a61b316c4543b77d7d779815b8eddf10c099", "python_binary_sha256": "5700a6a7804feb44da6c963ebd1323982478b7ca57478e4e81981c47818453bd", "environment_lock_sha256": "627d4fe088b8f64841b0520ae5bd9dc5c81e9dcd5969b4bd45c9a9910b2f3c01", "base_composite_sha256": "26cbdb468ced4891fee1fffa2be7b7722e5d8d836d0bc986eecd97fa12cd1747", "base_lock_sha256": "9a145eebf5d9df466a5f554c4850290be671acd284e0f703b7dfdb087555858b", "frozen_rows_sha256": "a3872b6c83623ad098a605056257f8414c451bb2beb8ba1025d1ca395de5806b", "ordered_ids_sha256": "e4b37fe0b96d39ed6435a7e607b6a7df82c09c655af90cb2cecda752ecb1f892", "update_plan_sha256": "43812327be005fdc9fcb08e193e82d306aacef1b740168dbd303cb0ea00f0ea5", "data_receipt_sha256": "e66346fb413557929ab53648bc656fb3102557cf3460abb49c7b1c6e7281420d", "decontamination_receipt_sha256": "66c360871b06208ed20e473e57ad0f09c79e4dac1b3124a9461a5b729b487153", "render_receipt_sha256": "e66346fb413557929ab53648bc656fb3102557cf3460abb49c7b1c6e7281420d", "token_bake_sha256": "74234e98afe7498fb5daf1f36ac2d78acc339464f950703b8c019892f982b90b", "continuation_sha256": "74234e98afe7498fb5daf1f36ac2d78acc339464f950703b8c019892f982b90b" }, "completed_optimizer_updates": 977, "next_update_index": 977, "next_ordered_position": 11750, "cumulative_planned_active_tokens": 63999854, "cumulative_realized_active_tokens": 63999854, "optimizer_step_count": 977, "scheduler_step_count": 977, "token_bake": { "enabled": false, "positive_lr_active_tokens": null, "frozen": null, "freeze_digest": null }, "updates": [ { "update_id": 0, "row_count": 8, "row_ids_sha256": "09a5b28b0cbfd8bf577a0c268a03d22c43b7b94c352c7bc57fd574105e3735bd", "input_ids_vector_sha256": "4dfed08746c0ec0e0b432131819bf8f87be3eb70c004ab5c61c96c95afaa7a83", "labels_vector_sha256": "4b484ccb8f1db05b5b85789bd43f86afa2a87b701686df7bc876455e6fc55f02", "planned_active_tokens": 67839, "realized_active_tokens": 67839, "cumulative_start": 0, "cumulative_end": 67839, "loss_sum": 57403.9306640625, "token_normalized_loss": 0.8461789039352363, "grad_norm_before_clip": 0.3969206213951111, "learning_rates_at_step": { "lora": 1.7666447655736694e-06, "row_tokens": 1.7666447655736694e-06 }, "learning_rates_after_step": { "lora": 3.482742537677823e-06, "row_tokens": 3.482742537677823e-06 } }, { "update_id": 1, "row_count": 8, "row_ids_sha256": "7e7395a7c3084285a85205283e7cca7c279babb574df49843a30ac66edb30dbf", "input_ids_vector_sha256": "525b6928df07fa771b5febb266924b3cf32be937caf6b775c2aebb8099c701e7", "labels_vector_sha256": "b7b5b5fe257a090596ccc1a9bb23296b5c41956e23ee21add19fd28020472912", "planned_active_tokens": 65898, "realized_active_tokens": 65898, "cumulative_start": 67839, "cumulative_end": 133737, "loss_sum": 52629.19287109375, "token_normalized_loss": 0.7986462847293355, "grad_norm_before_clip": 0.3650885820388794, "learning_rates_at_step": { "lora": 3.482742537677823e-06, "row_tokens": 3.482742537677823e-06 }, "learning_rates_after_step": { "lora": 5.269725892586728e-06, "row_tokens": 5.269725892586728e-06 } }, { "update_id": 2, "row_count": 9, "row_ids_sha256": "a2e08ebdc19f2f539a3fa8c5b8ee2c2b900b55c6195c9d5791ad5690210cf3e7", "input_ids_vector_sha256": "a3e93f70151794d463cc480019c473efca7dc635bba6518be3e0eb4b5ed8ba88", "labels_vector_sha256": "2d0384729b2da6f4f676477042b8b8194e1b44e4130825228259275c8e42d24f", "planned_active_tokens": 68620, "realized_active_tokens": 68620, "cumulative_start": 133737, "cumulative_end": 202357, "loss_sum": 51882.449462890625, "token_normalized_loss": 0.7560834955244917, "grad_norm_before_clip": 0.34726089239120483, "learning_rates_at_step": { "lora": 5.269725892586728e-06, "row_tokens": 5.269725892586728e-06 }, "learning_rates_after_step": { "lora": 6.909677652890332e-06, "row_tokens": 6.909677652890332e-06 } }, { "update_id": 3, "row_count": 9, "row_ids_sha256": "7312b711ad94bfae1b489a7a2abf50acaa6e95289be119d4730dc3f4e0d1988c", "input_ids_vector_sha256": "ef9986586c7ba8a00f2e62365af26c29c1c17399c8bb17f318d749444f62fbc5", "labels_vector_sha256": "fc54f30d0b685dbf4dea0d8a577ae489c9255023939f1b103b4bab6dcaa60378", "planned_active_tokens": 62974, "realized_active_tokens": 62974, "cumulative_start": 202357, "cumulative_end": 265331, "loss_sum": 47589.0, "token_normalized_loss": 0.7556928256105695, "grad_norm_before_clip": 0.35594141483306885, "learning_rates_at_step": { "lora": 6.909677652890332e-06, "row_tokens": 6.909677652890332e-06 }, "learning_rates_after_step": { "lora": 8.702103728888948e-06, "row_tokens": 8.702103728888948e-06 } }, { "update_id": 4, "row_count": 8, "row_ids_sha256": "41384e02f0a89c101f46efb0ff2b96cead97f1b5cb031fa8b712622b70c9c338", "input_ids_vector_sha256": "4e9dee3088f2f9f6034816f3f7f16d80319fa15a913d8e2a1ed0d36254068656", "labels_vector_sha256": "528fde1384b90d7ac0132fdadf0d532e2a0078f5e2797c366395ae6ab49cee80", "planned_active_tokens": 68829, "realized_active_tokens": 68829, "cumulative_start": 265331, "cumulative_end": 334160, "loss_sum": 49234.31787109375, "token_normalized_loss": 0.7153135723473208, "grad_norm_before_clip": 0.362050861120224, "learning_rates_at_step": { "lora": 8.702103728888948e-06, "row_tokens": 8.702103728888948e-06 }, "learning_rates_after_step": { "lora": 1.0349737798864635e-05, "row_tokens": 1.0349737798864635e-05 } }, { "update_id": 5, "row_count": 9, "row_ids_sha256": "357b687cf3736a6935d55709d71fcacd22de7bc03e27833df7b568c9a4c398cf", "input_ids_vector_sha256": "718446d17c47ac5d92cce76898b5c07c30ee15a9fcbfa64bfc0e5cba7a902e35", "labels_vector_sha256": "fc7d332eada4af0979eb6989a9e177c9a6cc6ec9a105055fcaa9acd8b8db41e5", "planned_active_tokens": 63269, "realized_active_tokens": 63269, "cumulative_start": 334160, "cumulative_end": 397429, "loss_sum": 48278.300048828125, "token_normalized_loss": 0.7630640605798752, "grad_norm_before_clip": 0.3604768216609955, "learning_rates_at_step": { "lora": 1.0349737798864635e-05, "row_tokens": 1.0349737798864635e-05 }, "learning_rates_after_step": { "lora": 1.201263232127367e-05, "row_tokens": 1.201263232127367e-05 } }, { "update_id": 6, "row_count": 10, "row_ids_sha256": "dc5f31b5195c2b21e7271e3fea626214070e25eaa8d2d0fc9bbda4b83a04f9c2", "input_ids_vector_sha256": "ed88788739860ead9ef43b78337fb4c011d07402bd567c7c06af40efe409a31a", "labels_vector_sha256": "2b59596c7c8820e48fc98b688dbac3560b44dba3261491b69396a6cdfc545ab3", "planned_active_tokens": 63855, "realized_active_tokens": 63855, "cumulative_start": 397429, "cumulative_end": 461284, "loss_sum": 42864.444580078125, "token_normalized_loss": 0.6712778103528013, "grad_norm_before_clip": 0.30803459882736206, "learning_rates_at_step": { "lora": 1.201263232127367e-05, "row_tokens": 1.201263232127367e-05 }, "learning_rates_after_step": { "lora": 1.3766985391372011e-05, "row_tokens": 1.3766985391372011e-05 } }, { "update_id": 7, "row_count": 9, "row_ids_sha256": "839ad6c898a6e921bf141404a1875f1a71727b8e668b82d3e22d41ba172addc4", "input_ids_vector_sha256": "a41f420ac0223620096cba853b91c547d2c3899ae636009be81ee3aef096884b", "labels_vector_sha256": "ae55cf52718c23c1330bb137d5247eaee4268e9db37ebb6f67908aa94d3522c7", "planned_active_tokens": 67367, "realized_active_tokens": 67367, "cumulative_start": 461284, "cumulative_end": 528651, "loss_sum": 50522.43469238281, "token_normalized_loss": 0.7499582093960369, "grad_norm_before_clip": 0.2804364562034607, "learning_rates_at_step": { "lora": 1.3766985391372011e-05, "row_tokens": 1.3766985391372011e-05 }, "learning_rates_after_step": { "lora": 1.541758821830572e-05, "row_tokens": 1.541758821830572e-05 } }, { "update_id": 8, "row_count": 9, "row_ids_sha256": "1da21ae87e8d05e304db4ac01c31bdd633271746b85ad471947b74bb8c74d778", "input_ids_vector_sha256": "91db3de017dcded3658700255e8b2d37bc9a690ed54f6fa989f15822342db9c6", "labels_vector_sha256": "2d5031b8dd83b5e2ad8d29cdea54cd21732789135e748b1cad9e2753062ebe82", "planned_active_tokens": 63383, "realized_active_tokens": 63383, "cumulative_start": 528651, "cumulative_end": 592034, "loss_sum": 43485.113037109375, "token_normalized_loss": 0.6860690254028584, "grad_norm_before_clip": 0.2748507261276245, "learning_rates_at_step": { "lora": 1.541758821830572e-05, "row_tokens": 1.541758821830572e-05 }, "learning_rates_after_step": { "lora": 1.7148920401115524e-05, "row_tokens": 1.7148920401115524e-05 } }, { "update_id": 9, "row_count": 9, "row_ids_sha256": "a698ba1b0223ec6b63bc7653b71d84e85b792398543dc63abe4f9d3ccc8ff498", "input_ids_vector_sha256": "7043d208380bda9e3bd9e79b81e3590ec1542f3eba792a28ad210397a0c1d850", "labels_vector_sha256": "6e68e563b79d4777ccae33d97680f713196a88eef1eb1b2b0be6c6e44f541a47", "planned_active_tokens": 66483, "realized_active_tokens": 66483, "cumulative_start": 592034, "cumulative_end": 658517, "loss_sum": 47279.410400390625, "token_normalized_loss": 0.7111503752897828, "grad_norm_before_clip": 0.2957935333251953, "learning_rates_at_step": { "lora": 1.7148920401115524e-05, "row_tokens": 1.7148920401115524e-05 }, "learning_rates_after_step": { "lora": 1.8801684691448495e-05, "row_tokens": 1.8801684691448495e-05 } }, { "update_id": 10, "row_count": 7, "row_ids_sha256": "457b9ca770f353fe2d9aa298949e6267eaaf10cdf6eb4529f9bb67757d136f39", "input_ids_vector_sha256": "42e8b1d7a0d3872db60d00e8c3ef6b4803b567deb0fe7c622898a92062b65914", "labels_vector_sha256": "176fa7ffdf9e77f2742047bbd1ffe75d5d0413f0b1515a52ea7f628b85447c21", "planned_active_tokens": 63466, "realized_active_tokens": 63466, "cumulative_start": 658517, "cumulative_end": 721983, "loss_sum": 41713.806884765625, "token_normalized_loss": 0.6572622645946747, "grad_norm_before_clip": 0.2274179458618164, "learning_rates_at_step": { "lora": 1.8801684691448495e-05, "row_tokens": 1.8801684691448495e-05 }, "learning_rates_after_step": { "lora": 2.0673485953482705e-05, "row_tokens": 2.0673485953482705e-05 } }, { "update_id": 11, "row_count": 10, "row_ids_sha256": "f9b533cd26c4ebe1c696d995b8f2831502b9b3d85d804efcbbc7afd07f063138", "input_ids_vector_sha256": "3b413d8fb71d9b6df3d8f98676322853ec8baa0c332b1d4f0509ead3ef5b21cb", "labels_vector_sha256": "4aefb139602cdf8fbc6799633135110e67ee7ef6e5acddb0987915b44f89bbb9", "planned_active_tokens": 71877, "realized_active_tokens": 71877, "cumulative_start": 721983, "cumulative_end": 793860, "loss_sum": 46688.028076171875, "token_normalized_loss": 0.6495544899783223, "grad_norm_before_clip": 0.2615135908126831, "learning_rates_at_step": { "lora": 2.0673485953482705e-05, "row_tokens": 2.0673485953482705e-05 }, "learning_rates_after_step": { "lora": 2.2315495010274763e-05, "row_tokens": 2.2315495010274763e-05 } }, { "update_id": 12, "row_count": 10, "row_ids_sha256": "aeef4a6043bea6d8c5ed5b0bee523261647886a9d39f0749970cc7f5fce4f966", "input_ids_vector_sha256": "737e0ed9540f2febd2a45afb8ac8560898aa242b1307556dee20a3e0e0745b89", "labels_vector_sha256": "eca4d882f3f403193d833174cb70e072ea3b9c9f2b59e4e895a715dc94fbba23", "planned_active_tokens": 63053, "realized_active_tokens": 63053, "cumulative_start": 793860, "cumulative_end": 856913, "loss_sum": 37408.80700683594, "token_normalized_loss": 0.593291469189982, "grad_norm_before_clip": 0.24505558609962463, "learning_rates_at_step": { "lora": 2.2315495010274763e-05, "row_tokens": 2.2315495010274763e-05 }, "learning_rates_after_step": { "lora": 2.4029691736256674e-05, "row_tokens": 2.4029691736256674e-05 } }, { "update_id": 13, "row_count": 8, "row_ids_sha256": "de2cdf6e49936cd294f931f2fce3c9ae53ab3c4bf9721f87414d72d1bd9e6330", "input_ids_vector_sha256": "1742f061c7fa1070be5b9e87ea6960a54b4a4e98532e4ad89af65daee4a58346", "labels_vector_sha256": "4b3943b1ff1ed1fd29851fdc773f981bd2d32616a6acb88f2890282b3e857268", "planned_active_tokens": 65825, "realized_active_tokens": 65825, "cumulative_start": 856913, "cumulative_end": 922738, "loss_sum": 44622.52575683594, "token_normalized_loss": 0.6778963274870632, "grad_norm_before_clip": 0.24700944125652313, "learning_rates_at_step": { "lora": 2.4029691736256674e-05, "row_tokens": 2.4029691736256674e-05 }, "learning_rates_after_step": { "lora": 2.5643080934304277e-05, "row_tokens": 2.5643080934304277e-05 } }, { "update_id": 14, "row_count": 8, "row_ids_sha256": "148da24cad445fbc96565766c0c9f36a5b02cda125d64d94f2b075b03dd88c4e", "input_ids_vector_sha256": "faf2849a023957bc885971a0b640297684f065d224c3fd707a32abf8f98822dd", "labels_vector_sha256": "22151d4ff21ddc6c0b9b19761d96326f6c5046bef0d94a2b3e7c0f0d387be000", "planned_active_tokens": 61954, "realized_active_tokens": 61954, "cumulative_start": 922738, "cumulative_end": 984692, "loss_sum": 39682.6591796875, "token_normalized_loss": 0.6405181131111389, "grad_norm_before_clip": 0.2520027160644531, "learning_rates_at_step": { "lora": 2.5643080934304277e-05, "row_tokens": 2.5643080934304277e-05 }, "learning_rates_after_step": { "lora": 2.736451726058733e-05, "row_tokens": 2.736451726058733e-05 } }, { "update_id": 15, "row_count": 10, "row_ids_sha256": "49d0c587d8efbcfe865f1a772503dab69fdd88ba4e2260d9182e3058dbf4dae1", "input_ids_vector_sha256": "e91999d1f667c51104daeae23b6c0fa55657a5c7cb6fbff89af850dd363057ae", "labels_vector_sha256": "61447dcc92b68b96f006b3450637b089ca556fdbe0cbf9b5f80dcd849535bfba", "planned_active_tokens": 66103, "realized_active_tokens": 66103, "cumulative_start": 984692, "cumulative_end": 1050795, "loss_sum": 39070.78576660156, "token_normalized_loss": 0.5910591919671053, "grad_norm_before_clip": 0.2029125690460205, "learning_rates_at_step": { "lora": 2.736451726058733e-05, "row_tokens": 2.736451726058733e-05 }, "learning_rates_after_step": { "lora": 2.9085224418494733e-05, "row_tokens": 2.9085224418494733e-05 } }, { "update_id": 16, "row_count": 9, "row_ids_sha256": "ba3176b14e2e3ab697808644db4e7fdbd8420ddfe70338e41a25d7568f51b95b", "input_ids_vector_sha256": "01951d33932ac059e15a53f33eefa4b670d106094ef36e51e2c1879be2c46928", "labels_vector_sha256": "94b735e4d4f8f15ecb38ec040c845fcdfeac9c00fee93f7301ddfdb56ad3a3c5", "planned_active_tokens": 66075, "realized_active_tokens": 66075, "cumulative_start": 1050795, "cumulative_end": 1116870, "loss_sum": 40955.557861328125, "token_normalized_loss": 0.6198343982039822, "grad_norm_before_clip": 0.23115721344947815, "learning_rates_at_step": { "lora": 2.9085224418494733e-05, "row_tokens": 2.9085224418494733e-05 }, "learning_rates_after_step": { "lora": 3.0734967868414274e-05, "row_tokens": 3.0734967868414274e-05 } }, { "update_id": 17, "row_count": 10, "row_ids_sha256": "e01cd9f1cac80111af05586afb2f8e474b35a95e0a380bf04b8afb2886505013", "input_ids_vector_sha256": "bbf778710d5f1ccd7ca2112824df8b6ec9bfa932316252eeb3f40f5af4c42a44", "labels_vector_sha256": "4218d07c2fa738e4312f665e069853ce7e4eb9ef2c1cf73fa3bbb0f828a043d2", "planned_active_tokens": 63350, "realized_active_tokens": 63350, "cumulative_start": 1116870, "cumulative_end": 1180220, "loss_sum": 40173.154541015625, "token_normalized_loss": 0.6341460858881709, "grad_norm_before_clip": 0.23090879619121552, "learning_rates_at_step": { "lora": 3.0734967868414274e-05, "row_tokens": 3.0734967868414274e-05 }, "learning_rates_after_step": { "lora": 3.2493878240860456e-05, "row_tokens": 3.2493878240860456e-05 } }, { "update_id": 18, "row_count": 8, "row_ids_sha256": "258af230d9b1f3b7e1e4bf31294fe84edb76e02f9ec1ad3976952eb0b8394646", "input_ids_vector_sha256": "49b553afe728ef445dcf18981d74e09639fbddbdffb41ddf30b2b01e621dd662", "labels_vector_sha256": "2010cb7ca9da93ad3066c71bff2d4f21173e99558b93f0c2ffd07258937d4966", "planned_active_tokens": 67542, "realized_active_tokens": 67542, "cumulative_start": 1180220, "cumulative_end": 1247762, "loss_sum": 44657.664794921875, "token_normalized_loss": 0.6611836308507577, "grad_norm_before_clip": 0.2440216988325119, "learning_rates_at_step": { "lora": 3.2493878240860456e-05, "row_tokens": 3.2493878240860456e-05 }, "learning_rates_after_step": { "lora": 3.418489782918762e-05, "row_tokens": 3.418489782918762e-05 } }, { "update_id": 19, "row_count": 11, "row_ids_sha256": "bb87bfe2ed5d585b8a02797ef161b8e1193982401137e9f1c63c8e70b4fad60a", "input_ids_vector_sha256": "66a8577b0d624246a0ea8aea796a3f888509dc183acb309446144ea34ce9ab59", "labels_vector_sha256": "26af5deeb8b8e6d1c3f3ae1e01a44f080f731ae061bca4c841cc07c0fe6c4d75", "planned_active_tokens": 64935, "realized_active_tokens": 64935, "cumulative_start": 1247762, "cumulative_end": 1312697, "loss_sum": 42016.788146972656, "token_normalized_loss": 0.6470591845225634, "grad_norm_before_clip": 0.26887932419776917, "learning_rates_at_step": { "lora": 3.418489782918762e-05, "row_tokens": 3.418489782918762e-05 }, "learning_rates_after_step": { "lora": 3.601810525076751e-05, "row_tokens": 3.601810525076751e-05 } }, { "update_id": 20, "row_count": 9, "row_ids_sha256": "93958dddcc8875ecb8b956bda19e9b9279998ed4791d2af068a8b45e466fcb16", "input_ids_vector_sha256": "851f9b7a9bf74eaf9783ff8009c385b984046fe585e61e73d0db5b3f282268d2", "labels_vector_sha256": "6aebea604978f366f2230e20035a23ad8d7f3427dc6d72207ba5726e24f4c6e0", "planned_active_tokens": 70395, "realized_active_tokens": 70395, "cumulative_start": 1312697, "cumulative_end": 1383092, "loss_sum": 45347.38818359375, "token_normalized_loss": 0.6441847884593188, "grad_norm_before_clip": 0.2391330897808075, "learning_rates_at_step": { "lora": 3.601810525076751e-05, "row_tokens": 3.601810525076751e-05 }, "learning_rates_after_step": { "lora": 3.7587926638369726e-05, "row_tokens": 3.7587926638369726e-05 } }, { "update_id": 21, "row_count": 10, "row_ids_sha256": "be1be625db3abb995b967b6f12fdeebe96b07209d3e3749ed7f9f99ad72932bc", "input_ids_vector_sha256": "232465463ac2446773a0b1c94271c55125da1d16eef58db8e58d3cd8e194a3ee", "labels_vector_sha256": "03f32550624e01be50b8e76311629539d7021061437daad92209ef80ceaaa87b", "planned_active_tokens": 60281, "realized_active_tokens": 60281, "cumulative_start": 1383092, "cumulative_end": 1443373, "loss_sum": 38374.52038574219, "token_normalized_loss": 0.6365939580587945, "grad_norm_before_clip": 0.26030898094177246, "learning_rates_at_step": { "lora": 3.7587926638369726e-05, "row_tokens": 3.7587926638369726e-05 }, "learning_rates_after_step": { "lora": 3.929850356420106e-05, "row_tokens": 3.929850356420106e-05 } }, { "update_id": 22, "row_count": 9, "row_ids_sha256": "d68caa69fd81f1065a47ca011fdaf7de3776eaeea7d44fb9dcdf41e36da6a5e5", "input_ids_vector_sha256": "69729dca54b22114bb7611521f37541e48214096f669f58e8a954ba4cc2fb4d5", "labels_vector_sha256": "027dd36ec3501d1d69ba56c81fae9794abafb6f64040aef48df4d05cc817ad52", "planned_active_tokens": 65686, "realized_active_tokens": 65686, "cumulative_start": 1443373, "cumulative_end": 1509059, "loss_sum": 42860.66143798828, "token_normalized_loss": 0.652508318941453, "grad_norm_before_clip": 0.24152226746082306, "learning_rates_at_step": { "lora": 3.929850356420106e-05, "row_tokens": 3.929850356420106e-05 }, "learning_rates_after_step": { "lora": 4.0987361689128964e-05, "row_tokens": 4.0987361689128964e-05 } }, { "update_id": 23, "row_count": 12, "row_ids_sha256": "feac90902ed1c1d7a7d58eaa772c597941c26835247dc06a270c12038124bd4e", "input_ids_vector_sha256": "b6b58bbc9140a6ae8292bd2a71280c30bcb74fd4724ab6f993d00a4eec08cbc1", "labels_vector_sha256": "3493ddd26db2aea75055c1e317bef93cb09c57111ebc4a72854b20034d515634", "planned_active_tokens": 64852, "realized_active_tokens": 64852, "cumulative_start": 1509059, "cumulative_end": 1573911, "loss_sum": 37284.64892578125, "token_normalized_loss": 0.5749190298800538, "grad_norm_before_clip": 0.21494677662849426, "learning_rates_at_step": { "lora": 4.0987361689128964e-05, "row_tokens": 4.0987361689128964e-05 }, "learning_rates_after_step": { "lora": 4.300582996158064e-05, "row_tokens": 4.300582996158064e-05 } }, { "update_id": 24, "row_count": 10, "row_ids_sha256": "b4dd67bbd82c13fe4ef7dfc5d2dfef5b19c9174d3de80ef4a8738e8c1941bad8", "input_ids_vector_sha256": "a8d373a6175d23c8379297f2753de524b054fde6730c4f37ef96584792f1d872", "labels_vector_sha256": "cc5a2bee05e45dc73f5b5a6fcd452d38d447b89ccf3a8cc73817962aec1c35ca", "planned_active_tokens": 77509, "realized_active_tokens": 77509, "cumulative_start": 1573911, "cumulative_end": 1651420, "loss_sum": 50474.64782714844, "token_normalized_loss": 0.6512101540098367, "grad_norm_before_clip": 0.21622566878795624, "learning_rates_at_step": { "lora": 4.300582996158064e-05, "row_tokens": 4.300582996158064e-05 }, "learning_rates_after_step": { "lora": 4.440088531457496e-05, "row_tokens": 4.440088531457496e-05 } }, { "update_id": 25, "row_count": 7, "row_ids_sha256": "cffef72f73831d31a9508b4107337803a4908ea7aa5e9af4626641a6deadcde3", "input_ids_vector_sha256": "4017f9f8fd67bb80a4dfc4dcc3f65fc0cc602548f4ebf1a520629e241bdb5f10", "labels_vector_sha256": "feaed8ed180508d0217fd21499884bc4227e36bb1cf12b90715ad6019d721c7b", "planned_active_tokens": 53570, "realized_active_tokens": 53570, "cumulative_start": 1651420, "cumulative_end": 1704990, "loss_sum": 32758.13427734375, "token_normalized_loss": 0.6115014798832136, "grad_norm_before_clip": 0.2008591592311859, "learning_rates_at_step": { "lora": 4.440088531457496e-05, "row_tokens": 4.440088531457496e-05 }, "learning_rates_after_step": { "lora": 4.6208415592640714e-05, "row_tokens": 4.6208415592640714e-05 } }, { "update_id": 26, "row_count": 11, "row_ids_sha256": "f103af32adf1073b2d80ced986d8ab97fa3c9595e56cb0faf64752fae5f18938", "input_ids_vector_sha256": "ac392b2c42ed07d5e8d124e3a8e912965977c60f448ea8cbb30a60e0951c1de1", "labels_vector_sha256": "10d3914b3915c4ea55f55b352d88678303796d1e238e474cdc2d38665fcf7ce5", "planned_active_tokens": 69409, "realized_active_tokens": 69409, "cumulative_start": 1704990, "cumulative_end": 1774399, "loss_sum": 38383.3994140625, "token_normalized_loss": 0.5530032043980248, "grad_norm_before_clip": 0.1758882701396942, "learning_rates_at_step": { "lora": 4.6208415592640714e-05, "row_tokens": 4.6208415592640714e-05 }, "learning_rates_after_step": { "lora": 4.796581554488019e-05, "row_tokens": 4.796581554488019e-05 } }, { "update_id": 27, "row_count": 7, "row_ids_sha256": "5f0d4e0b4d17a30df426c78348e4805fe13fac4524b6709fe66c881651963436", "input_ids_vector_sha256": "608ba74572a2027dc693a46dc4036b0741166b382165bffa69c3043f13df1109", "labels_vector_sha256": "9ce277b8fe35dc585dca98fc5b702116ed36ad1fe345bad9d12beffdf3373c86", "planned_active_tokens": 67484, "realized_active_tokens": 67484, "cumulative_start": 1774399, "cumulative_end": 1841883, "loss_sum": 43864.883544921875, "token_normalized_loss": 0.6500042016614587, "grad_norm_before_clip": 0.19833891093730927, "learning_rates_at_step": { "lora": 4.796581554488019e-05, "row_tokens": 4.796581554488019e-05 }, "learning_rates_after_step": { "lora": 4.9529543168200135e-05, "row_tokens": 4.9529543168200135e-05 } }, { "update_id": 28, "row_count": 11, "row_ids_sha256": "0f4b4f9c4035ee55b2dd4c84a746e3449c075afd5bc85a0829e982f6fd441b80", "input_ids_vector_sha256": "f8d15b3640303ab4b8cc531cd10bc382cddf451ee7894f77374574225ee4b18f", "labels_vector_sha256": "9fda27c6a221f73bf437d59c68be4af365efdb2970079d194b1e284fd02723f9", "planned_active_tokens": 60047, "realized_active_tokens": 60047, "cumulative_start": 1841883, "cumulative_end": 1901930, "loss_sum": 32812.185302734375, "token_normalized_loss": 0.5464417090401581, "grad_norm_before_clip": 0.17866182327270508, "learning_rates_at_step": { "lora": 4.9529543168200135e-05, "row_tokens": 4.9529543168200135e-05 }, "learning_rates_after_step": { "lora": 5.126118785174236e-05, "row_tokens": 5.126118785174236e-05 } }, { "update_id": 29, "row_count": 10, "row_ids_sha256": "404ab1b2322874233d5d5ccbd2008aad3b70690a26f94ffd11eeb8ba0252d952", "input_ids_vector_sha256": "10fe4d3239dd23f84b533f711a03ebe4b22bfa05073692fddce0726ec991f9e3", "labels_vector_sha256": "3e632dbd5a6cbf216c3764b48c32a3f6c446c1520a468e2ea6f1db0105a8ce59", "planned_active_tokens": 66495, "realized_active_tokens": 66495, "cumulative_start": 1901930, "cumulative_end": 1968425, "loss_sum": 41039.58056640625, "token_normalized_loss": 0.6171829546041996, "grad_norm_before_clip": 0.17919136583805084, "learning_rates_at_step": { "lora": 5.126118785174236e-05, "row_tokens": 5.126118785174236e-05 }, "learning_rates_after_step": { "lora": 5.298377001404431e-05, "row_tokens": 5.298377001404431e-05 } }, { "update_id": 30, "row_count": 12, "row_ids_sha256": "b0adb750a137382edd285feed68c8e5e67fcdcf1f1281e44047baaeb22c5ae29", "input_ids_vector_sha256": "eb5d3903e0c23db58ca8099855a847e9ae075122d9bd3d2f413d1dd7942e6e69", "labels_vector_sha256": "21051390ab101a120db4781aebabb2d340bb31d943f538fa4d8cf536e2c6d668", "planned_active_tokens": 66147, "realized_active_tokens": 66147, "cumulative_start": 1968425, "cumulative_end": 2034572, "loss_sum": 38551.80261230469, "token_normalized_loss": 0.5828201220358397, "grad_norm_before_clip": 0.18849460780620575, "learning_rates_at_step": { "lora": 5.298377001404431e-05, "row_tokens": 5.298377001404431e-05 }, "learning_rates_after_step": { "lora": 5.474848769176804e-05, "row_tokens": 5.474848769176804e-05 } }, { "update_id": 31, "row_count": 10, "row_ids_sha256": "9b00ede76d848979aaf06059eb1ca6fcb037521cb89c27240d4a7ac37c0a1221", "input_ids_vector_sha256": "9bbb78a0529dd7928136c5bec2e54919ce854b267b1c97e1cc2b3ab8da1ad7c3", "labels_vector_sha256": "d1804845b00b58153fcf5f85de3cf987bf0e2f0f75da00400383b95ccdf41103", "planned_active_tokens": 67765, "realized_active_tokens": 67765, "cumulative_start": 2034572, "cumulative_end": 2102337, "loss_sum": 36207.52917480469, "token_normalized_loss": 0.5343101774486045, "grad_norm_before_clip": 0.1806352138519287, "learning_rates_at_step": { "lora": 5.474848769176804e-05, "row_tokens": 5.474848769176804e-05 }, "learning_rates_after_step": { "lora": 5.637195503843629e-05, "row_tokens": 5.637195503843629e-05 } }, { "update_id": 32, "row_count": 10, "row_ids_sha256": "8567df32e50dbb6ae43cb70c4349df9455e20867977660d4d4f69ff20bb0cf94", "input_ids_vector_sha256": "e776eff592d05ff1624d6a498d9b7c2314536b031006ee17ca0b2a95946e0021", "labels_vector_sha256": "ee37d3ae5ca8b76edec2f363c4be5be78e97c1874752a493aa99a7bbd43bfebd", "planned_active_tokens": 62341, "realized_active_tokens": 62341, "cumulative_start": 2102337, "cumulative_end": 2164678, "loss_sum": 36946.00720214844, "token_normalized_loss": 0.5926438010642825, "grad_norm_before_clip": 0.1897186040878296, "learning_rates_at_step": { "lora": 5.637195503843629e-05, "row_tokens": 5.637195503843629e-05 }, "learning_rates_after_step": { "lora": 5.806177670728916e-05, "row_tokens": 5.806177670728916e-05 } }, { "update_id": 33, "row_count": 11, "row_ids_sha256": "99b2a34beec199ded6398013936e05633a8c3f939e96b69c917531eee82d4a8c", "input_ids_vector_sha256": "3576d1d4cd1e2cd799725522c32c3a459912c7d2a942456536b9b1176ea1bf4b", "labels_vector_sha256": "225e04bcc37b99a85e9bdc226877ec0a74829be5f577fd7d8e1ec7ddca912765", "planned_active_tokens": 64889, "realized_active_tokens": 64889, "cumulative_start": 2164678, "cumulative_end": 2229567, "loss_sum": 36003.9931640625, "token_normalized_loss": 0.5548551089408451, "grad_norm_before_clip": 0.17424215376377106, "learning_rates_at_step": { "lora": 5.806177670728916e-05, "row_tokens": 5.806177670728916e-05 }, "learning_rates_after_step": { "lora": 5.980581725321752e-05, "row_tokens": 5.980581725321752e-05 } }, { "update_id": 34, "row_count": 13, "row_ids_sha256": "6875f37112b5ca66e700dd52c149fa32e3df7862b2e4de7afb6a17d6943c04e1", "input_ids_vector_sha256": "e8aed701fc0db4ef566b8b71fde0b092c80d1305e737e2c57ad1f943799bef46", "labels_vector_sha256": "93649d226332cab4e28fa2d3d1e57204ded7fe4f1a45f694f8af74f026334afe", "planned_active_tokens": 66971, "realized_active_tokens": 66971, "cumulative_start": 2229567, "cumulative_end": 2296538, "loss_sum": 35234.13787841797, "token_normalized_loss": 0.5261103743175101, "grad_norm_before_clip": 0.16642823815345764, "learning_rates_at_step": { "lora": 5.980581725321752e-05, "row_tokens": 5.980581725321752e-05 }, "learning_rates_after_step": { "lora": 6.158420683798478e-05, "row_tokens": 6.158420683798478e-05 } }, { "update_id": 35, "row_count": 12, "row_ids_sha256": "ef39b240b46bb9092247188ba17b1655b93f78c2be8a50d8c66d0d9f80c056b1", "input_ids_vector_sha256": "10b81fc60e3b10198aed1779ea06a57f45fd1aa73cb50d4f019fc006f0c26255", "labels_vector_sha256": "dc1679be08ba490a3491806617d7c0ca26d70ee221eb65f019bfcc63bbb7c777", "planned_active_tokens": 68290, "realized_active_tokens": 68290, "cumulative_start": 2296538, "cumulative_end": 2364828, "loss_sum": 35480.79455566406, "token_normalized_loss": 0.5195606173036178, "grad_norm_before_clip": 0.18569456040859222, "learning_rates_at_step": { "lora": 6.158420683798478e-05, "row_tokens": 6.158420683798478e-05 }, "learning_rates_after_step": { "lora": 6.315233551328636e-05, "row_tokens": 6.315233551328636e-05 } }, { "update_id": 36, "row_count": 11, "row_ids_sha256": "0c65896a253462d54e715fde41071f77a84478d5ddbe9dc77aad41afe5f8c71a", "input_ids_vector_sha256": "8bd2a088cdc0c57f665c87908c7375dc7e552d0fc4846923fe8c66d142a557ca", "labels_vector_sha256": "052bb449578478d085c098e794878d48d7b03b2ab47714682486df4c6aa5f11d", "planned_active_tokens": 60216, "realized_active_tokens": 60216, "cumulative_start": 2364828, "cumulative_end": 2425044, "loss_sum": 32505.725158691406, "token_normalized_loss": 0.5398187385195198, "grad_norm_before_clip": 0.17586398124694824, "learning_rates_at_step": { "lora": 6.315233551328636e-05, "row_tokens": 6.315233551328636e-05 }, "learning_rates_after_step": { "lora": 6.492174070199644e-05, "row_tokens": 6.492174070199644e-05 } }, { "update_id": 37, "row_count": 11, "row_ids_sha256": "8f3bba94d0e5112a82a56dfa2512d8ea15799fd1c1356d9ebe715dfd4ac6fad3", "input_ids_vector_sha256": "4155f85a856ee9bdd1f4e1fc8e4f2bcf3f7300ce7f0299cb7b52a9189edb86f5", "labels_vector_sha256": "44649a1a8e2340cf3c212a1c8a2ee8237fefe86e2f8456be6cb5286b1455294f", "planned_active_tokens": 67945, "realized_active_tokens": 67945, "cumulative_start": 2425044, "cumulative_end": 2492989, "loss_sum": 43409.192138671875, "token_normalized_loss": 0.6388872196434157, "grad_norm_before_clip": 0.19625578820705414, "learning_rates_at_step": { "lora": 6.492174070199644e-05, "row_tokens": 6.492174070199644e-05 }, "learning_rates_after_step": { "lora": 6.670697926114931e-05, "row_tokens": 6.670697926114931e-05 } }, { "update_id": 38, "row_count": 12, "row_ids_sha256": "7f051c974da1eb4411f14b55654c65a51bf5b345cc8342672fb1062fc9d5635d", "input_ids_vector_sha256": "f5b332d55e353703fffd6e33cf0765a27c7f3f1cea31535443983146e5813046", "labels_vector_sha256": "cd298d4bfb9b8dd3015437f064b58b241a683450ece886b0067f1bd2a63ad480", "planned_active_tokens": 68553, "realized_active_tokens": 68553, "cumulative_start": 2492989, "cumulative_end": 2561542, "loss_sum": 36043.786865234375, "token_normalized_loss": 0.5257798617891905, "grad_norm_before_clip": 0.17000406980514526, "learning_rates_at_step": { "lora": 6.670697926114931e-05, "row_tokens": 6.670697926114931e-05 }, "learning_rates_after_step": { "lora": 6.83228424233286e-05, "row_tokens": 6.83228424233286e-05 } }, { "update_id": 39, "row_count": 10, "row_ids_sha256": "510a40af6132f3604b92cdb85d5260b0eb34d67a9fa2fd1637832b87d706fbf1", "input_ids_vector_sha256": "1e2811e8497d88ed20fdce0af064ac6148b5d0cb262eb1fedb6f8e4066acc2c7", "labels_vector_sha256": "3c54f0e1458d75327fc74ae6193c342b3af4b259912682ca7a98f89969f35284", "planned_active_tokens": 62049, "realized_active_tokens": 62049, "cumulative_start": 2561542, "cumulative_end": 2623591, "loss_sum": 30551.934204101562, "token_normalized_loss": 0.4923839901384642, "grad_norm_before_clip": 0.16343837976455688, "learning_rates_at_step": { "lora": 6.83228424233286e-05, "row_tokens": 6.83228424233286e-05 }, "learning_rates_after_step": { "lora": 7.001276825909228e-05, "row_tokens": 7.001276825909228e-05 } }, { "update_id": 40, "row_count": 9, "row_ids_sha256": "7f6bb3de7f695cd8fec54b65795ec31cb59f8815a49a0db9ff109f09a0fd39da", "input_ids_vector_sha256": "3ed0204e33c2955022a804f0116fc4945d98b79b91d90abe61544a3b40463708", "labels_vector_sha256": "11b3dc09395ae3a6fa42eb5064c1636b40be76959d3482477cffe80ea4d3b79a", "planned_active_tokens": 64893, "realized_active_tokens": 64893, "cumulative_start": 2623591, "cumulative_end": 2688484, "loss_sum": 36839.9609375, "token_normalized_loss": 0.5677031565423081, "grad_norm_before_clip": 0.18231543898582458, "learning_rates_at_step": { "lora": 7.001276825909228e-05, "row_tokens": 7.001276825909228e-05 }, "learning_rates_after_step": { "lora": 7.180683496393612e-05, "row_tokens": 7.180683496393612e-05 } }, { "update_id": 41, "row_count": 10, "row_ids_sha256": "d5f4693b3907f57459720577f6800c2d9abd9fd0d7d8c3978082f184424684b8", "input_ids_vector_sha256": "2789d2015bf999b4531a1695c2752d48c427eb1aaa86cfa29e42ef5f35c9e880", "labels_vector_sha256": "bc35657c31923a32759facdf2fae83e88884af8ac9039bea55793839bcdf916f", "planned_active_tokens": 68892, "realized_active_tokens": 68892, "cumulative_start": 2688484, "cumulative_end": 2757376, "loss_sum": 36186.73083496094, "token_normalized_loss": 0.5252675322963615, "grad_norm_before_clip": 0.16318684816360474, "learning_rates_at_step": { "lora": 7.180683496393612e-05, "row_tokens": 7.180683496393612e-05 }, "learning_rates_after_step": { "lora": 7.34438179672817e-05, "row_tokens": 7.34438179672817e-05 } }, { "update_id": 42, "row_count": 11, "row_ids_sha256": "801da2a1e041b636eb55826ef03d03943a97b2907f7fcc7688302b68ef7ed0bd", "input_ids_vector_sha256": "1e3b54cd228f6c7500bed04c295eade2da12a7fafe4a4a61e62de160b811bd86", "labels_vector_sha256": "a1754f207825bffc5ab7a455f69a009ec68d12efa37e4f403524d962e2cd47d8", "planned_active_tokens": 62860, "realized_active_tokens": 62860, "cumulative_start": 2757376, "cumulative_end": 2820236, "loss_sum": 31526.010620117188, "token_normalized_loss": 0.5015273722576709, "grad_norm_before_clip": 0.1709180325269699, "learning_rates_at_step": { "lora": 7.34438179672817e-05, "row_tokens": 7.34438179672817e-05 }, "learning_rates_after_step": { "lora": 7.512280627741055e-05, "row_tokens": 7.512280627741055e-05 } }, { "update_id": 43, "row_count": 9, "row_ids_sha256": "b4de5e689329a4a8e71a4f175165247f9df3921f43f07c4bf2f32d969f9bb186", "input_ids_vector_sha256": "e14f93358788b8ce720f214952d573fc8e317e1f0222a7991dd31eb0ce27b7b6", "labels_vector_sha256": "1f244e1a2aaf989aeb43a4447cc3ae8a5c9790b379efa8bf2c80a9a724c37daf", "planned_active_tokens": 64473, "realized_active_tokens": 64473, "cumulative_start": 2820236, "cumulative_end": 2884709, "loss_sum": 37286.134033203125, "token_normalized_loss": 0.5783216855614463, "grad_norm_before_clip": 0.17968891561031342, "learning_rates_at_step": { "lora": 7.512280627741055e-05, "row_tokens": 7.512280627741055e-05 }, "learning_rates_after_step": { "lora": 7.685830513665267e-05, "row_tokens": 7.685830513665267e-05 } }, { "update_id": 44, "row_count": 12, "row_ids_sha256": "14aca6045177ac5ada17e6f3168c263e6875f1846a609b515f597dcfa974dab4", "input_ids_vector_sha256": "467e70a70f5f2f3488788f33782af4fc1c72c5467304a638310e0e6665b61427", "labels_vector_sha256": "e10997d03626eef0eca73d64421e2348d550339747e281567b7a7564e487025f", "planned_active_tokens": 66643, "realized_active_tokens": 66643, "cumulative_start": 2884709, "cumulative_end": 2951352, "loss_sum": 33910.677673339844, "token_normalized_loss": 0.5088408035853704, "grad_norm_before_clip": 0.15913020074367523, "learning_rates_at_step": { "lora": 7.685830513665267e-05, "row_tokens": 7.685830513665267e-05 }, "learning_rates_after_step": { "lora": 7.85740643662967e-05, "row_tokens": 7.85740643662967e-05 } }, { "update_id": 45, "row_count": 9, "row_ids_sha256": "949b75e52a70e5cf06d713b1538f6485e49de7ac8bf966117804a3b495fc6b8a", "input_ids_vector_sha256": "47666c9d255c6b62d0a9a7754293d0b61cfbdb9b9bd736c610f8949fc974fad5", "labels_vector_sha256": "4fea8d56d1bf29f73887ec3df88fe5d8a5bae1bbc2fa6a3c2d051b3e6e801ddc", "planned_active_tokens": 65885, "realized_active_tokens": 65885, "cumulative_start": 2951352, "cumulative_end": 3017237, "loss_sum": 34943.39794921875, "token_normalized_loss": 0.530369552238275, "grad_norm_before_clip": 0.1645393818616867, "learning_rates_at_step": { "lora": 7.85740643662967e-05, "row_tokens": 7.85740643662967e-05 }, "learning_rates_after_step": { "lora": 8.03357872453347e-05, "row_tokens": 8.03357872453347e-05 } }, { "update_id": 46, "row_count": 11, "row_ids_sha256": "d8e95af9bd48895dbdbbf63748654723e67afba009de1d5560f858d01c6e56d9", "input_ids_vector_sha256": "7799ae62d684a918996596caf48bca712fd44ae4b480c74f1e9355ac090de922", "labels_vector_sha256": "27b3fab88ca785c33a6ace4bc86fab944edfb80db10682fa90fcfe82da956ad2", "planned_active_tokens": 67650, "realized_active_tokens": 67650, "cumulative_start": 3017237, "cumulative_end": 3084887, "loss_sum": 35122.20098876953, "token_normalized_loss": 0.5191751809130751, "grad_norm_before_clip": 0.1641765832901001, "learning_rates_at_step": { "lora": 8.03357872453347e-05, "row_tokens": 8.03357872453347e-05 }, "learning_rates_after_step": { "lora": 8.19770931754788e-05, "row_tokens": 8.19770931754788e-05 } }, { "update_id": 47, "row_count": 8, "row_ids_sha256": "a3d1bf74eb7b32df586a28819e471b1e239a32887843b352007b8e7b0c7a2eb9", "input_ids_vector_sha256": "0b64dadd918f37279024f10092001ac2aa5c2d354307c088c14dc9831d1f3ff1", "labels_vector_sha256": "f8450556b67c1abceb8685e06009f1303968b179101c0420783a644004613bf7", "planned_active_tokens": 63026, "realized_active_tokens": 63026, "cumulative_start": 3084887, "cumulative_end": 3147913, "loss_sum": 33533.98876953125, "token_normalized_loss": 0.5320659532499484, "grad_norm_before_clip": 0.1714269369840622, "learning_rates_at_step": { "lora": 8.19770931754788e-05, "row_tokens": 8.19770931754788e-05 }, "learning_rates_after_step": { "lora": 8.370134200835366e-05, "row_tokens": 8.370134200835366e-05 } }, { "update_id": 48, "row_count": 12, "row_ids_sha256": "5b390f49943e09194ecff766179708e8d92aa56e76897c4d611ecc992bd65afe", "input_ids_vector_sha256": "8b6e18c8cf628b357f910334b1f64917917852d413b62856ae88fceeab8573f3", "labels_vector_sha256": "c6b6fcf4ece266b66dab97e4662f8164b87637794a54aedcb7786fe541b1455d", "planned_active_tokens": 66211, "realized_active_tokens": 66211, "cumulative_start": 3147913, "cumulative_end": 3214124, "loss_sum": 36051.64453125, "token_normalized_loss": 0.5444963001804836, "grad_norm_before_clip": 0.18432076275348663, "learning_rates_at_step": { "lora": 8.370134200835366e-05, "row_tokens": 8.370134200835366e-05 }, "learning_rates_after_step": { "lora": 8.546811698256585e-05, "row_tokens": 8.546811698256585e-05 } }, { "update_id": 49, "row_count": 9, "row_ids_sha256": "41dbf09209f4a11d9444152c4be786dbca1608dd8401d6767d4ae2f3054b7768", "input_ids_vector_sha256": "21118bf04ece4b25a987c1c2207b1b3cfd933e69c9794a2df9b4769953fcd6c2", "labels_vector_sha256": "e95220555f63a2ec687eaa74aa1526184231df73426570f9661fdd2bdaa7d700", "planned_active_tokens": 67844, "realized_active_tokens": 67844, "cumulative_start": 3214124, "cumulative_end": 3281968, "loss_sum": 38600.31884765625, "token_normalized_loss": 0.5689570020584908, "grad_norm_before_clip": 0.18976490199565887, "learning_rates_at_step": { "lora": 8.546811698256585e-05, "row_tokens": 8.546811698256585e-05 }, "learning_rates_after_step": { "lora": 8.713900631537939e-05, "row_tokens": 8.713900631537939e-05 } }, { "update_id": 50, "row_count": 12, "row_ids_sha256": "e77b7f9ffdec70a1d36edb035842fc0f2bf981b00c86f25d4793136d65c6987f", "input_ids_vector_sha256": "7ae866e0953217fc1a1cce9d136c9dd67f3e101a1d3a8a93bdf178fab6743955", "labels_vector_sha256": "574631c0e0c72f61a87b5de83462802fcc461486db96fc4a5a980ebf4c9ef5fb", "planned_active_tokens": 64162, "realized_active_tokens": 64162, "cumulative_start": 3281968, "cumulative_end": 3346130, "loss_sum": 34510.82312011719, "token_normalized_loss": 0.5378701274916179, "grad_norm_before_clip": 0.17181485891342163, "learning_rates_at_step": { "lora": 8.713900631537939e-05, "row_tokens": 8.713900631537939e-05 }, "learning_rates_after_step": { "lora": 8.885520825439435e-05, "row_tokens": 8.885520825439435e-05 } }, { "update_id": 51, "row_count": 13, "row_ids_sha256": "39dda80c358f117a2ea854d9e51bf9ebf2f09e9e1fe0be5c40c6224da4fbf3cc", "input_ids_vector_sha256": "04338c91f1243dbdc8cbee093885ac27dc87557147de1c5de2de9e796f9d3a87", "labels_vector_sha256": "32e4aaad7537d994e63ecdd90ee6adcb33ad7b4e1de87a075bad0b9c82429a2c", "planned_active_tokens": 65902, "realized_active_tokens": 65902, "cumulative_start": 3346130, "cumulative_end": 3412032, "loss_sum": 30129.23504638672, "token_normalized_loss": 0.45718240791458103, "grad_norm_before_clip": 0.17543651163578033, "learning_rates_at_step": { "lora": 8.885520825439435e-05, "row_tokens": 8.885520825439435e-05 }, "learning_rates_after_step": { "lora": 9.048792041439681e-05, "row_tokens": 9.048792041439681e-05 } }, { "update_id": 52, "row_count": 9, "row_ids_sha256": "098ef270dfad8ab1872ba39b29b3f76abe66c376db4978a8c69deef3d41a8b2e", "input_ids_vector_sha256": "3ffa497ecdd4d36d6b65ab51b363e2f3646c6c61c9384f7c332bf639815ce039", "labels_vector_sha256": "9c323cc9d4f136d33d0abf38f18c8981a6dff33779237648b94713d399b84c1e", "planned_active_tokens": 62696, "realized_active_tokens": 62696, "cumulative_start": 3412032, "cumulative_end": 3474728, "loss_sum": 27527.536987304688, "token_normalized_loss": 0.4390636880710841, "grad_norm_before_clip": 0.2949720025062561, "learning_rates_at_step": { "lora": 9.048792041439681e-05, "row_tokens": 9.048792041439681e-05 }, "learning_rates_after_step": { "lora": 9.21926639932229e-05, "row_tokens": 9.21926639932229e-05 } }, { "update_id": 53, "row_count": 13, "row_ids_sha256": "e37932b4ccba05b482a01b7453764d596f7dca8999025f936e864c420259b8e5", "input_ids_vector_sha256": "714c0e7fa2dd995b9903f3a740b96fb74e65ffb463439cda8cb0e97b3ad6238a", "labels_vector_sha256": "9fc1ddaa37d57bac88eca1f3fec5cd004fe17edb940e73df5bc7542e06e007c6", "planned_active_tokens": 65462, "realized_active_tokens": 65462, "cumulative_start": 3474728, "cumulative_end": 3540190, "loss_sum": 28044.682678222656, "token_normalized_loss": 0.42841163848068586, "grad_norm_before_clip": 0.15824459493160248, "learning_rates_at_step": { "lora": 9.21926639932229e-05, "row_tokens": 9.21926639932229e-05 }, "learning_rates_after_step": { "lora": 9.389131380776675e-05, "row_tokens": 9.389131380776675e-05 } }, { "update_id": 54, "row_count": 8, "row_ids_sha256": "184096b67dc9f9dc6a626da47dabc0d14c4515f3847282bc86c99c390f2fa0d7", "input_ids_vector_sha256": "571a02dd410a15e0ed764c6cd33ec24fa16757a59a234cc24ba109217129eb5a", "labels_vector_sha256": "5c37a1ab4b662784c21f7bf7088aff578660b836d3a9683892ec1f79877facf1", "planned_active_tokens": 65228, "realized_active_tokens": 65228, "cumulative_start": 3540190, "cumulative_end": 3605418, "loss_sum": 31633.38836669922, "token_normalized_loss": 0.4849664004215861, "grad_norm_before_clip": 0.16227945685386658, "learning_rates_at_step": { "lora": 9.389131380776675e-05, "row_tokens": 9.389131380776675e-05 }, "learning_rates_after_step": { "lora": 9.566275025123758e-05, "row_tokens": 9.566275025123758e-05 } }, { "update_id": 55, "row_count": 9, "row_ids_sha256": "5a0ac52c3dcd6425a0c3a443392242394c39d30bc3a33a3eac7a7eb8cb3395bd", "input_ids_vector_sha256": "39ae135ee966edc12daf3261201c681832e0a4d0a61412ffb225a612f1118075", "labels_vector_sha256": "856868fee380b12b3d384f486806ff748bedd83ae8d00852b477b9b151e1ccdc", "planned_active_tokens": 68023, "realized_active_tokens": 68023, "cumulative_start": 3605418, "cumulative_end": 3673441, "loss_sum": 32620.216552734375, "token_normalized_loss": 0.4795468672762797, "grad_norm_before_clip": 0.16977475583553314, "learning_rates_at_step": { "lora": 9.566275025123758e-05, "row_tokens": 9.566275025123758e-05 }, "learning_rates_after_step": { "lora": 9.736343132054216e-05, "row_tokens": 9.736343132054216e-05 } }, { "update_id": 56, "row_count": 12, "row_ids_sha256": "e142e3e41f144a56187120d1be9d203c90991783b66aa89a9ee734e490408e3c", "input_ids_vector_sha256": "ac3e2ce5cb1bcefc71e4dd20d47411c5db41dac92374d38b2718aa0dbaeb0a90", "labels_vector_sha256": "57c9294b6558a7ca93caf96e703902bd63a52352a6d72e983d5024e0e88697b7", "planned_active_tokens": 65306, "realized_active_tokens": 65306, "cumulative_start": 3673441, "cumulative_end": 3738747, "loss_sum": 31506.511291503906, "token_normalized_loss": 0.4824443587343262, "grad_norm_before_clip": 0.17646987736225128, "learning_rates_at_step": { "lora": 9.736343132054216e-05, "row_tokens": 9.736343132054216e-05 }, "learning_rates_after_step": { "lora": 9.907309678590394e-05, "row_tokens": 9.907309678590394e-05 } }, { "update_id": 57, "row_count": 9, "row_ids_sha256": "c0a8db473751114b84bb91b68b900899a46073fc8ccd3bacf0a6a0d0ee95d751", "input_ids_vector_sha256": "f14267dab05de9c272944c402702f2c8d82b2564319aa66a2be593e241d7807c", "labels_vector_sha256": "c67276185699fd4b1040f68e050ba7083bc28da3a5cd982e41ead7a1d77d1b1c", "planned_active_tokens": 65651, "realized_active_tokens": 65651, "cumulative_start": 3738747, "cumulative_end": 3804398, "loss_sum": 30207.182739257812, "token_normalized_loss": 0.4601176332311437, "grad_norm_before_clip": 0.17495335638523102, "learning_rates_at_step": { "lora": 9.907309678590394e-05, "row_tokens": 9.907309678590394e-05 }, "learning_rates_after_step": { "lora": 9.9999904685253e-05, "row_tokens": 9.9999904685253e-05 } }, { "update_id": 58, "row_count": 12, "row_ids_sha256": "05da0e6a37f40b3b70d575996863d59bf95099c50a2f13478c312ce1dc51bc03", "input_ids_vector_sha256": "90acef6c607ded20cddb4a34a1ea6d7734b24a207bd37cb633561d11da4e309c", "labels_vector_sha256": "712845587a82afc169d0925a914ad5f1b1bf91a8073e49f06c7d534da6e2bd7d", "planned_active_tokens": 72984, "realized_active_tokens": 72984, "cumulative_start": 3804398, "cumulative_end": 3877382, "loss_sum": 37222.687438964844, "token_normalized_loss": 0.5100116112978851, "grad_norm_before_clip": 0.1672561913728714, "learning_rates_at_step": { "lora": 9.9999904685253e-05, "row_tokens": 9.9999904685253e-05 }, "learning_rates_after_step": { "lora": 9.999940120177828e-05, "row_tokens": 9.999940120177828e-05 } }, { "update_id": 59, "row_count": 8, "row_ids_sha256": "91326c35f40bd8b04cc66376786f68185ae19340df78f6f4d890303b1be42603", "input_ids_vector_sha256": "185a18f3d91476578e8ff91bf68af2583b34f57bfa8ceb508b2505e40e150f8e", "labels_vector_sha256": "8a40cdd6a6fdd48ba90f1a1ea6aec9dce2cf48df7223a5885cc6b574386c48fe", "planned_active_tokens": 56328, "realized_active_tokens": 56328, "cumulative_start": 3877382, "cumulative_end": 3933710, "loss_sum": 25198.958862304688, "token_normalized_loss": 0.4473611500906243, "grad_norm_before_clip": 0.22643113136291504, "learning_rates_at_step": { "lora": 9.999940120177828e-05, "row_tokens": 9.999940120177828e-05 }, "learning_rates_after_step": { "lora": 9.99981963471111e-05, "row_tokens": 9.99981963471111e-05 } }, { "update_id": 60, "row_count": 11, "row_ids_sha256": "e8e077e6ddeed74c051f8772d9f1f4282e459b31371cf887706811c7227e11f1", "input_ids_vector_sha256": "5656eefc22b7114b37cbb8f5b18b2a22c303eb7211a3f4acf9e6c13327d67588", "labels_vector_sha256": "76e1240dc83c13c3953e50348ec26591b7e387fcb570879a0d90e79fdccbbcc6", "planned_active_tokens": 68935, "realized_active_tokens": 68935, "cumulative_start": 3933710, "cumulative_end": 4002645, "loss_sum": 37610.2431640625, "token_normalized_loss": 0.5455899494315297, "grad_norm_before_clip": 0.17891603708267212, "learning_rates_at_step": { "lora": 9.99981963471111e-05, "row_tokens": 9.99981963471111e-05 }, "learning_rates_after_step": { "lora": 9.999658846977373e-05, "row_tokens": 9.999658846977373e-05 } }, { "update_id": 61, "row_count": 11, "row_ids_sha256": "f98aa0e1d5460a2a7550feeeeefe4e625ab6ff33a8ed6febab6257a72c5c8b0d", "input_ids_vector_sha256": "9f7a4ba1466f31951c21fbdada1f40358923f1bd358508caedf4f6b869462e62", "labels_vector_sha256": "fa381a27c95bc5520bec7adf344e56688a8ef1a5b8137488cab0df23b70920b1", "planned_active_tokens": 61045, "realized_active_tokens": 61045, "cumulative_start": 4002645, "cumulative_end": 4063690, "loss_sum": 30327.907836914062, "token_normalized_loss": 0.4968123161096578, "grad_norm_before_clip": 0.16830290853977203, "learning_rates_at_step": { "lora": 9.999658846977373e-05, "row_tokens": 9.999658846977373e-05 }, "learning_rates_after_step": { "lora": 9.999419283922117e-05, "row_tokens": 9.999419283922117e-05 } }, { "update_id": 62, "row_count": 9, "row_ids_sha256": "4affc62634c4fe37e5ddcf26b2781fe98c3002754064eea27d2e0d3610f3e993", "input_ids_vector_sha256": "bbb0216e3a871cb2815158fc7988fea10759550db40ef9f1eee0786909da0640", "labels_vector_sha256": "a4efa08d364912d9be80f96fd87c67cd6b37f9e4c2b0e3b402486d5a6d27137f", "planned_active_tokens": 68160, "realized_active_tokens": 68160, "cumulative_start": 4063690, "cumulative_end": 4131850, "loss_sum": 39506.96325683594, "token_normalized_loss": 0.5796209398009967, "grad_norm_before_clip": 0.1860145926475525, "learning_rates_at_step": { "lora": 9.999419283922117e-05, "row_tokens": 9.999419283922117e-05 }, "learning_rates_after_step": { "lora": 9.999103811778758e-05, "row_tokens": 9.999103811778758e-05 } }, { "update_id": 63, "row_count": 12, "row_ids_sha256": "4cec778c462902a0c17010263589b7c1dd98a50eb74b969f5e623742934a5b6f", "input_ids_vector_sha256": "e0efbd9d2a9379f9c8f076ae8d3c8badc65141bd6aa73c81d345eb724b732cff", "labels_vector_sha256": "06fb4522117bd6c02bf3a84210814920d5a39ca69e6166dc0ce2f73076d15609", "planned_active_tokens": 70712, "realized_active_tokens": 70712, "cumulative_start": 4131850, "cumulative_end": 4202562, "loss_sum": 37714.5029296875, "token_normalized_loss": 0.5333536447800585, "grad_norm_before_clip": 0.16934731602668762, "learning_rates_at_step": { "lora": 9.999103811778758e-05, "row_tokens": 9.999103811778758e-05 }, "learning_rates_after_step": { "lora": 9.99876637611264e-05, "row_tokens": 9.99876637611264e-05 } }, { "update_id": 64, "row_count": 10, "row_ids_sha256": "3e17d6d8c75ab16777e03339d599dbdc379bb520845204abede20f531ff8c20b", "input_ids_vector_sha256": "046d6841eebc68decb1979bb603eb4fd120da77d233ecc04bd64023943b25337", "labels_vector_sha256": "17cdd6b8d1870ecab7a809ab9ced44dc06bfc9c5268eaac076c3cc6baec6a553", "planned_active_tokens": 62819, "realized_active_tokens": 62819, "cumulative_start": 4202562, "cumulative_end": 4265381, "loss_sum": 30152.185485839844, "token_normalized_loss": 0.4799851237020622, "grad_norm_before_clip": 0.1839524209499359, "learning_rates_at_step": { "lora": 9.99876637611264e-05, "row_tokens": 9.99876637611264e-05 }, "learning_rates_after_step": { "lora": 9.99839104893514e-05, "row_tokens": 9.99839104893514e-05 } }, { "update_id": 65, "row_count": 10, "row_ids_sha256": "1e6d20c3b457337df38caaa68d42515d7fd60b67cee99fa70ee64ddd406b75be", "input_ids_vector_sha256": "27c85d65fd7522ecc9d52d7375c1bbae6fd91e9c14a1a2c135eb4ba8c89000ce", "labels_vector_sha256": "195b0ee0d90051b84d459f57245980804dc231c418f72cc8eb4d58110c66eed2", "planned_active_tokens": 60424, "realized_active_tokens": 60424, "cumulative_start": 4265381, "cumulative_end": 4325805, "loss_sum": 32224.562744140625, "token_normalized_loss": 0.5333073405292702, "grad_norm_before_clip": 0.17862454056739807, "learning_rates_at_step": { "lora": 9.99839104893514e-05, "row_tokens": 9.99839104893514e-05 }, "learning_rates_after_step": { "lora": 9.997895154973141e-05, "row_tokens": 9.997895154973141e-05 } }, { "update_id": 66, "row_count": 10, "row_ids_sha256": "c9071fc90a550f3d44cff9cd19b590ed68a97b2b585305aa09ce12cbd1605f80", "input_ids_vector_sha256": "332e896dc1495ed80ec85bc48936cbcb099f0a55e9c4589503072c3b268964b3", "labels_vector_sha256": "9c9b93c43d9376ec56b1e48f8ef51dd114ee3c8cb835a0b0d509fef9c488c92c", "planned_active_tokens": 69850, "realized_active_tokens": 69850, "cumulative_start": 4325805, "cumulative_end": 4395655, "loss_sum": 36000.309814453125, "token_normalized_loss": 0.5153945571145758, "grad_norm_before_clip": 0.29493963718414307, "learning_rates_at_step": { "lora": 9.997895154973141e-05, "row_tokens": 9.997895154973141e-05 }, "learning_rates_after_step": { "lora": 9.997332993710234e-05, "row_tokens": 9.997332993710234e-05 } }, { "update_id": 67, "row_count": 11, "row_ids_sha256": "4562f486963cc490d7878c51d18daae00748b142fbd215b36e8556c0ef11ef7e", "input_ids_vector_sha256": "edb01c64ef49301769230720ee6c58b219cb3c8e87d577b6760aef46f825452a", "labels_vector_sha256": "35596cf6070a10340ef76675ba2b25e78ff4eca6bb38e3105ab8434f7adcbd36", "planned_active_tokens": 69823, "realized_active_tokens": 69823, "cumulative_start": 4395655, "cumulative_end": 4465478, "loss_sum": 36442.785888671875, "token_normalized_loss": 0.5219309667111393, "grad_norm_before_clip": 0.17795254290103912, "learning_rates_at_step": { "lora": 9.997332993710234e-05, "row_tokens": 9.997332993710234e-05 }, "learning_rates_after_step": { "lora": 9.996795572584212e-05, "row_tokens": 9.996795572584212e-05 } }, { "update_id": 68, "row_count": 7, "row_ids_sha256": "5d37702d52577f41012e489a1e00a82a28687d721485c35bf57f3edbed6b5115", "input_ids_vector_sha256": "596796376dd417eaaf36bf1559a8acd349bd27700f6475f2895022363ae6ca1e", "labels_vector_sha256": "01dfbaab7071d839fa7a042517ca953bf5d5c7b680929777f7c1f72b9b6ebc2b", "planned_active_tokens": 60136, "realized_active_tokens": 60136, "cumulative_start": 4465478, "cumulative_end": 4525614, "loss_sum": 30997.243896484375, "token_normalized_loss": 0.515452372896175, "grad_norm_before_clip": 0.17822858691215515, "learning_rates_at_step": { "lora": 9.996795572584212e-05, "row_tokens": 9.996795572584212e-05 }, "learning_rates_after_step": { "lora": 9.996170492913826e-05, "row_tokens": 9.996170492913826e-05 } }, { "update_id": 69, "row_count": 11, "row_ids_sha256": "908457d1fa116ddc83f2d72913f3c746e7b310e5685f2f455c4221636d6985ae", "input_ids_vector_sha256": "e13ac9630c6868bf3523acc92ede48036f26fc22e826b4b92a48ddd46293e7e4", "labels_vector_sha256": "9d943f53a6dd25c218f20d16001452ab97992db6881cf23e019e70ab821a650e", "planned_active_tokens": 63902, "realized_active_tokens": 63902, "cumulative_start": 4525614, "cumulative_end": 4589516, "loss_sum": 32117.699768066406, "token_normalized_loss": 0.5026086784148603, "grad_norm_before_clip": 0.19357886910438538, "learning_rates_at_step": { "lora": 9.996170492913826e-05, "row_tokens": 9.996170492913826e-05 }, "learning_rates_after_step": { "lora": 9.995479571256599e-05, "row_tokens": 9.995479571256599e-05 } }, { "update_id": 70, "row_count": 11, "row_ids_sha256": "9cc578d9749f1c7e3d4a3d1f5d61df4166578fb370062605c92d58a37b35eee6", "input_ids_vector_sha256": "ebf2198a8f622808a7a84d1014e579a324c838862ba5ed67297fd0b6b3e7f3ee", "labels_vector_sha256": "fcaf7f27a432d08c3f33779f0727455a6e002609e2cb9f45569f1c373dc8a228", "planned_active_tokens": 64822, "realized_active_tokens": 64822, "cumulative_start": 4589516, "cumulative_end": 4654338, "loss_sum": 29466.830810546875, "token_normalized_loss": 0.45458071041539716, "grad_norm_before_clip": 0.16328562796115875, "learning_rates_at_step": { "lora": 9.995479571256599e-05, "row_tokens": 9.995479571256599e-05 }, "learning_rates_after_step": { "lora": 9.9946954334628e-05, "row_tokens": 9.9946954334628e-05 } }, { "update_id": 71, "row_count": 10, "row_ids_sha256": "ecfd764a2bd2bdf7527625b0f4829a144668a8784e5c1bd5b02d132014f6f146", "input_ids_vector_sha256": "84ce2bdf4a0d227c35b1ec94098bbc1d2c8b5601819b186a7e3f2af8de699a61", "labels_vector_sha256": "ba8a22f008e7e1e09fdeab4e53b3d894c55be965c932c36ff9cffb9d0a41e5b5", "planned_active_tokens": 67819, "realized_active_tokens": 67819, "cumulative_start": 4654338, "cumulative_end": 4722157, "loss_sum": 30499.37387084961, "token_normalized_loss": 0.4497172454747137, "grad_norm_before_clip": 0.16171815991401672, "learning_rates_at_step": { "lora": 9.9946954334628e-05, "row_tokens": 9.9946954334628e-05 }, "learning_rates_after_step": { "lora": 9.993892837884291e-05, "row_tokens": 9.993892837884291e-05 } }, { "update_id": 72, "row_count": 11, "row_ids_sha256": "9c509db1813f8e729a4b6b76fb0fcd36fcefc888256810ffb325f94bb78021e6", "input_ids_vector_sha256": "8d5ecab8878097fe676c8a0dd1be60a3fcb8440ea63fc80b32529c5448a1171d", "labels_vector_sha256": "2b17c1a4a7fb409599345733f204a202bba9781413f4b113b7c07b769bfbaf01", "planned_active_tokens": 64400, "realized_active_tokens": 64400, "cumulative_start": 4722157, "cumulative_end": 4786557, "loss_sum": 32072.69256591797, "token_normalized_loss": 0.49802317648940947, "grad_norm_before_clip": 0.19207066297531128, "learning_rates_at_step": { "lora": 9.993892837884291e-05, "row_tokens": 9.993892837884291e-05 }, "learning_rates_after_step": { "lora": 9.993042811360464e-05, "row_tokens": 9.993042811360464e-05 } }, { "update_id": 73, "row_count": 10, "row_ids_sha256": "0f85d0ad561ba82be5b42abf4838c70d6ccb16db22dfa2aaa74235d00b844aad", "input_ids_vector_sha256": "45eb81e48cd7def1a76c7492b69c62b585d77dcae6bc6e01cd77a2419388f525", "labels_vector_sha256": "074442bfb4b4d800ba6cb401dd1cbf4b94ed32540d946a071696b9aba709e3c9", "planned_active_tokens": 63743, "realized_active_tokens": 63743, "cumulative_start": 4786557, "cumulative_end": 4850300, "loss_sum": 31928.232849121094, "token_normalized_loss": 0.5008900247732472, "grad_norm_before_clip": 0.18298958241939545, "learning_rates_at_step": { "lora": 9.993042811360464e-05, "row_tokens": 9.993042811360464e-05 }, "learning_rates_after_step": { "lora": 9.992108951050722e-05, "row_tokens": 9.992108951050722e-05 } }, { "update_id": 74, "row_count": 11, "row_ids_sha256": "6b63b3e2095dcab0e770e1fa7dedcc047f6ac8d145e4214290b77b703f6a55fe", "input_ids_vector_sha256": "dc2aafc924c56f6070ef3604a0bd179c44bcc39b3088cd6655be9534cd5f34e0", "labels_vector_sha256": "7c7f7233d72b95d7d25255e7c3666fe15b52dde827a4d8ac5a1d8c6bea0da2ed", "planned_active_tokens": 65689, "realized_active_tokens": 65689, "cumulative_start": 4850300, "cumulative_end": 4915989, "loss_sum": 26263.750244140625, "token_normalized_loss": 0.3998196082166059, "grad_norm_before_clip": 0.17210666835308075, "learning_rates_at_step": { "lora": 9.992108951050722e-05, "row_tokens": 9.992108951050722e-05 }, "learning_rates_after_step": { "lora": 9.991002085114226e-05, "row_tokens": 9.991002085114226e-05 } }, { "update_id": 75, "row_count": 12, "row_ids_sha256": "8cfd2cb332a86e33d3833362dc2fd68fe4680a3c5653219c0d1d59423f5f62c5", "input_ids_vector_sha256": "26e3b34eaba0dd50355d7af4ee3aecab326e0b6b71de047d70c1c068a6b492b4", "labels_vector_sha256": "021dfd32b61ab24673397cd167b8afbe0314fe42dac044e5f954f5cd804c5bdc", "planned_active_tokens": 73010, "realized_active_tokens": 73010, "cumulative_start": 4915989, "cumulative_end": 4988999, "loss_sum": 37453.75634765625, "token_normalized_loss": 0.5129948821758149, "grad_norm_before_clip": 0.20365408062934875, "learning_rates_at_step": { "lora": 9.991002085114226e-05, "row_tokens": 9.991002085114226e-05 }, "learning_rates_after_step": { "lora": 9.990047830574643e-05, "row_tokens": 9.990047830574643e-05 } }, { "update_id": 76, "row_count": 10, "row_ids_sha256": "850bea52f370fa0ab0f277b750a26e47b5a5d2bacd598120054f39b9ca917871", "input_ids_vector_sha256": "6fcaa50588db36a75006abb2d5198f3b7c53b64cafd8cacaf1ec9acc1597c921", "labels_vector_sha256": "0da434d94465f3e35181e886c59daed891f75167e65ca525642b9e52dae55865", "planned_active_tokens": 59412, "realized_active_tokens": 59412, "cumulative_start": 4988999, "cumulative_end": 5048411, "loss_sum": 28213.609252929688, "token_normalized_loss": 0.4748806512645541, "grad_norm_before_clip": 0.16703973710536957, "learning_rates_at_step": { "lora": 9.990047830574643e-05, "row_tokens": 9.990047830574643e-05 }, "learning_rates_after_step": { "lora": 9.988892515475423e-05, "row_tokens": 9.988892515475423e-05 } }, { "update_id": 77, "row_count": 13, "row_ids_sha256": "b260c67a37ff4158cdba0b9830030ec3196acfa77b5a5e117aabce0bc02628eb", "input_ids_vector_sha256": "ba061cef038958b3594ef8ca87f91bb896e9ebaa4a3cc4ca09ac0e55d75c620c", "labels_vector_sha256": "d39354c4d1a257d968503544b39267414a635f577a8dc94961e1bd5053d4af4d", "planned_active_tokens": 68240, "realized_active_tokens": 68240, "cumulative_start": 5048411, "cumulative_end": 5116651, "loss_sum": 27933.084594726562, "token_normalized_loss": 0.4093359407199086, "grad_norm_before_clip": 0.15506987273693085, "learning_rates_at_step": { "lora": 9.988892515475423e-05, "row_tokens": 9.988892515475423e-05 }, "learning_rates_after_step": { "lora": 9.987798509871012e-05, "row_tokens": 9.987798509871012e-05 } }, { "update_id": 78, "row_count": 9, "row_ids_sha256": "d2a4dd50f0b73062b9058f1a87dcfb84a255c1788715c935ff551ee46eae785c", "input_ids_vector_sha256": "3b9f4a3869daf9e446ebe27b13116f2983419f638b509cf206f8c65db5e31818", "labels_vector_sha256": "4ebcce56cc8cbe9b9c6c393838c6a37f507a5b794a863a2403804b1689105342", "planned_active_tokens": 61419, "realized_active_tokens": 61419, "cumulative_start": 5116651, "cumulative_end": 5178070, "loss_sum": 31794.985961914062, "token_normalized_loss": 0.5176734554765474, "grad_norm_before_clip": 0.18736615777015686, "learning_rates_at_step": { "lora": 9.987798509871012e-05, "row_tokens": 9.987798509871012e-05 }, "learning_rates_after_step": { "lora": 9.986535284135346e-05, "row_tokens": 9.986535284135346e-05 } }, { "update_id": 79, "row_count": 11, "row_ids_sha256": "0403d121af65908abb273311adcab652e6dd2121d023159b54cd19104bfff4cd", "input_ids_vector_sha256": "61133371bc0d7585302d026db1e54079dc86c73ec87444faa9df33dfbfa4fb6a", "labels_vector_sha256": "44d7759bebd4f078199b2fa28401c58c3b5337e6caf596b17383b39ba8a5b6b8", "planned_active_tokens": 67590, "realized_active_tokens": 67590, "cumulative_start": 5178070, "cumulative_end": 5245660, "loss_sum": 32639.441040039062, "token_normalized_loss": 0.48290340346262856, "grad_norm_before_clip": 0.1768949180841446, "learning_rates_at_step": { "lora": 9.986535284135346e-05, "row_tokens": 9.986535284135346e-05 }, "learning_rates_after_step": { "lora": 9.985268757177089e-05, "row_tokens": 9.985268757177089e-05 } }, { "update_id": 80, "row_count": 12, "row_ids_sha256": "723d6b48d324ddec618de1b2d8df50069d2223429347fa9f8e5971bb3af22adb", "input_ids_vector_sha256": "c669b87f04b5cf61386f3dce490912fcba95fadc690f609d2c64e4bd756aa93f", "labels_vector_sha256": "4ea97e55327aed5f9cededb4427b925362170a569906cb3a3fee63438233557c", "planned_active_tokens": 64656, "realized_active_tokens": 64656, "cumulative_start": 5245660, "cumulative_end": 5310316, "loss_sum": 29991.1767578125, "token_normalized_loss": 0.46385759647693176, "grad_norm_before_clip": 0.17321111261844635, "learning_rates_at_step": { "lora": 9.985268757177089e-05, "row_tokens": 9.985268757177089e-05 }, "learning_rates_after_step": { "lora": 9.983837504574681e-05, "row_tokens": 9.983837504574681e-05 } }, { "update_id": 81, "row_count": 12, "row_ids_sha256": "1aa7390ddcbf91e4f399dcb610d588b6c20f67eab1b6cf166587be264ce72c52", "input_ids_vector_sha256": "0279f6b68229d3326d00e799cac969474ea3edbd44cf641eb162333d1ec898b6", "labels_vector_sha256": "96580a196d4c897231ef2c9c695dc0d5f4fa4df6689665f02cba9629c6045167", "planned_active_tokens": 69808, "realized_active_tokens": 69808, "cumulative_start": 5310316, "cumulative_end": 5380124, "loss_sum": 35782.1259765625, "token_normalized_loss": 0.5125791596459217, "grad_norm_before_clip": 0.1884336620569229, "learning_rates_at_step": { "lora": 9.983837504574681e-05, "row_tokens": 9.983837504574681e-05 }, "learning_rates_after_step": { "lora": 9.982549402727799e-05, "row_tokens": 9.982549402727799e-05 } }, { "update_id": 82, "row_count": 10, "row_ids_sha256": "eec4d0622366ba1c5d6f5ee44c958b7b5cb27ea89f8f40995d96d4acf084ec97", "input_ids_vector_sha256": "128e31238f45cb886151ee62353ca1eef2242782f112868475b60abb7ca452fe", "labels_vector_sha256": "291e81ea70db7c26b1358851ebb2b80bdf28588a33bba0896ed5680d013242f4", "planned_active_tokens": 60230, "realized_active_tokens": 60230, "cumulative_start": 5380124, "cumulative_end": 5440354, "loss_sum": 27183.884338378906, "token_normalized_loss": 0.451334622918461, "grad_norm_before_clip": 0.1616625338792801, "learning_rates_at_step": { "lora": 9.982549402727799e-05, "row_tokens": 9.982549402727799e-05 }, "learning_rates_after_step": { "lora": 9.980989764968769e-05, "row_tokens": 9.980989764968769e-05 } }, { "update_id": 83, "row_count": 12, "row_ids_sha256": "3593a5dcd5ae545be808c04129cc25a267481df9bba7446af9d0f32d96b22a55", "input_ids_vector_sha256": "99ed1828613257d228498a5fe4eb7e15dabeda1257cb5944fd3c77751aa278da", "labels_vector_sha256": "ca653536f059ee161547d812061d60c703a8efac5397f6d9cd3e378db01bcd59", "planned_active_tokens": 70029, "realized_active_tokens": 70029, "cumulative_start": 5440354, "cumulative_end": 5510383, "loss_sum": 32407.706115722656, "token_normalized_loss": 0.46277550894233327, "grad_norm_before_clip": 0.2105463445186615, "learning_rates_at_step": { "lora": 9.980989764968769e-05, "row_tokens": 9.980989764968769e-05 }, "learning_rates_after_step": { "lora": 9.979432299996373e-05, "row_tokens": 9.979432299996373e-05 } }, { "update_id": 84, "row_count": 14, "row_ids_sha256": "2e62f0cb9b085ec357bc78eb93a6ab43e481865470d5ec155b61c164ace5e05a", "input_ids_vector_sha256": "557dd06c64f625b3d1ea3ed073dffabe39551be5020d6c26eb9516351d3515e9", "labels_vector_sha256": "57277af53c9e0ee562fb15bf6908b1ec798c233bf43348899548553b36fa9abf", "planned_active_tokens": 67124, "realized_active_tokens": 67124, "cumulative_start": 5510383, "cumulative_end": 5577507, "loss_sum": 27592.570251464844, "token_normalized_loss": 0.4110686230180687, "grad_norm_before_clip": 0.15863585472106934, "learning_rates_at_step": { "lora": 9.979432299996373e-05, "row_tokens": 9.979432299996373e-05 }, "learning_rates_after_step": { "lora": 9.977949366432256e-05, "row_tokens": 9.977949366432256e-05 } }, { "update_id": 85, "row_count": 8, "row_ids_sha256": "3c95b8312ff508798638e7984addb82904b883e1c69d89180f14ce5818a20b8f", "input_ids_vector_sha256": "d99d188d5826839ea528c1d645f33f0466e1aefc20951d1a1d64ea749ad72b2a", "labels_vector_sha256": "5d117f385a631b49c3d6d6233103b94e563810b00ccc5c4bed166af7c850e56c", "planned_active_tokens": 61592, "realized_active_tokens": 61592, "cumulative_start": 5577507, "cumulative_end": 5639099, "loss_sum": 31714.244018554688, "token_normalized_loss": 0.5149084949109412, "grad_norm_before_clip": 0.190715491771698, "learning_rates_at_step": { "lora": 9.977949366432256e-05, "row_tokens": 9.977949366432256e-05 }, "learning_rates_after_step": { "lora": 9.976371929630363e-05, "row_tokens": 9.976371929630363e-05 } }, { "update_id": 86, "row_count": 9, "row_ids_sha256": "4387381bd494fe0fc086e031fcd030abcf48533c87ca2aebc86e9e7484403801", "input_ids_vector_sha256": "53d50c203718140c28cdb378d8698ed7e369f03409bf41c4fd79ae3cd2c58a1c", "labels_vector_sha256": "cb870bc07e18cfcc7ba156c5cb85a07c4d9a5817e8c27f66f5ef321a845d44db", "planned_active_tokens": 63289, "realized_active_tokens": 63289, "cumulative_start": 5639099, "cumulative_end": 5702388, "loss_sum": 30702.866088867188, "token_normalized_loss": 0.48512168131693006, "grad_norm_before_clip": 0.16630207002162933, "learning_rates_at_step": { "lora": 9.976371929630363e-05, "row_tokens": 9.976371929630363e-05 }, "learning_rates_after_step": { "lora": 9.974629161691638e-05, "row_tokens": 9.974629161691638e-05 } }, { "update_id": 87, "row_count": 11, "row_ids_sha256": "708f4c05a59341daec99deb6c73700abdbb66f16a5bef9c2ba4651ba4a04098a", "input_ids_vector_sha256": "c2c0e60db54b6423c1fe9bffa77ef00238e5d25f48cfed5c1997888861ea41f6", "labels_vector_sha256": "70a30479e2136647e2fafd7bdb289070c1dfeae2f0bff92a362a939007e43753", "planned_active_tokens": 67518, "realized_active_tokens": 67518, "cumulative_start": 5702388, "cumulative_end": 5769906, "loss_sum": 30871.79052734375, "token_normalized_loss": 0.45723792954980524, "grad_norm_before_clip": 0.17190368473529816, "learning_rates_at_step": { "lora": 9.974629161691638e-05, "row_tokens": 9.974629161691638e-05 }, "learning_rates_after_step": { "lora": 9.972899885277403e-05, "row_tokens": 9.972899885277403e-05 } }, { "update_id": 88, "row_count": 10, "row_ids_sha256": "4f85c1c4262a62050058fd56d509fa17950bf0ff763db03356182804e69d9dbd", "input_ids_vector_sha256": "9597a0668dd7e87e056a37bebdfd17c332f3ce2f3a2f4e9189c0bb9f2208b1ac", "labels_vector_sha256": "e68eb4c2ad648b0dd01b24963f2d1ea4ed5cf8cba7bb0c48f0b69a4d9dfc456d", "planned_active_tokens": 64745, "realized_active_tokens": 64745, "cumulative_start": 5769906, "cumulative_end": 5834651, "loss_sum": 28613.57049560547, "token_normalized_loss": 0.44194255148050765, "grad_norm_before_clip": 0.17118580639362335, "learning_rates_at_step": { "lora": 9.972899885277403e-05, "row_tokens": 9.972899885277403e-05 }, "learning_rates_after_step": { "lora": 9.971048480675954e-05, "row_tokens": 9.971048480675954e-05 } }, { "update_id": 89, "row_count": 13, "row_ids_sha256": "abb8300e07941dce245c91cab9858547ed2529e10abf9c020c4614a9d3966ca4", "input_ids_vector_sha256": "0d5192fca123875c18a87009eed648a615f26a60dbed1f221c3f3efb472959e8", "labels_vector_sha256": "b4aec7afb54599af7187369dfafe58ae559c058112d6cf6e55b113cbc03f2c63", "planned_active_tokens": 67073, "realized_active_tokens": 67073, "cumulative_start": 5834651, "cumulative_end": 5901724, "loss_sum": 30875.412231445312, "token_normalized_loss": 0.46032549955191077, "grad_norm_before_clip": 0.16820061206817627, "learning_rates_at_step": { "lora": 9.971048480675954e-05, "row_tokens": 9.971048480675954e-05 }, "learning_rates_after_step": { "lora": 9.969142433580527e-05, "row_tokens": 9.969142433580527e-05 } }, { "update_id": 90, "row_count": 10, "row_ids_sha256": "592920fddb2f3436b93c2d20bcbab3bf16a99669e8c3e6344301110defa94541", "input_ids_vector_sha256": "6fd6387ae8d257ceda00211af34ef729d02a9c03ce6609922045a1bcca2ae71c", "labels_vector_sha256": "9b0f3773f29481d76ee09b3145c0189acd98cb2980cd884476cace3083def50b", "planned_active_tokens": 66854, "realized_active_tokens": 66854, "cumulative_start": 5901724, "cumulative_end": 5968578, "loss_sum": 34559.42248535156, "token_normalized_loss": 0.5169387394224962, "grad_norm_before_clip": 0.17043273150920868, "learning_rates_at_step": { "lora": 9.969142433580527e-05, "row_tokens": 9.969142433580527e-05 }, "learning_rates_after_step": { "lora": 9.967342400829085e-05, "row_tokens": 9.967342400829085e-05 } }, { "update_id": 91, "row_count": 7, "row_ids_sha256": "4963aed02d0dd149d00112ed48afc825ee0486167374cc0ea5c72d6f1354fede", "input_ids_vector_sha256": "90795eb8c3d9d8ac4dafc05612225307a3c5bee28de3aca971a0cbf056b96827", "labels_vector_sha256": "b81905e04050d08ad3bc5e028c0eef6a1bf7ca804f92cd15030de9668047ae5b", "planned_active_tokens": 61270, "realized_active_tokens": 61270, "cumulative_start": 5968578, "cumulative_end": 6029848, "loss_sum": 34895.8056640625, "token_normalized_loss": 0.5695414666894484, "grad_norm_before_clip": 0.18756996095180511, "learning_rates_at_step": { "lora": 9.967342400829085e-05, "row_tokens": 9.967342400829085e-05 }, "learning_rates_after_step": { "lora": 9.965315268594106e-05, "row_tokens": 9.965315268594106e-05 } }, { "update_id": 92, "row_count": 9, "row_ids_sha256": "3a9d57d9728938509b50da93a001752f38fcc17fb1fc3ca7235da37b391298a6", "input_ids_vector_sha256": "d4b4005aac4c74f055010f959d6cd99652993a5af2f09c22a9b0124bf4d139f4", "labels_vector_sha256": "3d2e0ae3fb33c6ff755e91054abb047951873441e534bbaa1d43413fe0c6c22c", "planned_active_tokens": 67018, "realized_active_tokens": 67018, "cumulative_start": 6029848, "cumulative_end": 6096866, "loss_sum": 39543.185546875, "token_normalized_loss": 0.5900382814598317, "grad_norm_before_clip": 0.188797265291214, "learning_rates_at_step": { "lora": 9.965315268594106e-05, "row_tokens": 9.965315268594106e-05 }, "learning_rates_after_step": { "lora": 9.963283657380766e-05, "row_tokens": 9.963283657380766e-05 } }, { "update_id": 93, "row_count": 9, "row_ids_sha256": "c4cf2c86c6505c5e3cbc6a675643d0459f78c03154dfcef79fe4f507e0e7eae1", "input_ids_vector_sha256": "46daca8d74808ee78e6fe6acf925bfe2d768a36d976675bb059ae3f4b107358c", "labels_vector_sha256": "2155fee0543786ea4ca229be4c8d2306c24df996f8100449fe9add3c531a8b5b", "planned_active_tokens": 65235, "realized_active_tokens": 65235, "cumulative_start": 6096866, "cumulative_end": 6162101, "loss_sum": 34615.04357910156, "token_normalized_loss": 0.530620733948058, "grad_norm_before_clip": 0.1795157790184021, "learning_rates_at_step": { "lora": 9.963283657380766e-05, "row_tokens": 9.963283657380766e-05 }, "learning_rates_after_step": { "lora": 9.961178536433832e-05, "row_tokens": 9.961178536433832e-05 } }, { "update_id": 94, "row_count": 11, "row_ids_sha256": "8f3be5e9c2ae99b491706f82a7688da109b301b50d34f8fe41694c3f3af39d1a", "input_ids_vector_sha256": "7f9b7a82cca0d35bba1a31a534df3eaf1a998ced98b418d33e8af737e5556280", "labels_vector_sha256": "0e8eaeb702e3cd5254f70cc8c8f9f6ade7b162526f1ef67d68e722552fcc77e0", "planned_active_tokens": 65725, "realized_active_tokens": 65725, "cumulative_start": 6162101, "cumulative_end": 6227826, "loss_sum": 30729.237365722656, "token_normalized_loss": 0.4675425997066969, "grad_norm_before_clip": 0.1730114221572876, "learning_rates_at_step": { "lora": 9.961178536433832e-05, "row_tokens": 9.961178536433832e-05 }, "learning_rates_after_step": { "lora": 9.958947284818698e-05, "row_tokens": 9.958947284818698e-05 } }, { "update_id": 95, "row_count": 11, "row_ids_sha256": "cb6d423fd34dc63f2ec37c6eab87570b3e0a8c767a840726df6760596a0e5d7d", "input_ids_vector_sha256": "6570c6e78282054f325b2fec07d10ff3e472ea1aa3e2c28fd96a30319d23dd60", "labels_vector_sha256": "56a2abf7b10443b0f695f5f6765e4a6729ac205c617b49205c0d9b9ee609cda9", "planned_active_tokens": 67753, "realized_active_tokens": 67753, "cumulative_start": 6227826, "cumulative_end": 6295579, "loss_sum": 33656.62335205078, "token_normalized_loss": 0.49675473192405917, "grad_norm_before_clip": 0.18831582367420197, "learning_rates_at_step": { "lora": 9.958947284818698e-05, "row_tokens": 9.958947284818698e-05 }, "learning_rates_after_step": { "lora": 9.956826688308697e-05, "row_tokens": 9.956826688308697e-05 } }, { "update_id": 96, "row_count": 12, "row_ids_sha256": "85ad84f3430b4300112ef3609296a7e5a09f12026238430679801804e752c279", "input_ids_vector_sha256": "724401f379bceac5335a8417336f2b9a2a46730ff71f51f515e218cf44de78bc", "labels_vector_sha256": "10d95b06901118a854c1de60b2aabd391629f79a3489fb82fea064a94437e0e6", "planned_active_tokens": 62713, "realized_active_tokens": 62713, "cumulative_start": 6295579, "cumulative_end": 6358292, "loss_sum": 31626.898681640625, "token_normalized_loss": 0.504311684684844, "grad_norm_before_clip": 0.1726009100675583, "learning_rates_at_step": { "lora": 9.956826688308697e-05, "row_tokens": 9.956826688308697e-05 }, "learning_rates_after_step": { "lora": 9.954577779850939e-05, "row_tokens": 9.954577779850939e-05 } }, { "update_id": 97, "row_count": 11, "row_ids_sha256": "7e335b9f7eba7f932880f44dea3dacbb3ed012b94d7f4f2deeed3436af5c5146", "input_ids_vector_sha256": "1b5ee4783ab296e3448776a47377f6d4a7b565f5f0e8af486c50e4c146df3177", "labels_vector_sha256": "32d767ab17f68d45379c7c3ed68f6d0e6ea5d762d217f94b0444f5333a07c4fd", "planned_active_tokens": 64854, "realized_active_tokens": 64854, "cumulative_start": 6358292, "cumulative_end": 6423146, "loss_sum": 29542.23260498047, "token_normalized_loss": 0.4555190521013425, "grad_norm_before_clip": 0.16060706973075867, "learning_rates_at_step": { "lora": 9.954577779850939e-05, "row_tokens": 9.954577779850939e-05 }, "learning_rates_after_step": { "lora": 9.952266176272273e-05, "row_tokens": 9.952266176272273e-05 } }, { "update_id": 98, "row_count": 11, "row_ids_sha256": "1b73554b7a8d8c714dcce2c2ad7b622d9b24fa89b4d0e51bc4540cdbe5689037", "input_ids_vector_sha256": "8c82e2ed6fc4aff17d2ea56f8f3eebc8e1ff7ddd4efdb0245d34819dba7f808f", "labels_vector_sha256": "784c1d2c5d1e1668354e607da48da555c17875c3f146755b2cae41015363c47d", "planned_active_tokens": 65017, "realized_active_tokens": 65017, "cumulative_start": 6423146, "cumulative_end": 6488163, "loss_sum": 32153.51318359375, "token_normalized_loss": 0.4945400923388306, "grad_norm_before_clip": 0.18077342212200165, "learning_rates_at_step": { "lora": 9.952266176272273e-05, "row_tokens": 9.952266176272273e-05 }, "learning_rates_after_step": { "lora": 9.949855886064486e-05, "row_tokens": 9.949855886064486e-05 } }, { "update_id": 99, "row_count": 13, "row_ids_sha256": "40e0d25bb5848193660de6ee1f316d6d00fc4b8a7b7a8ad9a31786a3a95567f6", "input_ids_vector_sha256": "d8378c0c38f84a37ca7191a98d3cdce1c9b1186759361d35ad24804982d8d65c", "labels_vector_sha256": "99a3b210051b8d9f7bc62112c3b71928e4ca942cd1280fbf6cc519f8c9a69d95", "planned_active_tokens": 66145, "realized_active_tokens": 66145, "cumulative_start": 6488163, "cumulative_end": 6554308, "loss_sum": 29735.70770263672, "token_normalized_loss": 0.44955337066500445, "grad_norm_before_clip": 0.16106748580932617, "learning_rates_at_step": { "lora": 9.949855886064486e-05, "row_tokens": 9.949855886064486e-05 }, "learning_rates_after_step": { "lora": 9.947395982971715e-05, "row_tokens": 9.947395982971715e-05 } }, { "update_id": 100, "row_count": 11, "row_ids_sha256": "0395f39bf2cc57082dc234bfea9b45704a746a3dcc41fab1c5d20cdf5f3a6a5c", "input_ids_vector_sha256": "a281482c7255c1ca78d9479e6889ca5e2c99aa7bbacf047ddc7f2fbf10096311", "labels_vector_sha256": "b7302fff3c27e499f2285370a0e7a288da3536951c7b7bc47b42d37dfe406809", "planned_active_tokens": 65895, "realized_active_tokens": 65895, "cumulative_start": 6554308, "cumulative_end": 6620203, "loss_sum": 31139.028198242188, "token_normalized_loss": 0.4725552499922936, "grad_norm_before_clip": 0.17518416047096252, "learning_rates_at_step": { "lora": 9.947395982971715e-05, "row_tokens": 9.947395982971715e-05 }, "learning_rates_after_step": { "lora": 9.944826487871614e-05, "row_tokens": 9.944826487871614e-05 } }, { "update_id": 101, "row_count": 12, "row_ids_sha256": "295fcf13d176df3c0bebcf71a0e39955026971c6dad526e8c81e3a0e2621997c", "input_ids_vector_sha256": "323df777b85a0e9f679dd518cefd4eb38b482bdf1dafca4c584cb8bed8aa7f89", "labels_vector_sha256": "3af9c9ebb8ba464d3d05e4c2cd095e9d07965aa7d45c4611b3b3ccc1a13fd258", "planned_active_tokens": 67214, "realized_active_tokens": 67214, "cumulative_start": 6620203, "cumulative_end": 6687417, "loss_sum": 32904.848693847656, "token_normalized_loss": 0.489553496203881, "grad_norm_before_clip": 0.17941588163375854, "learning_rates_at_step": { "lora": 9.944826487871614e-05, "row_tokens": 9.944826487871614e-05 }, "learning_rates_after_step": { "lora": 9.942141033043259e-05, "row_tokens": 9.942141033043259e-05 } }, { "update_id": 102, "row_count": 11, "row_ids_sha256": "3ac715559ce3492f0b8e209905b10b40610c6e64bcf256ff38ef1a73d7b937ed", "input_ids_vector_sha256": "35a729a41a9af6a55df94afbd62ec66033225da5dbc43dfd1b05a3cdb3238d84", "labels_vector_sha256": "9803aa6bed527a9e83c50d517455f0598576828f14a0b4f13f7ff75bece35082", "planned_active_tokens": 68604, "realized_active_tokens": 68604, "cumulative_start": 6687417, "cumulative_end": 6756021, "loss_sum": 33588.205810546875, "token_normalized_loss": 0.48959544356811374, "grad_norm_before_clip": 0.16392581164836884, "learning_rates_at_step": { "lora": 9.942141033043259e-05, "row_tokens": 9.942141033043259e-05 }, "learning_rates_after_step": { "lora": 9.939620123590655e-05, "row_tokens": 9.939620123590655e-05 } }, { "update_id": 103, "row_count": 11, "row_ids_sha256": "3f7dc549c0762eee3fcf80982f41bc292d4c05dd07af89f388fb2527e1adcc21", "input_ids_vector_sha256": "33de6ccf530a4e6dd3ea98de473388fb40981cc0eaa8da843a152830e71bde01", "labels_vector_sha256": "4ecdf3c9b89e8bbeb3141c7d141048069d6afe9671c96e08c0429d59ee37b36f", "planned_active_tokens": 62974, "realized_active_tokens": 62974, "cumulative_start": 6756021, "cumulative_end": 6818995, "loss_sum": 29271.223510742188, "token_normalized_loss": 0.46481442358341835, "grad_norm_before_clip": 0.17772020399570465, "learning_rates_at_step": { "lora": 9.939620123590655e-05, "row_tokens": 9.939620123590655e-05 }, "learning_rates_after_step": { "lora": 9.937059341132274e-05, "row_tokens": 9.937059341132274e-05 } }, { "update_id": 104, "row_count": 10, "row_ids_sha256": "fb4821375c7b8c7c55fce64e19a97f61f422623874bf924aa0a168105df515c8", "input_ids_vector_sha256": "515c1fecc3b37af98b529c9055664049134defb73b76595637b3bfa042c2a8df", "labels_vector_sha256": "ee580b5d83825069dbd9bb50d0158ec0d35b6dbdeca9541b4e6c8b51a4d1ed97", "planned_active_tokens": 62646, "realized_active_tokens": 62646, "cumulative_start": 6818995, "cumulative_end": 6881641, "loss_sum": 24858.040954589844, "token_normalized_loss": 0.39680172644047257, "grad_norm_before_clip": 0.15126480162143707, "learning_rates_at_step": { "lora": 9.937059341132274e-05, "row_tokens": 9.937059341132274e-05 }, "learning_rates_after_step": { "lora": 9.934329822096954e-05, "row_tokens": 9.934329822096954e-05 } }, { "update_id": 105, "row_count": 11, "row_ids_sha256": "f4705476c25b8669130191a8a84efe219408c4ed2ff2cd298755204a542aaca4", "input_ids_vector_sha256": "a1e09ba3b366de653d2f4772e46426c526858bc381195a9de418c6ae40bfbb35", "labels_vector_sha256": "bd3f9e84d0fb51824adb821e36da73c83e511bd93514da741a0076ed9c384187", "planned_active_tokens": 65395, "realized_active_tokens": 65395, "cumulative_start": 6881641, "cumulative_end": 6947036, "loss_sum": 29954.674560546875, "token_normalized_loss": 0.45805756648898044, "grad_norm_before_clip": 0.16956855356693268, "learning_rates_at_step": { "lora": 9.934329822096954e-05, "row_tokens": 9.934329822096954e-05 }, "learning_rates_after_step": { "lora": 9.931483669464626e-05, "row_tokens": 9.931483669464626e-05 } }, { "update_id": 106, "row_count": 11, "row_ids_sha256": "2881e052fff377640307a08f4f979b008e6e122b29a8f9a8b38ce2c135bed63c", "input_ids_vector_sha256": "3b1758a2cb2497b763b7d7eaecea326a1fcfcd0d1fae1ffcf2e5812c0ccb02c2", "labels_vector_sha256": "a9f2968fa1de87c1b580198567c7d0c5243482e11bb3489c84cd4815e168a957", "planned_active_tokens": 66767, "realized_active_tokens": 66767, "cumulative_start": 6947036, "cumulative_end": 7013803, "loss_sum": 30092.03887939453, "token_normalized_loss": 0.4507022762651389, "grad_norm_before_clip": 0.1833207905292511, "learning_rates_at_step": { "lora": 9.931483669464626e-05, "row_tokens": 9.931483669464626e-05 }, "learning_rates_after_step": { "lora": 9.928432201043356e-05, "row_tokens": 9.928432201043356e-05 } }, { "update_id": 107, "row_count": 12, "row_ids_sha256": "44be556edd315a2686f5c0a35c5b9f428958377b7534f0056816e4b684f844ed", "input_ids_vector_sha256": "39db4b9885134fab79863e55f17c1d12a57d6a71160916ce5b8e3fcef71a9207", "labels_vector_sha256": "efe80a47bc157e4d2e215beb479622ba5b55e5b83b06c74585d87f530824a83e", "planned_active_tokens": 70071, "realized_active_tokens": 70071, "cumulative_start": 7013803, "cumulative_end": 7083874, "loss_sum": 35471.440185546875, "token_normalized_loss": 0.5062214066524935, "grad_norm_before_clip": 0.17251992225646973, "learning_rates_at_step": { "lora": 9.928432201043356e-05, "row_tokens": 9.928432201043356e-05 }, "learning_rates_after_step": { "lora": 9.925503953929789e-05, "row_tokens": 9.925503953929789e-05 } }, { "update_id": 108, "row_count": 11, "row_ids_sha256": "722ce14418bb55f70653e10cd4b019e84b75505b1511120e7241a33e0b1e870f", "input_ids_vector_sha256": "9e0802873432293f604d822b12eff207cf6b1eb1936a0aa7e8dfcd32fbf046e7", "labels_vector_sha256": "cc3bdc60c01dfae4a71194f53af00d5ccb223847aedfd29d3f79952ee3142adb", "planned_active_tokens": 65860, "realized_active_tokens": 65860, "cumulative_start": 7083874, "cumulative_end": 7149734, "loss_sum": 30924.31915283203, "token_normalized_loss": 0.4695462974921353, "grad_norm_before_clip": 0.1730765700340271, "learning_rates_at_step": { "lora": 9.925503953929789e-05, "row_tokens": 9.925503953929789e-05 }, "learning_rates_after_step": { "lora": 9.922704836717248e-05, "row_tokens": 9.922704836717248e-05 } }, { "update_id": 109, "row_count": 11, "row_ids_sha256": "374e4dca2921a8fe0f5e60464a378a103e11d604c66ed3260f1b9dfa899baea4", "input_ids_vector_sha256": "87cc8698c6e952fbde12487aa252aaba954eb7c7abfdc85bc171bcdbab3216ed", "labels_vector_sha256": "686864dbef1c487482e9e58c3bb0ba5294172a9ff17fcec12bb4c0968f29407b", "planned_active_tokens": 61765, "realized_active_tokens": 61765, "cumulative_start": 7149734, "cumulative_end": 7211499, "loss_sum": 27176.38427734375, "token_normalized_loss": 0.43999650736410184, "grad_norm_before_clip": 0.19888810813426971, "learning_rates_at_step": { "lora": 9.922704836717248e-05, "row_tokens": 9.922704836717248e-05 }, "learning_rates_after_step": { "lora": 9.91973805929913e-05, "row_tokens": 9.91973805929913e-05 } }, { "update_id": 110, "row_count": 12, "row_ids_sha256": "f63be03184ca18667759f6d856de48a88b8c02d25840a817cd265cca227a22a8", "input_ids_vector_sha256": "d0411f5acd0d9cdfbedb9d7d25873bad87a9c052bce91d9990ce1f1b63201a1f", "labels_vector_sha256": "5b28de60267719f00c1ec11d98ab1bb8eff91421141802567493b7ee801ee0e1", "planned_active_tokens": 64265, "realized_active_tokens": 64265, "cumulative_start": 7211499, "cumulative_end": 7275764, "loss_sum": 27381.109802246094, "token_normalized_loss": 0.42606566252619765, "grad_norm_before_clip": 0.18112222850322723, "learning_rates_at_step": { "lora": 9.91973805929913e-05, "row_tokens": 9.91973805929913e-05 }, "learning_rates_after_step": { "lora": 9.916673772956275e-05, "row_tokens": 9.916673772956275e-05 } }, { "update_id": 111, "row_count": 12, "row_ids_sha256": "db75e23c571f4b1169abea26081272129243d0867ef246db6e5be2d084cc1cf6", "input_ids_vector_sha256": "dd213bc12d793839c588b202c8a4c0f3803f161b876c577873663e180fc4131e", "labels_vector_sha256": "f5671e079e39be9118ad39b744cc8a5bf7da37f2407f46605851bd060b85ab6d", "planned_active_tokens": 65152, "realized_active_tokens": 65152, "cumulative_start": 7275764, "cumulative_end": 7340916, "loss_sum": 30597.364868164062, "token_normalized_loss": 0.46963047747059283, "grad_norm_before_clip": 0.1785985827445984, "learning_rates_at_step": { "lora": 9.916673772956275e-05, "row_tokens": 9.916673772956275e-05 }, "learning_rates_after_step": { "lora": 9.913516264091188e-05, "row_tokens": 9.913516264091188e-05 } }, { "update_id": 112, "row_count": 12, "row_ids_sha256": "bd3d911c6a2046414f8874afa473452a5ca5f35e21581666af112adcdc7b33ae", "input_ids_vector_sha256": "8f4432f0e38253fe13270978239a2e89d6063f0000462f154fecb86859781da0", "labels_vector_sha256": "d09b78bd9c17b051b54869d2ee1ac947fc19cec3d07f5f6089a8045793dd9c65", "planned_active_tokens": 65903, "realized_active_tokens": 65903, "cumulative_start": 7340916, "cumulative_end": 7406819, "loss_sum": 27708.281616210938, "token_normalized_loss": 0.4204403686662358, "grad_norm_before_clip": 0.44250109791755676, "learning_rates_at_step": { "lora": 9.913516264091188e-05, "row_tokens": 9.913516264091188e-05 }, "learning_rates_after_step": { "lora": 9.91020580532789e-05, "row_tokens": 9.91020580532789e-05 } }, { "update_id": 113, "row_count": 10, "row_ids_sha256": "c098bef6a068282660d40cd4f67521679bf0eaa9d24137da5dbf31705e796455", "input_ids_vector_sha256": "46b391af91879a926249d71dcd55f54f8e28ab6073365fdeae226acb5886bf50", "labels_vector_sha256": "5c4b7222ffdda3cd1bea6a304db0a797fbffde2974f823b38e15b9f00b7aa2e8", "planned_active_tokens": 67827, "realized_active_tokens": 67827, "cumulative_start": 7406819, "cumulative_end": 7474646, "loss_sum": 31890.862670898438, "token_normalized_loss": 0.47017946644991576, "grad_norm_before_clip": 0.16465431451797485, "learning_rates_at_step": { "lora": 9.91020580532789e-05, "row_tokens": 9.91020580532789e-05 }, "learning_rates_after_step": { "lora": 9.90706648783103e-05, "row_tokens": 9.90706648783103e-05 } }, { "update_id": 114, "row_count": 11, "row_ids_sha256": "0e06cf01520b27f2bb282a78ede33f4add2c5e6307a9ff281c7192f1d093c84b", "input_ids_vector_sha256": "5770a5a0826859a09a1eeec8ae0cb191c71168e1d89ac6cdab0371507c6eb9e4", "labels_vector_sha256": "b426e19e65d0eba57d942a6f97967255e69b724d93958eb01753ad9fae96d018", "planned_active_tokens": 63185, "realized_active_tokens": 63185, "cumulative_start": 7474646, "cumulative_end": 7537831, "loss_sum": 29003.315551757812, "token_normalized_loss": 0.4590221658899709, "grad_norm_before_clip": 0.18692949414253235, "learning_rates_at_step": { "lora": 9.90706648783103e-05, "row_tokens": 9.90706648783103e-05 }, "learning_rates_after_step": { "lora": 9.903786241058578e-05, "row_tokens": 9.903786241058578e-05 } }, { "update_id": 115, "row_count": 11, "row_ids_sha256": "35070ddaa9a77c47a247baeb7ceee360fe8b6c309a9a1558b1454e38a1f10af5", "input_ids_vector_sha256": "4899b997c13db5b6de8bb763c8f36421b32ecbc5df7eb9fb732ea738132e10f1", "labels_vector_sha256": "7d977a404d95d859b2b81323554557b4354e6d548d8f479e2b2521f70797d274", "planned_active_tokens": 64902, "realized_active_tokens": 64902, "cumulative_start": 7537831, "cumulative_end": 7602733, "loss_sum": 31374.01385498047, "token_normalized_loss": 0.4834059636834068, "grad_norm_before_clip": 0.16845276951789856, "learning_rates_at_step": { "lora": 9.903786241058578e-05, "row_tokens": 9.903786241058578e-05 }, "learning_rates_after_step": { "lora": 9.900306111926869e-05, "row_tokens": 9.900306111926869e-05 } }, { "update_id": 116, "row_count": 10, "row_ids_sha256": "f68beb41ea41ffcec4da9ce0c761c69582dd95031073c287f8e651a3817dfea0", "input_ids_vector_sha256": "b3dbb5160aa9ef57f80fdc90493d91468fc0d6f3c27c67e93ce08e6cb9781553", "labels_vector_sha256": "7b51e06e08190abe47993f09844aa8cabd6c7c8736d220129db5fdb5cad53e85", "planned_active_tokens": 67670, "realized_active_tokens": 67670, "cumulative_start": 7602733, "cumulative_end": 7670403, "loss_sum": 36813.31622314453, "token_normalized_loss": 0.544012357368768, "grad_norm_before_clip": 0.18133606016635895, "learning_rates_at_step": { "lora": 9.900306111926869e-05, "row_tokens": 9.900306111926869e-05 }, "learning_rates_after_step": { "lora": 9.89682511344225e-05, "row_tokens": 9.89682511344225e-05 } }, { "update_id": 117, "row_count": 15, "row_ids_sha256": "dfe269c8f4dd89148cc1f1ad48753633dd969288dde2a671f6811d9a25f06553", "input_ids_vector_sha256": "79fe19851f11ed5915d85971425ab1302ffda975d232103cddf9206dcbcd3d40", "labels_vector_sha256": "61a3283925f75f93d42d9fe0ff6c7bc5687a52f607dd017a77040f336830dfc1", "planned_active_tokens": 66527, "realized_active_tokens": 66527, "cumulative_start": 7670403, "cumulative_end": 7736930, "loss_sum": 31229.165588378906, "token_normalized_loss": 0.4694209206544547, "grad_norm_before_clip": 0.16767680644989014, "learning_rates_at_step": { "lora": 9.89682511344225e-05, "row_tokens": 9.89682511344225e-05 }, "learning_rates_after_step": { "lora": 9.893339576003727e-05, "row_tokens": 9.893339576003727e-05 } }, { "update_id": 118, "row_count": 11, "row_ids_sha256": "fdffc118c169ec07ac10a4debaff69ef9f88ef74157c6f2619f14be92cb1f2a0", "input_ids_vector_sha256": "be5778e6b4a86f5b3633c11c722e6458c79e284fd357bf1a4522f7591921266d", "labels_vector_sha256": "618a5b31922bb2fd45b535275f1879c497637e330501f4ced7b6d8c1786d06e7", "planned_active_tokens": 65510, "realized_active_tokens": 65510, "cumulative_start": 7736930, "cumulative_end": 7802440, "loss_sum": 34729.74572753906, "token_normalized_loss": 0.53014418756738, "grad_norm_before_clip": 0.18127545714378357, "learning_rates_at_step": { "lora": 9.893339576003727e-05, "row_tokens": 9.893339576003727e-05 }, "learning_rates_after_step": { "lora": 9.889729105166992e-05, "row_tokens": 9.889729105166992e-05 } }, { "update_id": 119, "row_count": 10, "row_ids_sha256": "2d189bc2fe1aa083c495c5d6cd5c9c140cab897b36b5a21dd21d98dc50792de7", "input_ids_vector_sha256": "206b04d49758637616539ad7becdbaf0b2f470ed2c998addd52cf6e8ad2b41ae", "labels_vector_sha256": "423204db4d3320f3e3dd4255633615275a4108abfd10cd3bc4f594e2817925e7", "planned_active_tokens": 66751, "realized_active_tokens": 66751, "cumulative_start": 7802440, "cumulative_end": 7869191, "loss_sum": 30395.775512695312, "token_normalized_loss": 0.45536060152949487, "grad_norm_before_clip": 0.17236283421516418, "learning_rates_at_step": { "lora": 9.889729105166992e-05, "row_tokens": 9.889729105166992e-05 }, "learning_rates_after_step": { "lora": 9.885851843503711e-05, "row_tokens": 9.885851843503711e-05 } }, { "update_id": 120, "row_count": 9, "row_ids_sha256": "01f9690e3c25f9162574f802736f6ff05119175cc36f127881fe8b78744b6ec8", "input_ids_vector_sha256": "1f5c97c5ddbe779e05d22265206a33a09ce9870a84b2c817c2c3bb79bc8ca336", "labels_vector_sha256": "b760bf25e02bf4b108d9b0d6721481c6d481bf4b28e1300040dbf480e32da54c", "planned_active_tokens": 70491, "realized_active_tokens": 70491, "cumulative_start": 7869191, "cumulative_end": 7939682, "loss_sum": 34995.23583984375, "token_normalized_loss": 0.496449700526929, "grad_norm_before_clip": 0.17228861153125763, "learning_rates_at_step": { "lora": 9.885851843503711e-05, "row_tokens": 9.885851843503711e-05 }, "learning_rates_after_step": { "lora": 9.882724672584232e-05, "row_tokens": 9.882724672584232e-05 } }, { "update_id": 121, "row_count": 8, "row_ids_sha256": "10b809e010a7dd4303e1bc3a5da0ed07510222fd4e720796acf13292d7075aff", "input_ids_vector_sha256": "edef1057f3ad1e7e4c59950d21b3d2bd20111668ce573708ff5fc91ca28c7bad", "labels_vector_sha256": "1008dac8428a58251ad62d1a4f83986aa23f9defb65f368ff7f51e47e693fb1c", "planned_active_tokens": 55996, "realized_active_tokens": 55996, "cumulative_start": 7939682, "cumulative_end": 7995678, "loss_sum": 28564.854125976562, "token_normalized_loss": 0.5101231181865948, "grad_norm_before_clip": 0.19556644558906555, "learning_rates_at_step": { "lora": 9.882724672584232e-05, "row_tokens": 9.882724672584232e-05 }, "learning_rates_after_step": { "lora": 9.878577309655167e-05, "row_tokens": 9.878577309655167e-05 } }, { "update_id": 122, "row_count": 14, "row_ids_sha256": "a31ceb62f763505d0f04f15dc2eb70cedc99172b807961dbead4852b2700451d", "input_ids_vector_sha256": "cff4fdc707d4c109f0478d864597ebb2fdfa4fbf4355388274b6e82689055412", "labels_vector_sha256": "2d48954bc9894000467a98dad2b56595a8796c6530c2adb2bf6e2e6301bdd7c7", "planned_active_tokens": 73138, "realized_active_tokens": 73138, "cumulative_start": 7995678, "cumulative_end": 8068816, "loss_sum": 34577.49621582031, "token_normalized_loss": 0.4727706009983909, "grad_norm_before_clip": 0.17897193133831024, "learning_rates_at_step": { "lora": 9.878577309655167e-05, "row_tokens": 9.878577309655167e-05 }, "learning_rates_after_step": { "lora": 9.875104179961975e-05, "row_tokens": 9.875104179961975e-05 } }, { "update_id": 123, "row_count": 10, "row_ids_sha256": "88b8d806b400a2ed0d046f813ba9361222c11ed884ffec27bf5897959814b919", "input_ids_vector_sha256": "ff9eb107813eb874df8535490615603178564b8526c9b81647f15290a9e24b79", "labels_vector_sha256": "05b6d1904426ceab83693768d8b51ddd91528e7ff48b8f87c98642d677982a71", "planned_active_tokens": 60304, "realized_active_tokens": 60304, "cumulative_start": 8068816, "cumulative_end": 8129120, "loss_sum": 23385.705200195312, "token_normalized_loss": 0.3877969156307262, "grad_norm_before_clip": 0.16537147760391235, "learning_rates_at_step": { "lora": 9.875104179961975e-05, "row_tokens": 9.875104179961975e-05 }, "learning_rates_after_step": { "lora": 9.87127413608528e-05, "row_tokens": 9.87127413608528e-05 } }, { "update_id": 124, "row_count": 14, "row_ids_sha256": "639780faa4526fa3b8355259f056e052025176d9b29e77a9687628635a21a703", "input_ids_vector_sha256": "1b5a4962fcdbf269f35a3fd391d15f926e182f5a037697e3e4d1bf79566c5277", "labels_vector_sha256": "b37885dff3dd2a468a198beb477d80ed5f95bc0671e27229294d95dd78ca8f3a", "planned_active_tokens": 65549, "realized_active_tokens": 65549, "cumulative_start": 8129120, "cumulative_end": 8194669, "loss_sum": 28178.635681152344, "token_normalized_loss": 0.42988658379460165, "grad_norm_before_clip": 0.16481885313987732, "learning_rates_at_step": { "lora": 9.87127413608528e-05, "row_tokens": 9.87127413608528e-05 }, "learning_rates_after_step": { "lora": 9.86711430113477e-05, "row_tokens": 9.86711430113477e-05 } }, { "update_id": 125, "row_count": 11, "row_ids_sha256": "f79a06349eb281168a91c153dbca2620f07173afa52fb53c516190871aa69ad9", "input_ids_vector_sha256": "47b441f0059e22b98c8cf776b60de04a26348a4f8701d5296af2bc04170a3aa2", "labels_vector_sha256": "e97b69b3584bc948511a07f6e8d0cc14637a93408b97d5ad8da2d8200fd5052f", "planned_active_tokens": 70112, "realized_active_tokens": 70112, "cumulative_start": 8194669, "cumulative_end": 8264781, "loss_sum": 33799.566162109375, "token_normalized_loss": 0.48207961778453584, "grad_norm_before_clip": 0.1613491177558899, "learning_rates_at_step": { "lora": 9.86711430113477e-05, "row_tokens": 9.86711430113477e-05 }, "learning_rates_after_step": { "lora": 9.8635610193654e-05, "row_tokens": 9.8635610193654e-05 } }, { "update_id": 126, "row_count": 13, "row_ids_sha256": "0e869f6b4bd9fd5bd012325a0db183dbf39b5bbe3bd89c8ce3b2c52e58fa7a8c", "input_ids_vector_sha256": "72a3f08555922021a3ccb6c38759ad22542e7be707c552454ddb5e4ee3c9dbb7", "labels_vector_sha256": "709d1244ead4c5212854b68bc52bce7e1dd83bb1a9385ebb7f3b5de2ac646ec7", "planned_active_tokens": 59036, "realized_active_tokens": 59036, "cumulative_start": 8264781, "cumulative_end": 8323817, "loss_sum": 24484.159729003906, "token_normalized_loss": 0.41473270087749686, "grad_norm_before_clip": 0.18988876044750214, "learning_rates_at_step": { "lora": 9.8635610193654e-05, "row_tokens": 9.8635610193654e-05 }, "learning_rates_after_step": { "lora": 9.858864385779228e-05, "row_tokens": 9.858864385779228e-05 } }, { "update_id": 127, "row_count": 13, "row_ids_sha256": "e454b717e45463ddb924474e54786c0dd126885b4dbe86deabd2a69e876a53c1", "input_ids_vector_sha256": "5acf952361d59912247326e7261c936b85ed605bd6af6aa7bde3377fbb9de04e", "labels_vector_sha256": "e2f5614adad8bd0d5079c6e84df7dd892945b4676011cbb734a2f558ce83f76f", "planned_active_tokens": 76881, "realized_active_tokens": 76881, "cumulative_start": 8323817, "cumulative_end": 8400698, "loss_sum": 34180.72216796875, "token_normalized_loss": 0.4445925803250315, "grad_norm_before_clip": 0.15379548072814941, "learning_rates_at_step": { "lora": 9.858864385779228e-05, "row_tokens": 9.858864385779228e-05 }, "learning_rates_after_step": { "lora": 9.855417002074334e-05, "row_tokens": 9.855417002074334e-05 } }, { "update_id": 128, "row_count": 8, "row_ids_sha256": "2576d716368bbb063c7ff9af24d8ba3e5d69f57ce79f9ebfc375fb427462ca3f", "input_ids_vector_sha256": "70199c4d5a87ac8f42999521b73c92829ec55420760890ad1a515c045a7b4a0c", "labels_vector_sha256": "717b01c1b907dc53dd354ec9cd859a68b485cac928e97470b41c2048fa207c3f", "planned_active_tokens": 55632, "realized_active_tokens": 55632, "cumulative_start": 8400698, "cumulative_end": 8456330, "loss_sum": 23372.119018554688, "token_normalized_loss": 0.4201200571353661, "grad_norm_before_clip": 0.16943997144699097, "learning_rates_at_step": { "lora": 9.855417002074334e-05, "row_tokens": 9.855417002074334e-05 }, "learning_rates_after_step": { "lora": 9.85125800138455e-05, "row_tokens": 9.85125800138455e-05 } }, { "update_id": 129, "row_count": 13, "row_ids_sha256": "0191e5f4c6c5488370fc4fadcfeb4834b2a1a101cf62936bb22197380735c8d0", "input_ids_vector_sha256": "24b43780c399c4dce0f183947ba09436edb1cd62147863cc00cbc1818925442e", "labels_vector_sha256": "9432bc584d06ec19902a1389b06cdf4817c2b1f1deb789fbc0f890eb8be93edf", "planned_active_tokens": 66253, "realized_active_tokens": 66253, "cumulative_start": 8456330, "cumulative_end": 8522583, "loss_sum": 26511.99102783203, "token_normalized_loss": 0.4001628760634542, "grad_norm_before_clip": 0.1538860946893692, "learning_rates_at_step": { "lora": 9.85125800138455e-05, "row_tokens": 9.85125800138455e-05 }, "learning_rates_after_step": { "lora": 9.846989078461757e-05, "row_tokens": 9.846989078461757e-05 } }, { "update_id": 130, "row_count": 10, "row_ids_sha256": "9845c72b5f7a945bcf2a102db663768ecfbd988444502b461760b7216a141b64", "input_ids_vector_sha256": "001f1048401fb2a5d4206ca18153fe27292feb18f77e3fb626048d7320222fe8", "labels_vector_sha256": "902869c95e0a2065b645ea9d8198b08ed00d6d585cf4832d96be1879dc407291", "planned_active_tokens": 67062, "realized_active_tokens": 67062, "cumulative_start": 8522583, "cumulative_end": 8589645, "loss_sum": 28470.822296142578, "token_normalized_loss": 0.4245447838737672, "grad_norm_before_clip": 0.16799168288707733, "learning_rates_at_step": { "lora": 9.846989078461757e-05, "row_tokens": 9.846989078461757e-05 }, "learning_rates_after_step": { "lora": 9.843043053220919e-05, "row_tokens": 9.843043053220919e-05 } }, { "update_id": 131, "row_count": 12, "row_ids_sha256": "2403db6a0a1139d85614e53c1eb19bf96ce7cb967c575ef7613c1379203a0d23", "input_ids_vector_sha256": "b54eb9c342f293ce20f4fc445f92ddbeae2e028dd27de33fd4222cf20ebecc7e", "labels_vector_sha256": "8ca28deafc3f2c75d344c4c5ecbd7f9fee065a242548bf52d37e58714b06e151", "planned_active_tokens": 61175, "realized_active_tokens": 61175, "cumulative_start": 8589645, "cumulative_end": 8650820, "loss_sum": 26576.11181640625, "token_normalized_loss": 0.4344276553560482, "grad_norm_before_clip": 0.16357511281967163, "learning_rates_at_step": { "lora": 9.843043053220919e-05, "row_tokens": 9.843043053220919e-05 }, "learning_rates_after_step": { "lora": 9.838594377260548e-05, "row_tokens": 9.838594377260548e-05 } }, { "update_id": 132, "row_count": 12, "row_ids_sha256": "c27aec041a651bc1b5a3df23da97a18d4fe44433152dd2a630b97bf83589b41b", "input_ids_vector_sha256": "034b29ab3b325b6c73120f3689ff8443d8b1977ec10910cd31778962f917b58e", "labels_vector_sha256": "48c3df94ee04df7e01e0fa249eb56e573e8eb4ea1414b81a208dd2129fbfa1f7", "planned_active_tokens": 68067, "realized_active_tokens": 68067, "cumulative_start": 8650820, "cumulative_end": 8718887, "loss_sum": 29377.155517578125, "token_normalized_loss": 0.4315917480949377, "grad_norm_before_clip": 0.23389245569705963, "learning_rates_at_step": { "lora": 9.838594377260548e-05, "row_tokens": 9.838594377260548e-05 }, "learning_rates_after_step": { "lora": 9.834213949375765e-05, "row_tokens": 9.834213949375765e-05 } }, { "update_id": 133, "row_count": 10, "row_ids_sha256": "5e5749c18c555be45750306c2bc8b8714a1b2e80be63d2a4ab17a89127186236", "input_ids_vector_sha256": "413b516ae102499dd04f36728b808843fd3b24e4a128e7efe9e3bd76fb44685f", "labels_vector_sha256": "e5170f2619e59e129a699fc7ef27483968c970e4baa2bf6ca5a61c5a5b0b915e", "planned_active_tokens": 66127, "realized_active_tokens": 66127, "cumulative_start": 8718887, "cumulative_end": 8785014, "loss_sum": 31180.005615234375, "token_normalized_loss": 0.471517014460574, "grad_norm_before_clip": 0.16395671665668488, "learning_rates_at_step": { "lora": 9.834213949375765e-05, "row_tokens": 9.834213949375765e-05 }, "learning_rates_after_step": { "lora": 9.829503474414096e-05, "row_tokens": 9.829503474414096e-05 } }, { "update_id": 134, "row_count": 13, "row_ids_sha256": "d63a54ae97c27e9dfb437c465ae7130483fa034c767f32b8de075f356a54b996", "input_ids_vector_sha256": "411294bb74f42a161228c8a35b1656b653185f5c5ed5346fd83fb8a0f4d4c155", "labels_vector_sha256": "9ddc05498a00f80c344f0d4cfd93f4e7b307eccc0ea74c4b657dde9721e91207", "planned_active_tokens": 70158, "realized_active_tokens": 70158, "cumulative_start": 8785014, "cumulative_end": 8855172, "loss_sum": 33626.469177246094, "token_normalized_loss": 0.4792962909040465, "grad_norm_before_clip": 0.17484435439109802, "learning_rates_at_step": { "lora": 9.829503474414096e-05, "row_tokens": 9.829503474414096e-05 }, "learning_rates_after_step": { "lora": 9.825562399721653e-05, "row_tokens": 9.825562399721653e-05 } }, { "update_id": 135, "row_count": 11, "row_ids_sha256": "9a28bca4c85a7ab09de546ba439042acbe4bdc2b552c6dd8919b32c0cf74019b", "input_ids_vector_sha256": "ddebec35a2edc27a04c8eeaacb7ac2e6d2af2fc3f9f7c5ec60072021e5b4b955", "labels_vector_sha256": "0cbf6bed487e01bc1febaf5682c5c1bc490a98f314d1931da9a35145893fd780", "planned_active_tokens": 57970, "realized_active_tokens": 57970, "cumulative_start": 8855172, "cumulative_end": 8913142, "loss_sum": 24074.491577148438, "token_normalized_loss": 0.41529224732013864, "grad_norm_before_clip": 0.17689259350299835, "learning_rates_at_step": { "lora": 9.825562399721653e-05, "row_tokens": 9.825562399721653e-05 }, "learning_rates_after_step": { "lora": 9.820840066347121e-05, "row_tokens": 9.820840066347121e-05 } }, { "update_id": 136, "row_count": 11, "row_ids_sha256": "eb97623acc46feb0916100e3720edf0d2d4cc67d73cca7fe5e296d0bc2902d96", "input_ids_vector_sha256": "8e1d3ca11745eb904a49e1ce28270c3f96f2d2b534120dc4b0ab8b29da837469", "labels_vector_sha256": "2a22a477cce3c21bd0c7cf4953b471739315e32f29b6591b28dbfac79b38b0fe", "planned_active_tokens": 68621, "realized_active_tokens": 68621, "cumulative_start": 8913142, "cumulative_end": 8981763, "loss_sum": 33682.22171020508, "token_normalized_loss": 0.49084422713462467, "grad_norm_before_clip": 0.1630178987979889, "learning_rates_at_step": { "lora": 9.820840066347121e-05, "row_tokens": 9.820840066347121e-05 }, "learning_rates_after_step": { "lora": 9.816368167458028e-05, "row_tokens": 9.816368167458028e-05 } }, { "update_id": 137, "row_count": 11, "row_ids_sha256": "9bcfeabce1da28e3e3649b6c5cad7096588136b32af8e288b65553b8d0af9d4c", "input_ids_vector_sha256": "33f392072231432f93ac4fec9ef2dd92a1d9730b69687a87c6b57e7f44d11be3", "labels_vector_sha256": "bbf9ae43cf9f5a7b14826a9d6b49a20865525715eff3e2c227151607bc40ac77", "planned_active_tokens": 64168, "realized_active_tokens": 64168, "cumulative_start": 8981763, "cumulative_end": 9045931, "loss_sum": 30493.396240234375, "token_normalized_loss": 0.4752118850553917, "grad_norm_before_clip": 0.16285179555416107, "learning_rates_at_step": { "lora": 9.816368167458028e-05, "row_tokens": 9.816368167458028e-05 }, "learning_rates_after_step": { "lora": 9.811462180870455e-05, "row_tokens": 9.811462180870455e-05 } }, { "update_id": 138, "row_count": 11, "row_ids_sha256": "f1eac1557484b86f6bc86d14634135f55497bd76c1f6480c7205169da6f993a4", "input_ids_vector_sha256": "99e48935860baa95400a72a6535df2436567640790b7c7da1d41b61015fd32d4", "labels_vector_sha256": "72569fb4ea0307c02f5466eedbf818247adff795acf9816575e4c1d04d096078", "planned_active_tokens": 69521, "realized_active_tokens": 69521, "cumulative_start": 9045931, "cumulative_end": 9115452, "loss_sum": 31575.73651123047, "token_normalized_loss": 0.4541899068084531, "grad_norm_before_clip": 0.16861550509929657, "learning_rates_at_step": { "lora": 9.811462180870455e-05, "row_tokens": 9.811462180870455e-05 }, "learning_rates_after_step": { "lora": 9.807188365143827e-05, "row_tokens": 9.807188365143827e-05 } }, { "update_id": 139, "row_count": 10, "row_ids_sha256": "8f63eddbbf15a6217eb57aeded20d88b7ce26b35a1365fbb48966a0b5de10607", "input_ids_vector_sha256": "d53e04125314c010020d1ce2478d23c216b4df6b873435f88712bdd871b4054f", "labels_vector_sha256": "1b83bde63fc156613e16dc0ef23a473d7885dcdda7606507d8e12dfc5a9b5650", "planned_active_tokens": 59843, "realized_active_tokens": 59843, "cumulative_start": 9115452, "cumulative_end": 9175295, "loss_sum": 29431.1376953125, "token_normalized_loss": 0.4918058535720552, "grad_norm_before_clip": 0.1804773509502411, "learning_rates_at_step": { "lora": 9.807188365143827e-05, "row_tokens": 9.807188365143827e-05 }, "learning_rates_after_step": { "lora": 9.802444668040613e-05, "row_tokens": 9.802444668040613e-05 } }, { "update_id": 140, "row_count": 12, "row_ids_sha256": "b81827a7d08eb79001d013ce863352f809002fb4f6506ebef1ccd094f5b1d518", "input_ids_vector_sha256": "b98df8fdb3b0c0f5d0f4622d799f4bb64909c49865c860d51d89b13a47f75b76", "labels_vector_sha256": "ec363896c709d2455395ccd39012dff89e1537b71414a96ab3af4ab271ed8ee5", "planned_active_tokens": 65666, "realized_active_tokens": 65666, "cumulative_start": 9175295, "cumulative_end": 9240961, "loss_sum": 30266.05633544922, "token_normalized_loss": 0.4609090904798407, "grad_norm_before_clip": 0.17685005068778992, "learning_rates_at_step": { "lora": 9.802444668040613e-05, "row_tokens": 9.802444668040613e-05 }, "learning_rates_after_step": { "lora": 9.797251739208946e-05, "row_tokens": 9.797251739208946e-05 } }, { "update_id": 141, "row_count": 14, "row_ids_sha256": "2bc5b59662458df42f5495f486f15045b4c9bfbafe3601937588760feea6b5c2", "input_ids_vector_sha256": "178f258fc4a5b2ebaa04ef38a15d2c5bd67cc96f0ca717d19976cd9e551702e1", "labels_vector_sha256": "44bb0639c8a3562c1987e8f0a97a05feee6a99c048818305801821f6351e7756", "planned_active_tokens": 71005, "realized_active_tokens": 71005, "cumulative_start": 9240961, "cumulative_end": 9311966, "loss_sum": 34955.34484863281, "token_normalized_loss": 0.4922941320841182, "grad_norm_before_clip": 0.16384874284267426, "learning_rates_at_step": { "lora": 9.797251739208946e-05, "row_tokens": 9.797251739208946e-05 }, "learning_rates_after_step": { "lora": 9.792427873034782e-05, "row_tokens": 9.792427873034782e-05 } }, { "update_id": 142, "row_count": 11, "row_ids_sha256": "8d8bb1c7831d7aa9807de3561806b4ef328f8e43f339862b886a68152c20b33b", "input_ids_vector_sha256": "c4fedc6cc0cfb8d2d1ddc4b6e57cd33a06026281810dbff70b55ea4c8eceefde", "labels_vector_sha256": "0de121117c0bc0a0edcf35227fb1b9ca427d7cd869aac8a127ff8b947373ae54", "planned_active_tokens": 65165, "realized_active_tokens": 65165, "cumulative_start": 9311966, "cumulative_end": 9377131, "loss_sum": 31119.343139648438, "token_normalized_loss": 0.47754689081022694, "grad_norm_before_clip": 0.2391611635684967, "learning_rates_at_step": { "lora": 9.792427873034782e-05, "row_tokens": 9.792427873034782e-05 }, "learning_rates_after_step": { "lora": 9.78762975368323e-05, "row_tokens": 9.78762975368323e-05 } }, { "update_id": 143, "row_count": 9, "row_ids_sha256": "a3b87124ccacd4e80f673a53c5257f87a129500bb8d7a186ed2bcfed7d1f226f", "input_ids_vector_sha256": "176826740e3b5646593feaa1a0b4daef167f38f3f6931520cca98ec23029543b", "labels_vector_sha256": "d1e7597c41be88b60fb4798101bf42fc44a73f4a5ad468734f1b0dd8397666ed", "planned_active_tokens": 64086, "realized_active_tokens": 64086, "cumulative_start": 9377131, "cumulative_end": 9441217, "loss_sum": 34077.17565917969, "token_normalized_loss": 0.5317413422460395, "grad_norm_before_clip": 0.20037449896335602, "learning_rates_at_step": { "lora": 9.78762975368323e-05, "row_tokens": 9.78762975368323e-05 }, "learning_rates_after_step": { "lora": 9.782533814398541e-05, "row_tokens": 9.782533814398541e-05 } }, { "update_id": 144, "row_count": 10, "row_ids_sha256": "40df4a10cc2d9334b53bfcb9a1f97b5e232a977d0935869de9153bd52885af35", "input_ids_vector_sha256": "2eb15c4def9e00a934b4a767cf192764f1e5ef6b1201b8eec68cb49078c70a44", "labels_vector_sha256": "80c9be3b6eec2ea7e3b7f3a8f6c1c4238f7527d3088df3a97fd00a03360290f2", "planned_active_tokens": 67293, "realized_active_tokens": 67293, "cumulative_start": 9441217, "cumulative_end": 9508510, "loss_sum": 34644.22302246094, "token_normalized_loss": 0.514826549900598, "grad_norm_before_clip": 0.17868424952030182, "learning_rates_at_step": { "lora": 9.782533814398541e-05, "row_tokens": 9.782533814398541e-05 }, "learning_rates_after_step": { "lora": 9.777625289816891e-05, "row_tokens": 9.777625289816891e-05 } }, { "update_id": 145, "row_count": 12, "row_ids_sha256": "812051d5e17a55347752fd6ea055e34fcb0095d9ca28c150554b6de7cf2c4057", "input_ids_vector_sha256": "c7184bbcc47d2164605cc7dd8bcc8d0a8d860a0068a21be1eed76e7154c8687b", "labels_vector_sha256": "41ccfcca57f9e069b80b9af4b63786edbe7f62d2774fb361f3e896416be61176", "planned_active_tokens": 64093, "realized_active_tokens": 64093, "cumulative_start": 9508510, "cumulative_end": 9572603, "loss_sum": 29950.531005859375, "token_normalized_loss": 0.46729800455368564, "grad_norm_before_clip": 0.1731354147195816, "learning_rates_at_step": { "lora": 9.777625289816891e-05, "row_tokens": 9.777625289816891e-05 }, "learning_rates_after_step": { "lora": 9.772424847943848e-05, "row_tokens": 9.772424847943848e-05 } }, { "update_id": 146, "row_count": 11, "row_ids_sha256": "8be0369320088f0bc87023cf001f385022c62bbb9a76ffb727cac49232ac3cd8", "input_ids_vector_sha256": "38d765093f42de2973d62f2e4b80e4def51f3552e92c2a5f6fff477739e29bb6", "labels_vector_sha256": "52cf809a9c52bce97340791c352bf0f5043d4713b48c214eb50a9c2be453019b", "planned_active_tokens": 67155, "realized_active_tokens": 67155, "cumulative_start": 9572603, "cumulative_end": 9639758, "loss_sum": 32049.77850341797, "token_normalized_loss": 0.4772508153289847, "grad_norm_before_clip": 0.16941222548484802, "learning_rates_at_step": { "lora": 9.772424847943848e-05, "row_tokens": 9.772424847943848e-05 }, "learning_rates_after_step": { "lora": 9.767695092427303e-05, "row_tokens": 9.767695092427303e-05 } }, { "update_id": 147, "row_count": 13, "row_ids_sha256": "5a9292fcc774fddbca5b9788db2ae76a4e102e6153d70cec9c79044c72f21025", "input_ids_vector_sha256": "fcb426838e2544ab29cc9307deaf2ac9a52a1db0b6279c7a8e6391acfd11bf7a", "labels_vector_sha256": "2b448b0810654aaf1f8881e7ccd2fb2b1556b8a40d5df5576b1a04ae4c712cec", "planned_active_tokens": 60429, "realized_active_tokens": 60429, "cumulative_start": 9639758, "cumulative_end": 9700187, "loss_sum": 26130.350006103516, "token_normalized_loss": 0.4324140728144354, "grad_norm_before_clip": 0.16539330780506134, "learning_rates_at_step": { "lora": 9.767695092427303e-05, "row_tokens": 9.767695092427303e-05 }, "learning_rates_after_step": { "lora": 9.762493263866787e-05, "row_tokens": 9.762493263866787e-05 } }, { "update_id": 148, "row_count": 15, "row_ids_sha256": "a1ea2038b057fa8053ff847a4775f2a39b10ac7ece3bd8855a992a5986ca2f06", "input_ids_vector_sha256": "fcb15274596d74203acb728eeb43ef22eed1f645d8ebb174988d0de136cf83a5", "labels_vector_sha256": "6dc0211296beb8a2753230ed3df2ee5d4a1eaf0568718c5b38ea415c55669700", "planned_active_tokens": 65771, "realized_active_tokens": 65771, "cumulative_start": 9700187, "cumulative_end": 9765958, "loss_sum": 26331.487426757812, "token_normalized_loss": 0.40035102745522816, "grad_norm_before_clip": 0.1534121036529541, "learning_rates_at_step": { "lora": 9.762493263866787e-05, "row_tokens": 9.762493263866787e-05 }, "learning_rates_after_step": { "lora": 9.757135504010218e-05, "row_tokens": 9.757135504010218e-05 } }, { "update_id": 149, "row_count": 10, "row_ids_sha256": "263ecdd17bda46b9101ba4b94d8ee8052d21550d1ab581e3c4d421543c57a4d8", "input_ids_vector_sha256": "6d415939982a9e7b1f7ea166debc32765273bd08ac20008346afb797b5f9b883", "labels_vector_sha256": "7ad5f9bb9063d7c23262674ec3ed25b3e02fb8f80530bd5f8700d6354d23127b", "planned_active_tokens": 67012, "realized_active_tokens": 67012, "cumulative_start": 9765958, "cumulative_end": 9832970, "loss_sum": 32074.267700195312, "token_normalized_loss": 0.478634687820022, "grad_norm_before_clip": 0.16601915657520294, "learning_rates_at_step": { "lora": 9.757135504010218e-05, "row_tokens": 9.757135504010218e-05 }, "learning_rates_after_step": { "lora": 9.751730783183868e-05, "row_tokens": 9.751730783183868e-05 } }, { "update_id": 150, "row_count": 14, "row_ids_sha256": "050830f09670607bd293021878986bc9e3105735ddc3276bad88bcc377ebdebf", "input_ids_vector_sha256": "9d2215ae20da930aa0ec4c37dad3e617786709e9f0dc5d90d032652f8eba0868", "labels_vector_sha256": "44b0f1adf2ac6a9a292f263d9f614e7cdae9f28da043c0c695ecefdce7995b3f", "planned_active_tokens": 66873, "realized_active_tokens": 66873, "cumulative_start": 9832970, "cumulative_end": 9899843, "loss_sum": 26344.610229492188, "token_normalized_loss": 0.3939498785682142, "grad_norm_before_clip": 0.15393789112567902, "learning_rates_at_step": { "lora": 9.751730783183868e-05, "row_tokens": 9.751730783183868e-05 }, "learning_rates_after_step": { "lora": 9.746391854644347e-05, "row_tokens": 9.746391854644347e-05 } }, { "update_id": 151, "row_count": 13, "row_ids_sha256": "60ae419699f26c3853e025eb0441c7efb32a7fb16846e6ecff3705a215668550", "input_ids_vector_sha256": "ef69b50eee7aa023049917e336926f089a44f59f39ac88aae8c8cded8fd22b46", "labels_vector_sha256": "3c83d109338ed014d63c75d632853e74f577bbcafcaa222efee06f9869421fd0", "planned_active_tokens": 65366, "realized_active_tokens": 65366, "cumulative_start": 9899843, "cumulative_end": 9965209, "loss_sum": 25906.04476928711, "token_normalized_loss": 0.396322931941485, "grad_norm_before_clip": 0.14498315751552582, "learning_rates_at_step": { "lora": 9.746391854644347e-05, "row_tokens": 9.746391854644347e-05 }, "learning_rates_after_step": { "lora": 9.740992562805194e-05, "row_tokens": 9.740992562805194e-05 } }, { "update_id": 152, "row_count": 11, "row_ids_sha256": "2f85ca1ab8a9c8b15aef95881105c025693de669528a458ca42647e6888c0b7d", "input_ids_vector_sha256": "9c89184e62b163d126c703dad785cc639db45073916ca6a31f0e1bc77a2b131c", "labels_vector_sha256": "56bade7ac6a881628b0ac44c6da95cb9fcaccdb1d62b0d826d3b581aa4e6acc5", "planned_active_tokens": 65427, "realized_active_tokens": 65427, "cumulative_start": 9965209, "cumulative_end": 10030636, "loss_sum": 33423.47473144531, "token_normalized_loss": 0.5108514028068735, "grad_norm_before_clip": 0.1621166467666626, "learning_rates_at_step": { "lora": 9.740992562805194e-05, "row_tokens": 9.740992562805194e-05 }, "learning_rates_after_step": { "lora": 9.735608475807262e-05, "row_tokens": 9.735608475807262e-05 } }, { "update_id": 153, "row_count": 7, "row_ids_sha256": "229a40d36d91f1ee5f8388d577d1178de25cd92e81a1a02fffa0fdb58018e480", "input_ids_vector_sha256": "b2b0ccca95f8b8888421ae911c19fc8af6bf30738083bc1a03d91a00a01e477e", "labels_vector_sha256": "0e723440803955d9df4bfac1f1f90606d5f7292366285bb953bbf6202ab38518", "planned_active_tokens": 64585, "realized_active_tokens": 64585, "cumulative_start": 10030636, "cumulative_end": 10095221, "loss_sum": 35532.5341796875, "token_normalized_loss": 0.5501669765377023, "grad_norm_before_clip": 0.1597985178232193, "learning_rates_at_step": { "lora": 9.735608475807262e-05, "row_tokens": 9.735608475807262e-05 }, "learning_rates_after_step": { "lora": 9.729530547393743e-05, "row_tokens": 9.729530547393743e-05 } }, { "update_id": 154, "row_count": 10, "row_ids_sha256": "1d556908e47056d3b8ad49a5c0ebb3d93834c68ffea7ee12bab28e8812f94c1d", "input_ids_vector_sha256": "f025756035f436eba8fd930c4b9b0504f6eab6d419cd2ccf60652c10d18c6d3d", "labels_vector_sha256": "50505111590e08d0c17243fd46dfe4522a6334c893a236c0913f24a034c88024", "planned_active_tokens": 72144, "realized_active_tokens": 72144, "cumulative_start": 10095221, "cumulative_end": 10167365, "loss_sum": 33421.954345703125, "token_normalized_loss": 0.4632672758053771, "grad_norm_before_clip": 0.14401622116565704, "learning_rates_at_step": { "lora": 9.729530547393743e-05, "row_tokens": 9.729530547393743e-05 }, "learning_rates_after_step": { "lora": 9.723774089483011e-05, "row_tokens": 9.723774089483011e-05 } }, { "update_id": 155, "row_count": 9, "row_ids_sha256": "f20a6b8797ac7279fb9233c71abe141682048555d885e3592f5fc7b032929a81", "input_ids_vector_sha256": "cdcdf8c38d9e15a9cb5f58c605be9e0a77e255d05114ee667ce15fc18966bd39", "labels_vector_sha256": "1dec3085863ce51d340463140a77f73c4ec27978ad204ba03fbf9d5273c2d468", "planned_active_tokens": 67605, "realized_active_tokens": 67605, "cumulative_start": 10167365, "cumulative_end": 10234970, "loss_sum": 34329.80627441406, "token_normalized_loss": 0.50779981176561, "grad_norm_before_clip": 0.15475037693977356, "learning_rates_at_step": { "lora": 9.723774089483011e-05, "row_tokens": 9.723774089483011e-05 }, "learning_rates_after_step": { "lora": 9.718955582874873e-05, "row_tokens": 9.718955582874873e-05 } }, { "update_id": 156, "row_count": 7, "row_ids_sha256": "a2dae7e00e434bfe3c5377aaec9d4dd1d80988130c0fcf16833b9dc2ba1acc4b", "input_ids_vector_sha256": "5ec5638115d927ba003db70aec13ba6f506d68acbb4cc5a56560d5058d40dd8f", "labels_vector_sha256": "3eaa7ef4f04d01311108386b7d1c5ec906c25ff91e93b3b09a3121fd05fbd871", "planned_active_tokens": 56065, "realized_active_tokens": 56065, "cumulative_start": 10234970, "cumulative_end": 10291035, "loss_sum": 29765.78485107422, "token_normalized_loss": 0.5309156309832198, "grad_norm_before_clip": 0.18197889626026154, "learning_rates_at_step": { "lora": 9.718955582874873e-05, "row_tokens": 9.718955582874873e-05 }, "learning_rates_after_step": { "lora": 9.71324288348445e-05, "row_tokens": 9.71324288348445e-05 } }, { "update_id": 157, "row_count": 10, "row_ids_sha256": "a5446ed4572647b39936848787860cfd7fb20aa0fc1266d43aab8b1e0d37ba15", "input_ids_vector_sha256": "7c01cbb75f7519a6549b07413718ec656beb5072886e4e4f32b8514bb0d971a9", "labels_vector_sha256": "d03cff2e9a33b0f0eb15a6353b00f0f48ee520425eb95332259dc6af955a3e3d", "planned_active_tokens": 65868, "realized_active_tokens": 65868, "cumulative_start": 10291035, "cumulative_end": 10356903, "loss_sum": 33300.7451171875, "token_normalized_loss": 0.5055678799597301, "grad_norm_before_clip": 0.15098890662193298, "learning_rates_at_step": { "lora": 9.71324288348445e-05, "row_tokens": 9.71324288348445e-05 }, "learning_rates_after_step": { "lora": 9.706858112034859e-05, "row_tokens": 9.706858112034859e-05 } }, { "update_id": 158, "row_count": 7, "row_ids_sha256": "e3e17e7fc79dd54c154c02592e85fba7d44c1838ed9dc936d2295db05468ec1b", "input_ids_vector_sha256": "7e8c3458ec39d6335d14d213fb5bfeaf16dc39879bda39939058278f9a649794", "labels_vector_sha256": "82773f39cf24f1037c943b1fb060470854563da137bab957c0e2206f75754468", "planned_active_tokens": 72868, "realized_active_tokens": 72868, "cumulative_start": 10356903, "cumulative_end": 10429771, "loss_sum": 36542.803466796875, "token_normalized_loss": 0.5014931584069396, "grad_norm_before_clip": 0.15414977073669434, "learning_rates_at_step": { "lora": 9.706858112034859e-05, "row_tokens": 9.706858112034859e-05 }, "learning_rates_after_step": { "lora": 9.701823482411476e-05, "row_tokens": 9.701823482411476e-05 } }, { "update_id": 159, "row_count": 8, "row_ids_sha256": "92e9325c4e33e814557f4e4ca7df12847d7b7f9d56d4dcbfa38cefb7d50a3327", "input_ids_vector_sha256": "0d0d8823e654a6ab555a324b904fe420e02bad8a3043adf2e9750dac2ad4b9e9", "labels_vector_sha256": "e627e888169d0f0bd874abe2fc2697fb2ec3ee5edb2bf5d250e1e78cf3c488b3", "planned_active_tokens": 56918, "realized_active_tokens": 56918, "cumulative_start": 10429771, "cumulative_end": 10486689, "loss_sum": 25101.171020507812, "token_normalized_loss": 0.4410058508821078, "grad_norm_before_clip": 0.1611107587814331, "learning_rates_at_step": { "lora": 9.701823482411476e-05, "row_tokens": 9.701823482411476e-05 }, "learning_rates_after_step": { "lora": 9.695540561898387e-05, "row_tokens": 9.695540561898387e-05 } }, { "update_id": 160, "row_count": 8, "row_ids_sha256": "dcd9a7acec7d0e1b77d4cbca81499336ae0a8110d6a622eaac3bfed29bc52d0e", "input_ids_vector_sha256": "55b5a056de609512e944380f83ef20fa821ccd000e828b86785aa30b35523340", "labels_vector_sha256": "d8ea4f1767a5a5a2948fadd0e9a4bee2ccee110bfb440325329eb6ce3a7f025f", "planned_active_tokens": 70381, "realized_active_tokens": 70381, "cumulative_start": 10486689, "cumulative_end": 10557070, "loss_sum": 34557.57165527344, "token_normalized_loss": 0.49100711350042536, "grad_norm_before_clip": 0.1794823706150055, "learning_rates_at_step": { "lora": 9.695540561898387e-05, "row_tokens": 9.695540561898387e-05 }, "learning_rates_after_step": { "lora": 9.689365193304738e-05, "row_tokens": 9.689365193304738e-05 } }, { "update_id": 161, "row_count": 8, "row_ids_sha256": "5adcaa083cd0da5ec9f040de2793706e4c61e8b58bc1ca340681f70d1d69fafe", "input_ids_vector_sha256": "a384f7222e3582d7f8e48d616ea2e71b0895d07ebd7ec9cf944e167d0d71ea3b", "labels_vector_sha256": "cf057a1a67cc7a4d20f465b1afab6d3d49261018e739725f6784dcbe59e53334", "planned_active_tokens": 68494, "realized_active_tokens": 68494, "cumulative_start": 10557070, "cumulative_end": 10625564, "loss_sum": 32211.985717773438, "token_normalized_loss": 0.4702891598939095, "grad_norm_before_clip": 0.15085290372371674, "learning_rates_at_step": { "lora": 9.689365193304738e-05, "row_tokens": 9.689365193304738e-05 }, "learning_rates_after_step": { "lora": 9.683580636441574e-05, "row_tokens": 9.683580636441574e-05 } }, { "update_id": 162, "row_count": 8, "row_ids_sha256": "3659d879058662349439e68a49d398f6ed2a4b2d9a902bbe8923a70dff927a77", "input_ids_vector_sha256": "3320e3e614a6fd8967fa3e88a6e32da7742fba837d5677a1b0b5812baa8f5962", "labels_vector_sha256": "078843480628350a1e057c887bce5289b83ffb3ff2d00926c1eee2ee8436f6e0", "planned_active_tokens": 63564, "realized_active_tokens": 63564, "cumulative_start": 10625564, "cumulative_end": 10689128, "loss_sum": 29610.05126953125, "token_normalized_loss": 0.46583052151424154, "grad_norm_before_clip": 0.15010742843151093, "learning_rates_at_step": { "lora": 9.683580636441574e-05, "row_tokens": 9.683580636441574e-05 }, "learning_rates_after_step": { "lora": 9.677572829697258e-05, "row_tokens": 9.677572829697258e-05 } }, { "update_id": 163, "row_count": 8, "row_ids_sha256": "1b6b1120ced67b692a5ae992b43573bed9005e7f85f001563567ad6ca73a5466", "input_ids_vector_sha256": "f1f368e9fec934c23e24ea577f02a10763ef981848768aedd1b4c88370540b8f", "labels_vector_sha256": "f9263037d398af2ae88829e483640e43b5484b0c41397c2b9376268e84c8a7aa", "planned_active_tokens": 65425, "realized_active_tokens": 65425, "cumulative_start": 10689128, "cumulative_end": 10754553, "loss_sum": 34472.49755859375, "token_normalized_loss": 0.5269009943995988, "grad_norm_before_clip": 0.1792556643486023, "learning_rates_at_step": { "lora": 9.677572829697258e-05, "row_tokens": 9.677572829697258e-05 }, "learning_rates_after_step": { "lora": 9.670742647952007e-05, "row_tokens": 9.670742647952007e-05 } }, { "update_id": 164, "row_count": 10, "row_ids_sha256": "9122f1061c4cba5d3a500dee15e191af15fd4bf1a073697496ab9d6d9e9e550e", "input_ids_vector_sha256": "55d2536ffe5211fca99fc2434a8b62cc4833ee201f82452f58a21d83fbd2068a", "labels_vector_sha256": "4dffbea8e91c7b76e832da51a8dafd9a8d5cf557e05bf8aab10cc363cc90ebe7", "planned_active_tokens": 73669, "realized_active_tokens": 73669, "cumulative_start": 10754553, "cumulative_end": 10828222, "loss_sum": 33621.861083984375, "token_normalized_loss": 0.45639089826092893, "grad_norm_before_clip": 0.1499422788619995, "learning_rates_at_step": { "lora": 9.670742647952007e-05, "row_tokens": 9.670742647952007e-05 }, "learning_rates_after_step": { "lora": 9.665923134259989e-05, "row_tokens": 9.665923134259989e-05 } }, { "update_id": 165, "row_count": 7, "row_ids_sha256": "02c8ff1b80cf51c0d077a7fdec2372cee62f5617d4c1326b55571a13e06cb745", "input_ids_vector_sha256": "8d2122e4f1a2c7adc7c5194ad1cf6c1a72c5acb9b19ecd545071daa219e4bd2b", "labels_vector_sha256": "b79565e625a78030062944dd5fedc389e2d9fbe453bb65baeb64fa672139d34b", "planned_active_tokens": 51539, "realized_active_tokens": 51539, "cumulative_start": 10828222, "cumulative_end": 10879761, "loss_sum": 23583.202270507812, "token_normalized_loss": 0.4575797409827085, "grad_norm_before_clip": 0.16441918909549713, "learning_rates_at_step": { "lora": 9.665923134259989e-05, "row_tokens": 9.665923134259989e-05 }, "learning_rates_after_step": { "lora": 9.658716833783552e-05, "row_tokens": 9.658716833783552e-05 } }, { "update_id": 166, "row_count": 9, "row_ids_sha256": "ef4aed0b06a2c5958c6cea151f33d760f8263e12d7c8a6c91840842ce2c0a2b4", "input_ids_vector_sha256": "effc11c7b83dd6182910af38c152f74f8644306f47a6c9ff849e26b68d313ba3", "labels_vector_sha256": "44bc331744d2f802e50cf74c243555160a75d92d90dec69ce0ac7d8770f5c470", "planned_active_tokens": 76398, "realized_active_tokens": 76398, "cumulative_start": 10879761, "cumulative_end": 10956159, "loss_sum": 36921.20703125, "token_normalized_loss": 0.4832745233023116, "grad_norm_before_clip": 0.1389743685722351, "learning_rates_at_step": { "lora": 9.658716833783552e-05, "row_tokens": 9.658716833783552e-05 }, "learning_rates_after_step": { "lora": 9.653303900210683e-05, "row_tokens": 9.653303900210683e-05 } }, { "update_id": 167, "row_count": 9, "row_ids_sha256": "35401e87337ed5f09a6bb07eb69e509058e05b815f1839eb8c76327841465be1", "input_ids_vector_sha256": "7a1b947bbcfa4c56661c821fdd52ec2e451491335c1e7e741624a1ea432fa8d7", "labels_vector_sha256": "47bfe3392efa8c4027e629d969330aa1b1c7d650ad1ee0e747f4225bf70c530e", "planned_active_tokens": 56875, "realized_active_tokens": 56875, "cumulative_start": 10956159, "cumulative_end": 11013034, "loss_sum": 25396.311767578125, "token_normalized_loss": 0.4465285585508242, "grad_norm_before_clip": 0.15283672511577606, "learning_rates_at_step": { "lora": 9.653303900210683e-05, "row_tokens": 9.653303900210683e-05 }, "learning_rates_after_step": { "lora": 9.647188927612079e-05, "row_tokens": 9.647188927612079e-05 } }, { "update_id": 168, "row_count": 9, "row_ids_sha256": "9981f08e4b81b82cd0083d13d03f92b45e80b057f3b8a1090bf322e150335154", "input_ids_vector_sha256": "423b6af1116cd69e97905a9aa4bd1160e4e5f86fb08cce4872c73cf4c6713728", "labels_vector_sha256": "2e0b4c56979d0cca3dfc05865d9a94f4d6b7c95350600d834d05f393439b61ac", "planned_active_tokens": 63739, "realized_active_tokens": 63739, "cumulative_start": 11013034, "cumulative_end": 11076773, "loss_sum": 26149.097778320312, "token_normalized_loss": 0.41025271463813856, "grad_norm_before_clip": 0.14223746955394745, "learning_rates_at_step": { "lora": 9.647188927612079e-05, "row_tokens": 9.647188927612079e-05 }, "learning_rates_after_step": { "lora": 9.640760120971338e-05, "row_tokens": 9.640760120971338e-05 } }, { "update_id": 169, "row_count": 13, "row_ids_sha256": "04a1ac4a5e92a9a789e483d412cab22f1e17b8f1a94b5d30bf20d29686a43b1b", "input_ids_vector_sha256": "71b7454a4e4bfa27840b471ef235323966f12f5717ccd5c05175b4b241b4c6b1", "labels_vector_sha256": "f672e163f00df71bb99d6c1579cc7813fa7300f15a8aac8547ad0c4b00d2b1e9", "planned_active_tokens": 66439, "realized_active_tokens": 66439, "cumulative_start": 11076773, "cumulative_end": 11143212, "loss_sum": 32256.584716796875, "token_normalized_loss": 0.4855067763933364, "grad_norm_before_clip": 0.21542653441429138, "learning_rates_at_step": { "lora": 9.640760120971338e-05, "row_tokens": 9.640760120971338e-05 }, "learning_rates_after_step": { "lora": 9.633884139853317e-05, "row_tokens": 9.633884139853317e-05 } }, { "update_id": 170, "row_count": 12, "row_ids_sha256": "87de609281a7011a642e51fc0f78db87304e3fd08b785af01677f7db4d6c19cd", "input_ids_vector_sha256": "0d4be239f4c3326c7f28415df3419479263beafcefdd69a6be5c60a76e65388f", "labels_vector_sha256": "a3c3a046bb49db82496e9891392010066ccc568d1e1900ac5cde172cf539f4c9", "planned_active_tokens": 70430, "realized_active_tokens": 70430, "cumulative_start": 11143212, "cumulative_end": 11213642, "loss_sum": 33605.485290527344, "token_normalized_loss": 0.4771473135102562, "grad_norm_before_clip": 0.1725342869758606, "learning_rates_at_step": { "lora": 9.633884139853317e-05, "row_tokens": 9.633884139853317e-05 }, "learning_rates_after_step": { "lora": 9.627886835810106e-05, "row_tokens": 9.627886835810106e-05 } }, { "update_id": 171, "row_count": 13, "row_ids_sha256": "63f10185305ea91ae8954c4d585c3ce55c74c5ac73f04d56ff65432bc579635b", "input_ids_vector_sha256": "9b2a90830b907e447cec00861dd99972de51d8b4c1b625323daca23d81e79d82", "labels_vector_sha256": "b10823a4ed1f4eee3851455367cfb9a5847ad28b2fa66f6a473de763f2fe0788", "planned_active_tokens": 60912, "realized_active_tokens": 60912, "cumulative_start": 11213642, "cumulative_end": 11274554, "loss_sum": 27406.55926513672, "token_normalized_loss": 0.44993694617048724, "grad_norm_before_clip": 0.15534591674804688, "learning_rates_at_step": { "lora": 9.627886835810106e-05, "row_tokens": 9.627886835810106e-05 }, "learning_rates_after_step": { "lora": 9.621578194862067e-05, "row_tokens": 9.621578194862067e-05 } }, { "update_id": 172, "row_count": 12, "row_ids_sha256": "359a5dc512ad7cad2856c4fbc7c4a41f19b6a37f028c0608d471ed43ab874b7f", "input_ids_vector_sha256": "7d712bd7955bf4e8358605a5b0ff75d6770e904d9ec6883a50b3940f21370d27", "labels_vector_sha256": "10886fbe2696b463c6cf611e543c0aa6eca66cec1fe3eb9934654db54293a577", "planned_active_tokens": 63567, "realized_active_tokens": 63567, "cumulative_start": 11274554, "cumulative_end": 11338121, "loss_sum": 25321.153930664062, "token_normalized_loss": 0.39833803594103956, "grad_norm_before_clip": 0.1496841460466385, "learning_rates_at_step": { "lora": 9.621578194862067e-05, "row_tokens": 9.621578194862067e-05 }, "learning_rates_after_step": { "lora": 9.614621861324644e-05, "row_tokens": 9.614621861324644e-05 } }, { "update_id": 173, "row_count": 15, "row_ids_sha256": "8036fae16d391f3a131fad6ba8649e1a0c52e8604e1cb752e726e004215d1343", "input_ids_vector_sha256": "26225b22f844d20e80d463c7f8f893ce021c6e028ec5650a9fb7baaf4ab1de04", "labels_vector_sha256": "2198f2c2cc527e121f7e774bc7ca84d4a0168efa8d3286e66d946d4a45352bd6", "planned_active_tokens": 69506, "realized_active_tokens": 69506, "cumulative_start": 11338121, "cumulative_end": 11407627, "loss_sum": 30783.10467529297, "token_normalized_loss": 0.442884134827108, "grad_norm_before_clip": 0.1493787169456482, "learning_rates_at_step": { "lora": 9.614621861324644e-05, "row_tokens": 9.614621861324644e-05 }, "learning_rates_after_step": { "lora": 9.607941900121498e-05, "row_tokens": 9.607941900121498e-05 } }, { "update_id": 174, "row_count": 13, "row_ids_sha256": "cf04e7aae674d19f8c6a2779e282630bc87a3ef6a9b44a652326aee10e9de8a7", "input_ids_vector_sha256": "61402895399164a2337f863a499481f45a2ab9b2af8b574bc82ba2363626b030", "labels_vector_sha256": "3de10884ade2c4f7208a747a597f722f4f7e6545dbe8a41b1c42dadefb2a1167", "planned_active_tokens": 66180, "realized_active_tokens": 66180, "cumulative_start": 11407627, "cumulative_end": 11473807, "loss_sum": 28619.471252441406, "token_normalized_loss": 0.43244894609310075, "grad_norm_before_clip": 0.14999936521053314, "learning_rates_at_step": { "lora": 9.607941900121498e-05, "row_tokens": 9.607941900121498e-05 }, "learning_rates_after_step": { "lora": 9.601661494285565e-05, "row_tokens": 9.601661494285565e-05 } }, { "update_id": 175, "row_count": 12, "row_ids_sha256": "4c24cb2e2e05786d7f627dba54470882b43c9a5a7a08ef34ec8ff55421d97a62", "input_ids_vector_sha256": "0f04dc2f0e2c2e3d442afb061f83bdaef3d6f5a8f6968e04e18fd183e51428dc", "labels_vector_sha256": "4e38de9c24bd01773122f2ccfd8dab92684f0521b6db0353273509aa261224d6", "planned_active_tokens": 61730, "realized_active_tokens": 61730, "cumulative_start": 11473807, "cumulative_end": 11535537, "loss_sum": 27380.221313476562, "token_normalized_loss": 0.44354805302894157, "grad_norm_before_clip": 0.16016654670238495, "learning_rates_at_step": { "lora": 9.601661494285565e-05, "row_tokens": 9.601661494285565e-05 }, "learning_rates_after_step": { "lora": 9.594752809346125e-05, "row_tokens": 9.594752809346125e-05 } }, { "update_id": 176, "row_count": 14, "row_ids_sha256": "063773c2efb33e6be623bed1d0b2569d7e8c0bed4fc52ccf6a92758d4188e50e", "input_ids_vector_sha256": "a128add1ffbc2ef7dda0779413846dcb6727888920734bc8007a3d71302862eb", "labels_vector_sha256": "6d437b8507ac01ff64f860ff06a3d8ae3bb716f1309760e914fa6723fd118a84", "planned_active_tokens": 67369, "realized_active_tokens": 67369, "cumulative_start": 11535537, "cumulative_end": 11602906, "loss_sum": 28956.012664794922, "token_normalized_loss": 0.42981211929514945, "grad_norm_before_clip": 0.1460251361131668, "learning_rates_at_step": { "lora": 9.594752809346125e-05, "row_tokens": 9.594752809346125e-05 }, "learning_rates_after_step": { "lora": 9.587733582027742e-05, "row_tokens": 9.587733582027742e-05 } }, { "update_id": 177, "row_count": 11, "row_ids_sha256": "8ef489b5cf9774d9d3a4695b19d2ef981d9d85f526206c8ed6f06d413e6dae56", "input_ids_vector_sha256": "01dfd949db3095af926dd8f37b3a141454d80f431191d335376855d7f3b66684", "labels_vector_sha256": "5dd74ba6593474e0252494da977d0f11ccde6685c16922e7dc90f7a435c4ef83", "planned_active_tokens": 67886, "realized_active_tokens": 67886, "cumulative_start": 11602906, "cumulative_end": 11670792, "loss_sum": 32843.57873535156, "token_normalized_loss": 0.48380488959949863, "grad_norm_before_clip": 0.2067507803440094, "learning_rates_at_step": { "lora": 9.587733582027742e-05, "row_tokens": 9.587733582027742e-05 }, "learning_rates_after_step": { "lora": 9.580849795103e-05, "row_tokens": 9.580849795103e-05 } }, { "update_id": 178, "row_count": 12, "row_ids_sha256": "b8e2fe19d8c6afc7741620c081e64510eafa93c3ac31222dc898282c4eb141c3", "input_ids_vector_sha256": "c2dff6b7f5fde9b431368a1412d84279719a983f9f1095322842178bfeb5d733", "labels_vector_sha256": "cd75c12ae98189d6b41e3780329c7068ded166dc4428a27b058c7ea28e2fd13e", "planned_active_tokens": 66041, "realized_active_tokens": 66041, "cumulative_start": 11670792, "cumulative_end": 11736833, "loss_sum": 31029.86001586914, "token_normalized_loss": 0.4698575129975188, "grad_norm_before_clip": 0.1537369340658188, "learning_rates_at_step": { "lora": 9.580849795103e-05, "row_tokens": 9.580849795103e-05 }, "learning_rates_after_step": { "lora": 9.57426573588249e-05, "row_tokens": 9.57426573588249e-05 } }, { "update_id": 179, "row_count": 10, "row_ids_sha256": "3289a607e925886843d4116711f48d5fce1ca873d98b6c7d4dc77505ec4b3366", "input_ids_vector_sha256": "354134d456063d8880cb4383eddd3d0624de136f3810f8b3945f68d5f179c115", "labels_vector_sha256": "9194cc46c75d364973ced97f795bc67ba06a98582491996fa59e70d58cccaf60", "planned_active_tokens": 62682, "realized_active_tokens": 62682, "cumulative_start": 11736833, "cumulative_end": 11799515, "loss_sum": 25437.51104736328, "token_normalized_loss": 0.4058184334795201, "grad_norm_before_clip": 0.15689225494861603, "learning_rates_at_step": { "lora": 9.57426573588249e-05, "row_tokens": 9.57426573588249e-05 }, "learning_rates_after_step": { "lora": 9.567488737677154e-05, "row_tokens": 9.567488737677154e-05 } }, { "update_id": 180, "row_count": 15, "row_ids_sha256": "80aefd69f5376ece3f47c084399344c7cea786570c92b59d0f5bb711c9075da1", "input_ids_vector_sha256": "ad7f62184b3f3943a74d44f70575f43290321ded5a94bc9a172ccaeb400924dc", "labels_vector_sha256": "9ff8268ede393383e31664d1cb9b8264eecb8f614db230dc52a1e996ea345085", "planned_active_tokens": 64037, "realized_active_tokens": 64037, "cumulative_start": 11799515, "cumulative_end": 11863552, "loss_sum": 24569.696655273438, "token_normalized_loss": 0.38367969541473584, "grad_norm_before_clip": 0.1572553664445877, "learning_rates_at_step": { "lora": 9.567488737677154e-05, "row_tokens": 9.567488737677154e-05 }, "learning_rates_after_step": { "lora": 9.56061228573395e-05, "row_tokens": 9.56061228573395e-05 } }, { "update_id": 181, "row_count": 12, "row_ids_sha256": "a03a49e4dbf9b9fa50ca8331750010a14d4242e9eba6ee02f0c22bfc1d7e5ebe", "input_ids_vector_sha256": "e9f1bc8479c640878631a19de0fecf1c83eeb35fd18e8d30a3d729740136e95b", "labels_vector_sha256": "7f4d8ed1f7be22441084a7f4c3fe7d018fc43bf952bc264e1804579541085f61", "planned_active_tokens": 64489, "realized_active_tokens": 64489, "cumulative_start": 11863552, "cumulative_end": 11928041, "loss_sum": 30307.61492919922, "token_normalized_loss": 0.46996565195923673, "grad_norm_before_clip": 0.15684150159358978, "learning_rates_at_step": { "lora": 9.56061228573395e-05, "row_tokens": 9.56061228573395e-05 }, "learning_rates_after_step": { "lora": 9.553043475052992e-05, "row_tokens": 9.553043475052992e-05 } }, { "update_id": 182, "row_count": 12, "row_ids_sha256": "f3c9be88aeca2fbeef1d20953ad4f34014825c774fcdbaef30f9351a1c11d605", "input_ids_vector_sha256": "39258e4a67afc727a2dcf16520a48b7b01c4f5841e480aa72aaeb20da628ba9e", "labels_vector_sha256": "0339b61f368e602719eb380ea98975fefd9a996ed8fb23e302266dc19dde50d7", "planned_active_tokens": 70428, "realized_active_tokens": 70428, "cumulative_start": 11928041, "cumulative_end": 11998469, "loss_sum": 31512.748596191406, "token_normalized_loss": 0.4474463082323991, "grad_norm_before_clip": 0.16193807125091553, "learning_rates_at_step": { "lora": 9.553043475052992e-05, "row_tokens": 9.553043475052992e-05 }, "learning_rates_after_step": { "lora": 9.546172387106819e-05, "row_tokens": 9.546172387106819e-05 } }, { "update_id": 183, "row_count": 11, "row_ids_sha256": "7442dd68630995c4a4e760f7060832477ff264609cbadd3e98a93f6a3922da8f", "input_ids_vector_sha256": "5146b862a8a3ca1a28aa7eed425371df674147ab36d42ac24aca58266ab31ba1", "labels_vector_sha256": "79db7850bcf911a6ef23a4bf2a80e8aff5a1a62028019a4d20c8410cf8171193", "planned_active_tokens": 63445, "realized_active_tokens": 63445, "cumulative_start": 11998469, "cumulative_end": 12061914, "loss_sum": 27056.499145507812, "token_normalized_loss": 0.42645597203101604, "grad_norm_before_clip": 0.158050075173378, "learning_rates_at_step": { "lora": 9.546172387106819e-05, "row_tokens": 9.546172387106819e-05 }, "learning_rates_after_step": { "lora": 9.53856526517044e-05, "row_tokens": 9.53856526517044e-05 } }, { "update_id": 184, "row_count": 13, "row_ids_sha256": "6f3045af5e83b6e84a8e346586697b3d41d8ee8628e57e5ae8306c9cfddb2ad4", "input_ids_vector_sha256": "041d6a250cd4694a3ddaa0385e382209a492c37f44976e2b20b092843cfb66c9", "labels_vector_sha256": "061c3226a9d916654efadb9bbfba52527d675685ae3fecc823cacfbdfd83a578", "planned_active_tokens": 69710, "realized_active_tokens": 69710, "cumulative_start": 12061914, "cumulative_end": 12131624, "loss_sum": 29720.467529296875, "token_normalized_loss": 0.4263443914688979, "grad_norm_before_clip": 0.1404147893190384, "learning_rates_at_step": { "lora": 9.53856526517044e-05, "row_tokens": 9.53856526517044e-05 }, "learning_rates_after_step": { "lora": 9.532082303449313e-05, "row_tokens": 9.532082303449313e-05 } }, { "update_id": 185, "row_count": 14, "row_ids_sha256": "083450afe0bf930831faca584e5a5b00c5008ad651224520be5c9faa5f8e8f13", "input_ids_vector_sha256": "5bacb5a7e3f58f72b10017c09a8942fa9ce2d7ac752d6169135240236235b026", "labels_vector_sha256": "28bd7faec4caea27ed20fd4fb7a7658709140db28c108be94062c7ccca3a13fe", "planned_active_tokens": 58978, "realized_active_tokens": 58978, "cumulative_start": 12131624, "cumulative_end": 12190602, "loss_sum": 25128.412719726562, "token_normalized_loss": 0.4260641717204138, "grad_norm_before_clip": 0.16081582009792328, "learning_rates_at_step": { "lora": 9.532082303449313e-05, "row_tokens": 9.532082303449313e-05 }, "learning_rates_after_step": { "lora": 9.524391573424723e-05, "row_tokens": 9.524391573424723e-05 } }, { "update_id": 186, "row_count": 10, "row_ids_sha256": "eb6eb6133769f20aa7e35fb9e1c4fcd7bae294036f62726b7aec739a2cb72a6c", "input_ids_vector_sha256": "8107cf31fc45c935d09fe0913263850b2b6093d612e786ee8d1427dd56ae2e8e", "labels_vector_sha256": "ae1d114c3ca837ce6c19f6c890aaa96048cc67d7d043ffa9ae953d0342a1aba5", "planned_active_tokens": 69464, "realized_active_tokens": 69464, "cumulative_start": 12190602, "cumulative_end": 12260066, "loss_sum": 36742.13830566406, "token_normalized_loss": 0.5289378427050567, "grad_norm_before_clip": 0.163568913936615, "learning_rates_at_step": { "lora": 9.524391573424723e-05, "row_tokens": 9.524391573424723e-05 }, "learning_rates_after_step": { "lora": 9.517298987325022e-05, "row_tokens": 9.517298987325022e-05 } }, { "update_id": 187, "row_count": 15, "row_ids_sha256": "d6e54cbff1fa361aaec41016cfb1afddac2aa160b6d50cf851b874c1012fe9af", "input_ids_vector_sha256": "eaf48796ef52acb7d70e728c6815b2dac7758ca0cf43f28836bf3b3a2a8d7aa4", "labels_vector_sha256": "17bf8b154676ecd58395a5ce0b44af628edafbac1df118b8c14503295184df8b", "planned_active_tokens": 63590, "realized_active_tokens": 63590, "cumulative_start": 12260066, "cumulative_end": 12323656, "loss_sum": 23678.431549072266, "token_normalized_loss": 0.37236093016311156, "grad_norm_before_clip": 0.14885757863521576, "learning_rates_at_step": { "lora": 9.517298987325022e-05, "row_tokens": 9.517298987325022e-05 }, "learning_rates_after_step": { "lora": 9.509854028220418e-05, "row_tokens": 9.509854028220418e-05 } }, { "update_id": 188, "row_count": 13, "row_ids_sha256": "0ba73abfdd7a723d22300efc7e9932c7e121fa4df200a23cdcde3a3f0f37d87d", "input_ids_vector_sha256": "2d97c81e85b849ddbd931f9617632e73b6b217ad3f669e3d0891f3ef51327c84", "labels_vector_sha256": "039fcd38f6fadccfd9258f3263f22e998141ebb7ccb6fdb07e3f95847a709cd9", "planned_active_tokens": 66274, "realized_active_tokens": 66274, "cumulative_start": 12323656, "cumulative_end": 12389930, "loss_sum": 27994.507690429688, "token_normalized_loss": 0.42240558424766406, "grad_norm_before_clip": 0.15319882333278656, "learning_rates_at_step": { "lora": 9.509854028220418e-05, "row_tokens": 9.509854028220418e-05 }, "learning_rates_after_step": { "lora": 9.502434539339775e-05, "row_tokens": 9.502434539339775e-05 } }, { "update_id": 189, "row_count": 16, "row_ids_sha256": "1ed9b320eaeb419f34f34df8392ba2483f826f2e8d9bfcd3b27699d524b82b1d", "input_ids_vector_sha256": "a4a226627d591e080be67ab5431f098856f9b8c5fdceab847ca3e62cfe8c2c61", "labels_vector_sha256": "5d1cb449bcfa8c4c9f5b7ccbd44414fe7577d6006e10fae156e40f43885a972d", "planned_active_tokens": 65574, "realized_active_tokens": 65574, "cumulative_start": 12389930, "cumulative_end": 12455504, "loss_sum": 24922.264099121094, "token_normalized_loss": 0.38006319729040616, "grad_norm_before_clip": 0.14735853672027588, "learning_rates_at_step": { "lora": 9.502434539339775e-05, "row_tokens": 9.502434539339775e-05 }, "learning_rates_after_step": { "lora": 9.494998733340576e-05, "row_tokens": 9.494998733340576e-05 } }, { "update_id": 190, "row_count": 11, "row_ids_sha256": "d8bb9649825b791b8e076c954cbc6c689334e032353c6ef16ee2c68c60a1d82b", "input_ids_vector_sha256": "90a72488b25bc1d02159c2675bfd605cadee68167bc51f4a5d81c4718b8de45d", "labels_vector_sha256": "fa4e75374d024ce09e0ce8e0f3d03d2a772ec4feb1dc34005b0227d105ef4343", "planned_active_tokens": 65255, "realized_active_tokens": 65255, "cumulative_start": 12455504, "cumulative_end": 12520759, "loss_sum": 30338.993286132812, "token_normalized_loss": 0.46492978754321984, "grad_norm_before_clip": 0.16415531933307648, "learning_rates_at_step": { "lora": 9.494998733340576e-05, "row_tokens": 9.494998733340576e-05 }, "learning_rates_after_step": { "lora": 9.487854857466851e-05, "row_tokens": 9.487854857466851e-05 } }, { "update_id": 191, "row_count": 12, "row_ids_sha256": "c4d06219436c555b0e0a76e846150d715b0f38271b10c8a51eba52829eedf13c", "input_ids_vector_sha256": "28272ce150583f1772a1e3c92bd0f246de937d8adbd911461c740fcdbcfdaf47", "labels_vector_sha256": "dbf5e5d575ecc755c7c27758ee9831d75b1a41ed07a148b32b04175d8a21acf0", "planned_active_tokens": 62266, "realized_active_tokens": 62266, "cumulative_start": 12520759, "cumulative_end": 12583025, "loss_sum": 23203.62811279297, "token_normalized_loss": 0.3726532636236946, "grad_norm_before_clip": 0.15890781581401825, "learning_rates_at_step": { "lora": 9.487854857466851e-05, "row_tokens": 9.487854857466851e-05 }, "learning_rates_after_step": { "lora": 9.480260911904788e-05, "row_tokens": 9.480260911904788e-05 } }, { "update_id": 192, "row_count": 11, "row_ids_sha256": "1a355f7a748cc09d13e7ba74808559745f52d668e58c8d79ec91f764f1ebf8d5", "input_ids_vector_sha256": "f15026eb8d0198b9173b76731560bf85a4378f2a50b345bf0e65c92f8b25dc49", "labels_vector_sha256": "5cf90d821064772cc6156eb2d765139f76d2da413d2b7f70f2eb813599f9d4b5", "planned_active_tokens": 65740, "realized_active_tokens": 65740, "cumulative_start": 12583025, "cumulative_end": 12648765, "loss_sum": 25577.534057617188, "token_normalized_loss": 0.3890710991423363, "grad_norm_before_clip": 0.15307176113128662, "learning_rates_at_step": { "lora": 9.480260911904788e-05, "row_tokens": 9.480260911904788e-05 }, "learning_rates_after_step": { "lora": 9.472163187434805e-05, "row_tokens": 9.472163187434805e-05 } }, { "update_id": 193, "row_count": 12, "row_ids_sha256": "2df095f1d1ee128e605273997feb9bb2015573f34a2e8881310f33077d8b6f1c", "input_ids_vector_sha256": "33a61fceb62af1bdab87f514b91e2ed0ea42363a675d0a224ba90547288a7fbd", "labels_vector_sha256": "cf61169f32d455bcfff57b254d4b65f6145e9c5bfa8195d37afdecb785721950", "planned_active_tokens": 69603, "realized_active_tokens": 69603, "cumulative_start": 12648765, "cumulative_end": 12718368, "loss_sum": 27738.764282226562, "token_normalized_loss": 0.39852828588173733, "grad_norm_before_clip": 0.14778761565685272, "learning_rates_at_step": { "lora": 9.472163187434805e-05, "row_tokens": 9.472163187434805e-05 }, "learning_rates_after_step": { "lora": 9.4642703939904e-05, "row_tokens": 9.4642703939904e-05 } }, { "update_id": 194, "row_count": 13, "row_ids_sha256": "4e5c851880a48d38aa8a10b60f848f17bdbad1fda38af7104965036b80e4c49f", "input_ids_vector_sha256": "15b07cc20521e53b0271db515ca35c4b25ce78f39c3a2ae98df603d05e05a527", "labels_vector_sha256": "f8c1aa7b87b2f79cdd3a5a4f8ee6c4c77e7b27fc7d688395cba8df06b636c9b3", "planned_active_tokens": 67358, "realized_active_tokens": 67358, "cumulative_start": 12718368, "cumulative_end": 12785726, "loss_sum": 27289.74301147461, "token_normalized_loss": 0.4051447936618458, "grad_norm_before_clip": 0.15937504172325134, "learning_rates_at_step": { "lora": 9.4642703939904e-05, "row_tokens": 9.4642703939904e-05 }, "learning_rates_after_step": { "lora": 9.457235626953136e-05, "row_tokens": 9.457235626953136e-05 } }, { "update_id": 195, "row_count": 12, "row_ids_sha256": "0c3a9e2bc852e3c24196ae587a3acf7686241d187ec6451d850716f95185ef78", "input_ids_vector_sha256": "efe19e8d0a4c8af28179a808700ca5a8306bb2e570ffcecece9f992c6f397a30", "labels_vector_sha256": "daf5f8e2b68b50a7ee07552a9326c5f8a0b8c4e10f3cfd3ff720806d8005e6b0", "planned_active_tokens": 59642, "realized_active_tokens": 59642, "cumulative_start": 12785726, "cumulative_end": 12845368, "loss_sum": 25324.31234741211, "token_normalized_loss": 0.4246053510514756, "grad_norm_before_clip": 0.158775195479393, "learning_rates_at_step": { "lora": 9.457235626953136e-05, "row_tokens": 9.457235626953136e-05 }, "learning_rates_after_step": { "lora": 9.449239011090447e-05, "row_tokens": 9.449239011090447e-05 } }, { "update_id": 196, "row_count": 10, "row_ids_sha256": "80bbc300e8db296faa98ccd455713dc426d0a3c9a72ae9db8cb3b33c5659011a", "input_ids_vector_sha256": "c43da7488f41025d6736804b46c7990bba40e0773caf734f9dee221cfa75003a", "labels_vector_sha256": "646d9bdc424217337a9a538145636a6080ec2cc7f0c7e3637f8313a168ee6b1a", "planned_active_tokens": 67356, "realized_active_tokens": 67356, "cumulative_start": 12845368, "cumulative_end": 12912724, "loss_sum": 32607.758880615234, "token_normalized_loss": 0.4841106787905344, "grad_norm_before_clip": 0.16227146983146667, "learning_rates_at_step": { "lora": 9.449239011090447e-05, "row_tokens": 9.449239011090447e-05 }, "learning_rates_after_step": { "lora": 9.439900941670956e-05, "row_tokens": 9.439900941670956e-05 } }, { "update_id": 197, "row_count": 14, "row_ids_sha256": "6a0a4469f6c55e112789a36fa4a6a9b4f211a7d0ea892f3e96c61ea25c7af0aa", "input_ids_vector_sha256": "e576eb9f1d059ef976639578a99b11fa776896a62650fc5714c83669b635c251", "labels_vector_sha256": "2a3dbf337512e4defc972c33ab4e55abfd162596553b28ef21cbbf72aeab7e8c", "planned_active_tokens": 78075, "realized_active_tokens": 78075, "cumulative_start": 12912724, "cumulative_end": 12990799, "loss_sum": 28720.80340576172, "token_normalized_loss": 0.3678617150914085, "grad_norm_before_clip": 0.13310202956199646, "learning_rates_at_step": { "lora": 9.439900941670956e-05, "row_tokens": 9.439900941670956e-05 }, "learning_rates_after_step": { "lora": 9.43365893241774e-05, "row_tokens": 9.43365893241774e-05 } }, { "update_id": 198, "row_count": 12, "row_ids_sha256": "22ca0c988ca407bda47a58f03ca6fa5d60edcfc1ba6d58b94fc1e569dc82f68a", "input_ids_vector_sha256": "0da352996b0896b7da8bfcbcd1de3f871d5fa053194bd83c24c13384b5be43de", "labels_vector_sha256": "fb38d30ba97f37a51934f89605bc3ca19d7766f48ff1d57f8a5bf4c94eb0f833", "planned_active_tokens": 51848, "realized_active_tokens": 51848, "cumulative_start": 12990799, "cumulative_end": 13042647, "loss_sum": 20536.112915039062, "token_normalized_loss": 0.3960830295293755, "grad_norm_before_clip": 0.1642385572195053, "learning_rates_at_step": { "lora": 9.43365893241774e-05, "row_tokens": 9.43365893241774e-05 }, "learning_rates_after_step": { "lora": 9.425750704018973e-05, "row_tokens": 9.425750704018973e-05 } }, { "update_id": 199, "row_count": 14, "row_ids_sha256": "6663bdd9598439c67c7db46cbddf2cf7bb02d55931c6daa174c950990f74d894", "input_ids_vector_sha256": "5148df77a9ec4d8ef185457cb6caa49c2ebcaa12619ff9ff60bafaef11cf1282", "labels_vector_sha256": "8fd52898894e258e8a5fae103778201ea874812ec5a3442db2e488d0077f0aac", "planned_active_tokens": 65304, "realized_active_tokens": 65304, "cumulative_start": 13042647, "cumulative_end": 13107951, "loss_sum": 26564.14859008789, "token_normalized_loss": 0.4067767455299505, "grad_norm_before_clip": 0.14956459403038025, "learning_rates_at_step": { "lora": 9.425750704018973e-05, "row_tokens": 9.425750704018973e-05 }, "learning_rates_after_step": { "lora": 9.417689753519177e-05, "row_tokens": 9.417689753519177e-05 } }, { "update_id": 200, "row_count": 10, "row_ids_sha256": "1afd56b1a2c1a357c4cc3a0d876ab9d4e08f1da31aeb6a386950a397c8178573", "input_ids_vector_sha256": "def35f6dc6cc05ad633ec54d3b1a5a391dc86652e371a7869e53501081b25421", "labels_vector_sha256": "13c4ea5d415271a85f9f5dd9dbb4abd8f86148ab576440af51630063f78f538e", "planned_active_tokens": 66132, "realized_active_tokens": 66132, "cumulative_start": 13107951, "cumulative_end": 13174083, "loss_sum": 31128.778350830078, "token_normalized_loss": 0.47070674334407064, "grad_norm_before_clip": 0.15467895567417145, "learning_rates_at_step": { "lora": 9.417689753519177e-05, "row_tokens": 9.417689753519177e-05 }, "learning_rates_after_step": { "lora": 9.409756547656231e-05, "row_tokens": 9.409756547656231e-05 } }, { "update_id": 201, "row_count": 11, "row_ids_sha256": "3e3ef40ae6bf0ea49b4c52b69db4fca5e3f58c44bfd990767e2dcb0f3052daab", "input_ids_vector_sha256": "6d28471c7f7c6911c1f4cb3c8a039c46f64af81732e4e4fe71fd2d39f8b46d87", "labels_vector_sha256": "3f3a1fa29f903dfc5d08cbaa18c89547f2e5d4aef6ba14814dd3f3a739d98bfa", "planned_active_tokens": 64666, "realized_active_tokens": 64666, "cumulative_start": 13174083, "cumulative_end": 13238749, "loss_sum": 26891.94140625, "token_normalized_loss": 0.4158590512208889, "grad_norm_before_clip": 0.14635859429836273, "learning_rates_at_step": { "lora": 9.409756547656231e-05, "row_tokens": 9.409756547656231e-05 }, "learning_rates_after_step": { "lora": 9.400886136310528e-05, "row_tokens": 9.400886136310528e-05 } }, { "update_id": 202, "row_count": 15, "row_ids_sha256": "6b5fd6f3046f5cee0464ddbbae15055a223d11db2403c14aba94564a60ac8d5e", "input_ids_vector_sha256": "e9cad944ae499cae78644960ab10179901e31bbdea39fa45a5f0692d86129ae5", "labels_vector_sha256": "437b588b1d8a7ad2a564f4d2643924150045ab6a2f0f86651b89d456ad287009", "planned_active_tokens": 71825, "realized_active_tokens": 71825, "cumulative_start": 13238749, "cumulative_end": 13310574, "loss_sum": 27879.469955444336, "token_normalized_loss": 0.3881583008067433, "grad_norm_before_clip": 0.13925960659980774, "learning_rates_at_step": { "lora": 9.400886136310528e-05, "row_tokens": 9.400886136310528e-05 }, "learning_rates_after_step": { "lora": 9.393374923528831e-05, "row_tokens": 9.393374923528831e-05 } }, { "update_id": 203, "row_count": 12, "row_ids_sha256": "c4dd70c2be2162c1c1605e5a117b726ed350f8298e6d2b188f67b68e81367d30", "input_ids_vector_sha256": "c62f261c04e0ea565ba5baa901eac1f10f6be0ff6ae5167f5d1554cc3633cee4", "labels_vector_sha256": "48b6fda890e7bcc6a094d18c0d1f6dbf6052c150a5567cebcabe02d12899efd7", "planned_active_tokens": 60431, "realized_active_tokens": 60431, "cumulative_start": 13310574, "cumulative_end": 13371005, "loss_sum": 24539.081909179688, "token_normalized_loss": 0.4060677782790238, "grad_norm_before_clip": 0.164203479886055, "learning_rates_at_step": { "lora": 9.393374923528831e-05, "row_tokens": 9.393374923528831e-05 }, "learning_rates_after_step": { "lora": 9.384624798200312e-05, "row_tokens": 9.384624798200312e-05 } }, { "update_id": 204, "row_count": 18, "row_ids_sha256": "048b1eac03d74b01a6cb35be61e4de02609baa802c1688222dcbc57138b4894c", "input_ids_vector_sha256": "480b9b64c276ecc2e03c0d7a7ae4a374d04f0656cbdfec899f8f81e8d7f03a05", "labels_vector_sha256": "2242bcf13271c799e954b56a2a1cffd878d6f2b0c6408dc84797b2b4357c799f", "planned_active_tokens": 69959, "realized_active_tokens": 69959, "cumulative_start": 13371005, "cumulative_end": 13440964, "loss_sum": 25485.32830810547, "token_normalized_loss": 0.36428948824462143, "grad_norm_before_clip": 0.14455915987491608, "learning_rates_at_step": { "lora": 9.384624798200312e-05, "row_tokens": 9.384624798200312e-05 }, "learning_rates_after_step": { "lora": 9.376775405275497e-05, "row_tokens": 9.376775405275497e-05 } }, { "update_id": 205, "row_count": 14, "row_ids_sha256": "3285269872e2b6ac274d5c7ee8d5064a2bc85f7eff82ab73f15e582bef35f189", "input_ids_vector_sha256": "73124992875502c0f9cf8414a266e6c8dc0581e3863029da8b3caa9d7ed3dad3", "labels_vector_sha256": "8d0b8d95593e7f5270bad87357c0fad60b8b87f41b05a1b03d54be2ff697928d", "planned_active_tokens": 62363, "realized_active_tokens": 62363, "cumulative_start": 13440964, "cumulative_end": 13503327, "loss_sum": 25169.277420043945, "token_normalized_loss": 0.403593114828407, "grad_norm_before_clip": 0.15841031074523926, "learning_rates_at_step": { "lora": 9.376775405275497e-05, "row_tokens": 9.376775405275497e-05 }, "learning_rates_after_step": { "lora": 9.368823720209358e-05, "row_tokens": 9.368823720209358e-05 } }, { "update_id": 206, "row_count": 16, "row_ids_sha256": "02e3c070494575fd654522b3abebdd329ca2e669b75e96913e451e163e33e7b5", "input_ids_vector_sha256": "38da9c5863c7ce7bd1471b13152b781cf1e28fe4981f1868a8d1123cb45e74f2", "labels_vector_sha256": "0231fd0a454cdf584793af94bf6786779ea1169e064ae57dffdf3eb650e4efc8", "planned_active_tokens": 62803, "realized_active_tokens": 62803, "cumulative_start": 13503327, "cumulative_end": 13566130, "loss_sum": 22077.006591796875, "token_normalized_loss": 0.35152789821818825, "grad_norm_before_clip": 0.15057365596294403, "learning_rates_at_step": { "lora": 9.368823720209358e-05, "row_tokens": 9.368823720209358e-05 }, "learning_rates_after_step": { "lora": 9.360075035120383e-05, "row_tokens": 9.360075035120383e-05 } }, { "update_id": 207, "row_count": 17, "row_ids_sha256": "123d41b22825f229d16fa2e7b72b5e79c0307d2d8f02e5489a2116b58dd82105", "input_ids_vector_sha256": "e0de1c2b325ae1d784e012c8ec1a40c18d5ea5425a1f0904a10c18b9d2d0c788", "labels_vector_sha256": "fce56bf2345243326e6e176d0894c3cc8b0a2a758488d74daf906fab17881756", "planned_active_tokens": 68673, "realized_active_tokens": 68673, "cumulative_start": 13566130, "cumulative_end": 13634803, "loss_sum": 25590.930633544922, "token_normalized_loss": 0.3726490852816234, "grad_norm_before_clip": 0.14689655601978302, "learning_rates_at_step": { "lora": 9.360075035120383e-05, "row_tokens": 9.360075035120383e-05 }, "learning_rates_after_step": { "lora": 9.351580218289578e-05, "row_tokens": 9.351580218289578e-05 } }, { "update_id": 208, "row_count": 15, "row_ids_sha256": "d1b4077e320884522826027426ef223c531853be19b9f2aa481faec67eb6c7c1", "input_ids_vector_sha256": "128ea8cc15d87e31542b8802a4e7b0eea75ae1f7ec0e311cc2a8f23c5e803b23", "labels_vector_sha256": "ed89eed4077b88cfcae193f493d48eaab1a40ff3870ed392ca2b568c062517d8", "planned_active_tokens": 66263, "realized_active_tokens": 66263, "cumulative_start": 13634803, "cumulative_end": 13701066, "loss_sum": 28336.427612304688, "token_normalized_loss": 0.4276357486426013, "grad_norm_before_clip": 0.1603502333164215, "learning_rates_at_step": { "lora": 9.351580218289578e-05, "row_tokens": 9.351580218289578e-05 }, "learning_rates_after_step": { "lora": 9.342970030008664e-05, "row_tokens": 9.342970030008664e-05 } }, { "update_id": 209, "row_count": 15, "row_ids_sha256": "e271f85c825bea44b43fa1da6728effda1688fe11b875d633c59e32154255c0e", "input_ids_vector_sha256": "ed3ca63ecd6992c81bdb3976b343f8f05cf1a868001b34a14ccf6d3db02db584", "labels_vector_sha256": "2add8e2376bf5ca4dd274fc07ba07e94ce24f6bbb8c349b36435ff3f334440ff", "planned_active_tokens": 66752, "realized_active_tokens": 66752, "cumulative_start": 13701066, "cumulative_end": 13767818, "loss_sum": 27947.82583618164, "token_normalized_loss": 0.41868147525439897, "grad_norm_before_clip": 0.22839316725730896, "learning_rates_at_step": { "lora": 9.342970030008664e-05, "row_tokens": 9.342970030008664e-05 }, "learning_rates_after_step": { "lora": 9.334457802490621e-05, "row_tokens": 9.334457802490621e-05 } }, { "update_id": 210, "row_count": 15, "row_ids_sha256": "0beeff99c5b8f1ed3f12bab9e5bf63d632be30b7aa0361969b4c6916fb041703", "input_ids_vector_sha256": "fbcbac951dc048d41c91efd185fb9aa563f0cbe1bbc4aac3bcf72ce8dddae84b", "labels_vector_sha256": "f48c7bb1699def516fce122f113f13c18f54d7349c83b3a70b62b572a9ba5c6c", "planned_active_tokens": 65594, "realized_active_tokens": 65594, "cumulative_start": 13767818, "cumulative_end": 13833412, "loss_sum": 24767.187133789062, "token_normalized_loss": 0.3775831193979489, "grad_norm_before_clip": 0.14319483935832977, "learning_rates_at_step": { "lora": 9.334457802490621e-05, "row_tokens": 9.334457802490621e-05 }, "learning_rates_after_step": { "lora": 9.326345977335401e-05, "row_tokens": 9.326345977335401e-05 } }, { "update_id": 211, "row_count": 15, "row_ids_sha256": "4e25e1d543d4d6671f190ca8960c270241cc08a08bf066f42e3da48c90d1aa0c", "input_ids_vector_sha256": "3d20e1137fcd1b878e5c91589ce7eb03752b060cf139941471e86e44005224dc", "labels_vector_sha256": "0d76064b60d4cac8adfd93e01ce94dd4286d0f28fe21ddafd4443a6a0a5794b9", "planned_active_tokens": 62147, "realized_active_tokens": 62147, "cumulative_start": 13833412, "cumulative_end": 13895559, "loss_sum": 24704.90869140625, "token_normalized_loss": 0.39752375322069045, "grad_norm_before_clip": 0.15195311605930328, "learning_rates_at_step": { "lora": 9.326345977335401e-05, "row_tokens": 9.326345977335401e-05 }, "learning_rates_after_step": { "lora": 9.317934262553147e-05, "row_tokens": 9.317934262553147e-05 } }, { "update_id": 212, "row_count": 15, "row_ids_sha256": "e9db4d3587ef90fc7a2cb493f24e5e5ab9c30bfeae24b79a7c5f70fa6acd5484", "input_ids_vector_sha256": "e7139f37317c21f2f3c543aa9153124573e4cf7491b899256a220f9ef248651c", "labels_vector_sha256": "3d24322fb347ea9863d955bfd9eaec54eef64b5b98f6910a345178ee77f11f83", "planned_active_tokens": 64079, "realized_active_tokens": 64079, "cumulative_start": 13895559, "cumulative_end": 13959638, "loss_sum": 25754.611907958984, "token_normalized_loss": 0.4019196914427345, "grad_norm_before_clip": 0.1456773579120636, "learning_rates_at_step": { "lora": 9.317934262553147e-05, "row_tokens": 9.317934262553147e-05 }, "learning_rates_after_step": { "lora": 9.309255321066945e-05, "row_tokens": 9.309255321066945e-05 } }, { "update_id": 213, "row_count": 15, "row_ids_sha256": "ff3a3d876ed39ff50cba3f75a945c050806e60224675631377db8981720a510d", "input_ids_vector_sha256": "4716b8bf8b01171ddb6978cfe59e4a2452b366c0c3aff7d20f0630f9009a7076", "labels_vector_sha256": "ea00ac8333f2d456b76c5ede07d45dc3ff8c3610b091aa7f2764461c2086561e", "planned_active_tokens": 65732, "realized_active_tokens": 65732, "cumulative_start": 13959638, "cumulative_end": 14025370, "loss_sum": 25899.3310546875, "token_normalized_loss": 0.3940140426989518, "grad_norm_before_clip": 0.14828939735889435, "learning_rates_at_step": { "lora": 9.309255321066945e-05, "row_tokens": 9.309255321066945e-05 }, "learning_rates_after_step": { "lora": 9.300177264733019e-05, "row_tokens": 9.300177264733019e-05 } }, { "update_id": 214, "row_count": 15, "row_ids_sha256": "de13ac86241b0d60ecd3fa11898f79462b4e33261e233733d045cb7c87703d36", "input_ids_vector_sha256": "8d1c4c4c2d60d804fc554d406f6110fa342764cce43d3fc502872369c8e44c35", "labels_vector_sha256": "8763949e2d0ee45bc84dabd268d0d9fa0d59868da341daf8926248e484bda162", "planned_active_tokens": 68347, "realized_active_tokens": 68347, "cumulative_start": 14025370, "cumulative_end": 14093717, "loss_sum": 25836.524017333984, "token_normalized_loss": 0.3780198694505097, "grad_norm_before_clip": 0.1377991884946823, "learning_rates_at_step": { "lora": 9.300177264733019e-05, "row_tokens": 9.300177264733019e-05 }, "learning_rates_after_step": { "lora": 9.291771341545852e-05, "row_tokens": 9.291771341545852e-05 } }, { "update_id": 215, "row_count": 15, "row_ids_sha256": "f78535333f54df8654d0ff697e9cf8746dce192d6223698c8ad7e10541849f48", "input_ids_vector_sha256": "d91719e3fb1188fb2a881077ff9d4dbd62442ed5b0dd45d55f270106d9f1e580", "labels_vector_sha256": "66def0da08cacc59e58e3a2fe7a6b9a6c6af704675993a22354f534fc7df6281", "planned_active_tokens": 62922, "realized_active_tokens": 62922, "cumulative_start": 14093717, "cumulative_end": 14156639, "loss_sum": 22117.033721923828, "token_normalized_loss": 0.35149921683868646, "grad_norm_before_clip": 0.13903510570526123, "learning_rates_at_step": { "lora": 9.291771341545852e-05, "row_tokens": 9.291771341545852e-05 }, "learning_rates_after_step": { "lora": 9.282884084250147e-05, "row_tokens": 9.282884084250147e-05 } }, { "update_id": 216, "row_count": 13, "row_ids_sha256": "36732fedb120fe8b40f2ea36c8018ada42dc29eefdf035aafde8164eb4d9ddeb", "input_ids_vector_sha256": "fc1a62283e6dca8e2e3c504a5549633770ea94ba7620a1feb4efab219c3e22bf", "labels_vector_sha256": "9010263ceff27b6b95a15b526a1d40685e8b18f4bb324b8e02db89865f4c035e", "planned_active_tokens": 66151, "realized_active_tokens": 66151, "cumulative_start": 14156639, "cumulative_end": 14222790, "loss_sum": 26826.38360595703, "token_normalized_loss": 0.4055325483508493, "grad_norm_before_clip": 0.1479479819536209, "learning_rates_at_step": { "lora": 9.282884084250147e-05, "row_tokens": 9.282884084250147e-05 }, "learning_rates_after_step": { "lora": 9.273666956908251e-05, "row_tokens": 9.273666956908251e-05 } }, { "update_id": 217, "row_count": 13, "row_ids_sha256": "86e8750c065466366d3789c8f1ad82a1247e05b9ad34bb99ad850eeea7c4da10", "input_ids_vector_sha256": "049d133756c1c17bdcbc83b69d472cffe786e229fecaa1140b8a50163df58e1b", "labels_vector_sha256": "91474f00cfdb0e75a9290634dd2b531215e97204e6c40cde40ae892fb00cec92", "planned_active_tokens": 68208, "realized_active_tokens": 68208, "cumulative_start": 14222790, "cumulative_end": 14290998, "loss_sum": 26980.674377441406, "token_normalized_loss": 0.39556466070609614, "grad_norm_before_clip": 0.15388965606689453, "learning_rates_at_step": { "lora": 9.273666956908251e-05, "row_tokens": 9.273666956908251e-05 }, "learning_rates_after_step": { "lora": 9.264635250293581e-05, "row_tokens": 9.264635250293581e-05 } }, { "update_id": 218, "row_count": 11, "row_ids_sha256": "95524296706cfe4f161ece07130d7caefb40175fa804e6632ddcededa97c49ac", "input_ids_vector_sha256": "7b4d11b7da8d2472b66d3dfcf06095080ee5c5b39df79f7efb92daa2454f8f4e", "labels_vector_sha256": "c53c37e8ed1dcef466e0c22049df18c67e034da4ea95353158192fce30655434", "planned_active_tokens": 66450, "realized_active_tokens": 66450, "cumulative_start": 14290998, "cumulative_end": 14357448, "loss_sum": 27497.545837402344, "token_normalized_loss": 0.41380806376828205, "grad_norm_before_clip": 0.149980366230011, "learning_rates_at_step": { "lora": 9.264635250293581e-05, "row_tokens": 9.264635250293581e-05 }, "learning_rates_after_step": { "lora": 9.255829335551573e-05, "row_tokens": 9.255829335551573e-05 } }, { "update_id": 219, "row_count": 12, "row_ids_sha256": "14a074132faef737fb1b4eb5405eab7c107833ea9ae79d5c9eca62a1acf56416", "input_ids_vector_sha256": "0f55a298b56ab125deaef800626e12382170daa85d85fbc3f1dd8827af7a5e8a", "labels_vector_sha256": "7f835d331ff7707d6c9a3b3b4caa33264aecc8571310cc8bf9e1004c1079f223", "planned_active_tokens": 64428, "realized_active_tokens": 64428, "cumulative_start": 14357448, "cumulative_end": 14421876, "loss_sum": 27580.549560546875, "token_normalized_loss": 0.42808327994888673, "grad_norm_before_clip": 0.15070867538452148, "learning_rates_at_step": { "lora": 9.255829335551573e-05, "row_tokens": 9.255829335551573e-05 }, "learning_rates_after_step": { "lora": 9.24706688017209e-05, "row_tokens": 9.24706688017209e-05 } }, { "update_id": 220, "row_count": 17, "row_ids_sha256": "dd8d7c969f5606bb773b6f9594d9b36b171cc48662650115f75aa23d518dcc99", "input_ids_vector_sha256": "17ffda62c2d466641ecdd305dba85f57016da56dfc4316b9a9014e56e44b68cc", "labels_vector_sha256": "a88d4a13f4a5f552dc16f9fd1e50c8e4da6649a0706128873499e5d167b37c58", "planned_active_tokens": 63763, "realized_active_tokens": 63763, "cumulative_start": 14421876, "cumulative_end": 14485639, "loss_sum": 19303.980895996094, "token_normalized_loss": 0.302745807066733, "grad_norm_before_clip": 0.1286001056432724, "learning_rates_at_step": { "lora": 9.24706688017209e-05, "row_tokens": 9.24706688017209e-05 }, "learning_rates_after_step": { "lora": 9.237596558063827e-05, "row_tokens": 9.237596558063827e-05 } }, { "update_id": 221, "row_count": 14, "row_ids_sha256": "db3bf1ea30a508d0db376be3a45c62ccb22645c686268a5f8201f41aa3f6ce84", "input_ids_vector_sha256": "cd2df106b37ea72a088367e6a7410ea9517d35f18a6bd24bedec36cd2910af74", "labels_vector_sha256": "8ec6475c7d2f49270a0b477873a852bb7fcc724ace1dda2e786643c33a459efb", "planned_active_tokens": 68532, "realized_active_tokens": 68532, "cumulative_start": 14485639, "cumulative_end": 14554171, "loss_sum": 25720.158203125, "token_normalized_loss": 0.3753014387895436, "grad_norm_before_clip": 0.13724550604820251, "learning_rates_at_step": { "lora": 9.237596558063827e-05, "row_tokens": 9.237596558063827e-05 }, "learning_rates_after_step": { "lora": 9.22904800550015e-05, "row_tokens": 9.22904800550015e-05 } }, { "update_id": 222, "row_count": 10, "row_ids_sha256": "f4c9d206036f8ae0e2f34e49ef86ec404ab2b8bc060637aa8a246f227a1be38b", "input_ids_vector_sha256": "1b25099e263bdf50eb3266b4bab6f3a534d77e9f1f225b03624fb9a1b0ffca57", "labels_vector_sha256": "a6349e0c8f5423149b93bfc218685de6f5430a2c2a1d620fc045a955bac855cb", "planned_active_tokens": 61527, "realized_active_tokens": 61527, "cumulative_start": 14554171, "cumulative_end": 14615698, "loss_sum": 25011.328125, "token_normalized_loss": 0.406509794480472, "grad_norm_before_clip": 0.1654040664434433, "learning_rates_at_step": { "lora": 9.22904800550015e-05, "row_tokens": 9.22904800550015e-05 }, "learning_rates_after_step": { "lora": 9.21933147456391e-05, "row_tokens": 9.21933147456391e-05 } }, { "update_id": 223, "row_count": 12, "row_ids_sha256": "e97828ba6d2a9290b6585f1fb25fd759e0dff256e22d06d13e269cf3dc2cd48e", "input_ids_vector_sha256": "8042e360f63ae57c3c88f1efbfa2fe3116a4aa89d39c6407098a82c4dad9e706", "labels_vector_sha256": "77cf56f0c6598106b6e7319ecd021adb44b87c313cb6715801c5fb563b09b18c", "planned_active_tokens": 69555, "realized_active_tokens": 69555, "cumulative_start": 14615698, "cumulative_end": 14685253, "loss_sum": 26936.364868164062, "token_normalized_loss": 0.3872671248388191, "grad_norm_before_clip": 0.14486634731292725, "learning_rates_at_step": { "lora": 9.21933147456391e-05, "row_tokens": 9.21933147456391e-05 }, "learning_rates_after_step": { "lora": 9.21037261737432e-05, "row_tokens": 9.21037261737432e-05 } }, { "update_id": 224, "row_count": 15, "row_ids_sha256": "1442a7d058c4f6ebca7518b43a0d1d81a0e11707be7b18e6f5deaaf1f29a012e", "input_ids_vector_sha256": "80546eb4bafb683c4104a4b4e2e21410d8015d71f31822f56ffecdeec7b88ebb", "labels_vector_sha256": "bb05a8e04f9e54b2a67ffc88ad8e6dee687d2fbfd1af6029a9af7f228456bb2e", "planned_active_tokens": 63781, "realized_active_tokens": 63781, "cumulative_start": 14685253, "cumulative_end": 14749034, "loss_sum": 22880.358276367188, "token_normalized_loss": 0.3587331380249163, "grad_norm_before_clip": 0.13812050223350525, "learning_rates_at_step": { "lora": 9.21037261737432e-05, "row_tokens": 9.21037261737432e-05 }, "learning_rates_after_step": { "lora": 9.201150451103852e-05, "row_tokens": 9.201150451103852e-05 } }, { "update_id": 225, "row_count": 12, "row_ids_sha256": "57afbd98b91dd35d8aaa1eed0faed51a73d720977b45f656df0ef7eb3fc5cdbb", "input_ids_vector_sha256": "31159cd729c9ed47a2197e7a82be01ca1f5e6345d9fa91f2824076a6efbc425d", "labels_vector_sha256": "9e33141e2cfe4ef57a88bd05f59c66108584cf4442697fbc9a6639b8dbcf8b23", "planned_active_tokens": 65311, "realized_active_tokens": 65311, "cumulative_start": 14749034, "cumulative_end": 14814345, "loss_sum": 25810.635192871094, "token_normalized_loss": 0.395195835201897, "grad_norm_before_clip": 0.15598852932453156, "learning_rates_at_step": { "lora": 9.201150451103852e-05, "row_tokens": 9.201150451103852e-05 }, "learning_rates_after_step": { "lora": 9.191617090962145e-05, "row_tokens": 9.191617090962145e-05 } }, { "update_id": 226, "row_count": 16, "row_ids_sha256": "e0431288106c63ae0f7e34fdf76816e76dd07c5563b9feffc20c579d17492181", "input_ids_vector_sha256": "b692989990fe02a0c3351f7f8a4b65bd9b0cded5e531c8d0e93eed4373f0cc65", "labels_vector_sha256": "f706d21e9f68044f5529b4a86b4cb9bed499195aef314c54cf065b177d6b9911", "planned_active_tokens": 67154, "realized_active_tokens": 67154, "cumulative_start": 14814345, "cumulative_end": 14881499, "loss_sum": 24653.184631347656, "token_normalized_loss": 0.3671141649246159, "grad_norm_before_clip": 0.13925573229789734, "learning_rates_at_step": { "lora": 9.191617090962145e-05, "row_tokens": 9.191617090962145e-05 }, "learning_rates_after_step": { "lora": 9.182881074471204e-05, "row_tokens": 9.182881074471204e-05 } }, { "update_id": 227, "row_count": 12, "row_ids_sha256": "5471e5d4f1a203ee1d1274c6c9283074719072b9f7a1faf7cd424ce475100e7c", "input_ids_vector_sha256": "bb3efcb3b262ee36f84689ca325c94b0d4526ff19feabde9217b2a31163ab71a", "labels_vector_sha256": "98df44c66ccfcab6f2d3ec509c10164267eee35c25c8b1f7b1972663f5239bf0", "planned_active_tokens": 61221, "realized_active_tokens": 61221, "cumulative_start": 14881499, "cumulative_end": 14942720, "loss_sum": 21855.004821777344, "token_normalized_loss": 0.3569854269250313, "grad_norm_before_clip": 0.1527470350265503, "learning_rates_at_step": { "lora": 9.182881074471204e-05, "row_tokens": 9.182881074471204e-05 }, "learning_rates_after_step": { "lora": 9.173547083485028e-05, "row_tokens": 9.173547083485028e-05 } }, { "update_id": 228, "row_count": 16, "row_ids_sha256": "003502357c80fd92e1ac319736278b07393a1140b0c86aa4db16868e507cb4ae", "input_ids_vector_sha256": "ef68ccb2afe2e378bb5f324b86594f93f796a1bebe73f7fb1ce574c8464f7289", "labels_vector_sha256": "1cfa4276863f9150785728d0ea00a6294b819d356779188606e0d671070b2c5b", "planned_active_tokens": 65083, "realized_active_tokens": 65083, "cumulative_start": 14942720, "cumulative_end": 15007803, "loss_sum": 23802.361358642578, "token_normalized_loss": 0.36572317438720675, "grad_norm_before_clip": 0.15167176723480225, "learning_rates_at_step": { "lora": 9.173547083485028e-05, "row_tokens": 9.173547083485028e-05 }, "learning_rates_after_step": { "lora": 9.163924663724187e-05, "row_tokens": 9.163924663724187e-05 } }, { "update_id": 229, "row_count": 13, "row_ids_sha256": "76d4194a5e7ee82530167be16e4a23b34a922c2d612acbc91fae20fc87a81661", "input_ids_vector_sha256": "77d114a9c824e5f362a3b75af05ccab81f30c0e23f945fc17cead6cfdb627300", "labels_vector_sha256": "13fc64319c6003ed1bafd68bc0216047e23961474bf20dc0a6c3fc5b01d86ddd", "planned_active_tokens": 66745, "realized_active_tokens": 66745, "cumulative_start": 15007803, "cumulative_end": 15074548, "loss_sum": 30591.876525878906, "token_normalized_loss": 0.45833959885952363, "grad_norm_before_clip": 0.17287102341651917, "learning_rates_at_step": { "lora": 9.163924663724187e-05, "row_tokens": 9.163924663724187e-05 }, "learning_rates_after_step": { "lora": 9.153937922565243e-05, "row_tokens": 9.153937922565243e-05 } }, { "update_id": 230, "row_count": 16, "row_ids_sha256": "cbedac2d2f85c235e4e13de1e13e6e859fe84ec0fafb2043612ef71ccbf3cb4a", "input_ids_vector_sha256": "7dea1dfc29ec3a072a23197bc3a2ce3633196b1751633c6453c04d78e0d0738e", "labels_vector_sha256": "2c4fa0413acccb59ecf1e0c547e10674347bc55fb85e2fda0703db5ea03d2811", "planned_active_tokens": 68904, "realized_active_tokens": 68904, "cumulative_start": 15074548, "cumulative_end": 15143452, "loss_sum": 25533.5263671875, "token_normalized_loss": 0.3705666778008171, "grad_norm_before_clip": 0.1444668173789978, "learning_rates_at_step": { "lora": 9.153937922565243e-05, "row_tokens": 9.153937922565243e-05 }, "learning_rates_after_step": { "lora": 9.144912571802834e-05, "row_tokens": 9.144912571802834e-05 } }, { "update_id": 231, "row_count": 14, "row_ids_sha256": "05b9fcf8322742dcc86564afdfce3e13468aead696689251764cad8b69085043", "input_ids_vector_sha256": "c35f04e22e07c59f38aade4b033143f37c23fc264a8480971210939aa2c7d451", "labels_vector_sha256": "f94feb649869ea362121ccbb7128d5ab31cd462a17d64056d158e9f1911de6c5", "planned_active_tokens": 61954, "realized_active_tokens": 61954, "cumulative_start": 15143452, "cumulative_end": 15205406, "loss_sum": 20901.918853759766, "token_normalized_loss": 0.337378036184262, "grad_norm_before_clip": 0.1504100114107132, "learning_rates_at_step": { "lora": 9.144912571802834e-05, "row_tokens": 9.144912571802834e-05 }, "learning_rates_after_step": { "lora": 9.134596092410575e-05, "row_tokens": 9.134596092410575e-05 } }, { "update_id": 232, "row_count": 13, "row_ids_sha256": "0542dd0559a2c7d84ab0dcd304dca8030508dc5a702dfdb4bde927118454fba8", "input_ids_vector_sha256": "7c14e4dde00be5df89fa4f8e0579d1913bf50ea3510fdbf25c7187bf6edf3e36", "labels_vector_sha256": "8378aed676d0f53200a24e073fd0603fa8273c5bb23f1bbdbccd144b3cd41554", "planned_active_tokens": 70455, "realized_active_tokens": 70455, "cumulative_start": 15205406, "cumulative_end": 15275861, "loss_sum": 28127.732391357422, "token_normalized_loss": 0.39922975504020186, "grad_norm_before_clip": 0.1629692167043686, "learning_rates_at_step": { "lora": 9.134596092410575e-05, "row_tokens": 9.134596092410575e-05 }, "learning_rates_after_step": { "lora": 9.125735689835435e-05, "row_tokens": 9.125735689835435e-05 } }, { "update_id": 233, "row_count": 15, "row_ids_sha256": "425a1255dc191535fab867b18ef038fc715e8bb96eef9447666be9783b445e6b", "input_ids_vector_sha256": "1b83e49501277fc3d7556dff8adb5a4af93e3dcd8766602aa94901ad617e80a3", "labels_vector_sha256": "f5265e24760b05ba70888863448eed2b93384a101c1a4025dfc3a44ced0cd426", "planned_active_tokens": 60208, "realized_active_tokens": 60208, "cumulative_start": 15275861, "cumulative_end": 15336069, "loss_sum": 21326.04443359375, "token_normalized_loss": 0.3542061592079749, "grad_norm_before_clip": 0.14166471362113953, "learning_rates_at_step": { "lora": 9.125735689835435e-05, "row_tokens": 9.125735689835435e-05 }, "learning_rates_after_step": { "lora": 9.11600600775703e-05, "row_tokens": 9.11600600775703e-05 } }, { "update_id": 234, "row_count": 17, "row_ids_sha256": "11681dfb3b7fb3d3cc4076a9ec37a9c762eac3c3e34671ab3308ceab18c7d832", "input_ids_vector_sha256": "c1cd62fd9a32158b6c26091055210918ff1d7f88af409a344946dd50f16cdf29", "labels_vector_sha256": "641331d9e39e28e5cf85a57653f433fbfb7c2d3c28cc93170a824c9209a8ad32", "planned_active_tokens": 65798, "realized_active_tokens": 65798, "cumulative_start": 15336069, "cumulative_end": 15401867, "loss_sum": 23541.322784423828, "token_normalized_loss": 0.357781737810022, "grad_norm_before_clip": 0.14642181992530823, "learning_rates_at_step": { "lora": 9.11600600775703e-05, "row_tokens": 9.11600600775703e-05 }, "learning_rates_after_step": { "lora": 9.106236222986735e-05, "row_tokens": 9.106236222986735e-05 } }, { "update_id": 235, "row_count": 14, "row_ids_sha256": "360a18f0fc29c6639928a443a7a6b1cb04596b879f4f4915986081f770e898d2", "input_ids_vector_sha256": "55cb50e485520e2f52e0c3a4b5d51f5641a545b23f894d0b34c4976b807acff9", "labels_vector_sha256": "e1b0e3c5ddd73951e2ef953855c3c3ab81be48a654bebd2c18c954838a8e9d1d", "planned_active_tokens": 65741, "realized_active_tokens": 65741, "cumulative_start": 15401867, "cumulative_end": 15467608, "loss_sum": 23277.53726196289, "token_normalized_loss": 0.3540794521221595, "grad_norm_before_clip": 0.6013354063034058, "learning_rates_at_step": { "lora": 9.106236222986735e-05, "row_tokens": 9.106236222986735e-05 }, "learning_rates_after_step": { "lora": 9.09591823592327e-05, "row_tokens": 9.09591823592327e-05 } }, { "update_id": 236, "row_count": 15, "row_ids_sha256": "a9c67c1106bb3f36aee1af09c86a8b2c9d83180f1e9af86bceceffa537ed5782", "input_ids_vector_sha256": "baeb16b218c2a9342bbaa468a360f75df70011e2afd7a28ccbe6b5d16200fcbf", "labels_vector_sha256": "d750ffbbb29d3686a2680d5858c458c062380c74ddc3e6d981351dda04aa75fd", "planned_active_tokens": 69079, "realized_active_tokens": 69079, "cumulative_start": 15467608, "cumulative_end": 15536687, "loss_sum": 26704.343811035156, "token_normalized_loss": 0.38657687301546284, "grad_norm_before_clip": 0.14286774396896362, "learning_rates_at_step": { "lora": 9.09591823592327e-05, "row_tokens": 9.09591823592327e-05 }, "learning_rates_after_step": { "lora": 9.086699317538943e-05, "row_tokens": 9.086699317538943e-05 } }, { "update_id": 237, "row_count": 13, "row_ids_sha256": "07578330a82d170816ff6f9086099b33370fddba2d51170475b32668d374f462", "input_ids_vector_sha256": "47750e02f78043bc6db9d0fcfc9fee5cbc5d35fac36625bb3581987938e39fc5", "labels_vector_sha256": "f03006f80ecd0d611a67df135efd80bf3385f206fb257edfe37931f1d42620a2", "planned_active_tokens": 61421, "realized_active_tokens": 61421, "cumulative_start": 15536687, "cumulative_end": 15598108, "loss_sum": 24405.632293701172, "token_normalized_loss": 0.39734996652124144, "grad_norm_before_clip": 0.14759612083435059, "learning_rates_at_step": { "lora": 9.086699317538943e-05, "row_tokens": 9.086699317538943e-05 }, "learning_rates_after_step": { "lora": 9.076678837159662e-05, "row_tokens": 9.076678837159662e-05 } }, { "update_id": 238, "row_count": 12, "row_ids_sha256": "dc93eec79e6813c13cb64f7620ade11a5a36d5bb527ccac9a33297f440e29dc4", "input_ids_vector_sha256": "63a50479cd52ef9c4fdd2ce0085e43f23dbd769efa2c34baa1db39c0dd95bf70", "labels_vector_sha256": "0de2e45f982b6d4d0dc7f8ce596dc7e4e0ef98070fea0db55a319203bc79b3d3", "planned_active_tokens": 66446, "realized_active_tokens": 66446, "cumulative_start": 15598108, "cumulative_end": 15664554, "loss_sum": 32238.916412353516, "token_normalized_loss": 0.4851897241723131, "grad_norm_before_clip": 0.16839855909347534, "learning_rates_at_step": { "lora": 9.076678837159662e-05, "row_tokens": 9.076678837159662e-05 }, "learning_rates_after_step": { "lora": 9.066788828289195e-05, "row_tokens": 9.066788828289195e-05 } }, { "update_id": 239, "row_count": 12, "row_ids_sha256": "13941b7b4a39d1ae6fc1a3939ab9c7dc94778c9827e48dc7f9bc87acf01fcf2f", "input_ids_vector_sha256": "d16771ace0c5bb1c70fb8018beb9a2c2ba33ca28785b8c1bfaabf91ad5909945", "labels_vector_sha256": "ba89f9752d86e1d24d6e217c7b07fb05f1abda75a35455afa6a017d7bb85f309", "planned_active_tokens": 65264, "realized_active_tokens": 65264, "cumulative_start": 15664554, "cumulative_end": 15729818, "loss_sum": 24054.666046142578, "token_normalized_loss": 0.36857480458051267, "grad_norm_before_clip": 0.14817164838314056, "learning_rates_at_step": { "lora": 9.066788828289195e-05, "row_tokens": 9.066788828289195e-05 }, "learning_rates_after_step": { "lora": 9.056802589420408e-05, "row_tokens": 9.056802589420408e-05 } }, { "update_id": 240, "row_count": 17, "row_ids_sha256": "975b8fad14a7024bec48c07f139a9f8271722e54f9dda60b6c0a0b0a9e983e01", "input_ids_vector_sha256": "84406086de2ffd60b4d9631cb0ddd1bec565d8dc7bcff904850f1cdf1c61ab80", "labels_vector_sha256": "f93009a75a8005b2c4459421a9e2c781a20370ee30ad25ff3eb6f4bbbcc6b6e5", "planned_active_tokens": 65585, "realized_active_tokens": 65585, "cumulative_start": 15729818, "cumulative_end": 15795403, "loss_sum": 24078.81967163086, "token_normalized_loss": 0.3671391274168005, "grad_norm_before_clip": 0.1545252650976181, "learning_rates_at_step": { "lora": 9.056802589420408e-05, "row_tokens": 9.056802589420408e-05 }, "learning_rates_after_step": { "lora": 9.046917510687041e-05, "row_tokens": 9.046917510687041e-05 } }, { "update_id": 241, "row_count": 14, "row_ids_sha256": "6dcc909e3b0bd4478c3b0b3a83b74e417a4ce80fcd0ff07ecff968a15d800fac", "input_ids_vector_sha256": "7915bcb7a3a22cd262e8a5b25436f93908d823f6348dd4e3208dc3da84e4ad95", "labels_vector_sha256": "5908f516173f22780e5e77239d553e4013349d088cbb1df7b9ecc2b6b74f84f3", "planned_active_tokens": 64615, "realized_active_tokens": 64615, "cumulative_start": 15795403, "cumulative_end": 15860018, "loss_sum": 24220.94647216797, "token_normalized_loss": 0.3748502123681493, "grad_norm_before_clip": 0.15854096412658691, "learning_rates_at_step": { "lora": 9.046917510687041e-05, "row_tokens": 9.046917510687041e-05 }, "learning_rates_after_step": { "lora": 9.036143519391047e-05, "row_tokens": 9.036143519391047e-05 } }, { "update_id": 242, "row_count": 11, "row_ids_sha256": "c7257e0e2ba5461595ce9de42890657c7087847198dff69687e4f140bddd0a3f", "input_ids_vector_sha256": "4ea4ee26dc912ba72f80b1281e67170d1c6df15e7322e3ab4b1627de46c44cb3", "labels_vector_sha256": "b4732eb79b044357c012a17a63c22d5dc3b118543974b8d7f48823744d428426", "planned_active_tokens": 70085, "realized_active_tokens": 70085, "cumulative_start": 15860018, "cumulative_end": 15930103, "loss_sum": 30495.58038330078, "token_normalized_loss": 0.4351227849511419, "grad_norm_before_clip": 0.16316434741020203, "learning_rates_at_step": { "lora": 9.036143519391047e-05, "row_tokens": 9.036143519391047e-05 }, "learning_rates_after_step": { "lora": 9.026547373657806e-05, "row_tokens": 9.026547373657806e-05 } }, { "update_id": 243, "row_count": 14, "row_ids_sha256": "f047feb55f3db84cf00bedd9338a404015d687699fec405fbaf9206d7985fbf8", "input_ids_vector_sha256": "e744bfdc9d1e50d7e890385045e0cff0c4af7ba42174ef4d3b55e04673b87c1f", "labels_vector_sha256": "ca66653682284e13a32a7ff0ca9c2de028a2b68f35a5ef0484f537433c29317a", "planned_active_tokens": 62129, "realized_active_tokens": 62129, "cumulative_start": 15930103, "cumulative_end": 15992232, "loss_sum": 23202.522186279297, "token_normalized_loss": 0.3734571969012747, "grad_norm_before_clip": 0.15345728397369385, "learning_rates_at_step": { "lora": 9.026547373657806e-05, "row_tokens": 9.026547373657806e-05 }, "learning_rates_after_step": { "lora": 9.016481704188196e-05, "row_tokens": 9.016481704188196e-05 } }, { "update_id": 244, "row_count": 14, "row_ids_sha256": "b0f8a75af54eb8b87b18e3026bc9e3ad85a3bc323c806d310f68ca25ecf0d435", "input_ids_vector_sha256": "87b9414439f4ce08271775d8d6479012fe96a2658c3cbf7037998ea6a4f6ca6a", "labels_vector_sha256": "b49ce6a86c1c66cee643911125ad2fd2789b3272d654bb9eb734a13a3b147b11", "planned_active_tokens": 64876, "realized_active_tokens": 64876, "cumulative_start": 15992232, "cumulative_end": 16057108, "loss_sum": 24897.279266357422, "token_normalized_loss": 0.38376717532457955, "grad_norm_before_clip": 0.185855433344841, "learning_rates_at_step": { "lora": 9.016481704188196e-05, "row_tokens": 9.016481704188196e-05 }, "learning_rates_after_step": { "lora": 9.00621808607982e-05, "row_tokens": 9.00621808607982e-05 } }, { "update_id": 245, "row_count": 13, "row_ids_sha256": "afe86a759bf6b10114ae7b9c2163b7af9469814cce0ffd4600bf3b78f81ada1d", "input_ids_vector_sha256": "5099474678e9fdf5e01aa8f5d79d82f2ff6f185eaff6896a61fe570ffb2bf019", "labels_vector_sha256": "bb065ddf2ee0ab00dc26ade5eae27a979aea2662fd2e868eea89ad9343a21ada", "planned_active_tokens": 65848, "realized_active_tokens": 65848, "cumulative_start": 16057108, "cumulative_end": 16122956, "loss_sum": 26849.213745117188, "token_normalized_loss": 0.40774531869027436, "grad_norm_before_clip": 0.2160780429840088, "learning_rates_at_step": { "lora": 9.00621808607982e-05, "row_tokens": 9.00621808607982e-05 }, "learning_rates_after_step": { "lora": 8.99551391183072e-05, "row_tokens": 8.99551391183072e-05 } }, { "update_id": 246, "row_count": 15, "row_ids_sha256": "8b663986721ff00ae60117607e63cc9d14b2f9dffc79b001a94976c883e4bfc8", "input_ids_vector_sha256": "90b57db4f0897222fb62b74726e4f6a2cca96324d1bac46e39c18642c56c8e12", "labels_vector_sha256": "314447a4d8ea30b28121aa3136cfc9bd9d7f91e781fa9150edaf112732068053", "planned_active_tokens": 68353, "realized_active_tokens": 68353, "cumulative_start": 16122956, "cumulative_end": 16191309, "loss_sum": 25554.878021240234, "token_normalized_loss": 0.3738662241780205, "grad_norm_before_clip": 0.14805251359939575, "learning_rates_at_step": { "lora": 8.99551391183072e-05, "row_tokens": 8.99551391183072e-05 }, "learning_rates_after_step": { "lora": 8.985335217227582e-05, "row_tokens": 8.985335217227582e-05 } }, { "update_id": 247, "row_count": 14, "row_ids_sha256": "bed7d6c4ef439ab3bf28ab000df9df67c49ba141a1d2821a9b82b439027e8ab4", "input_ids_vector_sha256": "fbdead93d3216ca35c1db59adc1dc86e483451093637ad4b94de6aae730684c3", "labels_vector_sha256": "3deff144d81231b5a8e215d8b466d8a5610d4b3c5dc548f97bc0b55023cc184b", "planned_active_tokens": 64698, "realized_active_tokens": 64698, "cumulative_start": 16191309, "cumulative_end": 16256007, "loss_sum": 24441.97430419922, "token_normalized_loss": 0.37778562404091653, "grad_norm_before_clip": 0.15498782694339752, "learning_rates_at_step": { "lora": 8.985335217227582e-05, "row_tokens": 8.985335217227582e-05 }, "learning_rates_after_step": { "lora": 8.974719006297719e-05, "row_tokens": 8.974719006297719e-05 } }, { "update_id": 248, "row_count": 14, "row_ids_sha256": "303c9a25ca34ea279fb808f3de21e8769e5349b5364343de6c0fb2b199a211c7", "input_ids_vector_sha256": "120655180ca004baed2e0a2a214dbc48185d1de09419d07d633f5140731c8221", "labels_vector_sha256": "8c9006e9a84d4ba505c4ad049eaf17f485851184d3ebce7b08fc612af498888f", "planned_active_tokens": 67173, "realized_active_tokens": 67173, "cumulative_start": 16256007, "cumulative_end": 16323180, "loss_sum": 26835.38934326172, "token_normalized_loss": 0.39949666299349024, "grad_norm_before_clip": 0.18532665073871613, "learning_rates_at_step": { "lora": 8.974719006297719e-05, "row_tokens": 8.974719006297719e-05 }, "learning_rates_after_step": { "lora": 8.964974616454788e-05, "row_tokens": 8.964974616454788e-05 } }, { "update_id": 249, "row_count": 8, "row_ids_sha256": "8d558bebe0096c3e3a8ee420b47cf320422f7f8ae24d240bbb219243c0e50d8f", "input_ids_vector_sha256": "011328662abee5a0a47c4e9276b059defd55d75e5ba5298530d4dd7bc37a89ae", "labels_vector_sha256": "c6f077500b286b11544c102f73f974ebb641330ebd3fba36f660e06da5337993", "planned_active_tokens": 61386, "realized_active_tokens": 61386, "cumulative_start": 16323180, "cumulative_end": 16384566, "loss_sum": 28341.08074951172, "token_normalized_loss": 0.46168639021131397, "grad_norm_before_clip": 0.16631726920604706, "learning_rates_at_step": { "lora": 8.964974616454788e-05, "row_tokens": 8.964974616454788e-05 }, "learning_rates_after_step": { "lora": 8.954560203967527e-05, "row_tokens": 8.954560203967527e-05 } }, { "update_id": 250, "row_count": 12, "row_ids_sha256": "43b364b77f97833948f919419e530da3937c40112ef9f28fb049a06cabf230dd", "input_ids_vector_sha256": "263ba606ef8d13b9a57373648cfcfeed08a6c821319a38d97804097ed318c421", "labels_vector_sha256": "4df9ed257a1c303d715f6047fb2f3ca913e5727c3531a71a7e4380ce5f948e3e", "planned_active_tokens": 65325, "realized_active_tokens": 65325, "cumulative_start": 16384566, "cumulative_end": 16449891, "loss_sum": 30355.09619140625, "token_normalized_loss": 0.46467808942068506, "grad_norm_before_clip": 0.15770742297172546, "learning_rates_at_step": { "lora": 8.954560203967527e-05, "row_tokens": 8.954560203967527e-05 }, "learning_rates_after_step": { "lora": 8.942546617858631e-05, "row_tokens": 8.942546617858631e-05 } }, { "update_id": 251, "row_count": 11, "row_ids_sha256": "259f968dd252b18647704f6276f94467887c00fa6d6b4d309e5672c1a8631448", "input_ids_vector_sha256": "ea87abe3f91107fffb485ac4cf39f440067127df887ab93d57f3bb21a30b429a", "labels_vector_sha256": "306899eb8dbbcf1674d7e420d8112d48830c304082fee88ddef45151ac24ac09", "planned_active_tokens": 75000, "realized_active_tokens": 75000, "cumulative_start": 16449891, "cumulative_end": 16524891, "loss_sum": 34593.1604309082, "token_normalized_loss": 0.46124213907877604, "grad_norm_before_clip": 0.14812210202217102, "learning_rates_at_step": { "lora": 8.942546617858631e-05, "row_tokens": 8.942546617858631e-05 }, "learning_rates_after_step": { "lora": 8.933145958392437e-05, "row_tokens": 8.933145958392437e-05 } }, { "update_id": 252, "row_count": 11, "row_ids_sha256": "f3f18d2032f00a5804df4283c1baaccb6a82d89acc7b96d514e79fda42a07c73", "input_ids_vector_sha256": "0027f8e861dc439bd2b1d899a5646c1884e14c2b93ff24f0ec58011eabd9da13", "labels_vector_sha256": "2d88fdc1f9e3a0bc39185582e46552915678cb9721a3c1302bde0a869497cd2e", "planned_active_tokens": 58426, "realized_active_tokens": 58426, "cumulative_start": 16524891, "cumulative_end": 16583317, "loss_sum": 23203.102081298828, "token_normalized_loss": 0.39713658441958766, "grad_norm_before_clip": 0.15540045499801636, "learning_rates_at_step": { "lora": 8.933145958392437e-05, "row_tokens": 8.933145958392437e-05 }, "learning_rates_after_step": { "lora": 8.922972211800505e-05, "row_tokens": 8.922972211800505e-05 } }, { "update_id": 253, "row_count": 14, "row_ids_sha256": "8831caeec31ea5997d511998c281b5633d315177b2a1137e5305587b6c4616b2", "input_ids_vector_sha256": "6e6aeefbce99faee19e4e11438defcb15a1a757108cf9df65655d1fc018026a4", "labels_vector_sha256": "4d36e92d9ab9bde58437ab16bdb58d2c99e0bc0c6bdb0cbab10bc61290df8e61", "planned_active_tokens": 62976, "realized_active_tokens": 62976, "cumulative_start": 16583317, "cumulative_end": 16646293, "loss_sum": 23458.61309814453, "token_normalized_loss": 0.37250084314889054, "grad_norm_before_clip": 0.14674854278564453, "learning_rates_at_step": { "lora": 8.922972211800505e-05, "row_tokens": 8.922972211800505e-05 }, "learning_rates_after_step": { "lora": 8.912130916933704e-05, "row_tokens": 8.912130916933704e-05 } }, { "update_id": 254, "row_count": 13, "row_ids_sha256": "0d7303c93b13ce703bd5b9d7a4d12baf05f00fcd77e76652610ac3a6bb177a47", "input_ids_vector_sha256": "4c1c59c8cdbb725f8bc04ba420988908b32e7d98513a431d3647e4c349ec229d", "labels_vector_sha256": "8e16fe8874f3612f7196a5272a134b5eef9910b011accb8c60e592a70260b5b8", "planned_active_tokens": 66821, "realized_active_tokens": 66821, "cumulative_start": 16646293, "cumulative_end": 16713114, "loss_sum": 28894.317108154297, "token_normalized_loss": 0.4324137188631463, "grad_norm_before_clip": 0.15607723593711853, "learning_rates_at_step": { "lora": 8.912130916933704e-05, "row_tokens": 8.912130916933704e-05 }, "learning_rates_after_step": { "lora": 8.901567121255376e-05, "row_tokens": 8.901567121255376e-05 } }, { "update_id": 255, "row_count": 11, "row_ids_sha256": "4fef15b173237ea86c7c5674e6c58490392c698ecc1fef8c378d7122e88be97b", "input_ids_vector_sha256": "2e8b2b9c795fe46d3c05eb2f6e5adc9c0704b7fd27949dff9b29af548b40bf00", "labels_vector_sha256": "a77a2c1f14e40e90a8826da7fcb44ddec71e781e50d0467cff0c40ecbbed0dc0", "planned_active_tokens": 64830, "realized_active_tokens": 64830, "cumulative_start": 16713114, "cumulative_end": 16777944, "loss_sum": 31043.018920898438, "token_normalized_loss": 0.4788372500524208, "grad_norm_before_clip": 0.1600266844034195, "learning_rates_at_step": { "lora": 8.901567121255376e-05, "row_tokens": 8.901567121255376e-05 }, "learning_rates_after_step": { "lora": 8.890256347999014e-05, "row_tokens": 8.890256347999014e-05 } }, { "update_id": 256, "row_count": 15, "row_ids_sha256": "6058c61a87577a26a76cc0c44304495c747af8c229877db91337a11797666cdb", "input_ids_vector_sha256": "45a3a219c506c67cc399f0fb43dd3d5e77e3f69253f8f278190d5b26f73756d3", "labels_vector_sha256": "e51134456fd798fabcee173af2610e16cc520d14bb9f72486e36565fa6ffdedf", "planned_active_tokens": 69112, "realized_active_tokens": 69112, "cumulative_start": 16777944, "cumulative_end": 16847056, "loss_sum": 27315.381134033203, "token_normalized_loss": 0.3952335503824691, "grad_norm_before_clip": 0.172450989484787, "learning_rates_at_step": { "lora": 8.890256347999014e-05, "row_tokens": 8.890256347999014e-05 }, "learning_rates_after_step": { "lora": 8.87982182639123e-05, "row_tokens": 8.87982182639123e-05 } }, { "update_id": 257, "row_count": 12, "row_ids_sha256": "0d2318c6abfb63062df5ca53f5ffa1edb60b29e43f208d20b9c82a56c6e58b4a", "input_ids_vector_sha256": "66a8017e629b83ff1d3c4b6effc624a5f55162045aa876c38ab735dfeda271ef", "labels_vector_sha256": "e01e032652a4b776fd521a8969da2f7c7bbecad42f12603c3cc89e88a841cba0", "planned_active_tokens": 63485, "realized_active_tokens": 63485, "cumulative_start": 16847056, "cumulative_end": 16910541, "loss_sum": 30227.273864746094, "token_normalized_loss": 0.4761325331140599, "grad_norm_before_clip": 0.16138619184494019, "learning_rates_at_step": { "lora": 8.87982182639123e-05, "row_tokens": 8.87982182639123e-05 }, "learning_rates_after_step": { "lora": 8.868936499918183e-05, "row_tokens": 8.868936499918183e-05 } }, { "update_id": 258, "row_count": 14, "row_ids_sha256": "798fa370d709ebf866d7d5847f1fe428ec64f8497173e1520e61964f69d4ea5f", "input_ids_vector_sha256": "973156c55db577fbb9b5612a7f7aaaac7a70d47041eee1812be4a0082767d827", "labels_vector_sha256": "07dc7d58ec83f7799d45de9715678c2125fb195c914b648eaa56b99bffe1ec34", "planned_active_tokens": 65953, "realized_active_tokens": 65953, "cumulative_start": 16910541, "cumulative_end": 16976494, "loss_sum": 23356.216369628906, "token_normalized_loss": 0.35413425271979904, "grad_norm_before_clip": 0.13279427587985992, "learning_rates_at_step": { "lora": 8.868936499918183e-05, "row_tokens": 8.868936499918183e-05 }, "learning_rates_after_step": { "lora": 8.858045972148848e-05, "row_tokens": 8.858045972148848e-05 } }, { "update_id": 259, "row_count": 14, "row_ids_sha256": "b5b062071774aa187945d7cb62d28dd8f855bc1a04e55b1de024d5ecd8946109", "input_ids_vector_sha256": "fa45ca0d356900095f036d4e5e17ff6ba0dc3a5d1d4adc496f2d1dd85640dac7", "labels_vector_sha256": "6a418c64db7a659959b37f70079cc610283790f5d1d8f05ca01458ffd019177f", "planned_active_tokens": 65708, "realized_active_tokens": 65708, "cumulative_start": 16976494, "cumulative_end": 17042202, "loss_sum": 27838.805297851562, "token_normalized_loss": 0.4236745190517374, "grad_norm_before_clip": 0.16373905539512634, "learning_rates_at_step": { "lora": 8.858045972148848e-05, "row_tokens": 8.858045972148848e-05 }, "learning_rates_after_step": { "lora": 8.847318483728956e-05, "row_tokens": 8.847318483728956e-05 } }, { "update_id": 260, "row_count": 13, "row_ids_sha256": "616f1c1bbcd2796df5405003cefe7d4874fc3e9f9231d531a15af63d4638fd0e", "input_ids_vector_sha256": "eb7e3ddfee074877c288d76e83ce6c8167a98f58894d3b8ad1f4842db62f6c31", "labels_vector_sha256": "82017f754939cb9561fca9ec93c2a6422c3eb26f91db66c0d74ae4d7bce9b2cd", "planned_active_tokens": 64458, "realized_active_tokens": 64458, "cumulative_start": 17042202, "cumulative_end": 17106660, "loss_sum": 25094.348693847656, "token_normalized_loss": 0.3893131759261481, "grad_norm_before_clip": 0.17671401798725128, "learning_rates_at_step": { "lora": 8.847318483728956e-05, "row_tokens": 8.847318483728956e-05 }, "learning_rates_after_step": { "lora": 8.835315266559818e-05, "row_tokens": 8.835315266559818e-05 } }, { "update_id": 261, "row_count": 14, "row_ids_sha256": "87227aa84c9ec393bcb292db9ec362d561f3996e91a52bbb36d5124e81b025ff", "input_ids_vector_sha256": "5c2ea92e5cf7f35516f79aa1a73a6ab27e26bb2448c6f06d487e1b87841c7d7d", "labels_vector_sha256": "a8f30d392b185e5f5a954a8950e3500f234e52be1c5f2bdce4cd0c12241a4f84", "planned_active_tokens": 71815, "realized_active_tokens": 71815, "cumulative_start": 17106660, "cumulative_end": 17178475, "loss_sum": 31853.070922851562, "token_normalized_loss": 0.44354342300148386, "grad_norm_before_clip": 0.1493663638830185, "learning_rates_at_step": { "lora": 8.835315266559818e-05, "row_tokens": 8.835315266559818e-05 }, "learning_rates_after_step": { "lora": 8.824928650862675e-05, "row_tokens": 8.824928650862675e-05 } }, { "update_id": 262, "row_count": 14, "row_ids_sha256": "8c187c20181cd9976a22fe235d18a54782c4de995f0091e0708f00bd428e037d", "input_ids_vector_sha256": "c7d36d22d3defd2c79c3449d7c11649abc2f5e9fa1e1eb58717e40f8580d4e91", "labels_vector_sha256": "da957802e6748dc374e23c2b64607aea24c313dd5789f76d215614f63bbcfce4", "planned_active_tokens": 61884, "realized_active_tokens": 61884, "cumulative_start": 17178475, "cumulative_end": 17240359, "loss_sum": 22883.410858154297, "token_normalized_loss": 0.36977911670471036, "grad_norm_before_clip": 0.1484571248292923, "learning_rates_at_step": { "lora": 8.824928650862675e-05, "row_tokens": 8.824928650862675e-05 }, "learning_rates_after_step": { "lora": 8.813593922616918e-05, "row_tokens": 8.813593922616918e-05 } }, { "update_id": 263, "row_count": 12, "row_ids_sha256": "4d3c0c01380030fb8d4739e56f19f43acca159c55d4449d5406e3d6b99bd1fab", "input_ids_vector_sha256": "2edbee6815bd50a6a6b605833ea9dadd34af8db60b8cbc039c8ff7829b24f8d9", "labels_vector_sha256": "5ae7fb1eced33d1f7cac60cb38cfe35e4de16d85870f14839a0686cee11e8449", "planned_active_tokens": 67263, "realized_active_tokens": 67263, "cumulative_start": 17240359, "cumulative_end": 17307622, "loss_sum": 27769.218017578125, "token_normalized_loss": 0.41284536844294967, "grad_norm_before_clip": 0.16085052490234375, "learning_rates_at_step": { "lora": 8.813593922616918e-05, "row_tokens": 8.813593922616918e-05 }, "learning_rates_after_step": { "lora": 8.80344102650905e-05, "row_tokens": 8.80344102650905e-05 } }, { "update_id": 264, "row_count": 10, "row_ids_sha256": "45312462805d02f1e1ccc91d4aff7d0cf3b965f18bcf2ed6eb84478658525609", "input_ids_vector_sha256": "1fc671a306b15897e4c82d1868ea2b8c25d378c95277dc61838d39489b9e0ea0", "labels_vector_sha256": "049e9bede3cce02ba8849cdf45eaaf1c35991a202e867260909a1476e168e8b4", "planned_active_tokens": 60014, "realized_active_tokens": 60014, "cumulative_start": 17307622, "cumulative_end": 17367636, "loss_sum": 29778.199493408203, "token_normalized_loss": 0.49618754779565105, "grad_norm_before_clip": 0.1658315658569336, "learning_rates_at_step": { "lora": 8.80344102650905e-05, "row_tokens": 8.80344102650905e-05 }, "learning_rates_after_step": { "lora": 8.791859790340697e-05, "row_tokens": 8.791859790340697e-05 } }, { "update_id": 265, "row_count": 15, "row_ids_sha256": "60a55a416f9134d1b47d084c21205e5ed92f4dd30a6e40df5e34135a629e6363", "input_ids_vector_sha256": "748aeb570c45dfd5ee135a87d08220c66a8ec046297274325fa89cd14a86d9b2", "labels_vector_sha256": "48fd4622df36cc15f19fbd27d22bf9bba8b99ac4cd3d5ab7541fc9554f0fb826", "planned_active_tokens": 68189, "realized_active_tokens": 68189, "cumulative_start": 17367636, "cumulative_end": 17435825, "loss_sum": 26934.558135986328, "token_normalized_loss": 0.39499857947742784, "grad_norm_before_clip": 0.14756107330322266, "learning_rates_at_step": { "lora": 8.791859790340697e-05, "row_tokens": 8.791859790340697e-05 }, "learning_rates_after_step": { "lora": 8.781120708299957e-05, "row_tokens": 8.781120708299957e-05 } }, { "update_id": 266, "row_count": 11, "row_ids_sha256": "9c56f3cf67d5d26abb794583e38dae92067b325454757d1884ab710e127b38c0", "input_ids_vector_sha256": "a4f1a98a1f2904faddde8af572b9863f0c701186b2c52e9f1e6ef3a0865f44ee", "labels_vector_sha256": "239fa8b4bf97924f26fbe0a33b542acda7c29c016e52b88489edce2b895d854b", "planned_active_tokens": 62979, "realized_active_tokens": 62979, "cumulative_start": 17435825, "cumulative_end": 17498804, "loss_sum": 28913.382568359375, "token_normalized_loss": 0.45909561232092244, "grad_norm_before_clip": 0.18234550952911377, "learning_rates_at_step": { "lora": 8.781120708299957e-05, "row_tokens": 8.781120708299957e-05 }, "learning_rates_after_step": { "lora": 8.769549698592766e-05, "row_tokens": 8.769549698592766e-05 } }, { "update_id": 267, "row_count": 12, "row_ids_sha256": "0b7bc992ae24e1c8f2a033e1e356308e7b6a57986cf7e5884440de477ee81b8a", "input_ids_vector_sha256": "eb3fba23cc1506aa5ae27fcb0144684cfbd70ee901b27bbc000f4bca5474078c", "labels_vector_sha256": "4dd351c5ff24df0d340c530e994e6bdaab20386d2ffc74b4ca6ffd602f2792bb", "planned_active_tokens": 67591, "realized_active_tokens": 67591, "cumulative_start": 17498804, "cumulative_end": 17566395, "loss_sum": 28107.43896484375, "token_normalized_loss": 0.41584588132804295, "grad_norm_before_clip": 0.15276668965816498, "learning_rates_at_step": { "lora": 8.769549698592766e-05, "row_tokens": 8.769549698592766e-05 }, "learning_rates_after_step": { "lora": 8.757891423390449e-05, "row_tokens": 8.757891423390449e-05 } }, { "update_id": 268, "row_count": 15, "row_ids_sha256": "474bd17fa04369b87a0d7342b3fd431e2e87dd811720f93acd084d4940663938", "input_ids_vector_sha256": "f3b5ac8a1a81afe2da93dc2ddc8432353520cde7f500847e8216cf3412d87591", "labels_vector_sha256": "d6badb2e09aaeb5ba9cf3b605c7957f671cf1acc777435814cbeeb62c3802d22", "planned_active_tokens": 67825, "realized_active_tokens": 67825, "cumulative_start": 17566395, "cumulative_end": 17634220, "loss_sum": 24823.41094970703, "token_normalized_loss": 0.3659920523362629, "grad_norm_before_clip": 0.14380602538585663, "learning_rates_at_step": { "lora": 8.757891423390449e-05, "row_tokens": 8.757891423390449e-05 }, "learning_rates_after_step": { "lora": 8.746954576480389e-05, "row_tokens": 8.746954576480389e-05 } }, { "update_id": 269, "row_count": 12, "row_ids_sha256": "da8c91449cb73d7f99a6c453ecc18f07ffcec55c2b5537681999e2f9d38301e3", "input_ids_vector_sha256": "209baebfd0a395d790caef0af907fb4e97cc3787679a4a23015d41ef0522a68e", "labels_vector_sha256": "4abc014aba364c5e006775699682e12bea46a5192b37a5b290e20b356523fe0c", "planned_active_tokens": 63380, "realized_active_tokens": 63380, "cumulative_start": 17634220, "cumulative_end": 17697600, "loss_sum": 28920.63101196289, "token_normalized_loss": 0.4563053173234915, "grad_norm_before_clip": 0.16132348775863647, "learning_rates_at_step": { "lora": 8.746954576480389e-05, "row_tokens": 8.746954576480389e-05 }, "learning_rates_after_step": { "lora": 8.735441119545769e-05, "row_tokens": 8.735441119545769e-05 } }, { "update_id": 270, "row_count": 13, "row_ids_sha256": "760d262e5d7448d60103295c258d3f3f07946118df556fff436eec531cbb2d77", "input_ids_vector_sha256": "8c2a3216351d8dffa9c57a7023388865883718658130daec930bae8c6c4b643b", "labels_vector_sha256": "6bd9872584be47382bc72598134110af63192dc9a4bb0935495af63a725e6662", "planned_active_tokens": 66466, "realized_active_tokens": 66466, "cumulative_start": 17697600, "cumulative_end": 17764066, "loss_sum": 27278.553161621094, "token_normalized_loss": 0.4104136424882059, "grad_norm_before_clip": 0.16517041623592377, "learning_rates_at_step": { "lora": 8.735441119545769e-05, "row_tokens": 8.735441119545769e-05 }, "learning_rates_after_step": { "lora": 8.72447292171043e-05, "row_tokens": 8.72447292171043e-05 } }, { "update_id": 271, "row_count": 14, "row_ids_sha256": "63f02e7094d8f31a1399fda794aeb9051b1c3646453054e4356a56a85a3ef618", "input_ids_vector_sha256": "76d162a28a5a22c43a0e0188df632d5fd1f4fabcde6aa50274d9ccc8a0dee558", "labels_vector_sha256": "4e0b609ae7cd248b976ce48fedf0fbf9f19d46dd03528885172e73849652ec23", "planned_active_tokens": 63078, "realized_active_tokens": 63078, "cumulative_start": 17764066, "cumulative_end": 17827144, "loss_sum": 24141.195251464844, "token_normalized_loss": 0.38271973194243386, "grad_norm_before_clip": 0.3397478461265564, "learning_rates_at_step": { "lora": 8.72447292171043e-05, "row_tokens": 8.72447292171043e-05 }, "learning_rates_after_step": { "lora": 8.71279074013331e-05, "row_tokens": 8.71279074013331e-05 } }, { "update_id": 272, "row_count": 15, "row_ids_sha256": "4a4dad59902748cdd60fa91cd624d50278a8d8942379520525a3acaf07ecd2e4", "input_ids_vector_sha256": "16623d96b767117575e1d5c8cc95baceb2ebab2bdc8e2826a1daee90f6b78141", "labels_vector_sha256": "fb881bde1fa4087589d3c156ee036ab1b8267302a15efb678fa7f0ba16c6a899", "planned_active_tokens": 66930, "realized_active_tokens": 66930, "cumulative_start": 17827144, "cumulative_end": 17894074, "loss_sum": 25703.6416015625, "token_normalized_loss": 0.38403767520637233, "grad_norm_before_clip": 0.14793187379837036, "learning_rates_at_step": { "lora": 8.71279074013331e-05, "row_tokens": 8.71279074013331e-05 }, "learning_rates_after_step": { "lora": 8.701438876528534e-05, "row_tokens": 8.701438876528534e-05 } }, { "update_id": 273, "row_count": 15, "row_ids_sha256": "d34f19d210c05a768b46b06ee3f599db0911f7f81b64c04dc26d1769b97abf27", "input_ids_vector_sha256": "ae12b69e1e90b8f394dd17dcfd91b73a7f3c0679568ad38ba89fbdac6ae7791d", "labels_vector_sha256": "927b279cb89bb9e3d3f33f703f7dbe3666e89d73c9102d27d5eeae237694fc4c", "planned_active_tokens": 64790, "realized_active_tokens": 64790, "cumulative_start": 17894074, "cumulative_end": 17958864, "loss_sum": 25279.333099365234, "token_normalized_loss": 0.3901733770545645, "grad_norm_before_clip": 0.1566431224346161, "learning_rates_at_step": { "lora": 8.701438876528534e-05, "row_tokens": 8.701438876528534e-05 }, "learning_rates_after_step": { "lora": 8.689962359561594e-05, "row_tokens": 8.689962359561594e-05 } }, { "update_id": 274, "row_count": 16, "row_ids_sha256": "2f29d1e9a4e058ab95dc5e3c2f43050398de2a7ce42a94f820ad180b6730cf6c", "input_ids_vector_sha256": "621896c5c0d571b89eb4bae772d209ecae1e2b8ba7da4aef78c35b59acc75ee7", "labels_vector_sha256": "c48cfb4c49bc2e935135ae905a844c835a630a40df09e2d08aeb9a1a5c0c5eff", "planned_active_tokens": 65257, "realized_active_tokens": 65257, "cumulative_start": 17958864, "cumulative_end": 18024121, "loss_sum": 20972.06365966797, "token_normalized_loss": 0.32137646014478094, "grad_norm_before_clip": 0.13214857876300812, "learning_rates_at_step": { "lora": 8.689962359561594e-05, "row_tokens": 8.689962359561594e-05 }, "learning_rates_after_step": { "lora": 8.678287182113774e-05, "row_tokens": 8.678287182113774e-05 } }, { "update_id": 275, "row_count": 17, "row_ids_sha256": "0590170c097c323c4adec889d48f63abd7e75c2ac72e1e9e5c4d97a58c745080", "input_ids_vector_sha256": "0fe791357a8bacb2205e36980be31e3a12abc921f1a0e0d92874034315c76a4f", "labels_vector_sha256": "a3667365bb6f31c8149cbc85c36f585874bce8e99560ca45156e9c977f22ca23", "planned_active_tokens": 66138, "realized_active_tokens": 66138, "cumulative_start": 18024121, "cumulative_end": 18090259, "loss_sum": 24770.702880859375, "token_normalized_loss": 0.37453057063805034, "grad_norm_before_clip": 0.1459100991487503, "learning_rates_at_step": { "lora": 8.678287182113774e-05, "row_tokens": 8.678287182113774e-05 }, "learning_rates_after_step": { "lora": 8.666700911635149e-05, "row_tokens": 8.666700911635149e-05 } }, { "update_id": 276, "row_count": 13, "row_ids_sha256": "28b47ae364aae72bf06aa084e6f56e5c9209e7b32543dcd99d45f2b2bc25b450", "input_ids_vector_sha256": "fb0d4568202303bea8b0950361e44ce7b38d8ce43cb522cf3b210283bd2eeee0", "labels_vector_sha256": "7f312d357ca53998bcb3e15221a3b8ccf580a42b595508af552ba991cf05fe08", "planned_active_tokens": 65390, "realized_active_tokens": 65390, "cumulative_start": 18090259, "cumulative_end": 18155649, "loss_sum": 23933.040161132812, "token_normalized_loss": 0.36600459032165183, "grad_norm_before_clip": 0.1464262455701828, "learning_rates_at_step": { "lora": 8.666700911635149e-05, "row_tokens": 8.666700911635149e-05 }, "learning_rates_after_step": { "lora": 8.654818878898907e-05, "row_tokens": 8.654818878898907e-05 } }, { "update_id": 277, "row_count": 17, "row_ids_sha256": "9c8fe72bbe9de337a259086088fdc9f93226be93e738486472a5a9d8c4ef900a", "input_ids_vector_sha256": "48777e4eeff7f4c96a2989ebfb666e5ba218f41dc4973898c4e82dd7d3414aca", "labels_vector_sha256": "d9d70cdd24e6bb78df778b2cf42ab2379f2baadd32ee7a12304f97f1e03e2e7c", "planned_active_tokens": 66810, "realized_active_tokens": 66810, "cumulative_start": 18155649, "cumulative_end": 18222459, "loss_sum": 24162.111877441406, "token_normalized_loss": 0.36165412179975165, "grad_norm_before_clip": 0.15123170614242554, "learning_rates_at_step": { "lora": 8.654818878898907e-05, "row_tokens": 8.654818878898907e-05 }, "learning_rates_after_step": { "lora": 8.641620511428521e-05, "row_tokens": 8.641620511428521e-05 } }, { "update_id": 278, "row_count": 15, "row_ids_sha256": "f13db5b3072df8ffde6d17253a0ea70bd4482e0ffd63845b49e4330fd8134a69", "input_ids_vector_sha256": "ff19e0c54891e2e7bdf9f9c07d186862485788aad1a562d7b319f4a67a4cd828", "labels_vector_sha256": "937d92fd5e34c44f89f3e5d262fb82ec23565198f2a4d5a0336d3906b0ff3aaf", "planned_active_tokens": 73920, "realized_active_tokens": 73920, "cumulative_start": 18222459, "cumulative_end": 18296379, "loss_sum": 32510.10418701172, "token_normalized_loss": 0.4398011930061109, "grad_norm_before_clip": 0.14450863003730774, "learning_rates_at_step": { "lora": 8.641620511428521e-05, "row_tokens": 8.641620511428521e-05 }, "learning_rates_after_step": { "lora": 8.63072636525808e-05, "row_tokens": 8.63072636525808e-05 } }, { "update_id": 279, "row_count": 10, "row_ids_sha256": "bfd83beeb6d1b49a168107a9d242cf542b77331161bd84e53c91d42f37db9b4a", "input_ids_vector_sha256": "201ec41aa149b831b1dba03ca0bf57ffd77f532be4fcdc5c6b6fd2cd9c5799fd", "labels_vector_sha256": "21f1a580122ac270e4f8b299503ce8839bc6224b57180a4f7f335a2333245cca", "planned_active_tokens": 60787, "realized_active_tokens": 60787, "cumulative_start": 18296379, "cumulative_end": 18357166, "loss_sum": 25021.031219482422, "token_normalized_loss": 0.41161812919674307, "grad_norm_before_clip": 0.1573934108018875, "learning_rates_at_step": { "lora": 8.63072636525808e-05, "row_tokens": 8.63072636525808e-05 }, "learning_rates_after_step": { "lora": 8.61990208380072e-05, "row_tokens": 8.61990208380072e-05 } }, { "update_id": 280, "row_count": 13, "row_ids_sha256": "f53b2fd7ea85b0361b5dd41ee40778bbd54a46449668a08b03c4a5fb494a956a", "input_ids_vector_sha256": "1121f0e34d1e30867949900c8c3def2f9f7cc144b7f737653fbe53734dbd381d", "labels_vector_sha256": "8fe5244a103fa0d43b41f18fd558f1576e5ebb0b18940274e48ebfc0b7d92c1b", "planned_active_tokens": 60196, "realized_active_tokens": 60196, "cumulative_start": 18357166, "cumulative_end": 18417362, "loss_sum": 23084.546951293945, "token_normalized_loss": 0.3834897161155882, "grad_norm_before_clip": 0.16196461021900177, "learning_rates_at_step": { "lora": 8.61990208380072e-05, "row_tokens": 8.61990208380072e-05 }, "learning_rates_after_step": { "lora": 8.608384190011407e-05, "row_tokens": 8.608384190011407e-05 } }, { "update_id": 281, "row_count": 12, "row_ids_sha256": "eab8bdc3cd2e5ff84586d83de03bc81976d3735e012b74ad7ae4849991fadb46", "input_ids_vector_sha256": "cde6df597a4b9593ad6b002d8a0044b91b75f4a4dbccacaef150152680118ce3", "labels_vector_sha256": "af25828ad75dd59b6e9559f25fc69583d8d3e87d199ca6c456c00e98807c9686", "planned_active_tokens": 63836, "realized_active_tokens": 63836, "cumulative_start": 18417362, "cumulative_end": 18481198, "loss_sum": 26603.937469482422, "token_normalized_loss": 0.41675445625481583, "grad_norm_before_clip": 0.16630129516124725, "learning_rates_at_step": { "lora": 8.608384190011407e-05, "row_tokens": 8.608384190011407e-05 }, "learning_rates_after_step": { "lora": 8.59592302980517e-05, "row_tokens": 8.59592302980517e-05 } }, { "update_id": 282, "row_count": 18, "row_ids_sha256": "04ec5127b74d3e79c831adc298ac5fd723031100df17320999f759a0c2e8a91c", "input_ids_vector_sha256": "66b3b4a516b1f7bd6865f36c84411c2c006698e05f5c1c38e5d493a25315405e", "labels_vector_sha256": "52272c3f3fce44203cb7b434bd5fc842800f5798e46786d4f4f68232b2c7ce4a", "planned_active_tokens": 68815, "realized_active_tokens": 68815, "cumulative_start": 18481198, "cumulative_end": 18550013, "loss_sum": 23838.894805908203, "token_normalized_loss": 0.346420036415145, "grad_norm_before_clip": 0.14298345148563385, "learning_rates_at_step": { "lora": 8.59592302980517e-05, "row_tokens": 8.59592302980517e-05 }, "learning_rates_after_step": { "lora": 8.584218369944301e-05, "row_tokens": 8.584218369944301e-05 } }, { "update_id": 283, "row_count": 13, "row_ids_sha256": "8f2db2275d0c9cb9730bc7402a864a977a8af3ea7462a2bef1e32c4444b40345", "input_ids_vector_sha256": "20eea0fd758d2df2f41b7e17d5a5068b1a6766fea8159de32b36c6171c2c1a8a", "labels_vector_sha256": "c399ee69e27e9c82784664ae8889f54fb24f22b8fbbd7be4ff4e9a7d4830e4a6", "planned_active_tokens": 64405, "realized_active_tokens": 64405, "cumulative_start": 18550013, "cumulative_end": 18614418, "loss_sum": 26213.292236328125, "token_normalized_loss": 0.4070070993917883, "grad_norm_before_clip": 0.1583898514509201, "learning_rates_at_step": { "lora": 8.584218369944301e-05, "row_tokens": 8.584218369944301e-05 }, "learning_rates_after_step": { "lora": 8.572246272134139e-05, "row_tokens": 8.572246272134139e-05 } }, { "update_id": 284, "row_count": 12, "row_ids_sha256": "0b6d7b01e23d05bee02e1c3be3f24533d5763afa59b4fb80422d2c0791fb9b71", "input_ids_vector_sha256": "7f4c927370222bf83ad685fce7ef94147bdda53bf053968c70181bd2b7590610", "labels_vector_sha256": "d4a15790c7aa8bf60e1c85b92d94654b9ff75d17a0b8d55d53b625e176acc15c", "planned_active_tokens": 65647, "realized_active_tokens": 65647, "cumulative_start": 18614418, "cumulative_end": 18680065, "loss_sum": 27235.707641601562, "token_normalized_loss": 0.4148812229287182, "grad_norm_before_clip": 0.15949131548404694, "learning_rates_at_step": { "lora": 8.572246272134139e-05, "row_tokens": 8.572246272134139e-05 }, "learning_rates_after_step": { "lora": 8.560113576803375e-05, "row_tokens": 8.560113576803375e-05 } }, { "update_id": 285, "row_count": 16, "row_ids_sha256": "12a083d7bb8d50f3492d3af6ec2d3fcfad6f86d277abf15c0349b2d12b3f11bf", "input_ids_vector_sha256": "44016e02d71add17db05bc2d882e5d65b3c8928fd9512f79f4ca8bd809a13cbc", "labels_vector_sha256": "2fb4cb76ab8048b8f6ef59668810b066ffa7fa0c3d15dee326ad74d29336f444", "planned_active_tokens": 66294, "realized_active_tokens": 66294, "cumulative_start": 18680065, "cumulative_end": 18746359, "loss_sum": 23627.58041381836, "token_normalized_loss": 0.3564060158357975, "grad_norm_before_clip": 0.14057540893554688, "learning_rates_at_step": { "lora": 8.560113576803375e-05, "row_tokens": 8.560113576803375e-05 }, "learning_rates_after_step": { "lora": 8.547851743096564e-05, "row_tokens": 8.547851743096564e-05 } }, { "update_id": 286, "row_count": 15, "row_ids_sha256": "18823a12eb1b78735d19c0e8be2e78f9b2822e9ca9a95859ee506f11bf0f763a", "input_ids_vector_sha256": "cabaf09ad9a6b75fd1dde3836f4f8d7e602d4a306f5fdf5d740d45756a2ab76a", "labels_vector_sha256": "70ba51913720ccde7d59473894e06038bc8f90ad0a66ccb020f60c4aab430ca9", "planned_active_tokens": 66764, "realized_active_tokens": 66764, "cumulative_start": 18746359, "cumulative_end": 18813123, "loss_sum": 25447.427947998047, "token_normalized_loss": 0.38115493301776476, "grad_norm_before_clip": 0.1563372164964676, "learning_rates_at_step": { "lora": 8.547851743096564e-05, "row_tokens": 8.547851743096564e-05 }, "learning_rates_after_step": { "lora": 8.536465001780349e-05, "row_tokens": 8.536465001780349e-05 } }, { "update_id": 287, "row_count": 11, "row_ids_sha256": "fc40ae149108614086718397eafe36d60e5258f3de7f2e43c6e478d71e8f4b33", "input_ids_vector_sha256": "615b7087e50bad639c42e991e84d4852839f268fb3b57ab91526573ba9410298", "labels_vector_sha256": "1d107a30cf05a31ce9067540a1a7964b7cd54aa9f823d8e40915a7b4f5375245", "planned_active_tokens": 61790, "realized_active_tokens": 61790, "cumulative_start": 18813123, "cumulative_end": 18874913, "loss_sum": 26340.373291015625, "token_normalized_loss": 0.4262886112803953, "grad_norm_before_clip": 0.16233481466770172, "learning_rates_at_step": { "lora": 8.536465001780349e-05, "row_tokens": 8.536465001780349e-05 }, "learning_rates_after_step": { "lora": 8.523953744179421e-05, "row_tokens": 8.523953744179421e-05 } }, { "update_id": 288, "row_count": 16, "row_ids_sha256": "d38fe92063193d6febd1312a8ade780af29932b5b5435d5b1663a4df6ae2a7c9", "input_ids_vector_sha256": "b2704c8293e7a9bfbc1114e53a57cff4d43f7e3082cca83b785ddf1b94909a62", "labels_vector_sha256": "d91a015389c2a0f5bbb12e183e3f2212fa2015c0310e21221ecf7aa350949cbb", "planned_active_tokens": 67663, "realized_active_tokens": 67663, "cumulative_start": 18874913, "cumulative_end": 18942576, "loss_sum": 28656.517547607422, "token_normalized_loss": 0.4235182824824117, "grad_norm_before_clip": 0.1460154801607132, "learning_rates_at_step": { "lora": 8.523953744179421e-05, "row_tokens": 8.523953744179421e-05 }, "learning_rates_after_step": { "lora": 8.512203260797805e-05, "row_tokens": 8.512203260797805e-05 } }, { "update_id": 289, "row_count": 15, "row_ids_sha256": "2fa76215a4c2ded54b9069df9daf6874c671f0c60075e297905b182cebd56111", "input_ids_vector_sha256": "68ef200916c7290e318bd0e3e0459d129a32cc06e78554ed4b2b015a2e838715", "labels_vector_sha256": "4498a541550fc6bfb1663926dadd6de8f135ec2a7040becc57a0d6629b843ad5", "planned_active_tokens": 63333, "realized_active_tokens": 63333, "cumulative_start": 18942576, "cumulative_end": 19005909, "loss_sum": 20775.519073486328, "token_normalized_loss": 0.32803623819314304, "grad_norm_before_clip": 0.1391238421201706, "learning_rates_at_step": { "lora": 8.512203260797805e-05, "row_tokens": 8.512203260797805e-05 }, "learning_rates_after_step": { "lora": 8.499649859074787e-05, "row_tokens": 8.499649859074787e-05 } }, { "update_id": 290, "row_count": 12, "row_ids_sha256": "3ae2ea6bb6316d13ff20330ce6bb90db885c34e490edb3d079188cf76ca666e3", "input_ids_vector_sha256": "b7f89e911ae0a20579f80883b14245db5b27751838e3853008e329cf2ad3fef8", "labels_vector_sha256": "1ebbb3d3e66b7dfd9d16b14a0204e6c9aa9e9b08ea9ca5613cc74a3e2b7ca59c", "planned_active_tokens": 67433, "realized_active_tokens": 67433, "cumulative_start": 19005909, "cumulative_end": 19073342, "loss_sum": 29376.725341796875, "token_normalized_loss": 0.4356431619799931, "grad_norm_before_clip": 0.14586544036865234, "learning_rates_at_step": { "lora": 8.499649859074787e-05, "row_tokens": 8.499649859074787e-05 }, "learning_rates_after_step": { "lora": 8.487383696997131e-05, "row_tokens": 8.487383696997131e-05 } }, { "update_id": 291, "row_count": 13, "row_ids_sha256": "172009327195f435853afbf5919592b67c372d281c79ab6902bccb963cf2ee7b", "input_ids_vector_sha256": "8fcecc99aa8c77dedc42d3da6cf9ac7176df3a3a8a915d31daa9810004c0be11", "labels_vector_sha256": "b92ecbc614df3e19c109d45059d0fce5eb1ae8d97a6da0eb0bc58ce990df97d7", "planned_active_tokens": 65666, "realized_active_tokens": 65666, "cumulative_start": 19073342, "cumulative_end": 19139008, "loss_sum": 24231.54296875, "token_normalized_loss": 0.3690120148745165, "grad_norm_before_clip": 0.14065992832183838, "learning_rates_at_step": { "lora": 8.487383696997131e-05, "row_tokens": 8.487383696997131e-05 }, "learning_rates_after_step": { "lora": 8.474371901268057e-05, "row_tokens": 8.474371901268057e-05 } }, { "update_id": 292, "row_count": 14, "row_ids_sha256": "4eb4a404c06035e5766a52a3bbf2bfb5a659f046cacb0cba35de8e9fdff5a54c", "input_ids_vector_sha256": "a9d6f8fc8a52b32c2920adf8383710f1d3beed3dcd4d01f22e732f73babc9db1", "labels_vector_sha256": "430528b8c4124574ee901a1eeb8d7d1971a474406162ca52183371727fea746e", "planned_active_tokens": 69419, "realized_active_tokens": 69419, "cumulative_start": 19139008, "cumulative_end": 19208427, "loss_sum": 25503.112274169922, "token_normalized_loss": 0.367379424569209, "grad_norm_before_clip": 0.15654683113098145, "learning_rates_at_step": { "lora": 8.474371901268057e-05, "row_tokens": 8.474371901268057e-05 }, "learning_rates_after_step": { "lora": 8.463242287162869e-05, "row_tokens": 8.463242287162869e-05 } }, { "update_id": 293, "row_count": 12, "row_ids_sha256": "0b0784f02d3563ffcc890a43641f4dc6d61484f5b6d7c25a577d18ad9d40af89", "input_ids_vector_sha256": "a0cbac0fb49a5262be3ef496c6665a1d79c34fcf5471b34665cf563d9103a80c", "labels_vector_sha256": "25a29d5fc0bcf101970424908dabf1abe8deb5a461648e817322c070e0cd2e0f", "planned_active_tokens": 59185, "realized_active_tokens": 59185, "cumulative_start": 19208427, "cumulative_end": 19267612, "loss_sum": 22347.022171020508, "token_normalized_loss": 0.37757915301208933, "grad_norm_before_clip": 0.1558205932378769, "learning_rates_at_step": { "lora": 8.463242287162869e-05, "row_tokens": 8.463242287162869e-05 }, "learning_rates_after_step": { "lora": 8.450352404432467e-05, "row_tokens": 8.450352404432467e-05 } }, { "update_id": 294, "row_count": 11, "row_ids_sha256": "3c2b8b3047699e0f99b850562dc17df09deef5ff8c75e66564a1ef0e3fd9a821", "input_ids_vector_sha256": "c80716aa9d149d42feadc2632a58661ee2293593974e68c12feb778389b096e9", "labels_vector_sha256": "5ed9a5928985b11cee90496383b8559b4ae245ca698bb0a2a37e487f76d809f0", "planned_active_tokens": 68327, "realized_active_tokens": 68327, "cumulative_start": 19267612, "cumulative_end": 19335939, "loss_sum": 29881.616088867188, "token_normalized_loss": 0.43733247601778485, "grad_norm_before_clip": 0.14635467529296875, "learning_rates_at_step": { "lora": 8.450352404432467e-05, "row_tokens": 8.450352404432467e-05 }, "learning_rates_after_step": { "lora": 8.437962177733365e-05, "row_tokens": 8.437962177733365e-05 } }, { "update_id": 295, "row_count": 13, "row_ids_sha256": "ac181585aaf6715de286e0308e3859df8b418ae08da7f90f7f7c5b6d50b41df8", "input_ids_vector_sha256": "3de356543f16ba18056bec65e6e21ba928680ca3759ca332d975bdfd4546702c", "labels_vector_sha256": "a75cedf89a0117d8d96fbfbf6f8e62bdc9689ac0695d71a4c0215c7e4936c9e7", "planned_active_tokens": 65460, "realized_active_tokens": 65460, "cumulative_start": 19335939, "cumulative_end": 19401399, "loss_sum": 24376.533294677734, "token_normalized_loss": 0.37238822631649454, "grad_norm_before_clip": 0.14074794948101044, "learning_rates_at_step": { "lora": 8.437962177733365e-05, "row_tokens": 8.437962177733365e-05 }, "learning_rates_after_step": { "lora": 8.425586364400584e-05, "row_tokens": 8.425586364400584e-05 } }, { "update_id": 296, "row_count": 14, "row_ids_sha256": "3d62367d7b10689582ce30405ac191e5c3af25fbc5f209df6b7e79a0e31de503", "input_ids_vector_sha256": "3ac80c75ce6748a443d3535544774d81134d625818ed2a2b1ee49927a74896a5", "labels_vector_sha256": "e347649eba8b52fdba0cc0751b76ae2375a7b34e6841852683c9074898c5baf4", "planned_active_tokens": 65173, "realized_active_tokens": 65173, "cumulative_start": 19401399, "cumulative_end": 19466572, "loss_sum": 23496.396575927734, "token_normalized_loss": 0.36052347714433486, "grad_norm_before_clip": 0.14616602659225464, "learning_rates_at_step": { "lora": 8.425586364400584e-05, "row_tokens": 8.425586364400584e-05 }, "learning_rates_after_step": { "lora": 8.411698922746759e-05, "row_tokens": 8.411698922746759e-05 } }, { "update_id": 297, "row_count": 13, "row_ids_sha256": "455575264b06871f8b1c44f7fca2a34015324ea440f6ba52560be2dcb91bc1d9", "input_ids_vector_sha256": "76a94b42ef41e6ea63f1497790e1cf8a2b83095bb180a3e6f0478f984d5f00dc", "labels_vector_sha256": "34581a95e9aeb7797e99222640962c3a73b94d2a2647dc78eb831f2f4da7a862", "planned_active_tokens": 72886, "realized_active_tokens": 72886, "cumulative_start": 19466572, "cumulative_end": 19539458, "loss_sum": 30489.179290771484, "token_normalized_loss": 0.41831324658743085, "grad_norm_before_clip": 0.1432787925004959, "learning_rates_at_step": { "lora": 8.411698922746759e-05, "row_tokens": 8.411698922746759e-05 }, "learning_rates_after_step": { "lora": 8.399467274400762e-05, "row_tokens": 8.399467274400762e-05 } }, { "update_id": 298, "row_count": 11, "row_ids_sha256": "c03406e8e5c9e0bbab7fd2801ada68f6de1fe61718ec3408cb7d23b6d6840bfe", "input_ids_vector_sha256": "6f3fea4939ff02db7ccde0fca68c42006f3f18a024c9eab714840e69c5025e44", "labels_vector_sha256": "d8d6f15466f11135de059fa3ca30e890fed3fd75ec71369a0d9031151fe9d1cf", "planned_active_tokens": 63982, "realized_active_tokens": 63982, "cumulative_start": 19539458, "cumulative_end": 19603440, "loss_sum": 27348.491821289062, "token_normalized_loss": 0.42744040232079433, "grad_norm_before_clip": 0.15734818577766418, "learning_rates_at_step": { "lora": 8.399467274400762e-05, "row_tokens": 8.399467274400762e-05 }, "learning_rates_after_step": { "lora": 8.388411133032461e-05, "row_tokens": 8.388411133032461e-05 } }, { "update_id": 299, "row_count": 12, "row_ids_sha256": "afe27e85b67b28822636a64abcf0bca12e61616c068eab31248ac3bf5ce09ca3", "input_ids_vector_sha256": "e5487806a8d54cfac71d1d0252742aff305f03e39cf1ad522f6d04f4f9f7df7b", "labels_vector_sha256": "8c4379bcf3ca87fababb0bb07b51ef57870a87914788375e453d075a5bf423d1", "planned_active_tokens": 57663, "realized_active_tokens": 57663, "cumulative_start": 19603440, "cumulative_end": 19661103, "loss_sum": 23636.437072753906, "token_normalized_loss": 0.40990647508374356, "grad_norm_before_clip": 0.15718650817871094, "learning_rates_at_step": { "lora": 8.388411133032461e-05, "row_tokens": 8.388411133032461e-05 }, "learning_rates_after_step": { "lora": 8.375758069285085e-05, "row_tokens": 8.375758069285085e-05 } }, { "update_id": 300, "row_count": 15, "row_ids_sha256": "17230ca013ceedca4b52fea2a93bf27c445b891ba0061f1bba2f0a3766d7c7c4", "input_ids_vector_sha256": "c2070df9b529fe10c6f7c18e43a1c8d42d90467c7fe9c457445885707b6e676d", "labels_vector_sha256": "1b8213a6721b3c128163092ed1d0eb9464a8ad2d92d75bcf0f5556c6f6535390", "planned_active_tokens": 65796, "realized_active_tokens": 65796, "cumulative_start": 19661103, "cumulative_end": 19726899, "loss_sum": 24646.421905517578, "token_normalized_loss": 0.3745884537892513, "grad_norm_before_clip": 0.16820251941680908, "learning_rates_at_step": { "lora": 8.375758069285085e-05, "row_tokens": 8.375758069285085e-05 }, "learning_rates_after_step": { "lora": 8.362489910474638e-05, "row_tokens": 8.362489910474638e-05 } }, { "update_id": 301, "row_count": 13, "row_ids_sha256": "b7d3701d99d3ae07dc1bdc546aedf6e5916cf3ac6967c73e17f3b9d55b5fcd48", "input_ids_vector_sha256": "a96261dc1c342afcbde155fd3780a95d64f5437f895d67b2da375dfc3fb2fa88", "labels_vector_sha256": "8a443bad011ad65c3b62b07a4c4727266b47b469f0f533da3390604ccc209e7e", "planned_active_tokens": 68773, "realized_active_tokens": 68773, "cumulative_start": 19726899, "cumulative_end": 19795672, "loss_sum": 26940.248931884766, "token_normalized_loss": 0.39172711575596186, "grad_norm_before_clip": 0.15802915394306183, "learning_rates_at_step": { "lora": 8.362489910474638e-05, "row_tokens": 8.362489910474638e-05 }, "learning_rates_after_step": { "lora": 8.35045134248342e-05, "row_tokens": 8.35045134248342e-05 } }, { "update_id": 302, "row_count": 16, "row_ids_sha256": "079af43d093c29cdb259604dd631efe0685c1b862fa06257c38130ab09f8dc56", "input_ids_vector_sha256": "f47ebf8c5cba20d3c893cfd1afb58e6db4543b0ef408e56bfebeb4a8d63e964e", "labels_vector_sha256": "c8f7f728aa31153b883509380609deae8aca0b5cd3d9577f172ae6e5b27b22de", "planned_active_tokens": 62206, "realized_active_tokens": 62206, "cumulative_start": 19795672, "cumulative_end": 19857878, "loss_sum": 19446.54071044922, "token_normalized_loss": 0.31261519323617043, "grad_norm_before_clip": 0.1376277059316635, "learning_rates_at_step": { "lora": 8.35045134248342e-05, "row_tokens": 8.35045134248342e-05 }, "learning_rates_after_step": { "lora": 8.336537989400665e-05, "row_tokens": 8.336537989400665e-05 } }, { "update_id": 303, "row_count": 16, "row_ids_sha256": "9d9da7c63cd1d9f025b294931ee3de148d105bffb320885bbdafd5ec614fe61f", "input_ids_vector_sha256": "c6cd02eff02d501075c80e525e3a99843eb8822d12cccc0acc09ef91ace175a8", "labels_vector_sha256": "6b77245ede08f72d3b46ce2d1ab2a93baa5e8c3e14b81681489cedc4abc6fe77", "planned_active_tokens": 71667, "realized_active_tokens": 71667, "cumulative_start": 19857878, "cumulative_end": 19929545, "loss_sum": 26481.031280517578, "token_normalized_loss": 0.36950104344422924, "grad_norm_before_clip": 0.14141060411930084, "learning_rates_at_step": { "lora": 8.336537989400665e-05, "row_tokens": 8.336537989400665e-05 }, "learning_rates_after_step": { "lora": 8.324839665883746e-05, "row_tokens": 8.324839665883746e-05 } }, { "update_id": 304, "row_count": 16, "row_ids_sha256": "58c97f48c91c320b9010afe408b6ac8203118ae789dad97b00f4604f3df07f18", "input_ids_vector_sha256": "cf731d1e19b121608db73d79865e0db0708394afb6d03655666a924f1a4b8794", "labels_vector_sha256": "d8e8fccd1d7f3989190017e4c258fb186874eceaf3d713d2bba0c1618868832e", "planned_active_tokens": 60072, "realized_active_tokens": 60072, "cumulative_start": 19929545, "cumulative_end": 19989617, "loss_sum": 19777.08819580078, "token_normalized_loss": 0.3292230689139829, "grad_norm_before_clip": 0.14016185700893402, "learning_rates_at_step": { "lora": 8.324839665883746e-05, "row_tokens": 8.324839665883746e-05 }, "learning_rates_after_step": { "lora": 8.312125064356968e-05, "row_tokens": 8.312125064356968e-05 } }, { "update_id": 305, "row_count": 13, "row_ids_sha256": "db429e364496170a28a6f5f71b8983af6e53906fe0fdb7377ad4ae7b70d1bca6", "input_ids_vector_sha256": "1aed630257f19f7ccc35952681fb7c695afec0b14768b1d74949af55affedb77", "labels_vector_sha256": "d9557645db56c31b71b20329c8d19e957dffd75202807cc55ad4a75a45a292d8", "planned_active_tokens": 65101, "realized_active_tokens": 65101, "cumulative_start": 19989617, "cumulative_end": 20054718, "loss_sum": 21719.72428894043, "token_normalized_loss": 0.3336311928993476, "grad_norm_before_clip": 0.13925288617610931, "learning_rates_at_step": { "lora": 8.312125064356968e-05, "row_tokens": 8.312125064356968e-05 }, "learning_rates_after_step": { "lora": 8.298879725415782e-05, "row_tokens": 8.298879725415782e-05 } }, { "update_id": 306, "row_count": 16, "row_ids_sha256": "9d27826f19ae65debbd69f34ef0f89027f65006a2d3482b4d2829152a0c97fa1", "input_ids_vector_sha256": "aa51ed339201e5263026f0265f307be1fcc14aad9499b8cd11b5d52b2f8ff1e9", "labels_vector_sha256": "6bd7a35d784e8ce2819870f7e327db97fcf5e0a37496b2d2cf980da80ab32989", "planned_active_tokens": 67611, "realized_active_tokens": 67611, "cumulative_start": 20054718, "cumulative_end": 20122329, "loss_sum": 22831.016479492188, "token_normalized_loss": 0.3376819819185072, "grad_norm_before_clip": 0.1383436769247055, "learning_rates_at_step": { "lora": 8.298879725415782e-05, "row_tokens": 8.298879725415782e-05 }, "learning_rates_after_step": { "lora": 8.286171865423462e-05, "row_tokens": 8.286171865423462e-05 } }, { "update_id": 307, "row_count": 12, "row_ids_sha256": "08ef955d2b2e34be26921bb000dafaa3d3f03fc16e187a0a1fb37b4383b6dac9", "input_ids_vector_sha256": "a0a9f87986ad57ef47b0ba84ae8a1f720c614569d7e21c4348255190eb0fb88a", "labels_vector_sha256": "d25d7f19d5cf37715cda1ce1148595557b932f051f72de1e6d9f55f0b85a8a2a", "planned_active_tokens": 64671, "realized_active_tokens": 64671, "cumulative_start": 20122329, "cumulative_end": 20187000, "loss_sum": 28389.843872070312, "token_normalized_loss": 0.4389887874328573, "grad_norm_before_clip": 0.1596294343471527, "learning_rates_at_step": { "lora": 8.286171865423462e-05, "row_tokens": 8.286171865423462e-05 }, "learning_rates_after_step": { "lora": 8.272616844329748e-05, "row_tokens": 8.272616844329748e-05 } }, { "update_id": 308, "row_count": 17, "row_ids_sha256": "4acae5ef112048d165d3373ea823e8a8937bcdd1cbfe0fbb905221a4f220da61", "input_ids_vector_sha256": "3ac7b959542ce4fd79ed58f7cea959e9338125dffa095d0789d77f7e856b8626", "labels_vector_sha256": "2ebc7f527256958a362e5d34024719fa855ecfa600e5280e3a0c79f32234cff6", "planned_active_tokens": 68773, "realized_active_tokens": 68773, "cumulative_start": 20187000, "cumulative_end": 20255773, "loss_sum": 24361.362365722656, "token_normalized_loss": 0.35422858339352153, "grad_norm_before_clip": 0.13911430537700653, "learning_rates_at_step": { "lora": 8.272616844329748e-05, "row_tokens": 8.272616844329748e-05 }, "learning_rates_after_step": { "lora": 8.26051637363045e-05, "row_tokens": 8.26051637363045e-05 } }, { "update_id": 309, "row_count": 15, "row_ids_sha256": "7c225fe57d8998168fe38380277bdd4548e6271f07508cfe52c8020d5dd21ba3", "input_ids_vector_sha256": "345521828c7cd263c9f197228895925201d156dba775a1bcdddda40284941f56", "labels_vector_sha256": "0ff7a0caea7a30b8f0001a15e103999501f432d153b5ff243804e13804a571bf", "planned_active_tokens": 61213, "realized_active_tokens": 61213, "cumulative_start": 20255773, "cumulative_end": 20316986, "loss_sum": 18661.07894897461, "token_normalized_loss": 0.3048548339237516, "grad_norm_before_clip": 0.1392173022031784, "learning_rates_at_step": { "lora": 8.26051637363045e-05, "row_tokens": 8.26051637363045e-05 }, "learning_rates_after_step": { "lora": 8.247291530445246e-05, "row_tokens": 8.247291530445246e-05 } }, { "update_id": 310, "row_count": 13, "row_ids_sha256": "1ee6da438808b9e825bb86808fde067070290b396734e690efbccf82f34398f7", "input_ids_vector_sha256": "e197de60970b82e2345f5fdd2fdd33d2bc4c3169fc4883316d10edd1a4132e75", "labels_vector_sha256": "3e92625b84155dfce4acf4bccabea826008d994e8ff4c7cda4fa920d778d9048", "planned_active_tokens": 66709, "realized_active_tokens": 66709, "cumulative_start": 20316986, "cumulative_end": 20383695, "loss_sum": 29457.864349365234, "token_normalized_loss": 0.44158755714169357, "grad_norm_before_clip": 0.1571079045534134, "learning_rates_at_step": { "lora": 8.247291530445246e-05, "row_tokens": 8.247291530445246e-05 }, "learning_rates_after_step": { "lora": 8.234138991738861e-05, "row_tokens": 8.234138991738861e-05 } }, { "update_id": 311, "row_count": 15, "row_ids_sha256": "ef11a73ea4d56a4dd6d7d1dee3749bf83bee0a52386dfe1d2b1fb17b9e374e61", "input_ids_vector_sha256": "f275ce1ed2354ad76dbbf86ec62899091f4563875a9a4ca3cdaa4ca4f101bfb1", "labels_vector_sha256": "199d9ebd5a7aa6d3ff2eac3254c988c85a00fefe6e540ce7e0d65f6a1cbecf78", "planned_active_tokens": 66148, "realized_active_tokens": 66148, "cumulative_start": 20383695, "cumulative_end": 20449843, "loss_sum": 24759.124633789062, "token_normalized_loss": 0.3742989150660498, "grad_norm_before_clip": 0.15232177078723907, "learning_rates_at_step": { "lora": 8.234138991738861e-05, "row_tokens": 8.234138991738861e-05 }, "learning_rates_after_step": { "lora": 8.221255005303711e-05, "row_tokens": 8.221255005303711e-05 } }, { "update_id": 312, "row_count": 14, "row_ids_sha256": "1e85c3a70879a2abd6eeea43c691d4008008963e44644e965596c98004a88701", "input_ids_vector_sha256": "2ee156197482ba8eed55dba85ce2681b34719af3cfe9e88f20a4e748dad9f55c", "labels_vector_sha256": "9ebf31554df0d5d074f2baff702ae35ba78aa95c4a251a3be27bd1022d991f4f", "planned_active_tokens": 64610, "realized_active_tokens": 64610, "cumulative_start": 20449843, "cumulative_end": 20514453, "loss_sum": 22365.783966064453, "token_normalized_loss": 0.3461659799731381, "grad_norm_before_clip": 0.14379724860191345, "learning_rates_at_step": { "lora": 8.221255005303711e-05, "row_tokens": 8.221255005303711e-05 }, "learning_rates_after_step": { "lora": 8.208147099920073e-05, "row_tokens": 8.208147099920073e-05 } }, { "update_id": 313, "row_count": 16, "row_ids_sha256": "4e19437dc61a240fd463aad8ca2ce5212d7e52666ec08127b996712456813d15", "input_ids_vector_sha256": "b9d81f76140a3d396ebe417d2d48c6f56c64d516938458b391b0e7a4b618f7e1", "labels_vector_sha256": "c978b1638fd0e24d08f18bc3e6156e490be4fa1b088ad03c1d01ff784a4c289b", "planned_active_tokens": 65545, "realized_active_tokens": 65545, "cumulative_start": 20514453, "cumulative_end": 20579998, "loss_sum": 21926.487670898438, "token_normalized_loss": 0.33452571013652355, "grad_norm_before_clip": 0.1489092856645584, "learning_rates_at_step": { "lora": 8.208147099920073e-05, "row_tokens": 8.208147099920073e-05 }, "learning_rates_after_step": { "lora": 8.193993871880293e-05, "row_tokens": 8.193993871880293e-05 } }, { "update_id": 314, "row_count": 15, "row_ids_sha256": "b60747160891d1241af6a9cc14f0e4cba63b67d12fcbdab57fe12108967eb555", "input_ids_vector_sha256": "f1dcd621b09ef436abaf5cfb8a557125e2c40bb4a23425b4a6d8e5c64a54effe", "labels_vector_sha256": "9214561a1c360654187026fafec04b5be7bef1878209ef358c9fe0518792de60", "planned_active_tokens": 70562, "realized_active_tokens": 70562, "cumulative_start": 20579998, "cumulative_end": 20650560, "loss_sum": 24815.725158691406, "token_normalized_loss": 0.35168681668166163, "grad_norm_before_clip": 0.1399400383234024, "learning_rates_at_step": { "lora": 8.193993871880293e-05, "row_tokens": 8.193993871880293e-05 }, "learning_rates_after_step": { "lora": 8.181451296045216e-05, "row_tokens": 8.181451296045216e-05 } }, { "update_id": 315, "row_count": 19, "row_ids_sha256": "9ff1abed6d3d86805a78186fa0f187e77daffa4a5c3b4439d30000d76232abb6", "input_ids_vector_sha256": "4cd5543497c64799bb66f5b90be8a68950cc04bd40e8d39f96e69a52b17ca7be", "labels_vector_sha256": "08d1aff5f9286f08cef2e216b307f4bd8348b901628bf8b6aa8f979693154b14", "planned_active_tokens": 62352, "realized_active_tokens": 62352, "cumulative_start": 20650560, "cumulative_end": 20712912, "loss_sum": 17699.46502685547, "token_normalized_loss": 0.2838636295043538, "grad_norm_before_clip": 0.13302895426750183, "learning_rates_at_step": { "lora": 8.181451296045216e-05, "row_tokens": 8.181451296045216e-05 }, "learning_rates_after_step": { "lora": 8.16856354521393e-05, "row_tokens": 8.16856354521393e-05 } }, { "update_id": 316, "row_count": 14, "row_ids_sha256": "631dc43cfab759c4567ad35802c9b957e8486eb3cf28d6415b3fbce3b2c526ec", "input_ids_vector_sha256": "e51796dfdd64f4914c9b9cf0ab4fe57baaf1324426a9cb305e1e5e5aab250351", "labels_vector_sha256": "073b6e368650eb5f0e55e1f3302bfe8f1eb75cd1f737cd23fc3812889038ec60", "planned_active_tokens": 63894, "realized_active_tokens": 63894, "cumulative_start": 20712912, "cumulative_end": 20776806, "loss_sum": 24309.47738647461, "token_normalized_loss": 0.38046573052985583, "grad_norm_before_clip": 0.16480568051338196, "learning_rates_at_step": { "lora": 8.16856354521393e-05, "row_tokens": 8.16856354521393e-05 }, "learning_rates_after_step": { "lora": 8.154839435700843e-05, "row_tokens": 8.154839435700843e-05 } }, { "update_id": 317, "row_count": 17, "row_ids_sha256": "6dcf2e5f99fbd2225ab15d16a5d2cdae304fcbfce1a136991c2095b827578d2f", "input_ids_vector_sha256": "1a2165f0d6bef59393ef24baa979c0c321879fbf80f5aaf8588582931cb189a9", "labels_vector_sha256": "35ef21ebaa08106d3963ad32dcc26a8f4a43169118d001d4c2f22e8d95419b41", "planned_active_tokens": 67849, "realized_active_tokens": 67849, "cumulative_start": 20776806, "cumulative_end": 20844655, "loss_sum": 26424.645553588867, "token_normalized_loss": 0.3894625647185495, "grad_norm_before_clip": 0.14862750470638275, "learning_rates_at_step": { "lora": 8.154839435700843e-05, "row_tokens": 8.154839435700843e-05 }, "learning_rates_after_step": { "lora": 8.142397430666764e-05, "row_tokens": 8.142397430666764e-05 } }, { "update_id": 318, "row_count": 13, "row_ids_sha256": "d5225c4fdb1c6c31271af19be55afae0a43c5c587e894b1b77189f4791875d0c", "input_ids_vector_sha256": "bf07154ddda99c5befc5219cbc2695151e429bf12932d17eb3c640ab2eead6b3", "labels_vector_sha256": "2b2e7123be41bde1da7f36ef5170ce0a60285f698695df5e3680be99c277e685", "planned_active_tokens": 61342, "realized_active_tokens": 61342, "cumulative_start": 20844655, "cumulative_end": 20905997, "loss_sum": 20591.41082763672, "token_normalized_loss": 0.335682091024693, "grad_norm_before_clip": 0.14160054922103882, "learning_rates_at_step": { "lora": 8.142397430666764e-05, "row_tokens": 8.142397430666764e-05 }, "learning_rates_after_step": { "lora": 8.127910408043209e-05, "row_tokens": 8.127910408043209e-05 } }, { "update_id": 319, "row_count": 14, "row_ids_sha256": "6dc4ca2b47cbe9d97f29c5173e9f4e0c98b0a0d99de6f1731ea9837068c33452", "input_ids_vector_sha256": "045860fd14994f290188d793ab41f64ef06c495d4e908d190ad556c3767b1e74", "labels_vector_sha256": "30345a8049c4cdc21afe63195f59a4a831510cb733d724bf002043e135abd45c", "planned_active_tokens": 71225, "realized_active_tokens": 71225, "cumulative_start": 20905997, "cumulative_end": 20977222, "loss_sum": 27243.300842285156, "token_normalized_loss": 0.3824963263220099, "grad_norm_before_clip": 0.18419887125492096, "learning_rates_at_step": { "lora": 8.127910408043209e-05, "row_tokens": 8.127910408043209e-05 }, "learning_rates_after_step": { "lora": 8.115260208143837e-05, "row_tokens": 8.115260208143837e-05 } }, { "update_id": 320, "row_count": 13, "row_ids_sha256": "3bcaeb5d51016b5eb1204d96c811c8689ac224f33881fe59b765d90285ecf74c", "input_ids_vector_sha256": "19f0270d54eb4da18140cdaf70906ebc4b22ff44590fc9f9b8fd87016663ca3a", "labels_vector_sha256": "24480b353fe816698be2f30a44e94c34dd4c27f62ac7f8598cd7fcc9b6d3cf77", "planned_active_tokens": 62021, "realized_active_tokens": 62021, "cumulative_start": 20977222, "cumulative_end": 21039243, "loss_sum": 25548.8406829834, "token_normalized_loss": 0.4119385479592944, "grad_norm_before_clip": 0.15770012140274048, "learning_rates_at_step": { "lora": 8.115260208143837e-05, "row_tokens": 8.115260208143837e-05 }, "learning_rates_after_step": { "lora": 8.100980385482256e-05, "row_tokens": 8.100980385482256e-05 } }, { "update_id": 321, "row_count": 10, "row_ids_sha256": "17e765b9dd622f91d77bc3073cd5209c0f7d99264cdf5518cdca116a0fbde87c", "input_ids_vector_sha256": "25b3f80dc6a938a54c73448b2835785d76b4f1dd18a263e659b0128f43dabf6d", "labels_vector_sha256": "dcd1a576f8489246f218c815c0f5d2384169027f0fa423df2f6065545de340c1", "planned_active_tokens": 69819, "realized_active_tokens": 69819, "cumulative_start": 21039243, "cumulative_end": 21109062, "loss_sum": 33648.858642578125, "token_normalized_loss": 0.4819441504830795, "grad_norm_before_clip": 0.1537432074546814, "learning_rates_at_step": { "lora": 8.100980385482256e-05, "row_tokens": 8.100980385482256e-05 }, "learning_rates_after_step": { "lora": 8.086808055934319e-05, "row_tokens": 8.086808055934319e-05 } }, { "update_id": 322, "row_count": 12, "row_ids_sha256": "d20e5de98c4809d48b1f222db14b9d765549cdb47c0f6c8595d750e2ecb11a53", "input_ids_vector_sha256": "b10909ed9f6e2d337812fd67b83c8872271c603b2ffd6553922fc5be695ac552", "labels_vector_sha256": "4998a1de54c46823a859f50b08a2034feb74c92149baa3a9db6472414add44b1", "planned_active_tokens": 69095, "realized_active_tokens": 69095, "cumulative_start": 21109062, "cumulative_end": 21178157, "loss_sum": 28876.537719726562, "token_normalized_loss": 0.417925142481027, "grad_norm_before_clip": 0.14799489080905914, "learning_rates_at_step": { "lora": 8.086808055934319e-05, "row_tokens": 8.086808055934319e-05 }, "learning_rates_after_step": { "lora": 8.075034434327202e-05, "row_tokens": 8.075034434327202e-05 } }, { "update_id": 323, "row_count": 11, "row_ids_sha256": "5a3bbfed53d640183c07244192a5a27581171e4c540c3b2daa26d23f50e6387e", "input_ids_vector_sha256": "9ab1d209f5610ab7ded86ceb9c0a458e39ba74c6f0dac2405b0a79ad4abdde64", "labels_vector_sha256": "01b819ffdcec6b7cf915f32ef33374d619e9505dccae9dba027bab0f20a2fe1d", "planned_active_tokens": 57252, "realized_active_tokens": 57252, "cumulative_start": 21178157, "cumulative_end": 21235409, "loss_sum": 24178.22998046875, "token_normalized_loss": 0.42231240795900143, "grad_norm_before_clip": 0.15171502530574799, "learning_rates_at_step": { "lora": 8.075034434327202e-05, "row_tokens": 8.075034434327202e-05 }, "learning_rates_after_step": { "lora": 8.061627552952346e-05, "row_tokens": 8.061627552952346e-05 } }, { "update_id": 324, "row_count": 17, "row_ids_sha256": "8734cd0308a00352ae07279ec0e3a31f9fa26082ee29e5e6ca6c308a3b45354a", "input_ids_vector_sha256": "8c4520ad3def7faa311bdb4507ac7add5ff32832e953687e1e3cd40c8c90d677", "labels_vector_sha256": "102c771b63fe2bfa67b64b475a26075c18cef6408d1da79391a90f01bf3f2af0", "planned_active_tokens": 65032, "realized_active_tokens": 65032, "cumulative_start": 21235409, "cumulative_end": 21300441, "loss_sum": 23121.763458251953, "token_normalized_loss": 0.35554440057590037, "grad_norm_before_clip": 0.1430918276309967, "learning_rates_at_step": { "lora": 8.061627552952346e-05, "row_tokens": 8.061627552952346e-05 }, "learning_rates_after_step": { "lora": 8.047304414506944e-05, "row_tokens": 8.047304414506944e-05 } }, { "update_id": 325, "row_count": 14, "row_ids_sha256": "b19450e49de9970ac19ce805ba5afe7f3e6d528cff625bbd4cee67db72b648cf", "input_ids_vector_sha256": "7f6336c9851fea0c727d9724bdfbbf0251bf8e75cdc426a65b21249dd706a065", "labels_vector_sha256": "acdc53c17aeb3e57cb652a4ca9198c371e8ff1deab1ce216d6709fac5a4e3b44", "planned_active_tokens": 69288, "realized_active_tokens": 69288, "cumulative_start": 21300441, "cumulative_end": 21369729, "loss_sum": 27157.487548828125, "token_normalized_loss": 0.39195080748222094, "grad_norm_before_clip": 0.1418635994195938, "learning_rates_at_step": { "lora": 8.047304414506944e-05, "row_tokens": 8.047304414506944e-05 }, "learning_rates_after_step": { "lora": 8.033685508255169e-05, "row_tokens": 8.033685508255169e-05 } }, { "update_id": 326, "row_count": 15, "row_ids_sha256": "c2581f3f105ec42ea7baa9a4642cce8956061b5a5871fee062aeba532063f1b3", "input_ids_vector_sha256": "4f86630735bce8f3f203324b206880953cee91e7149ba6c3a40e0cb1a827545d", "labels_vector_sha256": "847fb8f05d5cf2c132f02160e1e4d1fa9ae2d64dc183ba54c1d6ca70051dbc16", "planned_active_tokens": 65703, "realized_active_tokens": 65703, "cumulative_start": 21369729, "cumulative_end": 21435432, "loss_sum": 24685.808166503906, "token_normalized_loss": 0.37571812803835297, "grad_norm_before_clip": 0.15987341105937958, "learning_rates_at_step": { "lora": 8.033685508255169e-05, "row_tokens": 8.033685508255169e-05 }, "learning_rates_after_step": { "lora": 8.020676357989468e-05, "row_tokens": 8.020676357989468e-05 } }, { "update_id": 327, "row_count": 12, "row_ids_sha256": "684b8a9ebb1b1f2df43faa44bc2778be2ec692ed8df59232a77154c93f8bbcc9", "input_ids_vector_sha256": "7125b39602c2767d91f68d843762fecfcc8ce28baf2cc7607d401a6b55e29222", "labels_vector_sha256": "57a6acaac1881c05e7308d2442aeaf9046640a98ff50ff1ff90e11b634e01264", "planned_active_tokens": 62601, "realized_active_tokens": 62601, "cumulative_start": 21435432, "cumulative_end": 21498033, "loss_sum": 23941.231231689453, "token_normalized_loss": 0.3824416739619088, "grad_norm_before_clip": 0.15096959471702576, "learning_rates_at_step": { "lora": 8.020676357989468e-05, "row_tokens": 8.020676357989468e-05 }, "learning_rates_after_step": { "lora": 8.006446702555244e-05, "row_tokens": 8.006446702555244e-05 } }, { "update_id": 328, "row_count": 13, "row_ids_sha256": "d8f611b1809a5c2793d7570cf1ed9549dcfcddb6389be797b36df9a6396a880f", "input_ids_vector_sha256": "6d4e35eb4520da3a05153a14d5c745495e80c5a857f57b043a15cb543dd54685", "labels_vector_sha256": "01867d51993437b57f6ce2c35b67d6768ed5d4f4b3f88ba34a657e2106870788", "planned_active_tokens": 68297, "realized_active_tokens": 68297, "cumulative_start": 21498033, "cumulative_end": 21566330, "loss_sum": 27863.787826538086, "token_normalized_loss": 0.4079796744591722, "grad_norm_before_clip": 0.1553472876548767, "learning_rates_at_step": { "lora": 8.006446702555244e-05, "row_tokens": 8.006446702555244e-05 }, "learning_rates_after_step": { "lora": 7.99291802674675e-05, "row_tokens": 7.99291802674675e-05 } }, { "update_id": 329, "row_count": 15, "row_ids_sha256": "02ae04e0adc2cbd6a34ee94fad59bb57d5ceee9ee2e32abfcaf284d31fce812e", "input_ids_vector_sha256": "0c958dca80034a0470aa032cc7705fd28bc7ef326a6c6ed4e403bb38b09b1ab4", "labels_vector_sha256": "484772a81b89071cf984024bcdc78dd4b5787e47765059a6235aa3d0cb13fc6e", "planned_active_tokens": 64763, "realized_active_tokens": 64763, "cumulative_start": 21566330, "cumulative_end": 21631093, "loss_sum": 26870.99478149414, "token_normalized_loss": 0.41491275545441286, "grad_norm_before_clip": 0.16448451578617096, "learning_rates_at_step": { "lora": 7.99291802674675e-05, "row_tokens": 7.99291802674675e-05 }, "learning_rates_after_step": { "lora": 7.979613656917389e-05, "row_tokens": 7.979613656917389e-05 } }, { "update_id": 330, "row_count": 11, "row_ids_sha256": "014c2543b8f13842ee854e387a6d729e2c9dda0b4954405851de850e048512be", "input_ids_vector_sha256": "8cd4cb5735a22d4bfceafff5b32e49dfbf1405f646dcf63c6128c2029a2a802a", "labels_vector_sha256": "b65a82c6a10ac0bb91687ae1b2cc963ead53abf6d7d2cfdd18bd9b02b1ce11de", "planned_active_tokens": 63530, "realized_active_tokens": 63530, "cumulative_start": 21631093, "cumulative_end": 21694623, "loss_sum": 26780.86737060547, "token_normalized_loss": 0.4215467868818742, "grad_norm_before_clip": 0.15637895464897156, "learning_rates_at_step": { "lora": 7.979613656917389e-05, "row_tokens": 7.979613656917389e-05 }, "learning_rates_after_step": { "lora": 7.965915160002911e-05, "row_tokens": 7.965915160002911e-05 } }, { "update_id": 331, "row_count": 12, "row_ids_sha256": "3704cbf3e36b4b7fea31084fd15ddd7ae57c72854439190694a1a88fe5acce1d", "input_ids_vector_sha256": "fe3514bb5aed7102526ff6f8b5a591014f8829054b536ea3a98dd41b3aa4a686", "labels_vector_sha256": "74dce0f3ec620afbab4e08321dadbfd675dbb3722b83ab2261a2dc41cf90c9ca", "planned_active_tokens": 65249, "realized_active_tokens": 65249, "cumulative_start": 21694623, "cumulative_end": 21759872, "loss_sum": 28103.72802734375, "token_normalized_loss": 0.43071507651218793, "grad_norm_before_clip": 0.15895944833755493, "learning_rates_at_step": { "lora": 7.965915160002911e-05, "row_tokens": 7.965915160002911e-05 }, "learning_rates_after_step": { "lora": 7.951994251986671e-05, "row_tokens": 7.951994251986671e-05 } }, { "update_id": 332, "row_count": 12, "row_ids_sha256": "9e2e006043837821390ed58abb04a25af2ed98b279d9a060b8750710aa00a3ea", "input_ids_vector_sha256": "3a2000d0011902bc40d4f3888c2a2fb45600ec2acad141e3c79b73982372a14e", "labels_vector_sha256": "84946ef14748199c20910c97466a696d1950c0cf59f10ff3e122c2885869e34f", "planned_active_tokens": 66141, "realized_active_tokens": 66141, "cumulative_start": 21759872, "cumulative_end": 21826013, "loss_sum": 27067.784454345703, "token_normalized_loss": 0.40924365301924226, "grad_norm_before_clip": 0.1567932367324829, "learning_rates_at_step": { "lora": 7.951994251986671e-05, "row_tokens": 7.951994251986671e-05 }, "learning_rates_after_step": { "lora": 7.938581490331434e-05, "row_tokens": 7.938581490331434e-05 } }, { "update_id": 333, "row_count": 10, "row_ids_sha256": "2ef7e0e86b586a8cc74239245bab4bf142d958c1d8872901e35795aadf240b4f", "input_ids_vector_sha256": "39d55c96ead7b16ef9152494c684998281dcfb940b621cac5c76f319b6d335bc", "labels_vector_sha256": "82a8c0f9063d88f0776d06335911566d8974b5d92bf1d9f82276517afcb7effe", "planned_active_tokens": 63569, "realized_active_tokens": 63569, "cumulative_start": 21826013, "cumulative_end": 21889582, "loss_sum": 25730.965942382812, "token_normalized_loss": 0.40477223084180675, "grad_norm_before_clip": 0.15629053115844727, "learning_rates_at_step": { "lora": 7.938581490331434e-05, "row_tokens": 7.938581490331434e-05 }, "learning_rates_after_step": { "lora": 7.923572926133839e-05, "row_tokens": 7.923572926133839e-05 } }, { "update_id": 334, "row_count": 16, "row_ids_sha256": "e855868fc0f17d46773e2e07666ac04566a65e50c8cdd5eebaa090164cbea56d", "input_ids_vector_sha256": "0455683f78451477c15f370e6c8573c0ab8e8cbeac227d072199453d3a87fec8", "labels_vector_sha256": "1726e28207ddad64968655877f978afcd0a782e3341917b623b79e422ff46647", "planned_active_tokens": 70951, "realized_active_tokens": 70951, "cumulative_start": 21889582, "cumulative_end": 21960533, "loss_sum": 27143.852630615234, "token_normalized_loss": 0.38257181196340057, "grad_norm_before_clip": 0.14474835991859436, "learning_rates_at_step": { "lora": 7.923572926133839e-05, "row_tokens": 7.923572926133839e-05 }, "learning_rates_after_step": { "lora": 7.909141375405907e-05, "row_tokens": 7.909141375405907e-05 } }, { "update_id": 335, "row_count": 12, "row_ids_sha256": "03ba16beb940751f4cd4c4c7fea999bcb437b2d550df783d4dd363f2be9a0d81", "input_ids_vector_sha256": "ad021df9c6e49fff69c724c8686da943785218ad03583da61d3bcbf76d949862", "labels_vector_sha256": "b0f462686335526a738c57ba270967a8984c6410ec629c19174ba69bf8c2b3e1", "planned_active_tokens": 68045, "realized_active_tokens": 68045, "cumulative_start": 21960533, "cumulative_end": 22028578, "loss_sum": 30874.078552246094, "token_normalized_loss": 0.4537303042434579, "grad_norm_before_clip": 0.15313854813575745, "learning_rates_at_step": { "lora": 7.909141375405907e-05, "row_tokens": 7.909141375405907e-05 }, "learning_rates_after_step": { "lora": 7.895619981319256e-05, "row_tokens": 7.895619981319256e-05 } }, { "update_id": 336, "row_count": 13, "row_ids_sha256": "62eba9d4ee7178a8d7ac0cd7f2b2d8ea857de75d2dca11cf93ce92ef20a9636d", "input_ids_vector_sha256": "824ee4fa81fafe3ee8173a441abbf2dae435d9d5e66122c6f397ac6a994d4b74", "labels_vector_sha256": "e0c56a3775c62d754a2fe84dc8f68808dd8103746401be24e3846cc0b5f5de3d", "planned_active_tokens": 63597, "realized_active_tokens": 63597, "cumulative_start": 22028578, "cumulative_end": 22092175, "loss_sum": 24729.221130371094, "token_normalized_loss": 0.3888425732404216, "grad_norm_before_clip": 0.14337004721164703, "learning_rates_at_step": { "lora": 7.895619981319256e-05, "row_tokens": 7.895619981319256e-05 }, "learning_rates_after_step": { "lora": 7.882778811866806e-05, "row_tokens": 7.882778811866806e-05 } }, { "update_id": 337, "row_count": 13, "row_ids_sha256": "d66786d349207aecd7a2a4916735e9acfdd50d1184bb94118a65bb4ed7c5834a", "input_ids_vector_sha256": "00a9579a535e39fa2691c27e9a0750168a05f9369ffd9586e623e21a97f5479c", "labels_vector_sha256": "a5f12d2a4e83509047095adedc15f7412a7a7268f680dc324ed2679b842af427", "planned_active_tokens": 60259, "realized_active_tokens": 60259, "cumulative_start": 22092175, "cumulative_end": 22152434, "loss_sum": 23413.16973876953, "token_normalized_loss": 0.38854228810251634, "grad_norm_before_clip": 0.16660478711128235, "learning_rates_at_step": { "lora": 7.882778811866806e-05, "row_tokens": 7.882778811866806e-05 }, "learning_rates_after_step": { "lora": 7.868279213542834e-05, "row_tokens": 7.868279213542834e-05 } }, { "update_id": 338, "row_count": 14, "row_ids_sha256": "078683c9f92e742f60681b129a6c3ccbf9862729ca24810f6b066701460e48a9", "input_ids_vector_sha256": "41b130aafdabee995e131ec6e0ac018e8eee0fa7007323336b74090a299603e4", "labels_vector_sha256": "b0bd0167ebf4a9e53e1009ef278ba28bec59df2caf2400b28a1a80e364328d67", "planned_active_tokens": 67881, "realized_active_tokens": 67881, "cumulative_start": 22152434, "cumulative_end": 22220315, "loss_sum": 22143.84487915039, "token_normalized_loss": 0.3262156550308686, "grad_norm_before_clip": 0.12692192196846008, "learning_rates_at_step": { "lora": 7.868279213542834e-05, "row_tokens": 7.868279213542834e-05 }, "learning_rates_after_step": { "lora": 7.854693283643637e-05, "row_tokens": 7.854693283643637e-05 } }, { "update_id": 339, "row_count": 16, "row_ids_sha256": "38dc64de63f8fabb88e6d3b10a6e7b3c6ab83320d1ca1983bac398cbd44f3d27", "input_ids_vector_sha256": "228f806a81ee9d1ea9644f9ed7119baf99f9796c123975034ebc9c3c242e3627", "labels_vector_sha256": "c76b00859df35a623e3eb802a1abc5ca95c995aba6ddff211cecf38fd24b3aa3", "planned_active_tokens": 63451, "realized_active_tokens": 63451, "cumulative_start": 22220315, "cumulative_end": 22283766, "loss_sum": 23522.354370117188, "token_normalized_loss": 0.37071684244719844, "grad_norm_before_clip": 0.14273522794246674, "learning_rates_at_step": { "lora": 7.854693283643637e-05, "row_tokens": 7.854693283643637e-05 }, "learning_rates_after_step": { "lora": 7.84024531695903e-05, "row_tokens": 7.84024531695903e-05 } }, { "update_id": 340, "row_count": 13, "row_ids_sha256": "377c9c5d115e52f8dd09e700c4923e8762b2a9e2403774715d3f4a11a11252af", "input_ids_vector_sha256": "4d1a7002740a179b2b09a96b10a561cd97c43d2c15095061b5c01407aeb5c651", "labels_vector_sha256": "e6e657ba403d3be3e1cf5d398fc2e3802bb7cc77e7505d7bd0e8bfcef5245d36", "planned_active_tokens": 67317, "realized_active_tokens": 67317, "cumulative_start": 22283766, "cumulative_end": 22351083, "loss_sum": 25189.063110351562, "token_normalized_loss": 0.37418576452235786, "grad_norm_before_clip": 0.148141548037529, "learning_rates_at_step": { "lora": 7.84024531695903e-05, "row_tokens": 7.84024531695903e-05 }, "learning_rates_after_step": { "lora": 7.826496098605777e-05, "row_tokens": 7.826496098605777e-05 } }, { "update_id": 341, "row_count": 13, "row_ids_sha256": "d15fa3c0c6de7276b9939073b48409da327a24ed5911b38f91cc62cfa437c7a3", "input_ids_vector_sha256": "24e0995c4bf854946691202c12614e9ef24b7a913775cf02b0f19e729f7ac566", "labels_vector_sha256": "454edaa89ce6e07b3616aa353c96bec2635183bcf52f8b46fe7ae5dece1ffc6a", "planned_active_tokens": 63910, "realized_active_tokens": 63910, "cumulative_start": 22351083, "cumulative_end": 22414993, "loss_sum": 24110.47152709961, "token_normalized_loss": 0.3772566347535536, "grad_norm_before_clip": 0.18306098878383636, "learning_rates_at_step": { "lora": 7.826496098605777e-05, "row_tokens": 7.826496098605777e-05 }, "learning_rates_after_step": { "lora": 7.811844722684921e-05, "row_tokens": 7.811844722684921e-05 } }, { "update_id": 342, "row_count": 15, "row_ids_sha256": "9f46b91d099194a162ef51422c5d7f3508ba5789028ea2c7150c5db667f18494", "input_ids_vector_sha256": "dbacb3ee36bc253c082059e1016a6f5b63d90e5b600692df170360ba41f818fb", "labels_vector_sha256": "5948309268f92b6c50645282107e335ac09c7bf5ebc1d1330eebe8f258d251d6", "planned_active_tokens": 67943, "realized_active_tokens": 67943, "cumulative_start": 22414993, "cumulative_end": 22482936, "loss_sum": 23695.992614746094, "token_normalized_loss": 0.348762824937758, "grad_norm_before_clip": 0.14347293972969055, "learning_rates_at_step": { "lora": 7.811844722684921e-05, "row_tokens": 7.811844722684921e-05 }, "learning_rates_after_step": { "lora": 7.797804803245213e-05, "row_tokens": 7.797804803245213e-05 } }, { "update_id": 343, "row_count": 14, "row_ids_sha256": "8b954d5875f20904a9264de961e99b8d2ec22d51cc36b1ec10cf68f7388c6ade", "input_ids_vector_sha256": "c7aae526bf466859adb38c406adb0391ea553fd81eb2be8dfd35136a9bfbb4d1", "labels_vector_sha256": "91c06f51e7959cdc61971442bee4f8778e24e035ea61782576b7c81d7474790a", "planned_active_tokens": 64954, "realized_active_tokens": 64954, "cumulative_start": 22482936, "cumulative_end": 22547890, "loss_sum": 22528.688232421875, "token_normalized_loss": 0.3468406600428284, "grad_norm_before_clip": 0.14320328831672668, "learning_rates_at_step": { "lora": 7.797804803245213e-05, "row_tokens": 7.797804803245213e-05 }, "learning_rates_after_step": { "lora": 7.784303099908904e-05, "row_tokens": 7.784303099908904e-05 } }, { "update_id": 344, "row_count": 12, "row_ids_sha256": "7cebdfd665ea3905d019523c4e39adbb88e17407130a4d67faca35020ab28ff4", "input_ids_vector_sha256": "1f9ea46edf6c45d0c36cad2610f03455450697001ba2192665d2dee8077d9003", "labels_vector_sha256": "168fc27b666ef2ec641db21101da763df09af1a7bd596498ba6fccaaa9d2176f", "planned_active_tokens": 62324, "realized_active_tokens": 62324, "cumulative_start": 22547890, "cumulative_end": 22610214, "loss_sum": 21357.02117919922, "token_normalized_loss": 0.34267731819522523, "grad_norm_before_clip": 0.14099928736686707, "learning_rates_at_step": { "lora": 7.784303099908904e-05, "row_tokens": 7.784303099908904e-05 }, "learning_rates_after_step": { "lora": 7.769268121102735e-05, "row_tokens": 7.769268121102735e-05 } }, { "update_id": 345, "row_count": 15, "row_ids_sha256": "2d68830ef0198b64b543be61ecc6ac5a49facb1553a9bfc9520671b8cab6b58b", "input_ids_vector_sha256": "4417179689bed6f01d657fa3fcb512017437bbd594e8307f415b5873cdce3021", "labels_vector_sha256": "ed5b56dd9094fafbfb5c17338970813455dcc8c647f71359bb1679cec45968d7", "planned_active_tokens": 69242, "realized_active_tokens": 69242, "cumulative_start": 22610214, "cumulative_end": 22679456, "loss_sum": 27483.111358642578, "token_normalized_loss": 0.3969138869276245, "grad_norm_before_clip": 0.14065313339233398, "learning_rates_at_step": { "lora": 7.769268121102735e-05, "row_tokens": 7.769268121102735e-05 }, "learning_rates_after_step": { "lora": 7.75527685527178e-05, "row_tokens": 7.75527685527178e-05 } }, { "update_id": 346, "row_count": 13, "row_ids_sha256": "09265758845e5d62d56151c37cb03154b8ec4a1f00f48ec34b44498a05ff3950", "input_ids_vector_sha256": "4f9cc0d6b3a56b9076c3678faa68998f3788ae82fcef4aa682d9daf5b6ae4810", "labels_vector_sha256": "ff69e467dffd8b73163b84f2e869af928131bb868e949fcc6a5aafb5118c9d0d", "planned_active_tokens": 64286, "realized_active_tokens": 64286, "cumulative_start": 22679456, "cumulative_end": 22743742, "loss_sum": 27204.8583984375, "token_normalized_loss": 0.42318480537655945, "grad_norm_before_clip": 0.1554267406463623, "learning_rates_at_step": { "lora": 7.75527685527178e-05, "row_tokens": 7.75527685527178e-05 }, "learning_rates_after_step": { "lora": 7.740399582932211e-05, "row_tokens": 7.740399582932211e-05 } }, { "update_id": 347, "row_count": 16, "row_ids_sha256": "a08405bd96cbdd5773ddf9765b8a1e8162a9d196eb637c5a99b96d89e146892c", "input_ids_vector_sha256": "2d87945cc2c713319f1a2e4a5b8fd3b0c9f1f95d3a4351d35a8623cb101b7bab", "labels_vector_sha256": "bd2a73d53434e50dfe41cdc82ccce032c991f9cf2614c4ef37bc6e05f38ac06f", "planned_active_tokens": 68201, "realized_active_tokens": 68201, "cumulative_start": 22743742, "cumulative_end": 22811943, "loss_sum": 23781.135009765625, "token_normalized_loss": 0.34869188149390223, "grad_norm_before_clip": 0.13714814186096191, "learning_rates_at_step": { "lora": 7.740399582932211e-05, "row_tokens": 7.740399582932211e-05 }, "learning_rates_after_step": { "lora": 7.727156244876978e-05, "row_tokens": 7.727156244876978e-05 } }, { "update_id": 348, "row_count": 14, "row_ids_sha256": "283dcc1f9003d8320b89bedce723c8854070f2f409f433f4c2d90ac21c8c4471", "input_ids_vector_sha256": "65e39e946f977b1e40858cef7d5fbeda8f209022324f47be43995f01ef83789a", "labels_vector_sha256": "c93e41468d376426a2a8f06b75ace1e42b0cbc168eee355a50871c91524d70e1", "planned_active_tokens": 60577, "realized_active_tokens": 60577, "cumulative_start": 22811943, "cumulative_end": 22872520, "loss_sum": 20648.673461914062, "token_normalized_loss": 0.34086655763596846, "grad_norm_before_clip": 0.1375528872013092, "learning_rates_at_step": { "lora": 7.727156244876978e-05, "row_tokens": 7.727156244876978e-05 }, "learning_rates_after_step": { "lora": 7.712072452233119e-05, "row_tokens": 7.712072452233119e-05 } }, { "update_id": 349, "row_count": 13, "row_ids_sha256": "7f857a95d7d2601424f915ce2b76aeb68c7cdc9e732ee7ee50cfc1d92bdceeaa", "input_ids_vector_sha256": "07da4018b6a255658b2ea7dd9493dc7375191ff00b84493db9ddb7ce62c3e442", "labels_vector_sha256": "88aa4d9918b28238210cb727b71e1ee2b79ac00f7fe18ae43a2abbc822c35d98", "planned_active_tokens": 68844, "realized_active_tokens": 68844, "cumulative_start": 22872520, "cumulative_end": 22941364, "loss_sum": 29682.42446899414, "token_normalized_loss": 0.4311548496454904, "grad_norm_before_clip": 0.14457589387893677, "learning_rates_at_step": { "lora": 7.712072452233119e-05, "row_tokens": 7.712072452233119e-05 }, "learning_rates_after_step": { "lora": 7.697444544703582e-05, "row_tokens": 7.697444544703582e-05 } }, { "update_id": 350, "row_count": 14, "row_ids_sha256": "97fff4a62093fde2158e8796508032c36cba5d1715369396fa08573b2c7e37e7", "input_ids_vector_sha256": "5bc76d0b43ae63e68dff16230b96f7a5fb4b5c907b3cc2ca5febeb902f6358e1", "labels_vector_sha256": "b65c843ca70a16eaa33cf2774fa36eadcf150ae40b73a14a0b9d117a4d9a2fe2", "planned_active_tokens": 66611, "realized_active_tokens": 66611, "cumulative_start": 22941364, "cumulative_end": 23007975, "loss_sum": 24750.008422851562, "token_normalized_loss": 0.37156037925945506, "grad_norm_before_clip": 0.14822271466255188, "learning_rates_at_step": { "lora": 7.697444544703582e-05, "row_tokens": 7.697444544703582e-05 }, "learning_rates_after_step": { "lora": 7.682607286800286e-05, "row_tokens": 7.682607286800286e-05 } }, { "update_id": 351, "row_count": 14, "row_ids_sha256": "4479e25c752fd4fdaac1e025e00331ea22a7b9fe405bf5e0351a2e5ab657b905", "input_ids_vector_sha256": "9e4f5c2e958f3a34d091774ab1d1299169e4f789bb77c15b879671e364baa181", "labels_vector_sha256": "edd6c0c1706899012137190175470d32c2f1edb2866b37bda560c370864962a2", "planned_active_tokens": 67413, "realized_active_tokens": 67413, "cumulative_start": 23007975, "cumulative_end": 23075388, "loss_sum": 24740.140380859375, "token_normalized_loss": 0.3669936122240425, "grad_norm_before_clip": 0.14693792164325714, "learning_rates_at_step": { "lora": 7.682607286800286e-05, "row_tokens": 7.682607286800286e-05 }, "learning_rates_after_step": { "lora": 7.668098720330701e-05, "row_tokens": 7.668098720330701e-05 } }, { "update_id": 352, "row_count": 16, "row_ids_sha256": "c215b7e170d20b9fa5d2ba56dd919a9827359a254f0de6200176a226a8d757ed", "input_ids_vector_sha256": "84061e7a0572806c234d742ad0332e38f57c14a74f5e2f307528a73f14df8a23", "labels_vector_sha256": "ebb1209fb623785ba69f2810d1c31b9021dd21762ba941a6f731a7a88917322e", "planned_active_tokens": 65774, "realized_active_tokens": 65774, "cumulative_start": 23075388, "cumulative_end": 23141162, "loss_sum": 23646.069610595703, "token_normalized_loss": 0.3595048136132165, "grad_norm_before_clip": 0.14817392826080322, "learning_rates_at_step": { "lora": 7.668098720330701e-05, "row_tokens": 7.668098720330701e-05 }, "learning_rates_after_step": { "lora": 7.653860300576989e-05, "row_tokens": 7.653860300576989e-05 } }, { "update_id": 353, "row_count": 11, "row_ids_sha256": "7c767a18bfd8179c7b95386d161a7607630d5b322f172888e9baad847cb5e4a4", "input_ids_vector_sha256": "57d1f086cec7219ec8312d21659c529f35531ba4e05537dc32c669e535b673b1", "labels_vector_sha256": "0efa34bb2694270e0716facde1633664af1f1cf8e0b740d0d3fe0cd1f239ad16", "planned_active_tokens": 64411, "realized_active_tokens": 64411, "cumulative_start": 23141162, "cumulative_end": 23205573, "loss_sum": 24623.856658935547, "token_normalized_loss": 0.38229272420759725, "grad_norm_before_clip": 0.14293743669986725, "learning_rates_at_step": { "lora": 7.653860300576989e-05, "row_tokens": 7.653860300576989e-05 }, "learning_rates_after_step": { "lora": 7.640448438156251e-05, "row_tokens": 7.640448438156251e-05 } }, { "update_id": 354, "row_count": 12, "row_ids_sha256": "c2224709198e46c3c15d8fef85469a164ab0c744988e14054e77702b0727839d", "input_ids_vector_sha256": "e765b9df5be3eecc171b76251330f901db4644243d4f6fe114f5ffe1b703ac86", "labels_vector_sha256": "6a966978783556c73bc4e3d669243dafb2d0778a8ba4651d0a3f2ba6a1b9c999", "planned_active_tokens": 60548, "realized_active_tokens": 60548, "cumulative_start": 23205573, "cumulative_end": 23266121, "loss_sum": 26193.856536865234, "token_normalized_loss": 0.43261307618526185, "grad_norm_before_clip": 0.16515997052192688, "learning_rates_at_step": { "lora": 7.640448438156251e-05, "row_tokens": 7.640448438156251e-05 }, "learning_rates_after_step": { "lora": 7.625822624504779e-05, "row_tokens": 7.625822624504779e-05 } }, { "update_id": 355, "row_count": 15, "row_ids_sha256": "db214fa9f1415a7e689fd1c9f6a3a4cf2f22acfd9000627f20e154ccc74ab5a4", "input_ids_vector_sha256": "0a9b2b0cc6065a467a7dbdbc15ef0284b830937aa685b9695387c8b66c63b2bd", "labels_vector_sha256": "6c8112511f9d14a1ac4a11ce7b2a7363cbf647954e17356d1a8e6a1d31b8477a", "planned_active_tokens": 65893, "realized_active_tokens": 65893, "cumulative_start": 23266121, "cumulative_end": 23332014, "loss_sum": 26103.378356933594, "token_normalized_loss": 0.3961479725757454, "grad_norm_before_clip": 0.22820082306861877, "learning_rates_at_step": { "lora": 7.625822624504779e-05, "row_tokens": 7.625822624504779e-05 }, "learning_rates_after_step": { "lora": 7.61003023352945e-05, "row_tokens": 7.61003023352945e-05 } }, { "update_id": 356, "row_count": 15, "row_ids_sha256": "729dcf5c8567877fb224e8af84cd815090f4d8d52fafcaf7270d2e47e1db1c32", "input_ids_vector_sha256": "816f165c26b859e0923e205e9e74efa2f4506263250aa79a9a3048fa3838df11", "labels_vector_sha256": "5edb44dc53e325924362bf9c230f9149fb712559f455ccf3f5c6b18e38ece93e", "planned_active_tokens": 70992, "realized_active_tokens": 70992, "cumulative_start": 23332014, "cumulative_end": 23403006, "loss_sum": 25287.484954833984, "token_normalized_loss": 0.35620189535206764, "grad_norm_before_clip": 0.13598522543907166, "learning_rates_at_step": { "lora": 7.61003023352945e-05, "row_tokens": 7.61003023352945e-05 }, "learning_rates_after_step": { "lora": 7.596325940326785e-05, "row_tokens": 7.596325940326785e-05 } }, { "update_id": 357, "row_count": 12, "row_ids_sha256": "ddd6d25784219a0b04d97ee490f1533387dbcd8ecf62a61e21aee2cfa79f4eca", "input_ids_vector_sha256": "29bbea535171d379b1bddf72925e310d82083870adcacda4fa12dbd5a1befb71", "labels_vector_sha256": "d8107438f1e65a99162988fd74ad9952d04d0245e66878a998a6a22b302459c2", "planned_active_tokens": 61475, "realized_active_tokens": 61475, "cumulative_start": 23403006, "cumulative_end": 23464481, "loss_sum": 22068.86785888672, "token_normalized_loss": 0.3589893104332935, "grad_norm_before_clip": 0.18615256249904633, "learning_rates_at_step": { "lora": 7.596325940326785e-05, "row_tokens": 7.596325940326785e-05 }, "learning_rates_after_step": { "lora": 7.581916749106855e-05, "row_tokens": 7.581916749106855e-05 } }, { "update_id": 358, "row_count": 14, "row_ids_sha256": "7cc591042a0cac4b2cefbe8c679d8a743c9a5675629c3f7fb6e990130d958af0", "input_ids_vector_sha256": "fa5f10c63f6a441196405db0843c998732f5881dd49d5f7a6c33cafddb4b0a88", "labels_vector_sha256": "a49ba5342fa19063fa5c5780026e628d846c1379e1a4f9cba5182934c26744f2", "planned_active_tokens": 64508, "realized_active_tokens": 64508, "cumulative_start": 23464481, "cumulative_end": 23528989, "loss_sum": 23844.1484375, "token_normalized_loss": 0.36963087427140817, "grad_norm_before_clip": 0.14218468964099884, "learning_rates_at_step": { "lora": 7.581916749106855e-05, "row_tokens": 7.581916749106855e-05 }, "learning_rates_after_step": { "lora": 7.567559812854825e-05, "row_tokens": 7.567559812854825e-05 } }, { "update_id": 359, "row_count": 15, "row_ids_sha256": "1cb568e7eef10890a384e78d8232942a799c70b4b2dac8d11042b9e56e25c902", "input_ids_vector_sha256": "67d8fba3dd799a7b1b14b4066b44cd4a76e71cf9b0af6f7a2395ab30b73c5b98", "labels_vector_sha256": "b5d0f1822d110891a1c882f4d332ffe54c37b95f67e857e73afbccfa8e3d05e2", "planned_active_tokens": 64144, "realized_active_tokens": 64144, "cumulative_start": 23528989, "cumulative_end": 23593133, "loss_sum": 24647.607482910156, "token_normalized_loss": 0.38425429475726736, "grad_norm_before_clip": 0.14580588042736053, "learning_rates_at_step": { "lora": 7.567559812854825e-05, "row_tokens": 7.567559812854825e-05 }, "learning_rates_after_step": { "lora": 7.552271985657436e-05, "row_tokens": 7.552271985657436e-05 } }, { "update_id": 360, "row_count": 15, "row_ids_sha256": "a6b5fbb8babe3224c179f9b096c0f2840a7f960f1351a19412db0661e549ae4f", "input_ids_vector_sha256": "d3f28bc6b486b3e2820781547991c7a478339ca9813e79aed02166f3e2e7cb59", "labels_vector_sha256": "b6a46ac2b6ba483285cc3002a30de3f72db68116329a2da12d5080642a2c2526", "planned_active_tokens": 68162, "realized_active_tokens": 68162, "cumulative_start": 23593133, "cumulative_end": 23661295, "loss_sum": 26050.291107177734, "token_normalized_loss": 0.38218202381352856, "grad_norm_before_clip": 0.14170847833156586, "learning_rates_at_step": { "lora": 7.552271985657436e-05, "row_tokens": 7.552271985657436e-05 }, "learning_rates_after_step": { "lora": 7.537961764929752e-05, "row_tokens": 7.537961764929752e-05 } }, { "update_id": 361, "row_count": 16, "row_ids_sha256": "8001cefa6743f040d62e07c997a58b5071f319535c7191605c611f2e4bbde61d", "input_ids_vector_sha256": "4a524de9a5100082af3d04889d2af7cd5cc1ab834112a62cf8570688ad1c4cea", "labels_vector_sha256": "307d0fa1ad32b5c076f121417131538fa6f706a1f6fac520a91d3c8c19ae78f8", "planned_active_tokens": 63673, "realized_active_tokens": 63673, "cumulative_start": 23661295, "cumulative_end": 23724968, "loss_sum": 21876.520294189453, "token_normalized_loss": 0.3435760886747829, "grad_norm_before_clip": 0.1421988308429718, "learning_rates_at_step": { "lora": 7.537961764929752e-05, "row_tokens": 7.537961764929752e-05 }, "learning_rates_after_step": { "lora": 7.523233297027966e-05, "row_tokens": 7.523233297027966e-05 } }, { "update_id": 362, "row_count": 15, "row_ids_sha256": "55cac9c5037d7cc24ea87f1781628e93b78fab42228bc3dc836a9b4b2f4f92d9", "input_ids_vector_sha256": "a0e85881ca4e684c2e2369779b7b1ee346fe500fd2f28f72685350affb837278", "labels_vector_sha256": "ee012654e4285ae7d9d5d17c773a5e4c014581b9c946b220f50aa33a8f9134aa", "planned_active_tokens": 65404, "realized_active_tokens": 65404, "cumulative_start": 23724968, "cumulative_end": 23790372, "loss_sum": 26833.660400390625, "token_normalized_loss": 0.4102755244387289, "grad_norm_before_clip": 0.16685403883457184, "learning_rates_at_step": { "lora": 7.523233297027966e-05, "row_tokens": 7.523233297027966e-05 }, "learning_rates_after_step": { "lora": 7.508053012957716e-05, "row_tokens": 7.508053012957716e-05 } }, { "update_id": 363, "row_count": 18, "row_ids_sha256": "960f3627c4e695e1b816a356281ec70eba6ee25d5903a9f36d4a744ac290d303", "input_ids_vector_sha256": "5bb2330306714615d1c600de20f36bf192f54debadbd18465811426fc937ee1d", "labels_vector_sha256": "a6526c931a48547047520624af67e32ea5d2cbb3d13a3a33e79a57e565618f1a", "planned_active_tokens": 67274, "realized_active_tokens": 67274, "cumulative_start": 23790372, "cumulative_end": 23857646, "loss_sum": 19408.209442138672, "token_normalized_loss": 0.2884949526137686, "grad_norm_before_clip": 0.12727123498916626, "learning_rates_at_step": { "lora": 7.508053012957716e-05, "row_tokens": 7.508053012957716e-05 }, "learning_rates_after_step": { "lora": 7.493785770915669e-05, "row_tokens": 7.493785770915669e-05 } }, { "update_id": 364, "row_count": 18, "row_ids_sha256": "2a31cfdaeb39f1be481fda3a46e4f9fe214b1df5855cbaa86dd15d9c23ffb045", "input_ids_vector_sha256": "c95f52fd3736d70304e5d5bb1bc547ecc44b56cd83e34c7beba4c73d03e4bbee", "labels_vector_sha256": "e9877ce4c4f5cbb33199c3d17d922b3269fe998ac914db25e2571148794adfad", "planned_active_tokens": 63103, "realized_active_tokens": 63103, "cumulative_start": 23857646, "cumulative_end": 23920749, "loss_sum": 20430.208709716797, "token_normalized_loss": 0.323759705714733, "grad_norm_before_clip": 0.13146977126598358, "learning_rates_at_step": { "lora": 7.493785770915669e-05, "row_tokens": 7.493785770915669e-05 }, "learning_rates_after_step": { "lora": 7.478547029213565e-05, "row_tokens": 7.478547029213565e-05 } }, { "update_id": 365, "row_count": 15, "row_ids_sha256": "f22b8633405912f19dce31de1c4153bd9a2a7f4a14fc7f1d2e5e62e1becf58df", "input_ids_vector_sha256": "87928b02cc1fd5060ded2b69c94f6b06c248de84236ac4443a40dd6f1ab23ab4", "labels_vector_sha256": "2d2ef1fc27216332e71f6ddc86289394115ab4ff4cb4ec7d61e1677e65651984", "planned_active_tokens": 67268, "realized_active_tokens": 67268, "cumulative_start": 23920749, "cumulative_end": 23988017, "loss_sum": 25255.680877685547, "token_normalized_loss": 0.37544866619619355, "grad_norm_before_clip": 0.14139556884765625, "learning_rates_at_step": { "lora": 7.478547029213565e-05, "row_tokens": 7.478547029213565e-05 }, "learning_rates_after_step": { "lora": 7.463957738956929e-05, "row_tokens": 7.463957738956929e-05 } }, { "update_id": 366, "row_count": 12, "row_ids_sha256": "e0ece9f7c688fc2ed0fcdee470a01d59a1e49b43c83a70e968c8a0164a3164c1", "input_ids_vector_sha256": "5619c3b9739c17595f22e1ca0beb8a5638bbb7a5fe03e9f5f52677d37fb920fe", "labels_vector_sha256": "10e7d535adc578fe8add91bda1e237a976c5e28dfe5d4d50dd028d2fed888771", "planned_active_tokens": 64275, "realized_active_tokens": 64275, "cumulative_start": 23988017, "cumulative_end": 24052292, "loss_sum": 25645.668701171875, "token_normalized_loss": 0.39899912409446714, "grad_norm_before_clip": 0.15674962103366852, "learning_rates_at_step": { "lora": 7.463957738956929e-05, "row_tokens": 7.463957738956929e-05 }, "learning_rates_after_step": { "lora": 7.44850547286094e-05, "row_tokens": 7.44850547286094e-05 } }, { "update_id": 367, "row_count": 16, "row_ids_sha256": "50aba93f49f34d46ccd58f5b07dcc41245423e1485cbd8efaa543c4a92289db6", "input_ids_vector_sha256": "a40b36f4671b5e231bd706b842bf98c329e673095719d2e88303630c4bd34b05", "labels_vector_sha256": "9effc89226dbca0f4d39483b68654cd1cb55a4862b5a6d2d877ea292b76c3315", "planned_active_tokens": 67944, "realized_active_tokens": 67944, "cumulative_start": 24052292, "cumulative_end": 24120236, "loss_sum": 23253.86541748047, "token_normalized_loss": 0.34225046240257373, "grad_norm_before_clip": 0.1433330625295639, "learning_rates_at_step": { "lora": 7.44850547286094e-05, "row_tokens": 7.44850547286094e-05 }, "learning_rates_after_step": { "lora": 7.433839416055522e-05, "row_tokens": 7.433839416055522e-05 } }, { "update_id": 368, "row_count": 16, "row_ids_sha256": "1c4f07ac858f2bd8f6b1d029a6e02a0a24880edb8331d5f6c53a2fbfed1eadab", "input_ids_vector_sha256": "2a88b9072117c7f6785cfd262616b138ae195c1f8168aa0fd1aa521dcd1f61f0", "labels_vector_sha256": "4534bcea8afe32ba93a89a9f6a377fdd61080cd403e82be7ecea90b7794aa64a", "planned_active_tokens": 64362, "realized_active_tokens": 64362, "cumulative_start": 24120236, "cumulative_end": 24184598, "loss_sum": 20387.320693969727, "token_normalized_loss": 0.31676021090037176, "grad_norm_before_clip": 0.1400744765996933, "learning_rates_at_step": { "lora": 7.433839416055522e-05, "row_tokens": 7.433839416055522e-05 }, "learning_rates_after_step": { "lora": 7.418999618756265e-05, "row_tokens": 7.418999618756265e-05 } }, { "update_id": 369, "row_count": 12, "row_ids_sha256": "710b84c54a1b75a3e9f28b2e3c056e710b4c3355351ed73de6d31080da20439b", "input_ids_vector_sha256": "ea40f356e4dbe780bc5d6b9771516e69149ef363c3059f9c29828bd5c8dce7ac", "labels_vector_sha256": "712db1737506a9f6984069f66a0b1f7cf7fcb099b10aa383fcaa3561b6eebf43", "planned_active_tokens": 65002, "realized_active_tokens": 65002, "cumulative_start": 24184598, "cumulative_end": 24249600, "loss_sum": 27034.505920410156, "token_normalized_loss": 0.41590267869311953, "grad_norm_before_clip": 0.19317029416561127, "learning_rates_at_step": { "lora": 7.418999618756265e-05, "row_tokens": 7.418999618756265e-05 }, "learning_rates_after_step": { "lora": 7.403098905643314e-05, "row_tokens": 7.403098905643314e-05 } }, { "update_id": 370, "row_count": 17, "row_ids_sha256": "6ff62ca05519a2b67df00412e14badc60e732968c936d72a19b0df52b6231163", "input_ids_vector_sha256": "743955c00ada999747c9f63f7f22c7567bc30171d207aeb4e1be043d32436c66", "labels_vector_sha256": "9604997de01b7a056de35a15eb9f57b4b6a04c02c0538b83dea0ec0e3d8c2f41", "planned_active_tokens": 69514, "realized_active_tokens": 69514, "cumulative_start": 24249600, "cumulative_end": 24319114, "loss_sum": 24040.126892089844, "token_normalized_loss": 0.3458314424733125, "grad_norm_before_clip": 0.13755358755588531, "learning_rates_at_step": { "lora": 7.403098905643314e-05, "row_tokens": 7.403098905643314e-05 }, "learning_rates_after_step": { "lora": 7.38823373343698e-05, "row_tokens": 7.38823373343698e-05 } }, { "update_id": 371, "row_count": 16, "row_ids_sha256": "16a92ef57a4aaef5ba1aa91745544b711198045ce431426b36f2d94fd153e4b2", "input_ids_vector_sha256": "8480df0ebb00ab7b7569808aa500943f41bb7f36a6ec56abd03bf45109cea72f", "labels_vector_sha256": "189d2cffaea8bb9757faec53879f2917e19fce3a1ee018cf5f6534618e8c6f66", "planned_active_tokens": 64862, "realized_active_tokens": 64862, "cumulative_start": 24319114, "cumulative_end": 24383976, "loss_sum": 22049.522430419922, "token_normalized_loss": 0.33994515171317446, "grad_norm_before_clip": 0.13871954381465912, "learning_rates_at_step": { "lora": 7.38823373343698e-05, "row_tokens": 7.38823373343698e-05 }, "learning_rates_after_step": { "lora": 7.373426422354868e-05, "row_tokens": 7.373426422354868e-05 } }, { "update_id": 372, "row_count": 12, "row_ids_sha256": "2e4a3973219eb3d237b87bf6a5669996bcee956a22956fb2947593c3c3fe184a", "input_ids_vector_sha256": "0e627e95c1501a527d277655811f87805f87506f6ba8680b9e90c1294e2d3522", "labels_vector_sha256": "ac6162698742ac601e29771806347eb28d19f24e2e75c60f81667bdae4cd10e1", "planned_active_tokens": 64491, "realized_active_tokens": 64491, "cumulative_start": 24383976, "cumulative_end": 24448467, "loss_sum": 24593.324630737305, "token_normalized_loss": 0.3813450656795104, "grad_norm_before_clip": 0.15000763535499573, "learning_rates_at_step": { "lora": 7.373426422354868e-05, "row_tokens": 7.373426422354868e-05 }, "learning_rates_after_step": { "lora": 7.357848061759588e-05, "row_tokens": 7.357848061759588e-05 } }, { "update_id": 373, "row_count": 15, "row_ids_sha256": "6306d735be48921c503228fcb4c38507521df6a4660a7172ad3446cd5dcebdcf", "input_ids_vector_sha256": "40990143b8eafd6136e0af015e8fdc338e7ce9b283d55a07b0951747aeabfb62", "labels_vector_sha256": "de6297287befc1029207e5bbfed3eacf17ddd2e9b0601eed831ef302085ccd40", "planned_active_tokens": 67723, "realized_active_tokens": 67723, "cumulative_start": 24448467, "cumulative_end": 24516190, "loss_sum": 22158.860717773438, "token_normalized_loss": 0.32719845130566333, "grad_norm_before_clip": 0.14011651277542114, "learning_rates_at_step": { "lora": 7.357848061759588e-05, "row_tokens": 7.357848061759588e-05 }, "learning_rates_after_step": { "lora": 7.342475735027132e-05, "row_tokens": 7.342475735027132e-05 } }, { "update_id": 374, "row_count": 15, "row_ids_sha256": "291f9781f0f634ba20d88a45bf9241b16d99459c4035c6d952fffde5f9511d0e", "input_ids_vector_sha256": "1d7e52c90ab7b87ba82d19eae6592ecbe938e8c0597bfc276b062c8304861d08", "labels_vector_sha256": "e38ea2a4877f48d7ce09f71137da1c012a3957d9c15dbdcc3680545df8f414ad", "planned_active_tokens": 66702, "realized_active_tokens": 66702, "cumulative_start": 24516190, "cumulative_end": 24582892, "loss_sum": 20760.73602294922, "token_normalized_loss": 0.3112460799218797, "grad_norm_before_clip": 0.1363234668970108, "learning_rates_at_step": { "lora": 7.342475735027132e-05, "row_tokens": 7.342475735027132e-05 }, "learning_rates_after_step": { "lora": 7.328233185621026e-05, "row_tokens": 7.328233185621026e-05 } }, { "update_id": 375, "row_count": 15, "row_ids_sha256": "837d108d1705af1942e3fc16c8f66ef4df9c864948a96bd22ed7ccb5065c2b17", "input_ids_vector_sha256": "3d1d7e8653fa41e5264e2d992efe5fd2fb8b1949b6d6e379e20024a30aee9952", "labels_vector_sha256": "526c75ac6bff60a1aa1be5a8ff02559fdb85e90820148d524b01660e3f2ff1ca", "planned_active_tokens": 61690, "realized_active_tokens": 61690, "cumulative_start": 24582892, "cumulative_end": 24644582, "loss_sum": 20103.924438476562, "token_normalized_loss": 0.3258862771677186, "grad_norm_before_clip": 0.16586194932460785, "learning_rates_at_step": { "lora": 7.328233185621026e-05, "row_tokens": 7.328233185621026e-05 }, "learning_rates_after_step": { "lora": 7.313366046247366e-05, "row_tokens": 7.313366046247366e-05 } }, { "update_id": 376, "row_count": 17, "row_ids_sha256": "f7d5656c3973b2b0c26e7fcceda27b132f1283e66db18fdf4228dee96e3a4509", "input_ids_vector_sha256": "6dafc2080615162fe78b4a8405233825145fdbf4337fac8302944c53e17a80ad", "labels_vector_sha256": "bf1009787c505a0b2cf683fdbcda4e99d18140656d78ab50e36aefd11c79da73", "planned_active_tokens": 64284, "realized_active_tokens": 64284, "cumulative_start": 24644582, "cumulative_end": 24708866, "loss_sum": 20127.226593017578, "token_normalized_loss": 0.3130985407413599, "grad_norm_before_clip": 0.144819438457489, "learning_rates_at_step": { "lora": 7.313366046247366e-05, "row_tokens": 7.313366046247366e-05 }, "learning_rates_after_step": { "lora": 7.298346925304766e-05, "row_tokens": 7.298346925304766e-05 } }, { "update_id": 377, "row_count": 14, "row_ids_sha256": "b5a2d739825fd1ec239b582857207cd67d76f97d8ad127d957938af2e38de720", "input_ids_vector_sha256": "be7bf39cc4223b5a2e813a454d2354a06211bcb6822e6c07a8e91286d2470562", "labels_vector_sha256": "79f15749d7c664f6a77b60eb0cbbe8b555cb39f7374b34aa884326d49ca74f14", "planned_active_tokens": 64827, "realized_active_tokens": 64827, "cumulative_start": 24708866, "cumulative_end": 24773693, "loss_sum": 23452.36181640625, "token_normalized_loss": 0.3617684269888511, "grad_norm_before_clip": 0.1513034552335739, "learning_rates_at_step": { "lora": 7.298346925304766e-05, "row_tokens": 7.298346925304766e-05 }, "learning_rates_after_step": { "lora": 7.282517687342203e-05, "row_tokens": 7.282517687342203e-05 } }, { "update_id": 378, "row_count": 19, "row_ids_sha256": "153964c0f3ea9077d4e875b2b3f9e5e835897445e6c61adc6f3f17ae650cd25b", "input_ids_vector_sha256": "ab8bae8ccf0418e9a196f574da03f3adf8531ea4310696485f72cdef0fef8838", "labels_vector_sha256": "a3c4aeecf44d114faad337901b41775b560897303458755f159699deb3da73a2", "planned_active_tokens": 68201, "realized_active_tokens": 68201, "cumulative_start": 24773693, "cumulative_end": 24841894, "loss_sum": 21733.6336517334, "token_normalized_loss": 0.3186703076455389, "grad_norm_before_clip": 0.1390632688999176, "learning_rates_at_step": { "lora": 7.282517687342203e-05, "row_tokens": 7.282517687342203e-05 }, "learning_rates_after_step": { "lora": 7.267183362726823e-05, "row_tokens": 7.267183362726823e-05 } }, { "update_id": 379, "row_count": 12, "row_ids_sha256": "b7fb38eca6c4f055932028bac5a1660f1f81af3ad28debc87d28209dc8ea142a", "input_ids_vector_sha256": "2ec23400984c4fb0ce1aec45c84659dcd642af54ba74e1c10db41f07cc5b2fc0", "labels_vector_sha256": "07177a3ee0bad2dcd42136814b27652dad2d8bd7f989a253fb6f85c7004bca18", "planned_active_tokens": 65950, "realized_active_tokens": 65950, "cumulative_start": 24841894, "cumulative_end": 24907844, "loss_sum": 21202.909759521484, "token_normalized_loss": 0.3214997689085896, "grad_norm_before_clip": 0.13442401587963104, "learning_rates_at_step": { "lora": 7.267183362726823e-05, "row_tokens": 7.267183362726823e-05 }, "learning_rates_after_step": { "lora": 7.252778141789753e-05, "row_tokens": 7.252778141789753e-05 } }, { "update_id": 380, "row_count": 14, "row_ids_sha256": "e7773e9259265a7a7328d611376404e6c026d35338732e5541235385ede56b61", "input_ids_vector_sha256": "1a780301c36b49a026c4d602cf8297eead567ba7ae86bb758f135faa7213c304", "labels_vector_sha256": "a3d020e835373d9fa3b8a324608c4d6c0a05a5adefec9099915b939e3e495546", "planned_active_tokens": 61849, "realized_active_tokens": 61849, "cumulative_start": 24907844, "cumulative_end": 24969693, "loss_sum": 19629.00848388672, "token_normalized_loss": 0.3173698602060942, "grad_norm_before_clip": 1.106634497642517, "learning_rates_at_step": { "lora": 7.252778141789753e-05, "row_tokens": 7.252778141789753e-05 }, "learning_rates_after_step": { "lora": 7.237267415181253e-05, "row_tokens": 7.237267415181253e-05 } }, { "update_id": 381, "row_count": 15, "row_ids_sha256": "6b528f019306cea64cc2511a03dc9454bbbd4e9149b8b8468602f9377d317c1f", "input_ids_vector_sha256": "837381efe0fc969b384bd77eb31d128156aa6bd77ce6320faadff09613dd2a14", "labels_vector_sha256": "53c02f5905e8276f8cbeca67e2e723d0f3101493438f49cb16508af372d03e04", "planned_active_tokens": 66483, "realized_active_tokens": 66483, "cumulative_start": 24969693, "cumulative_end": 25036176, "loss_sum": 24699.827423095703, "token_normalized_loss": 0.3715209515680054, "grad_norm_before_clip": 0.14720119535923004, "learning_rates_at_step": { "lora": 7.237267415181253e-05, "row_tokens": 7.237267415181253e-05 }, "learning_rates_after_step": { "lora": 7.22184550733204e-05, "row_tokens": 7.22184550733204e-05 } }, { "update_id": 382, "row_count": 16, "row_ids_sha256": "3f99eb398d556aab4547291c6f8d249f20024232bd2616cdae51e035a9bea905", "input_ids_vector_sha256": "ef849ab5c17c178021eaeb4154521be226ef9e4e39dec0cfa4beac38e9383f05", "labels_vector_sha256": "9e2e823e0dba21fb102e017d6f72779534663a6190ff86b78d898c971e5e7d82", "planned_active_tokens": 65988, "realized_active_tokens": 65988, "cumulative_start": 25036176, "cumulative_end": 25102164, "loss_sum": 22275.740936279297, "token_normalized_loss": 0.3375726031441974, "grad_norm_before_clip": 0.14356857538223267, "learning_rates_at_step": { "lora": 7.22184550733204e-05, "row_tokens": 7.22184550733204e-05 }, "learning_rates_after_step": { "lora": 7.205941478511967e-05, "row_tokens": 7.205941478511967e-05 } }, { "update_id": 383, "row_count": 18, "row_ids_sha256": "d6a08ebaa91c9b5b0e898c52361a91908b5107fddaccd6f373c1ed2fb6d62ea0", "input_ids_vector_sha256": "69f02f5d265a327101e874916dd5300a6d569e61468e57af1ba17dc08e519968", "labels_vector_sha256": "5cfed9cfc1ba901bed0be63109d66c7a683057c555fd493deb27c01a11663eac", "planned_active_tokens": 67933, "realized_active_tokens": 67933, "cumulative_start": 25102164, "cumulative_end": 25170097, "loss_sum": 23516.488037109375, "token_normalized_loss": 0.3461717874539528, "grad_norm_before_clip": 0.14240460097789764, "learning_rates_at_step": { "lora": 7.205941478511967e-05, "row_tokens": 7.205941478511967e-05 }, "learning_rates_after_step": { "lora": 7.190364116926036e-05, "row_tokens": 7.190364116926036e-05 } }, { "update_id": 384, "row_count": 17, "row_ids_sha256": "4abcb4e1c98b751a4a1c176d91132353f9b533490929f9a744ecb8cabe754ad8", "input_ids_vector_sha256": "44301f4f6d00f0528b13b9339b4fdd3de3e5cc557b0dc7af2ce36390bc8f849f", "labels_vector_sha256": "0bb20cda628a906671501103c6895a090e59dc9a3b63bd4923687ebabfa5a321", "planned_active_tokens": 66423, "realized_active_tokens": 66423, "cumulative_start": 25170097, "cumulative_end": 25236520, "loss_sum": 22559.562072753906, "token_normalized_loss": 0.3396347962716816, "grad_norm_before_clip": 0.14035572111606598, "learning_rates_at_step": { "lora": 7.190364116926036e-05, "row_tokens": 7.190364116926036e-05 }, "learning_rates_after_step": { "lora": 7.175028425370545e-05, "row_tokens": 7.175028425370545e-05 } }, { "update_id": 385, "row_count": 17, "row_ids_sha256": "8658cd58da8eeb9440487af47384354199f17e0e3bab3f6aba9626afea79ab5c", "input_ids_vector_sha256": "d7a0d76f9e883540ae19ef9a1cb30fb91c61cf3c9324b98182ccca509c7365e7", "labels_vector_sha256": "42cea5ebf8f7e077c3947b1549081c0f380549bc9444e94a0cf8a0399b0b705e", "planned_active_tokens": 65283, "realized_active_tokens": 65283, "cumulative_start": 25236520, "cumulative_end": 25301803, "loss_sum": 21756.69305419922, "token_normalized_loss": 0.33326735986702843, "grad_norm_before_clip": 0.15863077342510223, "learning_rates_at_step": { "lora": 7.175028425370545e-05, "row_tokens": 7.175028425370545e-05 }, "learning_rates_after_step": { "lora": 7.160307497744264e-05, "row_tokens": 7.160307497744264e-05 } }, { "update_id": 386, "row_count": 14, "row_ids_sha256": "ef1c7ee0993c4deb7a34a479dac98b60198739f31caffb6484b6425307f28c8c", "input_ids_vector_sha256": "fc8b4dc75816f2131ce7a1b85b802774adbfc2419738703de32f7c98b93f572b", "labels_vector_sha256": "56d3c65120a11b18b02341f9f26998d1124a1638f86176c9994fa7d0b12f7ce7", "planned_active_tokens": 62565, "realized_active_tokens": 62565, "cumulative_start": 25301803, "cumulative_end": 25364368, "loss_sum": 22561.69287109375, "token_normalized_loss": 0.36061204940611763, "grad_norm_before_clip": 0.1546609103679657, "learning_rates_at_step": { "lora": 7.160307497744264e-05, "row_tokens": 7.160307497744264e-05 }, "learning_rates_after_step": { "lora": 7.145047709036141e-05, "row_tokens": 7.145047709036141e-05 } }, { "update_id": 387, "row_count": 13, "row_ids_sha256": "ad844d6b27e22b93940d9c025cb82273d5fef56168e6e3742cfb11931421bdb0", "input_ids_vector_sha256": "959d325de6fcd3d244992d24071a94b5ae288cdbe8841833c1feb33a8c9bfd50", "labels_vector_sha256": "fac2526a79860b6f497f576389b3aaadec1fe1a57e41bfa285d07ecda0731a9e", "planned_active_tokens": 64752, "realized_active_tokens": 64752, "cumulative_start": 25364368, "cumulative_end": 25429120, "loss_sum": 24458.405151367188, "token_normalized_loss": 0.37772431973324666, "grad_norm_before_clip": 0.1491282731294632, "learning_rates_at_step": { "lora": 7.145047709036141e-05, "row_tokens": 7.145047709036141e-05 }, "learning_rates_after_step": { "lora": 7.128997734527179e-05, "row_tokens": 7.128997734527179e-05 } }, { "update_id": 388, "row_count": 12, "row_ids_sha256": "38eeb8331cd5945bdc294b79bf7a3a21057b9922e7b794c7830edcbcd2cbbfbc", "input_ids_vector_sha256": "5565f7846c516f3f3be5dece72e52a584555137600ee1b1633e408b5fe49409b", "labels_vector_sha256": "5b3a84ea12bf3bbd4ea5f7fa4269c88e100e578181840965f3bb8b760369c86b", "planned_active_tokens": 67993, "realized_active_tokens": 67993, "cumulative_start": 25429120, "cumulative_end": 25497113, "loss_sum": 30212.6005859375, "token_normalized_loss": 0.44434869157027196, "grad_norm_before_clip": 0.15505065023899078, "learning_rates_at_step": { "lora": 7.128997734527179e-05, "row_tokens": 7.128997734527179e-05 }, "learning_rates_after_step": { "lora": 7.112707700595557e-05, "row_tokens": 7.112707700595557e-05 } }, { "update_id": 389, "row_count": 14, "row_ids_sha256": "f4522babdb689cc8f21dc56b50c0d7ee7651b02aa1f9ec80768ff39e7fe5958b", "input_ids_vector_sha256": "4da15977a1e09551dd4b167a7e97161721e3839c5549f212aae59b5bc0bf5493", "labels_vector_sha256": "43ccd76d22f9a3256edcd8b7c313a4e69ea22bc590be1555643ba00ebe24239b", "planned_active_tokens": 68894, "realized_active_tokens": 68894, "cumulative_start": 25497113, "cumulative_end": 25566007, "loss_sum": 28244.732666015625, "token_normalized_loss": 0.40997376645303835, "grad_norm_before_clip": 0.1492498368024826, "learning_rates_at_step": { "lora": 7.112707700595557e-05, "row_tokens": 7.112707700595557e-05 }, "learning_rates_after_step": { "lora": 7.096919628394116e-05, "row_tokens": 7.096919628394116e-05 } }, { "update_id": 390, "row_count": 16, "row_ids_sha256": "fb01a46e1e35d1b62d59618b58fd265e952dd75351f872b9b9b08e935571d90d", "input_ids_vector_sha256": "1a03a89d26119f0fd505d7bf3ca5ef0233d484ce9d58321e5b94bf762b6ad7d5", "labels_vector_sha256": "5afb1bdaa38c2c0753258f2375dfd4aadf31526292701317f7848403878838e7", "planned_active_tokens": 66661, "realized_active_tokens": 66661, "cumulative_start": 25566007, "cumulative_end": 25632668, "loss_sum": 27827.213592529297, "token_normalized_loss": 0.41744368660130055, "grad_norm_before_clip": 0.2971709668636322, "learning_rates_at_step": { "lora": 7.096919628394116e-05, "row_tokens": 7.096919628394116e-05 }, "learning_rates_after_step": { "lora": 7.08185491515746e-05, "row_tokens": 7.08185491515746e-05 } }, { "update_id": 391, "row_count": 14, "row_ids_sha256": "8884d61e2be184e936a5aa9c5be319eb8e6ee8abd7a4692bce044128ad2b318c", "input_ids_vector_sha256": "0b5a088c7212104e625ddb9d2ebeec7643505a9043c9875393a26b5b2e034725", "labels_vector_sha256": "e2331d5dbfe8d998c19c6b370ce6d55fbbab13a69cd94a60d4c5cf34f7265066", "planned_active_tokens": 63507, "realized_active_tokens": 63507, "cumulative_start": 25632668, "cumulative_end": 25696175, "loss_sum": 25972.951538085938, "token_normalized_loss": 0.40897777470335456, "grad_norm_before_clip": 0.15155594050884247, "learning_rates_at_step": { "lora": 7.08185491515746e-05, "row_tokens": 7.08185491515746e-05 }, "learning_rates_after_step": { "lora": 7.067673342054397e-05, "row_tokens": 7.067673342054397e-05 } }, { "update_id": 392, "row_count": 13, "row_ids_sha256": "470647b374be5e92c7a1f52f8ee15219f322f763370ca1e2f7b145de5dd378ed", "input_ids_vector_sha256": "6c8f0bef5a0cb1a9aaca879252b9006405866312b5d4712466a0051e63bbb866", "labels_vector_sha256": "59c425235ba9adc93f95f3b1e8db329ef1bc7fc295c842935ae8db67140aa7ef", "planned_active_tokens": 59696, "realized_active_tokens": 59696, "cumulative_start": 25696175, "cumulative_end": 25755871, "loss_sum": 22812.489532470703, "token_normalized_loss": 0.38214435694972365, "grad_norm_before_clip": 0.23909515142440796, "learning_rates_at_step": { "lora": 7.067673342054397e-05, "row_tokens": 7.067673342054397e-05 }, "learning_rates_after_step": { "lora": 7.051044764215758e-05, "row_tokens": 7.051044764215758e-05 } }, { "update_id": 393, "row_count": 15, "row_ids_sha256": "84d99b2ae53c8ae00a6fd9728ab1f47d7fc90623e93e9a9bb28c200146ebfa76", "input_ids_vector_sha256": "6f5b5c133d564c69947f6e1b0eadecd84f663deea836cedf55ef3434a1bc3bbf", "labels_vector_sha256": "0747ce734d4c21b94a655536a9be28be27a20516ae39d412174104e2dd412182", "planned_active_tokens": 69889, "realized_active_tokens": 69889, "cumulative_start": 25755871, "cumulative_end": 25825760, "loss_sum": 24951.733520507812, "token_normalized_loss": 0.3570194668761581, "grad_norm_before_clip": 0.15517055988311768, "learning_rates_at_step": { "lora": 7.051044764215758e-05, "row_tokens": 7.051044764215758e-05 }, "learning_rates_after_step": { "lora": 7.035738526676764e-05, "row_tokens": 7.035738526676764e-05 } }, { "update_id": 394, "row_count": 14, "row_ids_sha256": "bbac1a3676850173de8fdb6823a6538815c739a918850c3d52af89d2322824f2", "input_ids_vector_sha256": "025c88b8704b491bf6fec4a4deab105c172b572ad428c49fd3e41a090f0cc933", "labels_vector_sha256": "2a669cfac652f497d35a7a6901b4c78242cad276b99d1434e48e7f4f5250477b", "planned_active_tokens": 64230, "realized_active_tokens": 64230, "cumulative_start": 25825760, "cumulative_end": 25889990, "loss_sum": 21878.075271606445, "token_normalized_loss": 0.3406208200468075, "grad_norm_before_clip": 0.13701874017715454, "learning_rates_at_step": { "lora": 7.035738526676764e-05, "row_tokens": 7.035738526676764e-05 }, "learning_rates_after_step": { "lora": 7.020768114344551e-05, "row_tokens": 7.020768114344551e-05 } }, { "update_id": 395, "row_count": 15, "row_ids_sha256": "26541d2cf04fabe5022a5009c767a532e1ee047a923499d0dbb369adfe11a15e", "input_ids_vector_sha256": "1845870d9b3153005f4e25cc6bd44b05c2f9f83f47867471336aa69452d7851f", "labels_vector_sha256": "f02e72ade8bcde6f84ef85f092ae6ec850e9184fcb2a82098d77969f46ccbadb", "planned_active_tokens": 62728, "realized_active_tokens": 62728, "cumulative_start": 25889990, "cumulative_end": 25952718, "loss_sum": 22150.112579345703, "token_normalized_loss": 0.35311364270095813, "grad_norm_before_clip": 0.1391322910785675, "learning_rates_at_step": { "lora": 7.020768114344551e-05, "row_tokens": 7.020768114344551e-05 }, "learning_rates_after_step": { "lora": 7.00405143470529e-05, "row_tokens": 7.00405143470529e-05 } }, { "update_id": 396, "row_count": 13, "row_ids_sha256": "628407e3d2a0854d5aeb5f0ff2ccffc0132318fd781021ca438bfdeef4edd152", "input_ids_vector_sha256": "1df121e97f0d77ebb208c610b5d68b85315d0f4b70b7983f3f90694631d6c255", "labels_vector_sha256": "3355f749316ee0a41d20c9ca6b1960753e195d72516e8e51b4c6fdf548e07d89", "planned_active_tokens": 69938, "realized_active_tokens": 69938, "cumulative_start": 25952718, "cumulative_end": 26022656, "loss_sum": 27376.698211669922, "token_normalized_loss": 0.3914423948593028, "grad_norm_before_clip": 0.14664480090141296, "learning_rates_at_step": { "lora": 7.00405143470529e-05, "row_tokens": 7.00405143470529e-05 }, "learning_rates_after_step": { "lora": 6.98912374846329e-05, "row_tokens": 6.98912374846329e-05 } }, { "update_id": 397, "row_count": 10, "row_ids_sha256": "5b6c77dc88459774e5898cfec29f87f40fdf12a727de0a81bd547a33fffddb0c", "input_ids_vector_sha256": "c6f03d4003553ac78f3caaefb4a0c8c8e65b650b9a42d2c96f0334cbaee19a96", "labels_vector_sha256": "9f47f294ae842d3f9ed747613c05bbda171230259a44c6a932262773280101e5", "planned_active_tokens": 62359, "realized_active_tokens": 62359, "cumulative_start": 26022656, "cumulative_end": 26085015, "loss_sum": 22774.161224365234, "token_normalized_loss": 0.3652104944653576, "grad_norm_before_clip": 0.14191153645515442, "learning_rates_at_step": { "lora": 6.98912374846329e-05, "row_tokens": 6.98912374846329e-05 }, "learning_rates_after_step": { "lora": 6.972440426630518e-05, "row_tokens": 6.972440426630518e-05 } }, { "update_id": 398, "row_count": 8, "row_ids_sha256": "6b354bb848212fba7223ebb35934a100e02fac4b631d8d938d47b1eee3de9257", "input_ids_vector_sha256": "3855b6d23d7368656eace9358d44eed13df80666660e0e6c0f4c32cdd12ed1d8", "labels_vector_sha256": "f496a572f942ed68b3fdbcb851f0ed66fc92cc8e2897d21407c624c11969b00a", "planned_active_tokens": 69589, "realized_active_tokens": 69589, "cumulative_start": 26085015, "cumulative_end": 26154604, "loss_sum": 24843.9658203125, "token_normalized_loss": 0.35700995588832285, "grad_norm_before_clip": 0.1358112394809723, "learning_rates_at_step": { "lora": 6.972440426630518e-05, "row_tokens": 6.972440426630518e-05 }, "learning_rates_after_step": { "lora": 6.957605244063441e-05, "row_tokens": 6.957605244063441e-05 } }, { "update_id": 399, "row_count": 14, "row_ids_sha256": "4eae2d28293509031160aad608a357f69f1f521a72ac3de37f07caa7ffaa6920", "input_ids_vector_sha256": "a40111dbd117dc200a0a14557f4d1a7c2b65a0be438c4d445b85648d350e9241", "labels_vector_sha256": "43ccbc418e6551ed985cf2a952f00e62cd51b20f5ef513dc613320ec339c5d36", "planned_active_tokens": 61789, "realized_active_tokens": 61789, "cumulative_start": 26154604, "cumulative_end": 26216393, "loss_sum": 23525.839904785156, "token_normalized_loss": 0.3807447912214983, "grad_norm_before_clip": 0.1511276513338089, "learning_rates_at_step": { "lora": 6.957605244063441e-05, "row_tokens": 6.957605244063441e-05 }, "learning_rates_after_step": { "lora": 6.940989876525479e-05, "row_tokens": 6.940989876525479e-05 } }, { "update_id": 400, "row_count": 8, "row_ids_sha256": "8abfd8409a2532a7a7cd785850424444d5f59c954aec16561bfa45843ae368cb", "input_ids_vector_sha256": "d0ecab3baa02c1fb93a3bb7bfb1b23376d4540489c8a8b0b288cded909b7716f", "labels_vector_sha256": "03e1da3acfeb69441a923839972ebb2f7f1902bd92607ab5e6e2f2cb0688a7e6", "planned_active_tokens": 69103, "realized_active_tokens": 69103, "cumulative_start": 26216393, "cumulative_end": 26285496, "loss_sum": 28513.88671875, "token_normalized_loss": 0.4126287819450675, "grad_norm_before_clip": 0.14826510846614838, "learning_rates_at_step": { "lora": 6.940989876525479e-05, "row_tokens": 6.940989876525479e-05 }, "learning_rates_after_step": { "lora": 6.926297233940607e-05, "row_tokens": 6.926297233940607e-05 } }, { "update_id": 401, "row_count": 12, "row_ids_sha256": "6e69472887ba3514b73bfb9c7021c3f47966e9e7f0add70ff0ed054167becf21", "input_ids_vector_sha256": "352138b50fd9108e8520569a1fd1ad8ba8c7ed739e989860f9f3d59bc6013f1f", "labels_vector_sha256": "628de90b1ace66e8067a3e28d5685ce2bb1fbf8230e38f4cd2c96e2f69ff2ba3", "planned_active_tokens": 61019, "realized_active_tokens": 61019, "cumulative_start": 26285496, "cumulative_end": 26346515, "loss_sum": 22036.431213378906, "token_normalized_loss": 0.3611404843307643, "grad_norm_before_clip": 0.13947847485542297, "learning_rates_at_step": { "lora": 6.926297233940607e-05, "row_tokens": 6.926297233940607e-05 }, "learning_rates_after_step": { "lora": 6.909898924814685e-05, "row_tokens": 6.909898924814685e-05 } }, { "update_id": 402, "row_count": 9, "row_ids_sha256": "402d55154f8dade1b489a3d3afa894b3dd39753a42debc38eec7daa9da8d1424", "input_ids_vector_sha256": "45e86a1f80eeb7664bb0f8067e215edefece0ee0ea75a7a257556d2b61a1073c", "labels_vector_sha256": "6ba11474fb5edae2fdeea310b56e79d7f0b223442e9873bfc5eea2fb6633346d", "planned_active_tokens": 68007, "realized_active_tokens": 68007, "cumulative_start": 26346515, "cumulative_end": 26414522, "loss_sum": 26977.62811279297, "token_normalized_loss": 0.396688989556854, "grad_norm_before_clip": 0.13714338839054108, "learning_rates_at_step": { "lora": 6.909898924814685e-05, "row_tokens": 6.909898924814685e-05 }, "learning_rates_after_step": { "lora": 6.894618782817878e-05, "row_tokens": 6.894618782817878e-05 } }, { "update_id": 403, "row_count": 7, "row_ids_sha256": "f8dd387ff969af0d651c7ed5d7c7d9948907ca00c6f5ebbd5bda1410e5769f0d", "input_ids_vector_sha256": "3bb36708b6046f791afc574b80da100411a1247a77a5db4d66efe73ec5965d5c", "labels_vector_sha256": "af0abac58839859e67441535afd718b324710476470efbcfbd666d4fc9f89632", "planned_active_tokens": 63280, "realized_active_tokens": 63280, "cumulative_start": 26414522, "cumulative_end": 26477802, "loss_sum": 28110.365661621094, "token_normalized_loss": 0.4442219605186646, "grad_norm_before_clip": 0.15732280910015106, "learning_rates_at_step": { "lora": 6.894618782817878e-05, "row_tokens": 6.894618782817878e-05 }, "learning_rates_after_step": { "lora": 6.877736887012674e-05, "row_tokens": 6.877736887012674e-05 } }, { "update_id": 404, "row_count": 9, "row_ids_sha256": "46239798577e6f83ea1c4a877b41bf64ab2c832b09935049b0486b6c92f4890a", "input_ids_vector_sha256": "17d5d07c3db23ff25a7e10fed2aab56ab14685c0f7716b3acc88fd1d64b4bdd5", "labels_vector_sha256": "80c1725870d428105e09733fc8c8b571d94c976ee1f4c89bbfa0c9b25372f592", "planned_active_tokens": 69814, "realized_active_tokens": 69814, "cumulative_start": 26477802, "cumulative_end": 26547616, "loss_sum": 29931.07177734375, "token_normalized_loss": 0.42872592570750495, "grad_norm_before_clip": 0.14600208401679993, "learning_rates_at_step": { "lora": 6.877736887012674e-05, "row_tokens": 6.877736887012674e-05 }, "learning_rates_after_step": { "lora": 6.861851241316097e-05, "row_tokens": 6.861851241316097e-05 } }, { "update_id": 405, "row_count": 12, "row_ids_sha256": "d0655202918560cf3d637c2c9d3de5e89dd137fb5b48d51869779f65a8107551", "input_ids_vector_sha256": "b22cf66d79a44ee37357d89ba385660bfe2f06045f06d169a3e3ffb4d47d7a15", "labels_vector_sha256": "94a9c51bdba5a16d49cbade3c2a7822024e6edef9652be2f9838c3fae644a73f", "planned_active_tokens": 65600, "realized_active_tokens": 65600, "cumulative_start": 26547616, "cumulative_end": 26613216, "loss_sum": 28029.241821289062, "token_normalized_loss": 0.4272750277635528, "grad_norm_before_clip": 0.15442395210266113, "learning_rates_at_step": { "lora": 6.861851241316097e-05, "row_tokens": 6.861851241316097e-05 }, "learning_rates_after_step": { "lora": 6.84551083659719e-05, "row_tokens": 6.84551083659719e-05 } }, { "update_id": 406, "row_count": 9, "row_ids_sha256": "bfa645493788a4b9eb91ddf18dd6980891d9b4ccf2af27bf3ae85a86612217da", "input_ids_vector_sha256": "99441440dff8d5b580895004ea3bfb2ccdb912d165598def9a0f141596069659", "labels_vector_sha256": "6fc579435f64c4c43eacace7b2554e1c24c67a16d144094750b5e1d4f8f206a7", "planned_active_tokens": 67384, "realized_active_tokens": 67384, "cumulative_start": 26613216, "cumulative_end": 26680600, "loss_sum": 27113.698944091797, "token_normalized_loss": 0.4023759192700314, "grad_norm_before_clip": 0.14464086294174194, "learning_rates_at_step": { "lora": 6.84551083659719e-05, "row_tokens": 6.84551083659719e-05 }, "learning_rates_after_step": { "lora": 6.831331746075455e-05, "row_tokens": 6.831331746075455e-05 } }, { "update_id": 407, "row_count": 10, "row_ids_sha256": "693dd2ca8fea5332cdbf2f60808ad369b9b1e121ed1c6d5e1a8aec72867f3908", "input_ids_vector_sha256": "7eef478ef983c0a7b710b696c557ed654c30c68b3ab80bedeced7f0d0744511d", "labels_vector_sha256": "21dc3d7ff30e2155b27e0947eb21b174def2464dd3f938058584e7fe650f2a22", "planned_active_tokens": 58395, "realized_active_tokens": 58395, "cumulative_start": 26680600, "cumulative_end": 26738995, "loss_sum": 24497.08856201172, "token_normalized_loss": 0.41950661121691446, "grad_norm_before_clip": 0.1564559042453766, "learning_rates_at_step": { "lora": 6.831331746075455e-05, "row_tokens": 6.831331746075455e-05 }, "learning_rates_after_step": { "lora": 6.814157143539292e-05, "row_tokens": 6.814157143539292e-05 } }, { "update_id": 408, "row_count": 10, "row_ids_sha256": "bee60301c7610f289c9e528f09d2f6a41e61fd11f51849c9ee2bb044e864f976", "input_ids_vector_sha256": "cf6d3cfacdbc52fd9d413b97c059e777845929f7d54592aa4423f2a7c1a56886", "labels_vector_sha256": "b615db36ef0f49517aef724b588dfb0afa5cc88da9ce0a109ef44887cbd422ef", "planned_active_tokens": 70638, "realized_active_tokens": 70638, "cumulative_start": 26738995, "cumulative_end": 26809633, "loss_sum": 31749.161987304688, "token_normalized_loss": 0.44946292345911104, "grad_norm_before_clip": 0.1532173752784729, "learning_rates_at_step": { "lora": 6.814157143539292e-05, "row_tokens": 6.814157143539292e-05 }, "learning_rates_after_step": { "lora": 6.797886159257272e-05, "row_tokens": 6.797886159257272e-05 } }, { "update_id": 409, "row_count": 12, "row_ids_sha256": "7b02c9d1ff64fcc8b2fcc06f65ef00c3fd815364141531a706decb0b22312b37", "input_ids_vector_sha256": "6c9a68ab77a0d631555eca2fda80fd13242c418c111549121668a312f8a6b023", "labels_vector_sha256": "c0f0237de2da2b86e4d79abb0b1a5058daf48c1713bb09922508e02c1c1f1321", "planned_active_tokens": 66828, "realized_active_tokens": 66828, "cumulative_start": 26809633, "cumulative_end": 26876461, "loss_sum": 24420.386749267578, "token_normalized_loss": 0.36542148125437807, "grad_norm_before_clip": 0.14054317772388458, "learning_rates_at_step": { "lora": 6.797886159257272e-05, "row_tokens": 6.797886159257272e-05 }, "learning_rates_after_step": { "lora": 6.782918430781611e-05, "row_tokens": 6.782918430781611e-05 } }, { "update_id": 410, "row_count": 10, "row_ids_sha256": "f384a5aeb4a25fe51fde16988f839c92fb403de9c39e7c17003aa0daae95aff8", "input_ids_vector_sha256": "fe6c8d7ca4f6ea1a6c6eba9f0d429269d6cc92b6859df4ad554203834bd7c299", "labels_vector_sha256": "a74102f55b07b81fe3014a36925da5884a4893801d4828db4a32204f16d5f3b9", "planned_active_tokens": 61396, "realized_active_tokens": 61396, "cumulative_start": 26876461, "cumulative_end": 26937857, "loss_sum": 22263.534057617188, "token_normalized_loss": 0.3626218981304513, "grad_norm_before_clip": 0.15156219899654388, "learning_rates_at_step": { "lora": 6.782918430781611e-05, "row_tokens": 6.782918430781611e-05 }, "learning_rates_after_step": { "lora": 6.766395052611437e-05, "row_tokens": 6.766395052611437e-05 } }, { "update_id": 411, "row_count": 7, "row_ids_sha256": "1a5c8f5b4aaff770d01ab2057958aed3153e877d91941354840151beb368da8f", "input_ids_vector_sha256": "be1f10794dce1dfc7400529fe1c8738e00559fec1fada5170adf591caa33bdad", "labels_vector_sha256": "e3a9d7413ba09b731476a7ff77fd058d94b0eb61fbfbe371b04c95c7feef8e14", "planned_active_tokens": 67690, "realized_active_tokens": 67690, "cumulative_start": 26937857, "cumulative_end": 27005547, "loss_sum": 33008.1943359375, "token_normalized_loss": 0.48763767670169156, "grad_norm_before_clip": 0.15203532576560974, "learning_rates_at_step": { "lora": 6.766395052611437e-05, "row_tokens": 6.766395052611437e-05 }, "learning_rates_after_step": { "lora": 6.750854835214507e-05, "row_tokens": 6.750854835214507e-05 } }, { "update_id": 412, "row_count": 10, "row_ids_sha256": "9577728ad131399947c5d4d641a35eb6694f897540f02a1f9c8244e31d3ef707", "input_ids_vector_sha256": "eda6177c5c46aba5a96d6d45a0de356b3edfec7747b19ede6b46d033ff1414f1", "labels_vector_sha256": "c1417984f342f9d472fcddf3ff04c433350a856709fe6035935daa16d04eadee", "planned_active_tokens": 63580, "realized_active_tokens": 63580, "cumulative_start": 27005547, "cumulative_end": 27069127, "loss_sum": 23016.078369140625, "token_normalized_loss": 0.36200186173546123, "grad_norm_before_clip": 0.14085540175437927, "learning_rates_at_step": { "lora": 6.750854835214507e-05, "row_tokens": 6.750854835214507e-05 }, "learning_rates_after_step": { "lora": 6.735057786597585e-05, "row_tokens": 6.735057786597585e-05 } }, { "update_id": 413, "row_count": 9, "row_ids_sha256": "083470b28208a3d9b9d77237e46edcda1f68f7e36f393ff6ec5b04ea9a6da718", "input_ids_vector_sha256": "994276fef9c77f36cbf303b0941c5a3b35e449e805b171c1182425a9bb0477d2", "labels_vector_sha256": "c2adb8ae472546b34415ab8bbfb71d583a334b184df129c647e2effb48ac8a17", "planned_active_tokens": 64550, "realized_active_tokens": 64550, "cumulative_start": 27069127, "cumulative_end": 27133677, "loss_sum": 26986.6357421875, "token_normalized_loss": 0.41807336548702556, "grad_norm_before_clip": 0.14866559207439423, "learning_rates_at_step": { "lora": 6.735057786597585e-05, "row_tokens": 6.735057786597585e-05 }, "learning_rates_after_step": { "lora": 6.719380041185517e-05, "row_tokens": 6.719380041185517e-05 } }, { "update_id": 414, "row_count": 10, "row_ids_sha256": "50abb8c14a6b1237fdb26f902d5af234fef2d4dcca06d5fab385d8ef4ae8c641", "input_ids_vector_sha256": "b4788dc96a626c19a186290bba1430a00f6dd80f7c0914142bb0c402b51939fc", "labels_vector_sha256": "e66be3321981cd9bd9727cbc3a34b8eb40039ca228c5df769e43709e08d04af4", "planned_active_tokens": 63983, "realized_active_tokens": 63983, "cumulative_start": 27133677, "cumulative_end": 27197660, "loss_sum": 25320.123107910156, "token_normalized_loss": 0.3957320398841904, "grad_norm_before_clip": 0.1800546944141388, "learning_rates_at_step": { "lora": 6.719380041185517e-05, "row_tokens": 6.719380041185517e-05 }, "learning_rates_after_step": { "lora": 6.701573283272072e-05, "row_tokens": 6.701573283272072e-05 } }, { "update_id": 415, "row_count": 15, "row_ids_sha256": "2dae78d51aa0d784f5e64c57488850fba47ec24d9b56fb04880c0324aa72fe6b", "input_ids_vector_sha256": "1774a7e6e2adfda08daa0dc22b8de569ae110f12673fbf4b61f21cae8572ce31", "labels_vector_sha256": "fe828c8c75032b3a7827695731b821b3d6e4d3b2b760f2642a826627ff7ab360", "planned_active_tokens": 72577, "realized_active_tokens": 72577, "cumulative_start": 27197660, "cumulative_end": 27270237, "loss_sum": 32379.48179626465, "token_normalized_loss": 0.44613971087623694, "grad_norm_before_clip": 0.14539772272109985, "learning_rates_at_step": { "lora": 6.701573283272072e-05, "row_tokens": 6.701573283272072e-05 }, "learning_rates_after_step": { "lora": 6.686968273836808e-05, "row_tokens": 6.686968273836808e-05 } }, { "update_id": 416, "row_count": 11, "row_ids_sha256": "83e5951ca595e724e7686f8779af1ba35f80a7997582462e0a056b455c048258", "input_ids_vector_sha256": "c8d18e7fc02321629df7bcc6ab712177420218081b1776ffeac1ebaa3f631429", "labels_vector_sha256": "96248a0b7b04eef5470317b35feb603a875b0ac4924b8bbfca41ff4ba6f86f4e", "planned_active_tokens": 59453, "realized_active_tokens": 59453, "cumulative_start": 27270237, "cumulative_end": 27329690, "loss_sum": 23154.756286621094, "token_normalized_loss": 0.38946321105110077, "grad_norm_before_clip": 0.15329484641551971, "learning_rates_at_step": { "lora": 6.686968273836808e-05, "row_tokens": 6.686968273836808e-05 }, "learning_rates_after_step": { "lora": 6.670794237327159e-05, "row_tokens": 6.670794237327159e-05 } }, { "update_id": 417, "row_count": 11, "row_ids_sha256": "b7bf37268fc2c157bb932a2edf5d2302e476896bc0fe33428cd9b796cafd492f", "input_ids_vector_sha256": "f384514a6e60fa0029e6be0c44272d891be70ff37a0239f96877af9df5b6eeb3", "labels_vector_sha256": "d7b8278cad2333b74e0d3f849799df9cff277573de4e2ebe9f0a299e1d0e31a4", "planned_active_tokens": 65763, "realized_active_tokens": 65763, "cumulative_start": 27329690, "cumulative_end": 27395453, "loss_sum": 28881.06869506836, "token_normalized_loss": 0.4391689657568596, "grad_norm_before_clip": 0.14717859029769897, "learning_rates_at_step": { "lora": 6.670794237327159e-05, "row_tokens": 6.670794237327159e-05 }, "learning_rates_after_step": { "lora": 6.654116571854995e-05, "row_tokens": 6.654116571854995e-05 } }, { "update_id": 418, "row_count": 8, "row_ids_sha256": "ad012290452489e8ba63b1ff5bfa70c38c5cc0c8c523f8cf4d1c51634df5d997", "input_ids_vector_sha256": "98fea9b86d2c9c03bbd3569c6f48954ed6de049767cbfd0fa0313c0d66d10c22", "labels_vector_sha256": "2d52a1d54ab8e694a434fd9769c5186ae6d06f30b1d0aef6b41211260be38f95", "planned_active_tokens": 67727, "realized_active_tokens": 67727, "cumulative_start": 27395453, "cumulative_end": 27463180, "loss_sum": 32018.799255371094, "token_normalized_loss": 0.47276269811701527, "grad_norm_before_clip": 0.15438750386238098, "learning_rates_at_step": { "lora": 6.654116571854995e-05, "row_tokens": 6.654116571854995e-05 }, "learning_rates_after_step": { "lora": 6.637586467870739e-05, "row_tokens": 6.637586467870739e-05 } }, { "update_id": 419, "row_count": 10, "row_ids_sha256": "b45789700136139b6a6688c6b5ec229d272a21594dfeddcebe0937b7f332b8cf", "input_ids_vector_sha256": "07f80ee63e5aa7a454df4ab57f0b984cb73163c9ad3d0078696b935011b19286", "labels_vector_sha256": "6572c20b77f52eab32870d96204e8aa2fe20791525f79be9e1661c3cdd38ab8a", "planned_active_tokens": 67045, "realized_active_tokens": 67045, "cumulative_start": 27463180, "cumulative_end": 27530225, "loss_sum": 24282.10189819336, "token_normalized_loss": 0.36217617865901053, "grad_norm_before_clip": 0.1546715795993805, "learning_rates_at_step": { "lora": 6.637586467870739e-05, "row_tokens": 6.637586467870739e-05 }, "learning_rates_after_step": { "lora": 6.62150508933858e-05, "row_tokens": 6.62150508933858e-05 } }, { "update_id": 420, "row_count": 7, "row_ids_sha256": "fa1bd0dee8f657d1111f23058efee19ec7983b86e3d591a0af94b90634db566b", "input_ids_vector_sha256": "1d87044f08d79046bb4376a875996dc4e32163769bd3cae7ce811ac0158f80b6", "labels_vector_sha256": "bfbf6d40f4b2b10c4e598e1193f6d8b7eb52cd791837569657eb946ad1a7fd17", "planned_active_tokens": 65147, "realized_active_tokens": 65147, "cumulative_start": 27530225, "cumulative_end": 27595372, "loss_sum": 26418.295166015625, "token_normalized_loss": 0.40551821520585174, "grad_norm_before_clip": 0.14747321605682373, "learning_rates_at_step": { "lora": 6.62150508933858e-05, "row_tokens": 6.62150508933858e-05 }, "learning_rates_after_step": { "lora": 6.606374490097315e-05, "row_tokens": 6.606374490097315e-05 } }, { "update_id": 421, "row_count": 9, "row_ids_sha256": "4ef4b94e91ed8f4c4a0d826d5ce0a5c68caced570b672456a4d4420001edf255", "input_ids_vector_sha256": "32ca9ffb7f1e52500d49645a86b99a29006d14f8d402de18fa31b67e5cc604ea", "labels_vector_sha256": "44840cf061970547ed9e641d4ebff3ae2a9b5b8e6e85735cae6ea72d4684afc5", "planned_active_tokens": 61226, "realized_active_tokens": 61226, "cumulative_start": 27595372, "cumulative_end": 27656598, "loss_sum": 27967.57208251953, "token_normalized_loss": 0.45679240980171054, "grad_norm_before_clip": 0.16388888657093048, "learning_rates_at_step": { "lora": 6.606374490097315e-05, "row_tokens": 6.606374490097315e-05 }, "learning_rates_after_step": { "lora": 6.589829112016633e-05, "row_tokens": 6.589829112016633e-05 } }, { "update_id": 422, "row_count": 8, "row_ids_sha256": "2127a7372306a069125c4e74bde7668ad28516c9df7b5f5cc7fc43650b9c468a", "input_ids_vector_sha256": "2a942c89271ff0d2cfe265b747932c22b21b424c0865d0641b76e73613af56a4", "labels_vector_sha256": "f582dbb436d994bd255cf93ce5290758b2355056f5f621deca2ebbe04f361282", "planned_active_tokens": 66875, "realized_active_tokens": 66875, "cumulative_start": 27656598, "cumulative_end": 27723473, "loss_sum": 29070.434173583984, "token_normalized_loss": 0.43469808110032127, "grad_norm_before_clip": 0.15523642301559448, "learning_rates_at_step": { "lora": 6.589829112016633e-05, "row_tokens": 6.589829112016633e-05 }, "learning_rates_after_step": { "lora": 6.572631095743485e-05, "row_tokens": 6.572631095743485e-05 } }, { "update_id": 423, "row_count": 10, "row_ids_sha256": "27997e5bb9ddc19415f5e391b041a5122635510d5b0f5cd8097135f78a5bc8c2", "input_ids_vector_sha256": "2d906dfb92492e14cb31ee9039168194dcd0f904c145b9e8d4a93c6150d42dc3", "labels_vector_sha256": "552df3997508aef864339e8ec592676b7012aed6747998b51bb209ea12393855", "planned_active_tokens": 69430, "realized_active_tokens": 69430, "cumulative_start": 27723473, "cumulative_end": 27792903, "loss_sum": 32591.468994140625, "token_normalized_loss": 0.4694147917923178, "grad_norm_before_clip": 0.14514920115470886, "learning_rates_at_step": { "lora": 6.572631095743485e-05, "row_tokens": 6.572631095743485e-05 }, "learning_rates_after_step": { "lora": 6.557435916254712e-05, "row_tokens": 6.557435916254712e-05 } }, { "update_id": 424, "row_count": 8, "row_ids_sha256": "8c34a0405063c4879500b1430d14bb73c00252263d15a385d8460275675f2b3c", "input_ids_vector_sha256": "0bb2cfefe7b2e7ff99d4f6655070f6c05a481aed4fb4cfb11a203bc01da37b6e", "labels_vector_sha256": "399b6c843a4ff9fda84968cefdb34dc7e9ab400723c8fd0a821198ee4bf9dd9f", "planned_active_tokens": 61275, "realized_active_tokens": 61275, "cumulative_start": 27792903, "cumulative_end": 27854178, "loss_sum": 24879.174560546875, "token_normalized_loss": 0.40602488062908, "grad_norm_before_clip": 0.1530352532863617, "learning_rates_at_step": { "lora": 6.557435916254712e-05, "row_tokens": 6.557435916254712e-05 }, "learning_rates_after_step": { "lora": 6.54120071331826e-05, "row_tokens": 6.54120071331826e-05 } }, { "update_id": 425, "row_count": 9, "row_ids_sha256": "5e10e3aa75aefba1e46a700a6241a7007784c088adff45bfa51a4fd93cb1b9d0", "input_ids_vector_sha256": "0eb26ea408f7f60c3513f58533d189a83f1b2e29227958b99f36dfafed308182", "labels_vector_sha256": "702975785d5d8d9f7ba197fd90c545e65d015adeeaf2ddae3e04e675b37f738d", "planned_active_tokens": 65398, "realized_active_tokens": 65398, "cumulative_start": 27854178, "cumulative_end": 27919576, "loss_sum": 30033.116668701172, "token_normalized_loss": 0.45923601132605235, "grad_norm_before_clip": 0.15229016542434692, "learning_rates_at_step": { "lora": 6.54120071331826e-05, "row_tokens": 6.54120071331826e-05 }, "learning_rates_after_step": { "lora": 6.524150298287826e-05, "row_tokens": 6.524150298287826e-05 } }, { "update_id": 426, "row_count": 8, "row_ids_sha256": "35e91c751ff71a923f81f3497e1cc0ce72007c6dcc46972d799b81457a1e98a6", "input_ids_vector_sha256": "aadba58bca77d30fa6a0a5f12d5163e638abd9da3bbd3462311d4d2c366bbc16", "labels_vector_sha256": "f05aea7e750a7c684faf2e8bfeef026458d6bd61c2c967dcf422feef0dfd0149", "planned_active_tokens": 68604, "realized_active_tokens": 68604, "cumulative_start": 27919576, "cumulative_end": 27988180, "loss_sum": 31072.22674560547, "token_normalized_loss": 0.45292150232647466, "grad_norm_before_clip": 0.14819307625293732, "learning_rates_at_step": { "lora": 6.524150298287826e-05, "row_tokens": 6.524150298287826e-05 }, "learning_rates_after_step": { "lora": 6.508849828550461e-05, "row_tokens": 6.508849828550461e-05 } }, { "update_id": 427, "row_count": 8, "row_ids_sha256": "4fb7af343b72cf99db6e884d691f1a4b9ba2722685af48165011bfefdaaf4ad7", "input_ids_vector_sha256": "2aafd061580c54d95f172536d328968a94e58761a1f4264df7cb9d66193242e3", "labels_vector_sha256": "441640ca38afb3a31fc04719bac2231d1ac7bb8b071576d644641a9a728db4e8", "planned_active_tokens": 61496, "realized_active_tokens": 61496, "cumulative_start": 27988180, "cumulative_end": 28049676, "loss_sum": 24525.47412109375, "token_normalized_loss": 0.3988141362217665, "grad_norm_before_clip": 0.15431828796863556, "learning_rates_at_step": { "lora": 6.508849828550461e-05, "row_tokens": 6.508849828550461e-05 }, "learning_rates_after_step": { "lora": 6.490691102917383e-05, "row_tokens": 6.490691102917383e-05 } }, { "update_id": 428, "row_count": 10, "row_ids_sha256": "d36bf44d6e68ec7ca457e22f7484474b78fdf6f5a7c16cf0282655b609d7c261", "input_ids_vector_sha256": "7e35d6717f04fdb62ba55688461605b6967f9826f9d9dd29881fdf685ba23a13", "labels_vector_sha256": "da5b83a81639d533902bf03762296746ee811cee4531300ec9c3ebc9eec02afc", "planned_active_tokens": 72903, "realized_active_tokens": 72903, "cumulative_start": 28049676, "cumulative_end": 28122579, "loss_sum": 31703.67999267578, "token_normalized_loss": 0.43487483358264795, "grad_norm_before_clip": 0.14550860226154327, "learning_rates_at_step": { "lora": 6.490691102917383e-05, "row_tokens": 6.490691102917383e-05 }, "learning_rates_after_step": { "lora": 6.476204034813041e-05, "row_tokens": 6.476204034813041e-05 } }, { "update_id": 429, "row_count": 8, "row_ids_sha256": "8ff6dc110010dca8df540f45498adb768b25b018c077f32171c10d9dfd96c511", "input_ids_vector_sha256": "71e5095321cbaff17b043cfbed0f91dfbaf05efe931aa35af56edbdce4a7e3c9", "labels_vector_sha256": "aaff42d15c9716aabbaac378dab43a13f97b57e36efb6867e45c82bb9a49a753", "planned_active_tokens": 58100, "realized_active_tokens": 58100, "cumulative_start": 28122579, "cumulative_end": 28180679, "loss_sum": 26161.51300048828, "token_normalized_loss": 0.45028421687587405, "grad_norm_before_clip": 0.15726570785045624, "learning_rates_at_step": { "lora": 6.476204034813041e-05, "row_tokens": 6.476204034813041e-05 }, "learning_rates_after_step": { "lora": 6.459329576278022e-05, "row_tokens": 6.459329576278022e-05 } }, { "update_id": 430, "row_count": 9, "row_ids_sha256": "d8e7c2dc2bcfdaaa4e7281a01d26398a91c2b00cb89e5c6e0ffd4d8c29164a5e", "input_ids_vector_sha256": "f39a183a106d4b8296a96d2655a962178c70b92344c9da543a7b60ee7ccd0313", "labels_vector_sha256": "56ebad62adb9704b7835b9a38458a7c30e4169061ebb7f838be983619dbeed90", "planned_active_tokens": 67606, "realized_active_tokens": 67606, "cumulative_start": 28180679, "cumulative_end": 28248285, "loss_sum": 31032.770935058594, "token_normalized_loss": 0.4590239170348578, "grad_norm_before_clip": 0.15417563915252686, "learning_rates_at_step": { "lora": 6.459329576278022e-05, "row_tokens": 6.459329576278022e-05 }, "learning_rates_after_step": { "lora": 6.443087172021715e-05, "row_tokens": 6.443087172021715e-05 } }, { "update_id": 431, "row_count": 10, "row_ids_sha256": "856a2330371d4008f455b0a9d13827dd6a3992998b5f6b8c3355ae62d2cbb0c1", "input_ids_vector_sha256": "2488b5fe9a37bb043ccfe983a7f62e52a89b5ffbdc0e0b343e8037fda4f766bd", "labels_vector_sha256": "7bc08e0b99addd3150cfc3ca80060b059234ff0887189c9ef300e41afcfadbf2", "planned_active_tokens": 65005, "realized_active_tokens": 65005, "cumulative_start": 28248285, "cumulative_end": 28313290, "loss_sum": 25262.921325683594, "token_normalized_loss": 0.38863043343871384, "grad_norm_before_clip": 0.1500575691461563, "learning_rates_at_step": { "lora": 6.443087172021715e-05, "row_tokens": 6.443087172021715e-05 }, "learning_rates_after_step": { "lora": 6.425160408290634e-05, "row_tokens": 6.425160408290634e-05 } }, { "update_id": 432, "row_count": 9, "row_ids_sha256": "b8fef3f25a80177370274e46527cb147b7c56ec58121dcd5bb7bdbcc5ca2176b", "input_ids_vector_sha256": "69e764d8c648249091f9a2bb699ec314dd448d2637f8372729c64f05360f7271", "labels_vector_sha256": "426168a496b4567633bf69995e50f156cf5515f840abaa2a6c59accc7cb0bd6e", "planned_active_tokens": 71669, "realized_active_tokens": 71669, "cumulative_start": 28313290, "cumulative_end": 28384959, "loss_sum": 29289.238525390625, "token_normalized_loss": 0.40867374353473085, "grad_norm_before_clip": 0.14423595368862152, "learning_rates_at_step": { "lora": 6.425160408290634e-05, "row_tokens": 6.425160408290634e-05 }, "learning_rates_after_step": { "lora": 6.40985200478896e-05, "row_tokens": 6.40985200478896e-05 } }, { "update_id": 433, "row_count": 11, "row_ids_sha256": "15ebc50965ff083450901e3029c59968870540cdc383f88f2d4f2945db4d3357", "input_ids_vector_sha256": "e0231b3dc2cdc5708dc31483064e1b9374f10566369a36fed0734fea0a4c9abc", "labels_vector_sha256": "ba2e57671775e4911317f88088213ec812cc5eef19f51edbd516061c866ce8cc", "planned_active_tokens": 61138, "realized_active_tokens": 61138, "cumulative_start": 28384959, "cumulative_end": 28446097, "loss_sum": 24014.930297851562, "token_normalized_loss": 0.39279875523981095, "grad_norm_before_clip": 0.15034852921962738, "learning_rates_at_step": { "lora": 6.40985200478896e-05, "row_tokens": 6.40985200478896e-05 }, "learning_rates_after_step": { "lora": 6.394132801489114e-05, "row_tokens": 6.394132801489114e-05 } }, { "update_id": 434, "row_count": 9, "row_ids_sha256": "709c984532873b12aa8ff134f7d574a69575610dc857be24e3d5489c5fd568a3", "input_ids_vector_sha256": "248c45c943e1298740137b8c8260c53e1bb690bdea237ecb82597ec7208b1944", "labels_vector_sha256": "d731689c348454cbefcee9e171d44a6c6c60232db9316abdaa9520a0a6d0d1f0", "planned_active_tokens": 62719, "realized_active_tokens": 62719, "cumulative_start": 28446097, "cumulative_end": 28508816, "loss_sum": 27418.816833496094, "token_normalized_loss": 0.4371692283597649, "grad_norm_before_clip": 0.1606661081314087, "learning_rates_at_step": { "lora": 6.394132801489114e-05, "row_tokens": 6.394132801489114e-05 }, "learning_rates_after_step": { "lora": 6.377338947507402e-05, "row_tokens": 6.377338947507402e-05 } }, { "update_id": 435, "row_count": 9, "row_ids_sha256": "31c1b0bd1044fd31841f3da5fd7df9c216e9618b4932121197c000b0f09a5d21", "input_ids_vector_sha256": "7700f59308edbabe4203b18251d366241e72dde0018f0133385f36d6cb541315", "labels_vector_sha256": "d34a89b991edd40b30cd10958a7471530eec52307334c6bf2ce96b8935e790da", "planned_active_tokens": 66941, "realized_active_tokens": 66941, "cumulative_start": 28508816, "cumulative_end": 28575757, "loss_sum": 28682.422729492188, "token_normalized_loss": 0.42847317383206385, "grad_norm_before_clip": 0.15542973577976227, "learning_rates_at_step": { "lora": 6.377338947507402e-05, "row_tokens": 6.377338947507402e-05 }, "learning_rates_after_step": { "lora": 6.360993071564727e-05, "row_tokens": 6.360993071564727e-05 } }, { "update_id": 436, "row_count": 9, "row_ids_sha256": "69530ca67a4e5a8224d12d5533088609fe5c7db3d73829c5be33dfddce1cdc97", "input_ids_vector_sha256": "801ddaa20413e00186610dd7c691e75c7e78edfc717108a156a38b078a52b1e2", "labels_vector_sha256": "0caae815f6b826153b46319d0425e7872fe830db049e35d78d5c353478bb1d58", "planned_active_tokens": 65091, "realized_active_tokens": 65091, "cumulative_start": 28575757, "cumulative_end": 28640848, "loss_sum": 27251.492401123047, "token_normalized_loss": 0.41866759461558506, "grad_norm_before_clip": 0.17904725670814514, "learning_rates_at_step": { "lora": 6.360993071564727e-05, "row_tokens": 6.360993071564727e-05 }, "learning_rates_after_step": { "lora": 6.344665421303508e-05, "row_tokens": 6.344665421303508e-05 } }, { "update_id": 437, "row_count": 10, "row_ids_sha256": "1cd33b529285be9b0343f007e7e2e719968232f52c100bb6fe645912994113c5", "input_ids_vector_sha256": "676628afc6699a7dca2b15c4e84180143a13bec39d7ad80976c3ec9b7c44c6ca", "labels_vector_sha256": "149ff8464ed92e59fe3638ed6bbf9ff038964f3119a0ff0356c52c043cf5cf55", "planned_active_tokens": 64956, "realized_active_tokens": 64956, "cumulative_start": 28640848, "cumulative_end": 28705804, "loss_sum": 24807.08221435547, "token_normalized_loss": 0.3819059396261387, "grad_norm_before_clip": 0.13855944573879242, "learning_rates_at_step": { "lora": 6.344665421303508e-05, "row_tokens": 6.344665421303508e-05 }, "learning_rates_after_step": { "lora": 6.325529986313542e-05, "row_tokens": 6.325529986313542e-05 } }, { "update_id": 438, "row_count": 11, "row_ids_sha256": "24b68c646de5371071653980efe4f91f43a6074973e6ceddf95ee4839305223d", "input_ids_vector_sha256": "e65f03241033a86380e8fe5ad8fac47671ccd9cca027cb336c35b5e439101b50", "labels_vector_sha256": "620e982ea338650045ca1836ed830cec22278b9f5c48a0f4310507093a9bfaf7", "planned_active_tokens": 76048, "realized_active_tokens": 76048, "cumulative_start": 28705804, "cumulative_end": 28781852, "loss_sum": 34082.989318847656, "token_normalized_loss": 0.4481773264102627, "grad_norm_before_clip": 0.14070257544517517, "learning_rates_at_step": { "lora": 6.325529986313542e-05, "row_tokens": 6.325529986313542e-05 }, "learning_rates_after_step": { "lora": 6.311058596512627e-05, "row_tokens": 6.311058596512627e-05 } }, { "update_id": 439, "row_count": 7, "row_ids_sha256": "656d586f25c761fd3eb971b7eeda0336b00319db10cb2b36eefd1b104ca6ad3b", "input_ids_vector_sha256": "be4ae3eab87bfa1338802012205f407030cc98e57e7da6648f0fdee62f3e5f02", "labels_vector_sha256": "a24442e66cb532774e1240269ffe6a5827ac7247bda4a224dc304d767870d94b", "planned_active_tokens": 57457, "realized_active_tokens": 57457, "cumulative_start": 28781852, "cumulative_end": 28839309, "loss_sum": 24919.16943359375, "token_normalized_loss": 0.4337011927805794, "grad_norm_before_clip": 0.16830380260944366, "learning_rates_at_step": { "lora": 6.311058596512627e-05, "row_tokens": 6.311058596512627e-05 }, "learning_rates_after_step": { "lora": 6.295029774645577e-05, "row_tokens": 6.295029774645577e-05 } }, { "update_id": 440, "row_count": 11, "row_ids_sha256": "1c349a4b8c4d321da8e4460685fec9f2292a57d2c6d0a8a6878925a44834086c", "input_ids_vector_sha256": "ec3522b5009f16bcf6fcda242c2e571ee1d7a3a2fc474772740ae637cc16ea14", "labels_vector_sha256": "ad6ff12f81bcdf9b182ac093a238558d17fd73b0841f533f3c29ebe290ef5bfc", "planned_active_tokens": 63586, "realized_active_tokens": 63586, "cumulative_start": 28839309, "cumulative_end": 28902895, "loss_sum": 26330.975952148438, "token_normalized_loss": 0.4141002099856641, "grad_norm_before_clip": 0.15080220997333527, "learning_rates_at_step": { "lora": 6.295029774645577e-05, "row_tokens": 6.295029774645577e-05 }, "learning_rates_after_step": { "lora": 6.277226486293366e-05, "row_tokens": 6.277226486293366e-05 } }, { "update_id": 441, "row_count": 12, "row_ids_sha256": "c029ecb597928cb7ac2200d5d5c46e9593808f19ba8311aaa7bfcece46982985", "input_ids_vector_sha256": "bd6a4ed4b3295d732f591896b7b752c3bcd09b67395c55ffc5b17f545651eb9b", "labels_vector_sha256": "cb84562eb4f06bae00b6443a671b8546a4213af0eaa0d3aa880854a86087f752", "planned_active_tokens": 70559, "realized_active_tokens": 70559, "cumulative_start": 28902895, "cumulative_end": 28973454, "loss_sum": 28230.176696777344, "token_normalized_loss": 0.4000932084748557, "grad_norm_before_clip": 0.13229000568389893, "learning_rates_at_step": { "lora": 6.277226486293366e-05, "row_tokens": 6.277226486293366e-05 }, "learning_rates_after_step": { "lora": 6.2603996420757e-05, "row_tokens": 6.2603996420757e-05 } }, { "update_id": 442, "row_count": 11, "row_ids_sha256": "d4cf4ed2615a1de92a0a3e23397e499a0c3832be397914976d0ed1cfc017d4e6", "input_ids_vector_sha256": "a6d91b3df865652f5c3eb6fe3fa6a04a5e77122131843d8105f3de3e0facf9f0", "labels_vector_sha256": "2c2391ed7e8f93b6273c702e6d3cdd83964800165c53d1fe4a829b1d063c8f49", "planned_active_tokens": 66626, "realized_active_tokens": 66626, "cumulative_start": 28973454, "cumulative_end": 29040080, "loss_sum": 28100.43634033203, "token_normalized_loss": 0.42176382103581234, "grad_norm_before_clip": 0.14393147826194763, "learning_rates_at_step": { "lora": 6.2603996420757e-05, "row_tokens": 6.2603996420757e-05 }, "learning_rates_after_step": { "lora": 6.24493149173969e-05, "row_tokens": 6.24493149173969e-05 } }, { "update_id": 443, "row_count": 13, "row_ids_sha256": "07837aacbf1f92e1a980a95da9c1a0773e1444d4ba3301d41ef825d173656a62", "input_ids_vector_sha256": "e26feddeb2e266d2fa904529fc562326f6c096eb08292c16743cdcc73113edf8", "labels_vector_sha256": "ee64cf7ae2b2f3a03faf0ea568f8cf41a9f80dbc63d06c394a41702470c882c8", "planned_active_tokens": 61193, "realized_active_tokens": 61193, "cumulative_start": 29040080, "cumulative_end": 29101273, "loss_sum": 25137.743118286133, "token_normalized_loss": 0.41079442286349965, "grad_norm_before_clip": 0.15137583017349243, "learning_rates_at_step": { "lora": 6.24493149173969e-05, "row_tokens": 6.24493149173969e-05 }, "learning_rates_after_step": { "lora": 6.228714130778372e-05, "row_tokens": 6.228714130778372e-05 } }, { "update_id": 444, "row_count": 15, "row_ids_sha256": "3c23c0c0fc7cbf1eec4625835c529790fe1c033116b8c4675737a22fbfa03f8b", "input_ids_vector_sha256": "99589dae7e7310845b86b9424695b0b2660ee0c1e5b54c3857fea361cb0a1c1b", "labels_vector_sha256": "137f24f7d6687ed0a433d3d219fd23aec05cf00e91d523829ed7d8179dc78681", "planned_active_tokens": 64103, "realized_active_tokens": 64103, "cumulative_start": 29101273, "cumulative_end": 29165376, "loss_sum": 21899.52178955078, "token_normalized_loss": 0.34163021683151773, "grad_norm_before_clip": 0.12933123111724854, "learning_rates_at_step": { "lora": 6.228714130778372e-05, "row_tokens": 6.228714130778372e-05 }, "learning_rates_after_step": { "lora": 6.211128250086016e-05, "row_tokens": 6.211128250086016e-05 } }, { "update_id": 445, "row_count": 16, "row_ids_sha256": "ce64d86e3da7d0482b5e23b9d0e3cdcaca73bffe361df766d4377af657f663e6", "input_ids_vector_sha256": "71943aae92d47dbc790b3bea2352544a86f1ebc64e88085633617162e3a6eb0e", "labels_vector_sha256": "ca393bf74db1601d78bac3fd03b40013bc7518b0cb89b4e211562977b127ce67", "planned_active_tokens": 69451, "realized_active_tokens": 69451, "cumulative_start": 29165376, "cumulative_end": 29234827, "loss_sum": 29679.87094116211, "token_normalized_loss": 0.4273497997316397, "grad_norm_before_clip": 0.14621159434318542, "learning_rates_at_step": { "lora": 6.211128250086016e-05, "row_tokens": 6.211128250086016e-05 }, "learning_rates_after_step": { "lora": 6.19545032595045e-05, "row_tokens": 6.19545032595045e-05 } }, { "update_id": 446, "row_count": 11, "row_ids_sha256": "167920f9938fa817e1df916b808b9435a2f205a6f9368c28b17c1926d38149b2", "input_ids_vector_sha256": "1e3a6a059272af63e6d478ff542496c9146a7c8df8138eb04ac29d65ee14166c", "labels_vector_sha256": "f2d28d3946748cc9860ad411a00f448bb0754d9299e0f1bf15a7c54de07290f4", "planned_active_tokens": 61863, "realized_active_tokens": 61863, "cumulative_start": 29234827, "cumulative_end": 29296690, "loss_sum": 23630.185302734375, "token_normalized_loss": 0.38197606489718205, "grad_norm_before_clip": 0.1409195363521576, "learning_rates_at_step": { "lora": 6.19545032595045e-05, "row_tokens": 6.19545032595045e-05 }, "learning_rates_after_step": { "lora": 6.179001508272739e-05, "row_tokens": 6.179001508272739e-05 } }, { "update_id": 447, "row_count": 12, "row_ids_sha256": "bc56b130b3389a5cb174a89ef07438edbe527176c6bef62804efe62168703732", "input_ids_vector_sha256": "49f53c6b60d0c9fa5ed6b053bb07783c2bc14d91b5bf279d7d0f95d8139b8892", "labels_vector_sha256": "b38a61af1464da95e527bbd52ad2c5421bf928991143486915e306089cb86f31", "planned_active_tokens": 64852, "realized_active_tokens": 64852, "cumulative_start": 29296690, "cumulative_end": 29361542, "loss_sum": 23906.440887451172, "token_normalized_loss": 0.3686307421120578, "grad_norm_before_clip": 0.13848070800304413, "learning_rates_at_step": { "lora": 6.179001508272739e-05, "row_tokens": 6.179001508272739e-05 }, "learning_rates_after_step": { "lora": 6.16207875541478e-05, "row_tokens": 6.16207875541478e-05 } }, { "update_id": 448, "row_count": 12, "row_ids_sha256": "57b72595261fc458c504fe080aed11e7ee5add80a87ad972aa3f9e1cec096cc2", "input_ids_vector_sha256": "e96fc8d8256ecbb81f909e15e66829f279befb95f18057cfc3124f83a5e390c9", "labels_vector_sha256": "2a615aa4bd15c222da6ce616400b9dce10435e0ab530d078472adde77bd35104", "planned_active_tokens": 66665, "realized_active_tokens": 66665, "cumulative_start": 29361542, "cumulative_end": 29428207, "loss_sum": 27125.420349121094, "token_normalized_loss": 0.4068914775237545, "grad_norm_before_clip": 0.13854286074638367, "learning_rates_at_step": { "lora": 6.16207875541478e-05, "row_tokens": 6.16207875541478e-05 }, "learning_rates_after_step": { "lora": 6.144861828772882e-05, "row_tokens": 6.144861828772882e-05 } }, { "update_id": 449, "row_count": 15, "row_ids_sha256": "9220b48a41c6a22559aac1dce999b0c53fa52ce9efdbbfd455ded476cb8c30c1", "input_ids_vector_sha256": "833ee824e86b058cc41f7c5105a3fac52bc57e9544c3d63adc47864ae42aafc0", "labels_vector_sha256": "5fc92ace0a717b9599ccedae472b2e701c91beb39cf34b8e4b5c018d9eeefb42", "planned_active_tokens": 67767, "realized_active_tokens": 67767, "cumulative_start": 29428207, "cumulative_end": 29495974, "loss_sum": 29416.544372558594, "token_normalized_loss": 0.4340836155143151, "grad_norm_before_clip": 0.15054666996002197, "learning_rates_at_step": { "lora": 6.144861828772882e-05, "row_tokens": 6.144861828772882e-05 }, "learning_rates_after_step": { "lora": 6.128599463965239e-05, "row_tokens": 6.128599463965239e-05 } }, { "update_id": 450, "row_count": 12, "row_ids_sha256": "74174d769ce07c4b00eb416caed2b86401422bf3e361bca186e09d8c68e871d4", "input_ids_vector_sha256": "e972b4ff355aed9320fe59243fb1bfd3724efab653aa418333b17cb82b54e177", "labels_vector_sha256": "7de3acd3253b10a92482985efe8fb17977d5eccd042b9be45309f5eb0d66eee9", "planned_active_tokens": 63958, "realized_active_tokens": 63958, "cumulative_start": 29495974, "cumulative_end": 29559932, "loss_sum": 23649.698028564453, "token_normalized_loss": 0.369769192729048, "grad_norm_before_clip": 0.1408027708530426, "learning_rates_at_step": { "lora": 6.128599463965239e-05, "row_tokens": 6.128599463965239e-05 }, "learning_rates_after_step": { "lora": 6.112692091849901e-05, "row_tokens": 6.112692091849901e-05 } }, { "update_id": 451, "row_count": 11, "row_ids_sha256": "e2fac06b98b1ca23b4bccf210ef677edc56c4bca10e2af0c34505ad1ff00f62b", "input_ids_vector_sha256": "28a540dbdb0300504bb027a01b293c5b5e3d657a96aae7de2379e126f833a990", "labels_vector_sha256": "26497f458c5f6250967ec60ae5f491f5ee276b70bc4a2a2a836d914a8231ef69", "planned_active_tokens": 62514, "realized_active_tokens": 62514, "cumulative_start": 29559932, "cumulative_end": 29622446, "loss_sum": 26179.141662597656, "token_normalized_loss": 0.4187724615701708, "grad_norm_before_clip": 0.15744639933109283, "learning_rates_at_step": { "lora": 6.112692091849901e-05, "row_tokens": 6.112692091849901e-05 }, "learning_rates_after_step": { "lora": 6.0950601462555655e-05, "row_tokens": 6.0950601462555655e-05 } }, { "update_id": 452, "row_count": 17, "row_ids_sha256": "7be57009f6425afc5899db358339155f08ed820bc70de28948a4f6a26e2db2ce", "input_ids_vector_sha256": "e14f3a27bd23934bf61a083f7bb7520cf4285ca370a9ec6a958b0d3abdb9fa44", "labels_vector_sha256": "24cb6b995cd9e5dae2f8f8cfc47355b84546af16f69a454202d0e2eb523c7c1d", "planned_active_tokens": 69237, "realized_active_tokens": 69237, "cumulative_start": 29622446, "cumulative_end": 29691683, "loss_sum": 24510.523071289062, "token_normalized_loss": 0.3540090279949891, "grad_norm_before_clip": 0.15471547842025757, "learning_rates_at_step": { "lora": 6.0950601462555655e-05, "row_tokens": 6.0950601462555655e-05 }, "learning_rates_after_step": { "lora": 6.076544931356316e-05, "row_tokens": 6.076544931356316e-05 } }, { "update_id": 453, "row_count": 11, "row_ids_sha256": "a63fd82ae9a595aad9f3dd0131deae5bdf1d6d9fb6093af2efbcc0d6f56c3cfa", "input_ids_vector_sha256": "b7e7580e0c6488f68ceab4f88e47696fcbdb543d0aaa467321dd087e39032885", "labels_vector_sha256": "9d261473d459aa8d7a1ed966f21e122eeab8cb7fb5ac7093880a0c8ef608aa3f", "planned_active_tokens": 72645, "realized_active_tokens": 72645, "cumulative_start": 29691683, "cumulative_end": 29764328, "loss_sum": 32744.328033447266, "token_normalized_loss": 0.45074441507945856, "grad_norm_before_clip": 0.1397392600774765, "learning_rates_at_step": { "lora": 6.076544931356316e-05, "row_tokens": 6.076544931356316e-05 }, "learning_rates_after_step": { "lora": 6.0622283124703413e-05, "row_tokens": 6.0622283124703413e-05 } }, { "update_id": 454, "row_count": 7, "row_ids_sha256": "573ae28686f7b41a9b0a98ffd4d2339b2d5aa0a81f7eba350b7a937661c3ba77", "input_ids_vector_sha256": "a2acf527eef259498564475af41da185d483fca982d11fffa28385a8026a256c", "labels_vector_sha256": "762e843d1a200f018dc2b65ecf19db4c8af61113cb4dfc6a290d589747c55ca7", "planned_active_tokens": 56130, "realized_active_tokens": 56130, "cumulative_start": 29764328, "cumulative_end": 29820458, "loss_sum": 26633.205474853516, "token_normalized_loss": 0.4744914568831911, "grad_norm_before_clip": 0.1608792394399643, "learning_rates_at_step": { "lora": 6.0622283124703413e-05, "row_tokens": 6.0622283124703413e-05 }, "learning_rates_after_step": { "lora": 6.045040164004033e-05, "row_tokens": 6.045040164004033e-05 } }, { "update_id": 455, "row_count": 15, "row_ids_sha256": "2202eb9479d6bd74f4a92ea523c235143ef973a86f76902c985aed624bed3236", "input_ids_vector_sha256": "fd7466086fdb0c88ec97874414410fddfd2697ee00322bbd8ff5b73c0e360208", "labels_vector_sha256": "1f8f1e3e13164dea7f4cf653c7496fa2ff2556108950714236be2dce8f227bd6", "planned_active_tokens": 67341, "realized_active_tokens": 67341, "cumulative_start": 29820458, "cumulative_end": 29887799, "loss_sum": 29002.68051147461, "token_normalized_loss": 0.4306838406242053, "grad_norm_before_clip": 0.14049233496189117, "learning_rates_at_step": { "lora": 6.045040164004033e-05, "row_tokens": 6.045040164004033e-05 }, "learning_rates_after_step": { "lora": 6.028739552843312e-05, "row_tokens": 6.028739552843312e-05 } }, { "update_id": 456, "row_count": 14, "row_ids_sha256": "e030a79bd0f0e3b7bde613026d5c4f3b8b4a86a06343326e7921453277a96d4c", "input_ids_vector_sha256": "a14232aac40221388068633ffce1523556299fab797874f1c8849b060a918d56", "labels_vector_sha256": "639c32bf06657e8356721a827f8a1db5e71d77d199ff072f0ab3bfbc95a44157", "planned_active_tokens": 63817, "realized_active_tokens": 63817, "cumulative_start": 29887799, "cumulative_end": 29951616, "loss_sum": 26545.72052001953, "token_normalized_loss": 0.4159662867264135, "grad_norm_before_clip": 0.1524667739868164, "learning_rates_at_step": { "lora": 6.028739552843312e-05, "row_tokens": 6.028739552843312e-05 }, "learning_rates_after_step": { "lora": 6.0120774674225355e-05, "row_tokens": 6.0120774674225355e-05 } }, { "update_id": 457, "row_count": 9, "row_ids_sha256": "9c32b623b2e8d72849ce0a3620609ddc0a5e94747fbd717ea4a556f55f2225bb", "input_ids_vector_sha256": "8300d854162d2e43cfa113caf01a390d6e1cd1e813ca5544516ce510e3ff2abe", "labels_vector_sha256": "0ec29f423ef1e09dc09ff61395410d17c8915fc91b9934687eddfc9569de9522", "planned_active_tokens": 65186, "realized_active_tokens": 65186, "cumulative_start": 29951616, "cumulative_end": 30016802, "loss_sum": 29039.027221679688, "token_normalized_loss": 0.4454795082023699, "grad_norm_before_clip": 0.14629115164279938, "learning_rates_at_step": { "lora": 6.0120774674225355e-05, "row_tokens": 6.0120774674225355e-05 }, "learning_rates_after_step": { "lora": 5.994906223989114e-05, "row_tokens": 5.994906223989114e-05 } }, { "update_id": 458, "row_count": 8, "row_ids_sha256": "a0400a45f7c82acf5014a1bcf513581566eca9910dbe3d1dd6753cda514268d5", "input_ids_vector_sha256": "4cac6bd4db83121d3894e0141a1aff10b760761ae14babe1c93391c9b937b13b", "labels_vector_sha256": "68c4d6c49805a80d44a27b01f5428fb20d971b066128a3d423a5af4497b118da", "planned_active_tokens": 67130, "realized_active_tokens": 67130, "cumulative_start": 30016802, "cumulative_end": 30083932, "loss_sum": 29644.70361328125, "token_normalized_loss": 0.44160142430033145, "grad_norm_before_clip": 0.45057395100593567, "learning_rates_at_step": { "lora": 5.994906223989114e-05, "row_tokens": 5.994906223989114e-05 }, "learning_rates_after_step": { "lora": 5.978406945044195e-05, "row_tokens": 5.978406945044195e-05 } }, { "update_id": 459, "row_count": 14, "row_ids_sha256": "6649a001ca43940dca3775c2151faa3021ca892457cbfc93a2598e218c709488", "input_ids_vector_sha256": "c421c2a8d33095f8057854cb509e266e0b6ba3914777c75b50153e84810f94e2", "labels_vector_sha256": "16e5198b3fc3debbf280df40631197a2ef15496215648cb39b065897ecc96a31", "planned_active_tokens": 64458, "realized_active_tokens": 64458, "cumulative_start": 30083932, "cumulative_end": 30148390, "loss_sum": 26471.488037109375, "token_normalized_loss": 0.4106780855302581, "grad_norm_before_clip": 0.1435604691505432, "learning_rates_at_step": { "lora": 5.978406945044195e-05, "row_tokens": 5.978406945044195e-05 }, "learning_rates_after_step": { "lora": 5.9618873563544754e-05, "row_tokens": 5.9618873563544754e-05 } }, { "update_id": 460, "row_count": 14, "row_ids_sha256": "2fbcd5b3e5718ecf334b5ae790469d90732f7020a7bc1a4b14d9c7fb6b44782b", "input_ids_vector_sha256": "3f0d689f50ae1b5f5fe6757b67d08f9e7d9dd315c3b7429defb08c416665eb84", "labels_vector_sha256": "ef00df012f0bb63281afd3b2d720bdd53bb31286a2c20b2e64ee5da5ac60b026", "planned_active_tokens": 64494, "realized_active_tokens": 64494, "cumulative_start": 30148390, "cumulative_end": 30212884, "loss_sum": 28049.780334472656, "token_normalized_loss": 0.4349207730094684, "grad_norm_before_clip": 0.1441393792629242, "learning_rates_at_step": { "lora": 5.9618873563544754e-05, "row_tokens": 5.9618873563544754e-05 }, "learning_rates_after_step": { "lora": 5.9445089471223816e-05, "row_tokens": 5.9445089471223816e-05 } }, { "update_id": 461, "row_count": 11, "row_ids_sha256": "ac8ee29188cfde8add8fa049669ba265a58ba38efc7d3c202b3419e0bb926a4e", "input_ids_vector_sha256": "87a235a8624fb9901c046953bc0da98ca3f25a7ecf1154b9ca881c021321ef71", "labels_vector_sha256": "c2fe35b52280c24abe30ec3809f471236d3f85f4cc426cbb0acd4a851d83e79a", "planned_active_tokens": 67801, "realized_active_tokens": 67801, "cumulative_start": 30212884, "cumulative_end": 30280685, "loss_sum": 31956.251068115234, "token_normalized_loss": 0.4713241850137201, "grad_norm_before_clip": 0.1417786180973053, "learning_rates_at_step": { "lora": 5.9445089471223816e-05, "row_tokens": 5.9445089471223816e-05 }, "learning_rates_after_step": { "lora": 5.9277224134586184e-05, "row_tokens": 5.9277224134586184e-05 } }, { "update_id": 462, "row_count": 11, "row_ids_sha256": "6c5b559407e07db2dd4d362fa446a54043ee5cf38309c6d152fc74f647cc1518", "input_ids_vector_sha256": "dacadaa070671b3055aab9ab1bd88d1db735b36b479a354177c11c6912e6972d", "labels_vector_sha256": "d5ca7426412baf20e8508b91b534f45b650a2cd04dd9316d3318f8837471560f", "planned_active_tokens": 65448, "realized_active_tokens": 65448, "cumulative_start": 30280685, "cumulative_end": 30346133, "loss_sum": 28399.365142822266, "token_normalized_loss": 0.43392258194020084, "grad_norm_before_clip": 0.13956861197948456, "learning_rates_at_step": { "lora": 5.9277224134586184e-05, "row_tokens": 5.9277224134586184e-05 }, "learning_rates_after_step": { "lora": 5.9115879218759496e-05, "row_tokens": 5.9115879218759496e-05 } }, { "update_id": 463, "row_count": 12, "row_ids_sha256": "d89e5b8bf0e729203af14d6588db54936e1b1e2a5a46374c007ab47616b602e0", "input_ids_vector_sha256": "4318ca86d2db821531ae955e4e8fe9d46e6183cccaf035456eb3dc13a878dda3", "labels_vector_sha256": "92366129971bb90a0a34c893eb7dd875aaf6c60cd34acee6616a9f52f193460c", "planned_active_tokens": 62866, "realized_active_tokens": 62866, "cumulative_start": 30346133, "cumulative_end": 30408999, "loss_sum": 23365.49560546875, "token_normalized_loss": 0.37167142184119795, "grad_norm_before_clip": 0.13853970170021057, "learning_rates_at_step": { "lora": 5.9115879218759496e-05, "row_tokens": 5.9115879218759496e-05 }, "learning_rates_after_step": { "lora": 5.894778528890155e-05, "row_tokens": 5.894778528890155e-05 } }, { "update_id": 464, "row_count": 13, "row_ids_sha256": "c208b10722d07a510aea5aa61ff7f8206dfabf4f13e7112ba0c4b0841b0d7810", "input_ids_vector_sha256": "c489ce227a8b5b521756d779edd3c3149a1776f7b762ee916a56318cd07b9ecb", "labels_vector_sha256": "6535f45bfced258e54b1772eed1e027b5856d07632cec43c28994820e6cb4c5e", "planned_active_tokens": 65455, "realized_active_tokens": 65455, "cumulative_start": 30408999, "cumulative_end": 30474454, "loss_sum": 28469.237228393555, "token_normalized_loss": 0.4349436594361554, "grad_norm_before_clip": 0.14333468675613403, "learning_rates_at_step": { "lora": 5.894778528890155e-05, "row_tokens": 5.894778528890155e-05 }, "learning_rates_after_step": { "lora": 5.87586289843974e-05, "row_tokens": 5.87586289843974e-05 } }, { "update_id": 465, "row_count": 15, "row_ids_sha256": "15006576b3bc04b23b0003801308c804cdc871b9fde4fcc5b39a9c31b2bcd731", "input_ids_vector_sha256": "299a2c998172493e11ea63079a02ba252db95e47698aa4bb260f5d819dbf0da6", "labels_vector_sha256": "118163ea92728db3b85fa531c072ee44365834865487b47a1a7065f8b124c6f0", "planned_active_tokens": 73608, "realized_active_tokens": 73608, "cumulative_start": 30474454, "cumulative_end": 30548062, "loss_sum": 27730.20590209961, "token_normalized_loss": 0.37672815321839487, "grad_norm_before_clip": 0.12669222056865692, "learning_rates_at_step": { "lora": 5.87586289843974e-05, "row_tokens": 5.87586289843974e-05 }, "learning_rates_after_step": { "lora": 5.860092290528516e-05, "row_tokens": 5.860092290528516e-05 } }, { "update_id": 466, "row_count": 11, "row_ids_sha256": "eff7f5630f6c6ce48739dbaa67ce2a4493bbdbc9cc0cf4bc37999b488dee145f", "input_ids_vector_sha256": "5be366b25af310f70d0c7512c6832cfe14f084bd81783d77b7691e8c23bd4a22", "labels_vector_sha256": "98d0096911916d07768fab7e76743b5a352b014b424efc2a838c8f0e1d92041a", "planned_active_tokens": 61331, "realized_active_tokens": 61331, "cumulative_start": 30548062, "cumulative_end": 30609393, "loss_sum": 25061.302185058594, "token_normalized_loss": 0.40862373326798185, "grad_norm_before_clip": 0.14624091982841492, "learning_rates_at_step": { "lora": 5.860092290528516e-05, "row_tokens": 5.860092290528516e-05 }, "learning_rates_after_step": { "lora": 5.8438920830133524e-05, "row_tokens": 5.8438920830133524e-05 } }, { "update_id": 467, "row_count": 9, "row_ids_sha256": "f89936ef9227d36bdd040cb254185f93aba5e986945afc4cbb4cdef06e39a603", "input_ids_vector_sha256": "b5605c497f288d002b85b79165672ea98954996227e81790aca6cbfcb9a337b2", "labels_vector_sha256": "f155a332700563248c8469224a29b6a31043008c64c78ec5493ec33bdfe75306", "planned_active_tokens": 62966, "realized_active_tokens": 62966, "cumulative_start": 30609393, "cumulative_end": 30672359, "loss_sum": 24347.166748046875, "token_normalized_loss": 0.3866716441896718, "grad_norm_before_clip": 0.1389392614364624, "learning_rates_at_step": { "lora": 5.8438920830133524e-05, "row_tokens": 5.8438920830133524e-05 }, "learning_rates_after_step": { "lora": 5.827320187256684e-05, "row_tokens": 5.827320187256684e-05 } }, { "update_id": 468, "row_count": 10, "row_ids_sha256": "5a4536f148d6915a7165344f6c90e36c1e697b38fb80ed064b6e9c1cf81c6b0c", "input_ids_vector_sha256": "902ae1c092a3bbbcceb352ffcac80052128594fe258eb1a05964993dbeb594cd", "labels_vector_sha256": "a6284ec13e7a0fd25637698ce60cc68d9a239ee98235d92fcd3c8d690f133b02", "planned_active_tokens": 64374, "realized_active_tokens": 64374, "cumulative_start": 30672359, "cumulative_end": 30736733, "loss_sum": 27086.344329833984, "token_normalized_loss": 0.4207652830309439, "grad_norm_before_clip": 0.14597275853157043, "learning_rates_at_step": { "lora": 5.827320187256684e-05, "row_tokens": 5.827320187256684e-05 }, "learning_rates_after_step": { "lora": 5.8096570571137186e-05, "row_tokens": 5.8096570571137186e-05 } }, { "update_id": 469, "row_count": 11, "row_ids_sha256": "53ae7728c0135db3b425621a73a98ff1f752f92bb63393a8cdbe21995963a3fb", "input_ids_vector_sha256": "959b99141cea9e03bec50f74985374f753a9df17cedd53d12e974b087ba391ca", "labels_vector_sha256": "9c4990f9be17f3f7bebb9f7c400505ab936bf54005707904f71e550170be5962", "planned_active_tokens": 68573, "realized_active_tokens": 68573, "cumulative_start": 30736733, "cumulative_end": 30805306, "loss_sum": 22724.965270996094, "token_normalized_loss": 0.33139814899444525, "grad_norm_before_clip": 0.12348838150501251, "learning_rates_at_step": { "lora": 5.8096570571137186e-05, "row_tokens": 5.8096570571137186e-05 }, "learning_rates_after_step": { "lora": 5.791286941160517e-05, "row_tokens": 5.791286941160517e-05 } }, { "update_id": 470, "row_count": 11, "row_ids_sha256": "5193632e3a98e123f5a5543ea8841db764f56d1ea08bdc33526374b65ceba4db", "input_ids_vector_sha256": "96f0169e1f2e2d63dec3f401f2b1531cb07ca70fd555bd5283ad4c4dbb2876d0", "labels_vector_sha256": "d0d1108b2d58c573ba601e2e173a936ea4458d47f95b1a7f0845fe3e86638843", "planned_active_tokens": 71275, "realized_active_tokens": 71275, "cumulative_start": 30805306, "cumulative_end": 30876581, "loss_sum": 30958.73162841797, "token_normalized_loss": 0.43435610843097816, "grad_norm_before_clip": 0.13443082571029663, "learning_rates_at_step": { "lora": 5.791286941160517e-05, "row_tokens": 5.791286941160517e-05 }, "learning_rates_after_step": { "lora": 5.774236677836758e-05, "row_tokens": 5.774236677836758e-05 } }, { "update_id": 471, "row_count": 11, "row_ids_sha256": "fd7636a9ee17907363ef36280a626ea06929d3ce62d352c46a0315383bdda240", "input_ids_vector_sha256": "f866c664e51f7d3f3039c9efe92a6323726fc986568fbe626d43f25c78d69cc3", "labels_vector_sha256": "9c8f18ac5e5ee16b2943b1e426f34da6483e5421aaf0c9e0056209b31cd61788", "planned_active_tokens": 66116, "realized_active_tokens": 66116, "cumulative_start": 30876581, "cumulative_end": 30942697, "loss_sum": 27037.43539428711, "token_normalized_loss": 0.408939370111427, "grad_norm_before_clip": 0.1390865594148636, "learning_rates_at_step": { "lora": 5.774236677836758e-05, "row_tokens": 5.774236677836758e-05 }, "learning_rates_after_step": { "lora": 5.759462770709758e-05, "row_tokens": 5.759462770709758e-05 } }, { "update_id": 472, "row_count": 12, "row_ids_sha256": "1ab676c11a4dc35c3b0fb969d2ea2ac9d71ee76d092828dc6015396830a0c95f", "input_ids_vector_sha256": "584524aceb644eb46e232d98a6a2e1ccbcac5e79ec6b31b85d9aed242e8c077c", "labels_vector_sha256": "6c55c4a245b672970243ae0993e2cf263c757dae6a778f5b78f98eb4b68d26c8", "planned_active_tokens": 57260, "realized_active_tokens": 57260, "cumulative_start": 30942697, "cumulative_end": 30999957, "loss_sum": 22421.487670898438, "token_normalized_loss": 0.3915733089573601, "grad_norm_before_clip": 0.15409038960933685, "learning_rates_at_step": { "lora": 5.759462770709758e-05, "row_tokens": 5.759462770709758e-05 }, "learning_rates_after_step": { "lora": 5.742077849954025e-05, "row_tokens": 5.742077849954025e-05 } }, { "update_id": 473, "row_count": 15, "row_ids_sha256": "ea645b3081ac8d32fc3333596090664b729e7bfdcbf08c2629399e3eaa5333e1", "input_ids_vector_sha256": "fca8a1b1812e9a4d12e3a4b449522bb6641ee9a41a92965264c9c4369b8f57e3", "labels_vector_sha256": "e59c2adc9ae236c2ca927d7c90782b8ce1ae034f6c641e39abac1e2648dcfd38", "planned_active_tokens": 67346, "realized_active_tokens": 67346, "cumulative_start": 30999957, "cumulative_end": 31067303, "loss_sum": 27637.495147705078, "token_normalized_loss": 0.41038064840829563, "grad_norm_before_clip": 0.13968327641487122, "learning_rates_at_step": { "lora": 5.742077849954025e-05, "row_tokens": 5.742077849954025e-05 }, "learning_rates_after_step": { "lora": 5.725750189276218e-05, "row_tokens": 5.725750189276218e-05 } }, { "update_id": 474, "row_count": 10, "row_ids_sha256": "41f16392069a370cb49bfa8fc524792f735fb23e212bc814dd2151d3b2ae6e2b", "input_ids_vector_sha256": "9b6654f64deb3a7835d5761f09fb51c6ddb8ad027239a7b8c58b3adaf0ae7933", "labels_vector_sha256": "823beef1973f2a30b736cb0d4aad04c24b1ba5799d74488acc502e4649eadea7", "planned_active_tokens": 63218, "realized_active_tokens": 63218, "cumulative_start": 31067303, "cumulative_end": 31130521, "loss_sum": 24362.628448486328, "token_normalized_loss": 0.3853748686843356, "grad_norm_before_clip": 0.13926102221012115, "learning_rates_at_step": { "lora": 5.725750189276218e-05, "row_tokens": 5.725750189276218e-05 }, "learning_rates_after_step": { "lora": 5.7088855427493204e-05, "row_tokens": 5.7088855427493204e-05 } }, { "update_id": 475, "row_count": 14, "row_ids_sha256": "e7889265b3fda2605522570999c9a0faffd3b02018f26bced858dee4632e5f32", "input_ids_vector_sha256": "796ef59441b02070154162be771ccf8236580c32c551bfa4c1a4a1c025b56397", "labels_vector_sha256": "e152af9fb6953993b341f1c97e3dabce0d7a82f4db8228065661b237baae1e00", "planned_active_tokens": 65265, "realized_active_tokens": 65265, "cumulative_start": 31130521, "cumulative_end": 31195786, "loss_sum": 26411.066833496094, "token_normalized_loss": 0.4046742792231072, "grad_norm_before_clip": 0.1422128975391388, "learning_rates_at_step": { "lora": 5.7088855427493204e-05, "row_tokens": 5.7088855427493204e-05 }, "learning_rates_after_step": { "lora": 5.6913775571586624e-05, "row_tokens": 5.6913775571586624e-05 } }, { "update_id": 476, "row_count": 8, "row_ids_sha256": "fb16bc7349c81efe8c18c99fd5b8ba513ecedf4ff59d5b554b5f5088aaa3aea5", "input_ids_vector_sha256": "268f705bab77d12a5cbba1eab6dcac999d5ddfe3ada5b83fd3680221a22addd2", "labels_vector_sha256": "173fdbc5a4716d5e4c59fbe5a371eaf2449ccf3a9d60be4c0cf7dac4e4590100", "planned_active_tokens": 67721, "realized_active_tokens": 67721, "cumulative_start": 31195786, "cumulative_end": 31263507, "loss_sum": 27079.4884185791, "token_normalized_loss": 0.3998684074154118, "grad_norm_before_clip": 0.13893848657608032, "learning_rates_at_step": { "lora": 5.6913775571586624e-05, "row_tokens": 5.6913775571586624e-05 }, "learning_rates_after_step": { "lora": 5.674880014871968e-05, "row_tokens": 5.674880014871968e-05 } }, { "update_id": 477, "row_count": 10, "row_ids_sha256": "19b11aa2cd15fb88499dddef4e683c4c3db5a2a8e9bc430824bd2f5c6a668a24", "input_ids_vector_sha256": "299606cd9d9fa29cc45e0e54f3fef0ec15bc23704622fa10956d0993155291ea", "labels_vector_sha256": "0732fb3f5022c622286fa8ba490a93b98ddc68cfa2e34c290a5317e202522672", "planned_active_tokens": 63782, "realized_active_tokens": 63782, "cumulative_start": 31263507, "cumulative_end": 31327289, "loss_sum": 27169.684692382812, "token_normalized_loss": 0.4259773085256469, "grad_norm_before_clip": 0.14449402689933777, "learning_rates_at_step": { "lora": 5.674880014871968e-05, "row_tokens": 5.674880014871968e-05 }, "learning_rates_after_step": { "lora": 5.6580165039391106e-05, "row_tokens": 5.6580165039391106e-05 } }, { "update_id": 478, "row_count": 13, "row_ids_sha256": "72b4beb239ab0f52617f781f9e2aae15979927bcc7a35803300a11ec70abcbb6", "input_ids_vector_sha256": "fb57cef24eccfe917ff5352b652045aefac12178dbca981d7b64900afa9bc7a7", "labels_vector_sha256": "95973c2effc0168eb6ae21a479b25fac87ebc7998619395a3b57da95a646e6a1", "planned_active_tokens": 65167, "realized_active_tokens": 65167, "cumulative_start": 31327289, "cumulative_end": 31392456, "loss_sum": 27535.51641845703, "token_normalized_loss": 0.42253773257104105, "grad_norm_before_clip": 0.181512713432312, "learning_rates_at_step": { "lora": 5.6580165039391106e-05, "row_tokens": 5.6580165039391106e-05 }, "learning_rates_after_step": { "lora": 5.641180589541159e-05, "row_tokens": 5.641180589541159e-05 } }, { "update_id": 479, "row_count": 11, "row_ids_sha256": "e487f8c9d8ccc9f2bc5673ac2dc991c67fc280325689ca3b0eeec8221bf5681a", "input_ids_vector_sha256": "5627e63517257f872c402c3f55b5a173e72aefe70b09ca62ae239cdeddadf01a", "labels_vector_sha256": "dbdd9be3346eaf285f170c52e0f2a67a894584fc9370876f9afcc04879ef7c7a", "planned_active_tokens": 65031, "realized_active_tokens": 65031, "cumulative_start": 31392456, "cumulative_end": 31457487, "loss_sum": 27768.907287597656, "token_normalized_loss": 0.4270103072011449, "grad_norm_before_clip": 0.14055205881595612, "learning_rates_at_step": { "lora": 5.641180589541159e-05, "row_tokens": 5.641180589541159e-05 }, "learning_rates_after_step": { "lora": 5.622737292676385e-05, "row_tokens": 5.622737292676385e-05 } }, { "update_id": 480, "row_count": 18, "row_ids_sha256": "593be6145911d980b5b91ac0bafb9930a02eb8aa00bf6c9bcf012d270956c62a", "input_ids_vector_sha256": "e5dfb114a67cb1e5da0d70385606a362393b1c081150b8cfbdedf643076ae130", "labels_vector_sha256": "46bf39f30a0cb802a770f8f27157d6060d2895feee18e06b45db74569ba5fdad", "planned_active_tokens": 71207, "realized_active_tokens": 71207, "cumulative_start": 31457487, "cumulative_end": 31528694, "loss_sum": 27693.523559570312, "token_normalized_loss": 0.388915746479564, "grad_norm_before_clip": 0.13719730079174042, "learning_rates_at_step": { "lora": 5.622737292676385e-05, "row_tokens": 5.622737292676385e-05 }, "learning_rates_after_step": { "lora": 5.607142852355456e-05, "row_tokens": 5.607142852355456e-05 } }, { "update_id": 481, "row_count": 8, "row_ids_sha256": "8a9d651bf0798a20e0ba10a63d8845356f650a19942b1cda11b329a1ad9dd27c", "input_ids_vector_sha256": "858a917613cdebc417d96d1ae4f0cbed19495b4e83540337e62cbf3b56e50565", "labels_vector_sha256": "203e87fa21c076f72b18f3cdbb8b7a70577dc2185533374a146c8b78261744bb", "planned_active_tokens": 60182, "realized_active_tokens": 60182, "cumulative_start": 31528694, "cumulative_end": 31588876, "loss_sum": 28138.963134765625, "token_normalized_loss": 0.4675644401110901, "grad_norm_before_clip": 0.15577034652233124, "learning_rates_at_step": { "lora": 5.607142852355456e-05, "row_tokens": 5.607142852355456e-05 }, "learning_rates_after_step": { "lora": 5.589582807084821e-05, "row_tokens": 5.589582807084821e-05 } }, { "update_id": 482, "row_count": 8, "row_ids_sha256": "47de35c12aca619e05e35b6c4f94b0e7637e2188c8e8ba236473ee3de7e61e61", "input_ids_vector_sha256": "bf65372f6ea3ddc97988b21090fffbb62b4649f99903405190057bcba2b2a6d3", "labels_vector_sha256": "aa27eeac4131f886935712a1a6f0e8a6d547d678cf423f5ff63fac50f1e49252", "planned_active_tokens": 67740, "realized_active_tokens": 67740, "cumulative_start": 31588876, "cumulative_end": 31656616, "loss_sum": 24941.342498779297, "token_normalized_loss": 0.3681922423793814, "grad_norm_before_clip": 0.13259707391262054, "learning_rates_at_step": { "lora": 5.589582807084821e-05, "row_tokens": 5.589582807084821e-05 }, "learning_rates_after_step": { "lora": 5.5731390443896804e-05, "row_tokens": 5.5731390443896804e-05 } }, { "update_id": 483, "row_count": 10, "row_ids_sha256": "f0081bac54671052ca2b35afe9114d369046c72eb978f62e3053c346d252cc4f", "input_ids_vector_sha256": "da88f21ef428bb1e6c4857f74cec3aba07d3d18248f802e0a970995a66aab5dc", "labels_vector_sha256": "58c732e25e7eae78942745a7d9997f4eff230bd58740243f2e19cf90836e40ad", "planned_active_tokens": 63408, "realized_active_tokens": 63408, "cumulative_start": 31656616, "cumulative_end": 31720024, "loss_sum": 29187.27619934082, "token_normalized_loss": 0.4603090493209188, "grad_norm_before_clip": 0.15009728074073792, "learning_rates_at_step": { "lora": 5.5731390443896804e-05, "row_tokens": 5.5731390443896804e-05 }, "learning_rates_after_step": { "lora": 5.556007337675987e-05, "row_tokens": 5.556007337675987e-05 } }, { "update_id": 484, "row_count": 15, "row_ids_sha256": "d3303f9e91cf60bdc55ac823296b36b0c8bfcd111c03375ff774c919de791d02", "input_ids_vector_sha256": "6b7ee1aaf5a444f49e10c1e1f8667c37b6f94ce03a5582f42c2dc83824e077ca", "labels_vector_sha256": "350dd265d289019e4532d238d49adef202a84375597d034acf4aa4de952ce926", "planned_active_tokens": 66035, "realized_active_tokens": 66035, "cumulative_start": 31720024, "cumulative_end": 31786059, "loss_sum": 24909.13735961914, "token_normalized_loss": 0.377211135907006, "grad_norm_before_clip": 0.1353967785835266, "learning_rates_at_step": { "lora": 5.556007337675987e-05, "row_tokens": 5.556007337675987e-05 }, "learning_rates_after_step": { "lora": 5.537297477501212e-05, "row_tokens": 5.537297477501212e-05 } }, { "update_id": 485, "row_count": 10, "row_ids_sha256": "b81f24a874c801f7e625b4a1cdedf5bf71315749ba550a0f9f362021859f5ecc", "input_ids_vector_sha256": "15f523977f4437932553f4fd440a48f5144b5f2b2fe4ee8d2e93ad70b49b4d29", "labels_vector_sha256": "dfc084bc303cfffa8e469531319d14f2616f51632dcfa5b0b74c0b1cd94a0865", "planned_active_tokens": 72089, "realized_active_tokens": 72089, "cumulative_start": 31786059, "cumulative_end": 31858148, "loss_sum": 33375.423828125, "token_normalized_loss": 0.4629752643000319, "grad_norm_before_clip": 0.14801816642284393, "learning_rates_at_step": { "lora": 5.537297477501212e-05, "row_tokens": 5.537297477501212e-05 }, "learning_rates_after_step": { "lora": 5.520077124276967e-05, "row_tokens": 5.520077124276967e-05 } }, { "update_id": 486, "row_count": 12, "row_ids_sha256": "e4207dbfa07a77b2d522ffe16e6de50b540bf847023ca85a8d438253fb27282b", "input_ids_vector_sha256": "d97927b0b6241a4f95a6207a05b53b5184bcfa87edbfa548dad075858d58ac9a", "labels_vector_sha256": "544b7ed38f7d73495704a9c125f68780651fceb88e25dc5dec061e760b9ce07f", "planned_active_tokens": 66324, "realized_active_tokens": 66324, "cumulative_start": 31858148, "cumulative_end": 31924472, "loss_sum": 26959.981842041016, "token_normalized_loss": 0.40648908150957447, "grad_norm_before_clip": 0.14081302285194397, "learning_rates_at_step": { "lora": 5.520077124276967e-05, "row_tokens": 5.520077124276967e-05 }, "learning_rates_after_step": { "lora": 5.504974446947821e-05, "row_tokens": 5.504974446947821e-05 } }, { "update_id": 487, "row_count": 8, "row_ids_sha256": "9079741a702835b3ff21045a93456c1fdef42afca806755bb27016b3e4bd984f", "input_ids_vector_sha256": "c2f6c1c77f665be2adf2c04ca91ad9b6bfd2f24de266d69e386e432adc8fe5b8", "labels_vector_sha256": "5435d9d8816be1a1ea81648f8a144ecb049d2914b7e343220cf77ee12e88e462", "planned_active_tokens": 58148, "realized_active_tokens": 58148, "cumulative_start": 31924472, "cumulative_end": 31982620, "loss_sum": 25541.279296875, "token_normalized_loss": 0.4392460496814164, "grad_norm_before_clip": 0.15556614100933075, "learning_rates_at_step": { "lora": 5.504974446947821e-05, "row_tokens": 5.504974446947821e-05 }, "learning_rates_after_step": { "lora": 5.486926853168918e-05, "row_tokens": 5.486926853168918e-05 } }, { "update_id": 488, "row_count": 9, "row_ids_sha256": "72297462bfab92a69529e70429147d40de666bd473da54d72c4d082827f60c9c", "input_ids_vector_sha256": "18ebe3fac91747e0d6861a8627d633073f23977ac730b7f0643c414c1d928776", "labels_vector_sha256": "21e238d1887891bc69a4cf095a46785a44f08beebe6842eb6e72a0274d50687d", "planned_active_tokens": 69463, "realized_active_tokens": 69463, "cumulative_start": 31982620, "cumulative_end": 32052083, "loss_sum": 36915.71710205078, "token_normalized_loss": 0.531444324346066, "grad_norm_before_clip": 0.16036252677440643, "learning_rates_at_step": { "lora": 5.486926853168918e-05, "row_tokens": 5.486926853168918e-05 }, "learning_rates_after_step": { "lora": 5.470606451404062e-05, "row_tokens": 5.470606451404062e-05 } }, { "update_id": 489, "row_count": 8, "row_ids_sha256": "43957b80bdacd4fc41283817d149ce37ec79429114f5f1ea5ac90e59853a4e4f", "input_ids_vector_sha256": "180b04fd35eaf6af52796f1acad338dc898d1504406ba7a53b981433bbc53928", "labels_vector_sha256": "f16cf577c23b7810018112daea3be8e83c128ba3bea31be3f100df88e9f201d8", "planned_active_tokens": 62794, "realized_active_tokens": 62794, "cumulative_start": 32052083, "cumulative_end": 32114877, "loss_sum": 34668.116455078125, "token_normalized_loss": 0.5520928186622627, "grad_norm_before_clip": 0.16842320561408997, "learning_rates_at_step": { "lora": 5.470606451404062e-05, "row_tokens": 5.470606451404062e-05 }, "learning_rates_after_step": { "lora": 5.4525666255700726e-05, "row_tokens": 5.4525666255700726e-05 } }, { "update_id": 490, "row_count": 8, "row_ids_sha256": "402359bd2a700d9f1aea3e9cda837a761d7f3e08757caeb042386cbfd07eebf1", "input_ids_vector_sha256": "fd56dfb4a6470b1a73d24aec050cc76d761c893c5dc69a6e04f1d2e37ddd0b00", "labels_vector_sha256": "7fc84dabc6e912ec6aba3dde48da80d92011d2eed8609d571d3cb57d22270837", "planned_active_tokens": 69387, "realized_active_tokens": 69387, "cumulative_start": 32114877, "cumulative_end": 32184264, "loss_sum": 32700.364990234375, "token_normalized_loss": 0.4712750946176427, "grad_norm_before_clip": 0.14624179899692535, "learning_rates_at_step": { "lora": 5.4525666255700726e-05, "row_tokens": 5.4525666255700726e-05 }, "learning_rates_after_step": { "lora": 5.4365822388298606e-05, "row_tokens": 5.4365822388298606e-05 } }, { "update_id": 491, "row_count": 9, "row_ids_sha256": "67990da82f206bb34db392059f36bca4da0dfe3a3e2a3d18d5780baf68bd2ba3", "input_ids_vector_sha256": "2da949c2d126f9f7f7a0ec15112cdf4de46524201dc9c415bf5beb8f26ac64d8", "labels_vector_sha256": "2870c21f4cad3ab88164767eac3a6892e58c9fb1dba973232b15c8bd497dc555", "planned_active_tokens": 61462, "realized_active_tokens": 61462, "cumulative_start": 32184264, "cumulative_end": 32245726, "loss_sum": 29713.632446289062, "token_normalized_loss": 0.4834472104111331, "grad_norm_before_clip": 0.16179506480693817, "learning_rates_at_step": { "lora": 5.4365822388298606e-05, "row_tokens": 5.4365822388298606e-05 }, "learning_rates_after_step": { "lora": 5.41860529891625e-05, "row_tokens": 5.41860529891625e-05 } }, { "update_id": 492, "row_count": 9, "row_ids_sha256": "a3f2bc6ec31586018b5b0ab9a8574eb0e18743ad6161a650e4926536d46b8c6e", "input_ids_vector_sha256": "8bca0ed5b25fd6fbbd50efe2baa6897fd03cd005205696751da7db9e81fc4931", "labels_vector_sha256": "b5010a053c92d3d2f53c9b5dd92b8128fc4f95958d40be9f952e86892e206621", "planned_active_tokens": 69103, "realized_active_tokens": 69103, "cumulative_start": 32245726, "cumulative_end": 32314829, "loss_sum": 30690.00469970703, "token_normalized_loss": 0.44411971549291684, "grad_norm_before_clip": 0.15273088216781616, "learning_rates_at_step": { "lora": 5.41860529891625e-05, "row_tokens": 5.41860529891625e-05 }, "learning_rates_after_step": { "lora": 5.401659791884568e-05, "row_tokens": 5.401659791884568e-05 } }, { "update_id": 493, "row_count": 8, "row_ids_sha256": "12f7ebdbd13b5eec718e61146661b35d7bc2f5047c97c67b5df65e8eb98c1229", "input_ids_vector_sha256": "6a2868646c6ddeb8c51612054c9217211cc3bfc07707df7884b220ceaebf618a", "labels_vector_sha256": "37631ff2370c6370b9c4709c4647256608679fe9d171f562ca57f7c45be9918f", "planned_active_tokens": 65119, "realized_active_tokens": 65119, "cumulative_start": 32314829, "cumulative_end": 32379948, "loss_sum": 28140.396240234375, "token_normalized_loss": 0.4321380279217183, "grad_norm_before_clip": 0.14855219423770905, "learning_rates_at_step": { "lora": 5.401659791884568e-05, "row_tokens": 5.401659791884568e-05 }, "learning_rates_after_step": { "lora": 5.385860547409868e-05, "row_tokens": 5.385860547409868e-05 } }, { "update_id": 494, "row_count": 10, "row_ids_sha256": "19ccda5c223ccd9d39644789f15183bc280639130f89ae1a0b9f93664e719784", "input_ids_vector_sha256": "2256e5dc6a69d93e566a762f6edd5acda1dd58c1aaf47318919f0d4b2f3baf96", "labels_vector_sha256": "0105d594e4295c97ccfd5d78f558b8023cdbcbd3779269031ae464f0cc9e5024", "planned_active_tokens": 60698, "realized_active_tokens": 60698, "cumulative_start": 32379948, "cumulative_end": 32440646, "loss_sum": 26143.893310546875, "token_normalized_loss": 0.430720836115636, "grad_norm_before_clip": 0.15427064895629883, "learning_rates_at_step": { "lora": 5.385860547409868e-05, "row_tokens": 5.385860547409868e-05 }, "learning_rates_after_step": { "lora": 5.3674941218793085e-05, "row_tokens": 5.3674941218793085e-05 } }, { "update_id": 495, "row_count": 10, "row_ids_sha256": "5bdfb40bb086f8315ca009801eeb86565f6add5810617c210b1db511d27d19e7", "input_ids_vector_sha256": "b6d182a1996c3de862323cdbbae8384515752f4863bb6921ecbfb5e87a875ad8", "labels_vector_sha256": "33717c495d505c03949d852b7bc5a7e79d7a0d7a0fc97266d459ce6ee9ee1561", "planned_active_tokens": 70542, "realized_active_tokens": 70542, "cumulative_start": 32440646, "cumulative_end": 32511188, "loss_sum": 32528.193237304688, "token_normalized_loss": 0.46111810321942515, "grad_norm_before_clip": 0.14883536100387573, "learning_rates_at_step": { "lora": 5.3674941218793085e-05, "row_tokens": 5.3674941218793085e-05 }, "learning_rates_after_step": { "lora": 5.3518096303265606e-05, "row_tokens": 5.3518096303265606e-05 } }, { "update_id": 496, "row_count": 7, "row_ids_sha256": "208fc3b38fc9017ce0641639a074788066a6c0cb02d0a68e2ed01d9128b4b187", "input_ids_vector_sha256": "175ebf648fa62ba9ac4d4d551532b06c44537bf0b67890d5dc338f14e1a3f2b9", "labels_vector_sha256": "75eb3699ae4561b896c10feca1b7608bc99cdb5e73e7c3c6fb72794a5b5b11c2", "planned_active_tokens": 60226, "realized_active_tokens": 60226, "cumulative_start": 32511188, "cumulative_end": 32571414, "loss_sum": 30469.6279296875, "token_normalized_loss": 0.5059214945320543, "grad_norm_before_clip": 0.21384043991565704, "learning_rates_at_step": { "lora": 5.3518096303265606e-05, "row_tokens": 5.3518096303265606e-05 }, "learning_rates_after_step": { "lora": 5.331279605607158e-05, "row_tokens": 5.331279605607158e-05 } }, { "update_id": 497, "row_count": 12, "row_ids_sha256": "c177c2fac6acdd342b85f50ec759aa3780c8dda2467a13270284dd5cc8523595", "input_ids_vector_sha256": "095d957e3337565689c44c01274b2f73796493ab2bcb048e6523bfc6a7931e07", "labels_vector_sha256": "54364eba5366f20522d9650b625f144844093e0d332373fd9c4d399b85dbec4d", "planned_active_tokens": 78812, "realized_active_tokens": 78812, "cumulative_start": 32571414, "cumulative_end": 32650226, "loss_sum": 32767.266235351562, "token_normalized_loss": 0.41576493726020863, "grad_norm_before_clip": 0.14122514426708221, "learning_rates_at_step": { "lora": 5.331279605607158e-05, "row_tokens": 5.331279605607158e-05 }, "learning_rates_after_step": { "lora": 5.315326470732256e-05, "row_tokens": 5.315326470732256e-05 } }, { "update_id": 498, "row_count": 7, "row_ids_sha256": "1d621a5641d5699fd7830632ab4eaa2ee6b8fce274ad9cc7041755cb5d21ad3a", "input_ids_vector_sha256": "92eb047eb996a0144e072ac9b670f379a8093039c5a4391f35251fc31a1df8d7", "labels_vector_sha256": "42b1b602636881b09e4e74f5a17dbc65e028da2a7c124f56b562b4e9a3d358e4", "planned_active_tokens": 61227, "realized_active_tokens": 61227, "cumulative_start": 32650226, "cumulative_end": 32711453, "loss_sum": 30216.28253173828, "token_normalized_loss": 0.49351238067745085, "grad_norm_before_clip": 0.15948712825775146, "learning_rates_at_step": { "lora": 5.315326470732256e-05, "row_tokens": 5.315326470732256e-05 }, "learning_rates_after_step": { "lora": 5.300126211810734e-05, "row_tokens": 5.300126211810734e-05 } }, { "update_id": 499, "row_count": 8, "row_ids_sha256": "4e9605dce920e5a2177ba48468523b2a376373e9a43f2cb27d7babde586b4aa7", "input_ids_vector_sha256": "fb20e72b127c0e4898618dc150393948009e04cea9f12d2023b7fbda673665b4", "labels_vector_sha256": "7b2b4e1f1e2d6a2046945cd038a4588717e042539bf706b7beebe81baf182d55", "planned_active_tokens": 58326, "realized_active_tokens": 58326, "cumulative_start": 32711453, "cumulative_end": 32769779, "loss_sum": 21533.801879882812, "token_normalized_loss": 0.3691973027446218, "grad_norm_before_clip": 0.15219680964946747, "learning_rates_at_step": { "lora": 5.300126211810734e-05, "row_tokens": 5.300126211810734e-05 }, "learning_rates_after_step": { "lora": 5.2826101295302575e-05, "row_tokens": 5.2826101295302575e-05 } }, { "update_id": 500, "row_count": 9, "row_ids_sha256": "6407fcc53c915314ab9330fea5b9779e344c274b28ed3fd31a29f0a7c8bd8929", "input_ids_vector_sha256": "e2db97b133be7265c0a5db7565835fbece264e9873c80fd058037d1a00d69d8a", "labels_vector_sha256": "6be26a7479ad6bf1fc7ab58b4246912a08f7e0af3baef285c4651ea9c456067b", "planned_active_tokens": 67199, "realized_active_tokens": 67199, "cumulative_start": 32769779, "cumulative_end": 32836978, "loss_sum": 27826.547485351562, "token_normalized_loss": 0.41409169013454905, "grad_norm_before_clip": 0.14405377209186554, "learning_rates_at_step": { "lora": 5.2826101295302575e-05, "row_tokens": 5.2826101295302575e-05 }, "learning_rates_after_step": { "lora": 5.263891693134242e-05, "row_tokens": 5.263891693134242e-05 } }, { "update_id": 501, "row_count": 11, "row_ids_sha256": "6b46ba69b7615666ab34565c84e775560321d40cb5142f664db6f90acb008b02", "input_ids_vector_sha256": "4bd7aa5e85ed91aa0b0619be6a4a2ff3ec139924998bf9372630640769181ce7", "labels_vector_sha256": "7795f669d0cd6725a1eb31cb923852561337ae78ba34ca5ea521f4dd27779c76", "planned_active_tokens": 71797, "realized_active_tokens": 71797, "cumulative_start": 32836978, "cumulative_end": 32908775, "loss_sum": 29856.4130859375, "token_normalized_loss": 0.4158448554387718, "grad_norm_before_clip": 0.14120429754257202, "learning_rates_at_step": { "lora": 5.263891693134242e-05, "row_tokens": 5.263891693134242e-05 }, "learning_rates_after_step": { "lora": 5.246993232657045e-05, "row_tokens": 5.246993232657045e-05 } }, { "update_id": 502, "row_count": 7, "row_ids_sha256": "d6e1207cf2418717228bb912ba1a191ec2d08c6a1d208178096f8e094a8a2830", "input_ids_vector_sha256": "f558f68705f3cb6ca098c073d0d849c6117662f02dea98285470156d9f5150be", "labels_vector_sha256": "939b81a3d99edbbc1d7e26b3f285677a6785dc213cea6cea961580e66592220e", "planned_active_tokens": 64804, "realized_active_tokens": 64804, "cumulative_start": 32908775, "cumulative_end": 32973579, "loss_sum": 29202.8173828125, "token_normalized_loss": 0.45063294523196873, "grad_norm_before_clip": 0.1526050716638565, "learning_rates_at_step": { "lora": 5.246993232657045e-05, "row_tokens": 5.246993232657045e-05 }, "learning_rates_after_step": { "lora": 5.23152804800085e-05, "row_tokens": 5.23152804800085e-05 } }, { "update_id": 503, "row_count": 10, "row_ids_sha256": "6fc9e3212f1411ff532036a0959265e4e904bf76d3b9cbf717e3e9321a14cb74", "input_ids_vector_sha256": "1521c3087b73758dae74d19455312e37098a87a32c7f13ecbd2cdff48ebc01c1", "labels_vector_sha256": "ea0e04868a54c2801c0e41c00887d880ce58752004740f7e353cb9b63a9a62fe", "planned_active_tokens": 59298, "realized_active_tokens": 59298, "cumulative_start": 32973579, "cumulative_end": 33032877, "loss_sum": 22953.58544921875, "token_normalized_loss": 0.38708869522106565, "grad_norm_before_clip": 0.15329670906066895, "learning_rates_at_step": { "lora": 5.23152804800085e-05, "row_tokens": 5.23152804800085e-05 }, "learning_rates_after_step": { "lora": 5.2143653029084914e-05, "row_tokens": 5.2143653029084914e-05 } }, { "update_id": 504, "row_count": 9, "row_ids_sha256": "171b05814a6830f92840d1bcde751a4953e692c1de2b50f360c19675c5bd950c", "input_ids_vector_sha256": "c71b61aa19eb7fb3d486051faf8990d95bac39900dea588b1b1273bdd7bc0ac4", "labels_vector_sha256": "905b5ce3d694b27de43a359f9560e846f60771d5a47fbe52dea57c9f8e832c1e", "planned_active_tokens": 65797, "realized_active_tokens": 65797, "cumulative_start": 33032877, "cumulative_end": 33098674, "loss_sum": 25855.052978515625, "token_normalized_loss": 0.39295185158161655, "grad_norm_before_clip": 0.1519881784915924, "learning_rates_at_step": { "lora": 5.2143653029084914e-05, "row_tokens": 5.2143653029084914e-05 }, "learning_rates_after_step": { "lora": 5.1978616691198456e-05, "row_tokens": 5.1978616691198456e-05 } }, { "update_id": 505, "row_count": 8, "row_ids_sha256": "ba2b1112895cb8f146cecfebab31e31b0abee7972ee089bcaf6557908484821e", "input_ids_vector_sha256": "9504d7051d65dee02fec93a8efd5ffc0dba810d6b5d3fcbe93a7c80b538152f2", "labels_vector_sha256": "14cfc753ed41fc7b05232246f93b949b73fb9112a1a73016e047cfa9e62d9f94", "planned_active_tokens": 63261, "realized_active_tokens": 63261, "cumulative_start": 33098674, "cumulative_end": 33161935, "loss_sum": 30025.4921875, "token_normalized_loss": 0.4746287947945812, "grad_norm_before_clip": 0.1615118831396103, "learning_rates_at_step": { "lora": 5.1978616691198456e-05, "row_tokens": 5.1978616691198456e-05 }, "learning_rates_after_step": { "lora": 5.17797859328714e-05, "row_tokens": 5.17797859328714e-05 } }, { "update_id": 506, "row_count": 11, "row_ids_sha256": "24143e03077711972c3f798dab6dd78caa5268593adbd0270e9caf63ed44f48d", "input_ids_vector_sha256": "ca0836df33f121787ddcac0745bd0abc6867a14dc3082d474a68fe6209ae3378", "labels_vector_sha256": "924c147481136cbac0ebde824cf28accb90483e731d8726ecbc0bc6949cdafbd", "planned_active_tokens": 76204, "realized_active_tokens": 76204, "cumulative_start": 33161935, "cumulative_end": 33238139, "loss_sum": 31860.39599609375, "token_normalized_loss": 0.41809348585499123, "grad_norm_before_clip": 0.14527203142642975, "learning_rates_at_step": { "lora": 5.17797859328714e-05, "row_tokens": 5.17797859328714e-05 }, "learning_rates_after_step": { "lora": 5.16335095868964e-05, "row_tokens": 5.16335095868964e-05 } }, { "update_id": 507, "row_count": 9, "row_ids_sha256": "4ee5223ca3e4e1ad26acd4c8f969a87e8fe1cb127569dd953f5c8d36459d47f0", "input_ids_vector_sha256": "eefd84ad1761c39b365da51da1042c3078cddb15193689162b48eb55f583c27a", "labels_vector_sha256": "43b0e4b0c72905101b8daa3ba7e6058a678b20c78057fb77dae31846434d0c5d", "planned_active_tokens": 56055, "realized_active_tokens": 56055, "cumulative_start": 33238139, "cumulative_end": 33294194, "loss_sum": 25159.311462402344, "token_normalized_loss": 0.4488326012381116, "grad_norm_before_clip": 0.16529995203018188, "learning_rates_at_step": { "lora": 5.16335095868964e-05, "row_tokens": 5.16335095868964e-05 }, "learning_rates_after_step": { "lora": 5.1448999703823276e-05, "row_tokens": 5.1448999703823276e-05 } }, { "update_id": 508, "row_count": 9, "row_ids_sha256": "2feeabb0164fc65d31500a00deb2c47e47b46dc8f6931babd4884a36ab3135f8", "input_ids_vector_sha256": "77048669caea8eaa192e7b8027e8dc89e72d7a8784962e56ff5d93cf7007e382", "labels_vector_sha256": "57494b8309fcacaa82f9c877c95e7970929b28cd605a8776b67a27ea691ac123", "planned_active_tokens": 70699, "realized_active_tokens": 70699, "cumulative_start": 33294194, "cumulative_end": 33364893, "loss_sum": 33304.59979248047, "token_normalized_loss": 0.47107596702188814, "grad_norm_before_clip": 0.15366722643375397, "learning_rates_at_step": { "lora": 5.1448999703823276e-05, "row_tokens": 5.1448999703823276e-05 }, "learning_rates_after_step": { "lora": 5.1284897404765617e-05, "row_tokens": 5.1284897404765617e-05 } }, { "update_id": 509, "row_count": 11, "row_ids_sha256": "f1aca910dce29585679e4f66c26e22de718157aa42c7c7b004a2ec8fcd0c180a", "input_ids_vector_sha256": "fb2a4463279846702f2c0b2ba3ee64a42c09abb41756f4517d5536e1862f32b6", "labels_vector_sha256": "fe84bc5a9164edfb0a88e5b95e3e5e8a33cdfa0d0ffedc43147a322a6392f1aa", "planned_active_tokens": 62873, "realized_active_tokens": 62873, "cumulative_start": 33364893, "cumulative_end": 33427766, "loss_sum": 26113.53350830078, "token_normalized_loss": 0.4153378001415676, "grad_norm_before_clip": 0.17619696259498596, "learning_rates_at_step": { "lora": 5.1284897404765617e-05, "row_tokens": 5.1284897404765617e-05 }, "learning_rates_after_step": { "lora": 5.111986501073785e-05, "row_tokens": 5.111986501073785e-05 } }, { "update_id": 510, "row_count": 9, "row_ids_sha256": "ff7037e8848f927dfeba80c0f0bc1af4d05aa468493a0fc23ac29572be0506a2", "input_ids_vector_sha256": "cb8b83f4e224f0b914e8413deaabd4dd4ffb1f14b581f960c943a97d5a9f937a", "labels_vector_sha256": "8382b9bb82885ab5c6526d6528a6ded43229b48d936a95519d22cca1368f4a5f", "planned_active_tokens": 63224, "realized_active_tokens": 63224, "cumulative_start": 33427766, "cumulative_end": 33490990, "loss_sum": 26946.64031982422, "token_normalized_loss": 0.4262090396024329, "grad_norm_before_clip": 0.1633017510175705, "learning_rates_at_step": { "lora": 5.111986501073785e-05, "row_tokens": 5.111986501073785e-05 }, "learning_rates_after_step": { "lora": 5.09512361069048e-05, "row_tokens": 5.09512361069048e-05 } }, { "update_id": 511, "row_count": 11, "row_ids_sha256": "f40b7c472f26bcf90f17687588ff3e4c337db9ea10581f83dbaa25ba8ca36f34", "input_ids_vector_sha256": "ef42e1262757143d0661ce8f7809a85d17f771310a0a74cfeb24b9425550b209", "labels_vector_sha256": "ec1ea7c1b357b9a3cf9884373363488a60ada7d37fefec34c18b20372be9b152", "planned_active_tokens": 64597, "realized_active_tokens": 64597, "cumulative_start": 33490990, "cumulative_end": 33555587, "loss_sum": 27719.075927734375, "token_normalized_loss": 0.4291077902647859, "grad_norm_before_clip": 0.1551317423582077, "learning_rates_at_step": { "lora": 5.09512361069048e-05, "row_tokens": 5.09512361069048e-05 }, "learning_rates_after_step": { "lora": 5.0779513120270906e-05, "row_tokens": 5.0779513120270906e-05 } }, { "update_id": 512, "row_count": 9, "row_ids_sha256": "8f9c19e3d9ccd55959357e4b7eb519d3caa6438d0a32b913afc76d9c990fb56b", "input_ids_vector_sha256": "17f4d9082235f1619ffea0e36f0dabf4d7cbb56204337254b53d2588b7378158", "labels_vector_sha256": "6a4d8deb0be7e6866cedb9c83b48149124aeb40cd5ea071e009ec201af17eacf", "planned_active_tokens": 65778, "realized_active_tokens": 65778, "cumulative_start": 33555587, "cumulative_end": 33621365, "loss_sum": 30437.143188476562, "token_normalized_loss": 0.46272527575293504, "grad_norm_before_clip": 0.1567302644252777, "learning_rates_at_step": { "lora": 5.0779513120270906e-05, "row_tokens": 5.0779513120270906e-05 }, "learning_rates_after_step": { "lora": 5.061150399821495e-05, "row_tokens": 5.061150399821495e-05 } }, { "update_id": 513, "row_count": 9, "row_ids_sha256": "5c1aabe567da385d72c97a54260d0a0a4512c4008763dd8e79d7cdea5f8a0249", "input_ids_vector_sha256": "c5e900196dde903095b2f3531405a64ccd01905b416419218df5402b3a779fed", "labels_vector_sha256": "19465fa60bff0fbb0711086d8a8d1f74829bd5ee3b9fcf99749bc7683152caf2", "planned_active_tokens": 64352, "realized_active_tokens": 64352, "cumulative_start": 33621365, "cumulative_end": 33685717, "loss_sum": 30732.048400878906, "token_normalized_loss": 0.477561667094712, "grad_norm_before_clip": 0.1529286950826645, "learning_rates_at_step": { "lora": 5.061150399821495e-05, "row_tokens": 5.061150399821495e-05 }, "learning_rates_after_step": { "lora": 5.043984049395448e-05, "row_tokens": 5.043984049395448e-05 } }, { "update_id": 514, "row_count": 10, "row_ids_sha256": "dbe533cbf778ccbe0719fb3731a9927a0cb807f2196bcd7de9c232d9a1bab7fd", "input_ids_vector_sha256": "33deca09fba3f2b11a087be52a1ab5384fd235bdc9e83c1b9629c44453d96b86", "labels_vector_sha256": "c88ef31b21e32796e059700794f04c02d33f8fd07f23faf0ec2ff8dba4463a70", "planned_active_tokens": 65749, "realized_active_tokens": 65749, "cumulative_start": 33685717, "cumulative_end": 33751466, "loss_sum": 25244.581787109375, "token_normalized_loss": 0.38395385157355055, "grad_norm_before_clip": 0.16514067351818085, "learning_rates_at_step": { "lora": 5.043984049395448e-05, "row_tokens": 5.043984049395448e-05 }, "learning_rates_after_step": { "lora": 5.0252597179680997e-05, "row_tokens": 5.0252597179680997e-05 } }, { "update_id": 515, "row_count": 8, "row_ids_sha256": "205537e14d867ea5364a4fa5afd91bdc577c4dc6708119cc286bc6c2290c60a2", "input_ids_vector_sha256": "0c891bd501c622c31b66abba1d37211a1ca0621f4669be90669ab02b315cbdf1", "labels_vector_sha256": "3b85d55c503838499c58fb21a394d59574e16d8b42a133e0662ab338e36482d9", "planned_active_tokens": 71714, "realized_active_tokens": 71714, "cumulative_start": 33751466, "cumulative_end": 33823180, "loss_sum": 34692.0029296875, "token_normalized_loss": 0.48375495621060743, "grad_norm_before_clip": 0.15023595094680786, "learning_rates_at_step": { "lora": 5.0252597179680997e-05, "row_tokens": 5.0252597179680997e-05 }, "learning_rates_after_step": { "lora": 5.0077912009249515e-05, "row_tokens": 5.0077912009249515e-05 } }, { "update_id": 516, "row_count": 10, "row_ids_sha256": "5f5918180a9bb318aa53c3150b630d067c86dee26df592a43d15693dae7a8ab0", "input_ids_vector_sha256": "68b519869acaa9becbbc064c310bfd80b4f965b2b6f2b50840251052875b35c5", "labels_vector_sha256": "343e34fda9e8a493dc0d1455fa3bd3a9d1ad6a7d527abe601e98ba3123ad60ec", "planned_active_tokens": 66903, "realized_active_tokens": 66903, "cumulative_start": 33823180, "cumulative_end": 33890083, "loss_sum": 28564.648315429688, "token_normalized_loss": 0.4269561651260734, "grad_norm_before_clip": 0.14753100275993347, "learning_rates_at_step": { "lora": 5.0077912009249515e-05, "row_tokens": 5.0077912009249515e-05 }, "learning_rates_after_step": { "lora": 4.9925636386019755e-05, "row_tokens": 4.9925636386019755e-05 } }, { "update_id": 517, "row_count": 10, "row_ids_sha256": "3d0ca8949c7ffc3df442d770eb2e12941867265b2e4ee89793b128fcf70b041b", "input_ids_vector_sha256": "4a6886456f0563c9fd7efaf886932f5f268a26fa83989fc3ba83877c952bdfa8", "labels_vector_sha256": "d15d0540737435782f19c189ac7e2a9a21bdcc7a83f8e1669d877671eeb9f667", "planned_active_tokens": 58320, "realized_active_tokens": 58320, "cumulative_start": 33890083, "cumulative_end": 33948403, "loss_sum": 25559.68231201172, "token_normalized_loss": 0.4382661576133697, "grad_norm_before_clip": 0.1565273553133011, "learning_rates_at_step": { "lora": 4.9925636386019755e-05, "row_tokens": 4.9925636386019755e-05 }, "learning_rates_after_step": { "lora": 4.975428281758177e-05, "row_tokens": 4.975428281758177e-05 } }, { "update_id": 518, "row_count": 10, "row_ids_sha256": "37b9043c216290cd87309b0deeaf384654670dd54602b263eb1bf021bc2048d2", "input_ids_vector_sha256": "9de6f276fe91d24214be3c048156a8677827b0b32c31f6a54143de4ea38dc551", "labels_vector_sha256": "0eb0ef4a0f7cbd093c8c55d825eb791e3b59ed9047777d902cec88359021cbad", "planned_active_tokens": 65627, "realized_active_tokens": 65627, "cumulative_start": 33948403, "cumulative_end": 34014030, "loss_sum": 28810.052001953125, "token_normalized_loss": 0.4389969372659595, "grad_norm_before_clip": 0.15459585189819336, "learning_rates_at_step": { "lora": 4.975428281758177e-05, "row_tokens": 4.975428281758177e-05 }, "learning_rates_after_step": { "lora": 4.957944130097742e-05, "row_tokens": 4.957944130097742e-05 } }, { "update_id": 519, "row_count": 13, "row_ids_sha256": "7918c12e15c8df26ba691b76e092ffaa35e6c0920c1b2a5c3b9fd9c0a77ab43e", "input_ids_vector_sha256": "212bc4c2515dd798b9dcaba9e31d0c1bbd1df8951d7fda1d84ada6cbcf683bb9", "labels_vector_sha256": "ccdd2af48490583bed286fbc9924e7903905edf0b25c8e21c0dd3f88833d5ed1", "planned_active_tokens": 66964, "realized_active_tokens": 66964, "cumulative_start": 34014030, "cumulative_end": 34080994, "loss_sum": 26166.428955078125, "token_normalized_loss": 0.39075367294483787, "grad_norm_before_clip": 0.14568796753883362, "learning_rates_at_step": { "lora": 4.957944130097742e-05, "row_tokens": 4.957944130097742e-05 }, "learning_rates_after_step": { "lora": 4.9407440313289535e-05, "row_tokens": 4.9407440313289535e-05 } }, { "update_id": 520, "row_count": 8, "row_ids_sha256": "996005b4e7e60f39e736d227d13214d719dd1a82f7e3495ab77faac78bbc327a", "input_ids_vector_sha256": "17435dc3883d751c8e881e80d4883a07f632aeabd917877b59c5ba51aeea05e9", "labels_vector_sha256": "6de890dbf8b4a115167afd3e42b4e194a7242ba2139861231a7395f44a8b05d1", "planned_active_tokens": 65878, "realized_active_tokens": 65878, "cumulative_start": 34080994, "cumulative_end": 34146872, "loss_sum": 29903.063720703125, "token_normalized_loss": 0.4539157794818168, "grad_norm_before_clip": 0.16285786032676697, "learning_rates_at_step": { "lora": 4.9407440313289535e-05, "row_tokens": 4.9407440313289535e-05 }, "learning_rates_after_step": { "lora": 4.923985847823704e-05, "row_tokens": 4.923985847823704e-05 } }, { "update_id": 521, "row_count": 12, "row_ids_sha256": "8cc279ed5cf950a801604ed808ab873968fa30d7af318308b6a61ac72d809954", "input_ids_vector_sha256": "7e71d1c52f833fa6541fad1612f266c6abf758ebd0ef1ac47d4b4454ebf12ab9", "labels_vector_sha256": "8241b4a15d5682188af53684532416839574da31a51b0d84fbf3e2400ddaf2d9", "planned_active_tokens": 64188, "realized_active_tokens": 64188, "cumulative_start": 34146872, "cumulative_end": 34211060, "loss_sum": 23633.8916015625, "token_normalized_loss": 0.3681979747236633, "grad_norm_before_clip": 0.1478847712278366, "learning_rates_at_step": { "lora": 4.923985847823704e-05, "row_tokens": 4.923985847823704e-05 }, "learning_rates_after_step": { "lora": 4.907010273342826e-05, "row_tokens": 4.907010273342826e-05 } }, { "update_id": 522, "row_count": 12, "row_ids_sha256": "090458d44fefa7b941303ae43b60bb499128703f19fb070994cb6d2f96f44fa9", "input_ids_vector_sha256": "c9bf42e1551c51689aecd7286cbc04dddab4f30eb46601f57721677e91dbb939", "labels_vector_sha256": "21acc2a687e8e86fa6af09698632759cacfa201d7c61810d2d666eb90cffd363", "planned_active_tokens": 65024, "realized_active_tokens": 65024, "cumulative_start": 34211060, "cumulative_end": 34276084, "loss_sum": 26797.04620361328, "token_normalized_loss": 0.4121100855624582, "grad_norm_before_clip": 0.15135417878627777, "learning_rates_at_step": { "lora": 4.907010273342826e-05, "row_tokens": 4.907010273342826e-05 }, "learning_rates_after_step": { "lora": 4.889021369721785e-05, "row_tokens": 4.889021369721785e-05 } }, { "update_id": 523, "row_count": 13, "row_ids_sha256": "498aea3cc6ddeca3b9bcbca5ef76624803620600868761bd8052fcaedc8bc6d6", "input_ids_vector_sha256": "62e3e36681e6096357f4d35cd7031766ff2ba66fa5fae37efa385bfda761b73c", "labels_vector_sha256": "ac6054d75939a3c8b364fe2f9b745e1def12845cd773bb0695a07bd5fe149878", "planned_active_tokens": 68910, "realized_active_tokens": 68910, "cumulative_start": 34276084, "cumulative_end": 34344994, "loss_sum": 25246.398223876953, "token_normalized_loss": 0.366367700244913, "grad_norm_before_clip": 0.13676302134990692, "learning_rates_at_step": { "lora": 4.889021369721785e-05, "row_tokens": 4.889021369721785e-05 }, "learning_rates_after_step": { "lora": 4.872206394383216e-05, "row_tokens": 4.872206394383216e-05 } }, { "update_id": 524, "row_count": 12, "row_ids_sha256": "bc1a178b0b304bc8074022d861f82af0e3636d0f50d1650c1e0d9da86a8954a5", "input_ids_vector_sha256": "2b1de6882ef424af939de0b4ebab2e0c9fc697864936d42c4cf067793ae43494", "labels_vector_sha256": "61c57ae7387e8484110934f6a066f2679c016a355902f51fef8815e83a08d938", "planned_active_tokens": 64418, "realized_active_tokens": 64418, "cumulative_start": 34344994, "cumulative_end": 34409412, "loss_sum": 25889.159057617188, "token_normalized_loss": 0.4018932450187399, "grad_norm_before_clip": 0.21755516529083252, "learning_rates_at_step": { "lora": 4.872206394383216e-05, "row_tokens": 4.872206394383216e-05 }, "learning_rates_after_step": { "lora": 4.855424706511102e-05, "row_tokens": 4.855424706511102e-05 } }, { "update_id": 525, "row_count": 9, "row_ids_sha256": "4a8c401dc99e64e2f3c669baafc976fbea3b6eb7296afd8251b7bbc183d7ec15", "input_ids_vector_sha256": "b5badff8011cbce60614b065ad91c68a0e5022b6d5af59ae06208c38d0ca7908", "labels_vector_sha256": "46d6a7ba0c8897ebf450ed28fa8394fcbeb6bee7b24fc83cc4532cd0ae93679e", "planned_active_tokens": 64296, "realized_active_tokens": 64296, "cumulative_start": 34409412, "cumulative_end": 34473708, "loss_sum": 32267.786010742188, "token_normalized_loss": 0.5018630398585011, "grad_norm_before_clip": 0.16959179937839508, "learning_rates_at_step": { "lora": 4.855424706511102e-05, "row_tokens": 4.855424706511102e-05 }, "learning_rates_after_step": { "lora": 4.8386882301031654e-05, "row_tokens": 4.8386882301031654e-05 } }, { "update_id": 526, "row_count": 12, "row_ids_sha256": "4598de20c12141e0dc0c40aff052468380662ca06a3575846524eeb52d7bcc26", "input_ids_vector_sha256": "12e17b280ff48900eebddaca4778160d36b4b3bc726e9fc1cb5e8835962e5bc1", "labels_vector_sha256": "bc8f37a77d337283447d7593c098705c2be55014994fe63f41d1bf128f6c6387", "planned_active_tokens": 64129, "realized_active_tokens": 64129, "cumulative_start": 34473708, "cumulative_end": 34537837, "loss_sum": 25904.780029296875, "token_normalized_loss": 0.40394798030995144, "grad_norm_before_clip": 0.1530139446258545, "learning_rates_at_step": { "lora": 4.8386882301031654e-05, "row_tokens": 4.8386882301031654e-05 }, "learning_rates_after_step": { "lora": 4.8212790393909914e-05, "row_tokens": 4.8212790393909914e-05 } }, { "update_id": 527, "row_count": 10, "row_ids_sha256": "0307106c99c828294b74b550460b2194580be0d786a93c20534003cb916b7c4f", "input_ids_vector_sha256": "7eaff73272b58a29a57c5a9fceef1640995e6d988c10431fea6f5876bc8a2924", "labels_vector_sha256": "b707ad2de11b4b0df15d65112112c4f82d8c7c2116758455427f137f8558fd48", "planned_active_tokens": 66714, "realized_active_tokens": 66714, "cumulative_start": 34537837, "cumulative_end": 34604551, "loss_sum": 24287.11932373047, "token_normalized_loss": 0.3640483155519152, "grad_norm_before_clip": 0.14350219070911407, "learning_rates_at_step": { "lora": 4.8212790393909914e-05, "row_tokens": 4.8212790393909914e-05 }, "learning_rates_after_step": { "lora": 4.8045258418424346e-05, "row_tokens": 4.8045258418424346e-05 } }, { "update_id": 528, "row_count": 10, "row_ids_sha256": "63d70ac7114c543eb8afea2c2244e58b0c2f24eda311538c9b653a4371bdd589", "input_ids_vector_sha256": "0b890b54e57fedf799f74ea80c398cfda4a967524ffe8f49d4de3167c5f7bba6", "labels_vector_sha256": "0e923697592fe4ce435b026c906d7aa59838c3982968c676c4cede98f57a5fc6", "planned_active_tokens": 64208, "realized_active_tokens": 64208, "cumulative_start": 34604551, "cumulative_end": 34668759, "loss_sum": 25784.981414794922, "token_normalized_loss": 0.4015851827621935, "grad_norm_before_clip": 0.1480889916419983, "learning_rates_at_step": { "lora": 4.8045258418424346e-05, "row_tokens": 4.8045258418424346e-05 }, "learning_rates_after_step": { "lora": 4.787185802543103e-05, "row_tokens": 4.787185802543103e-05 } }, { "update_id": 529, "row_count": 9, "row_ids_sha256": "eef5151627173b5d3312a0ff4470a9d25172d640f7af740af4550e2e9fa3901b", "input_ids_vector_sha256": "db4d77d6d39792e1ff290617e69f2ab5f914cddd05cb024b1f019afd92438ec7", "labels_vector_sha256": "f91f21e0bfb8945b12d508636325c9352f163bc16fb5f1bc6afeee0ef15dfc87", "planned_active_tokens": 66466, "realized_active_tokens": 66466, "cumulative_start": 34668759, "cumulative_end": 34735225, "loss_sum": 28253.850708007812, "token_normalized_loss": 0.42508727331278867, "grad_norm_before_clip": 0.1604718714952469, "learning_rates_at_step": { "lora": 4.787185802543103e-05, "row_tokens": 4.787185802543103e-05 }, "learning_rates_after_step": { "lora": 4.7701287163829116e-05, "row_tokens": 4.7701287163829116e-05 } }, { "update_id": 530, "row_count": 12, "row_ids_sha256": "f4928b3b7f05ec8a1ad258b1f9fc9dc2f71ad96b45535a56e1a0f1270e2c7c0c", "input_ids_vector_sha256": "35802e06880dfa83505c260f88897c4fcef1bdd45ed87db73c0418ba9b5d0728", "labels_vector_sha256": "64cefb5e9c3a6fb6d260fd5fb8e6eb49aa57b4a07d90bfd93ece9fd5ef269f33", "planned_active_tokens": 65391, "realized_active_tokens": 65391, "cumulative_start": 34735225, "cumulative_end": 34800616, "loss_sum": 23264.938537597656, "token_normalized_loss": 0.3557819659830505, "grad_norm_before_clip": 0.13910561800003052, "learning_rates_at_step": { "lora": 4.7701287163829116e-05, "row_tokens": 4.7701287163829116e-05 }, "learning_rates_after_step": { "lora": 4.752630455380788e-05, "row_tokens": 4.752630455380788e-05 } }, { "update_id": 531, "row_count": 10, "row_ids_sha256": "111b671b0f65f5a4e31ba5e447c810bb496e3defdbe4fba7ca2fdd35fbd76aa6", "input_ids_vector_sha256": "d5673d510217c5df0a74e8f9d1253c4993306a42be907c3310c773bd08b41bff", "labels_vector_sha256": "36feea73a9eb930414c9f8ada802be50b66b83f6e1dbe4b275d8b4b326916656", "planned_active_tokens": 67093, "realized_active_tokens": 67093, "cumulative_start": 34800616, "cumulative_end": 34867709, "loss_sum": 29024.749755859375, "token_normalized_loss": 0.43260473903178237, "grad_norm_before_clip": 0.1550244390964508, "learning_rates_at_step": { "lora": 4.752630455380788e-05, "row_tokens": 4.752630455380788e-05 }, "learning_rates_after_step": { "lora": 4.735616813632017e-05, "row_tokens": 4.735616813632017e-05 } }, { "update_id": 532, "row_count": 10, "row_ids_sha256": "256d4cfb5809d679bc9e57584e135313b55654b783d259bf4d2220031d44cf3f", "input_ids_vector_sha256": "63be5fb7523fac5c1a4ff8dae9cc241090040ae72d1e4a4d2622cb89940bd4e1", "labels_vector_sha256": "35f2678163d4f82e6ef533919a43b3bb944f9bcd4a7aa32dd9f7157a85b5100f", "planned_active_tokens": 65246, "realized_active_tokens": 65246, "cumulative_start": 34867709, "cumulative_end": 34932955, "loss_sum": 26801.085083007812, "token_normalized_loss": 0.4107697802625113, "grad_norm_before_clip": 0.150460347533226, "learning_rates_at_step": { "lora": 4.735616813632017e-05, "row_tokens": 4.735616813632017e-05 }, "learning_rates_after_step": { "lora": 4.7170082265606705e-05, "row_tokens": 4.7170082265606705e-05 } }, { "update_id": 533, "row_count": 11, "row_ids_sha256": "560dcc4f868066f8f434fa8d07022d362f8e356f03ce10dc8ca8418fdc64ddf9", "input_ids_vector_sha256": "93adf2ca88929df78be906b3ba5f5d8c4fc481a3a32c36f117186b668806ee74", "labels_vector_sha256": "10389639ede1690465a163e7716b7d130ba69a007f6edcdc941cef4ebf22d78a", "planned_active_tokens": 71376, "realized_active_tokens": 71376, "cumulative_start": 34932955, "cumulative_end": 35004331, "loss_sum": 29877.308532714844, "token_normalized_loss": 0.4185904019938753, "grad_norm_before_clip": 0.14394544064998627, "learning_rates_at_step": { "lora": 4.7170082265606705e-05, "row_tokens": 4.7170082265606705e-05 }, "learning_rates_after_step": { "lora": 4.7013111910636884e-05, "row_tokens": 4.7013111910636884e-05 } }, { "update_id": 534, "row_count": 11, "row_ids_sha256": "eef5743ca837cc359b6612875707354cfcd075a8d870f5b478c50f3c56bdc0cc", "input_ids_vector_sha256": "c85fc2e7e68b4f49c09ac6e94ded0e43cde70f9d65ae3e5119d0593615555b01", "labels_vector_sha256": "3d397d17d4e2c68ec228259a784a28d9665b6f77b98bfaa29c936663887f4c02", "planned_active_tokens": 60220, "realized_active_tokens": 60220, "cumulative_start": 35004331, "cumulative_end": 35064551, "loss_sum": 20835.13946533203, "token_normalized_loss": 0.3459837174581872, "grad_norm_before_clip": 0.151065394282341, "learning_rates_at_step": { "lora": 4.7013111910636884e-05, "row_tokens": 4.7013111910636884e-05 }, "learning_rates_after_step": { "lora": 4.6841117122600614e-05, "row_tokens": 4.6841117122600614e-05 } }, { "update_id": 535, "row_count": 8, "row_ids_sha256": "7bd8dd0568fe395a5ba27344cb011846d0c0867b3e82b96fdf58f6ad2299d075", "input_ids_vector_sha256": "1b6e1a112f0b418005b7365443cfd610d8852fe7a1688b0654101ac43c0d5011", "labels_vector_sha256": "87229295ba28a8cefe95fec858ea09ffa1a69acdce9416882d05f5e6254ff47f", "planned_active_tokens": 65997, "realized_active_tokens": 65997, "cumulative_start": 35064551, "cumulative_end": 35130548, "loss_sum": 27199.064208984375, "token_normalized_loss": 0.41212576645884474, "grad_norm_before_clip": 0.18271563947200775, "learning_rates_at_step": { "lora": 4.6841117122600614e-05, "row_tokens": 4.6841117122600614e-05 }, "learning_rates_after_step": { "lora": 4.667514410831898e-05, "row_tokens": 4.667514410831898e-05 } }, { "update_id": 536, "row_count": 10, "row_ids_sha256": "34b5e46336b724ea483ade2f0b8012d0cbe8ad28fad46f7afd466f9cbdedb4f6", "input_ids_vector_sha256": "52fd9fe9c213184454044ae788920779ef8365bd3e0f6f3e901e0bbf0edb6650", "labels_vector_sha256": "cadc75b5c98e6154260fbf2908b90df1f9eb2e3d90e83c6bcdaa9911872a1c47", "planned_active_tokens": 63700, "realized_active_tokens": 63700, "cumulative_start": 35130548, "cumulative_end": 35194248, "loss_sum": 27263.885131835938, "token_normalized_loss": 0.4280044761669692, "grad_norm_before_clip": 0.15791940689086914, "learning_rates_at_step": { "lora": 4.667514410831898e-05, "row_tokens": 4.667514410831898e-05 }, "learning_rates_after_step": { "lora": 4.650757736570644e-05, "row_tokens": 4.650757736570644e-05 } }, { "update_id": 537, "row_count": 9, "row_ids_sha256": "a736f636ed0d9201e558e1a3ef38f6f63f2be3d5d07c40c1543f8f1b124fd9fd", "input_ids_vector_sha256": "6851e518f921a09ad65d8dd6c86a218c349af07df9d2ff22e275354e52f3e6fe", "labels_vector_sha256": "e3613b9cf7058c5005642f23c74c6cb8ac2f4e93db3693c9e561d1637da14721", "planned_active_tokens": 64326, "realized_active_tokens": 64326, "cumulative_start": 35194248, "cumulative_end": 35258574, "loss_sum": 28655.043853759766, "token_normalized_loss": 0.4454659679407979, "grad_norm_before_clip": 0.1794072389602661, "learning_rates_at_step": { "lora": 4.650757736570644e-05, "row_tokens": 4.650757736570644e-05 }, "learning_rates_after_step": { "lora": 4.6319793564228884e-05, "row_tokens": 4.6319793564228884e-05 } }, { "update_id": 538, "row_count": 14, "row_ids_sha256": "5b9b3f61cb658cf97db53672bdb85382137c167b7d232bfc805eb0498ea9ebd1", "input_ids_vector_sha256": "1c2a190db9c52ec40648bca4ca290887bef13dc236e72ddea01c009b83d96433", "labels_vector_sha256": "ec981f60043531fc0db92b741de2a3bc0a1742702b9044330f741227a67a92eb", "planned_active_tokens": 72105, "realized_active_tokens": 72105, "cumulative_start": 35258574, "cumulative_end": 35330679, "loss_sum": 31572.854919433594, "token_normalized_loss": 0.43787330863925655, "grad_norm_before_clip": 0.1507759839296341, "learning_rates_at_step": { "lora": 4.6319793564228884e-05, "row_tokens": 4.6319793564228884e-05 }, "learning_rates_after_step": { "lora": 4.6161504948684876e-05, "row_tokens": 4.6161504948684876e-05 } }, { "update_id": 539, "row_count": 10, "row_ids_sha256": "65eb4ec0e46298c45f6daf81de046250ade06c8943050332cadda207a57480bc", "input_ids_vector_sha256": "ba5be3e1f3ea7c0c2c1a5ee90c20fb1029b67286f6564b98900ab1c50c408472", "labels_vector_sha256": "c525058db1bc4fd1e6852f926307a46fff2fad276463e50b6ed58392e5b67726", "planned_active_tokens": 60795, "realized_active_tokens": 60795, "cumulative_start": 35330679, "cumulative_end": 35391474, "loss_sum": 22747.09503173828, "token_normalized_loss": 0.37416062228371216, "grad_norm_before_clip": 0.15442630648612976, "learning_rates_at_step": { "lora": 4.6161504948684876e-05, "row_tokens": 4.6161504948684876e-05 }, "learning_rates_after_step": { "lora": 4.599477814432635e-05, "row_tokens": 4.599477814432635e-05 } }, { "update_id": 540, "row_count": 11, "row_ids_sha256": "9d10616ffffe93dd169c89cb52ef7f83d71fde76f0bb3d1d188cae6ccf52a747", "input_ids_vector_sha256": "38c6706e9cc45a3c21cd0866d0e72aab24e32cd06e0a8784149e4f6fd07b073b", "labels_vector_sha256": "57cfbb333f88083f466e2b6b5fadfe396d18c2d64e5a5d41ae72759c1d03bce4", "planned_active_tokens": 64052, "realized_active_tokens": 64052, "cumulative_start": 35391474, "cumulative_end": 35455526, "loss_sum": 22410.481811523438, "token_normalized_loss": 0.3498795012103203, "grad_norm_before_clip": 0.14333173632621765, "learning_rates_at_step": { "lora": 4.599477814432635e-05, "row_tokens": 4.599477814432635e-05 }, "learning_rates_after_step": { "lora": 4.5821276524801274e-05, "row_tokens": 4.5821276524801274e-05 } }, { "update_id": 541, "row_count": 12, "row_ids_sha256": "76a0e6ddd960fd88103e2de55a5c872edb50e868703e15d70202061cc71aa42f", "input_ids_vector_sha256": "1e879a39a99f2810784b149884087e5cdbe62d0da63f6f2f5fb03148aab03b79", "labels_vector_sha256": "51375d6356e87ad900fa888e478af854ef076c087efe686482a8d90404b747f8", "planned_active_tokens": 66673, "realized_active_tokens": 66673, "cumulative_start": 35455526, "cumulative_end": 35522199, "loss_sum": 21985.448486328125, "token_normalized_loss": 0.32975040100682623, "grad_norm_before_clip": 0.13978353142738342, "learning_rates_at_step": { "lora": 4.5821276524801274e-05, "row_tokens": 4.5821276524801274e-05 }, "learning_rates_after_step": { "lora": 4.564373140202566e-05, "row_tokens": 4.564373140202566e-05 } }, { "update_id": 542, "row_count": 10, "row_ids_sha256": "5c386e735b7378da78d9a13f2f04b097b1dfee748206dc8a88e044667ae8cf23", "input_ids_vector_sha256": "d708b8f5f2eb55f41659d8dc1451355f0a80eed54b02578092e11f9d4858d3f0", "labels_vector_sha256": "f451f25f51ae869d37b2ac47c3a4b283c8e3999a18251d530101ca5744dd22a8", "planned_active_tokens": 68247, "realized_active_tokens": 68247, "cumulative_start": 35522199, "cumulative_end": 35590446, "loss_sum": 22827.962646484375, "token_normalized_loss": 0.33449034604428585, "grad_norm_before_clip": 0.1381523460149765, "learning_rates_at_step": { "lora": 4.564373140202566e-05, "row_tokens": 4.564373140202566e-05 }, "learning_rates_after_step": { "lora": 4.547280215831046e-05, "row_tokens": 4.547280215831046e-05 } }, { "update_id": 543, "row_count": 9, "row_ids_sha256": "4522e303f43d804fba51b70f7a7165aa78cf5a2958df1cf6a0805947f9c43cfb", "input_ids_vector_sha256": "6bfc3e572e72f469327d94a2ec3b495368f04ec3c688a2f19a7fca457c570006", "labels_vector_sha256": "7dc143124edec4b957d9bfd703655dd09b227c79fe6fac7b2b4491250911f14c", "planned_active_tokens": 65724, "realized_active_tokens": 65724, "cumulative_start": 35590446, "cumulative_end": 35656170, "loss_sum": 25838.217651367188, "token_normalized_loss": 0.3931321534198647, "grad_norm_before_clip": 0.14999204874038696, "learning_rates_at_step": { "lora": 4.547280215831046e-05, "row_tokens": 4.547280215831046e-05 }, "learning_rates_after_step": { "lora": 4.5306467564112796e-05, "row_tokens": 4.5306467564112796e-05 } }, { "update_id": 544, "row_count": 10, "row_ids_sha256": "4d9f514185c52b6ec980f2497c8911868599b0fd935e02fd795b65b7dbd124c4", "input_ids_vector_sha256": "2f55faee32ce0ad9cf38521e328253d9d3506856a6814a6d3e4a7578825702dd", "labels_vector_sha256": "3d53c0a55e3304ba57fc94e327d862089e6b33430ec6ac770d1bd03481638c2b", "planned_active_tokens": 63977, "realized_active_tokens": 63977, "cumulative_start": 35656170, "cumulative_end": 35720147, "loss_sum": 24872.250854492188, "token_normalized_loss": 0.38876863332904305, "grad_norm_before_clip": 0.16693273186683655, "learning_rates_at_step": { "lora": 4.5306467564112796e-05, "row_tokens": 4.5306467564112796e-05 }, "learning_rates_after_step": { "lora": 4.5129712807877435e-05, "row_tokens": 4.5129712807877435e-05 } }, { "update_id": 545, "row_count": 10, "row_ids_sha256": "8e65cf884c796e90be961dfdc4c9ee0ae61adf1c0af5ccd0d55ea8f9776bef08", "input_ids_vector_sha256": "18a362de81b10db618c6c656dc7d4b7f9d9ddc0d723c6530097c86b4983d6658", "labels_vector_sha256": "2f3e44af64d50d2c08ad14afe99829c74be464d3bb4913eb779aa999f914d955", "planned_active_tokens": 68007, "realized_active_tokens": 68007, "cumulative_start": 35720147, "cumulative_end": 35788154, "loss_sum": 23430.286010742188, "token_normalized_loss": 0.3445275634970251, "grad_norm_before_clip": 0.13962413370609283, "learning_rates_at_step": { "lora": 4.5129712807877435e-05, "row_tokens": 4.5129712807877435e-05 }, "learning_rates_after_step": { "lora": 4.496876959291761e-05, "row_tokens": 4.496876959291761e-05 } }, { "update_id": 546, "row_count": 12, "row_ids_sha256": "fa1b7b513a8e5dca7802a58592a6566ee9c02a3b768ff21d60e932c5bb9b6c3c", "input_ids_vector_sha256": "8c831cbc16ec3524c6d8cf746a8cc3aa21d90fe6337095fffe74fa5b56144775", "labels_vector_sha256": "0ee542fd89c38c1193899a5f1d5ccc062341a7e45898a7ea2f353c7676d76d03", "planned_active_tokens": 61944, "realized_active_tokens": 61944, "cumulative_start": 35788154, "cumulative_end": 35850098, "loss_sum": 22642.970153808594, "token_normalized_loss": 0.3655393606129503, "grad_norm_before_clip": 0.15260466933250427, "learning_rates_at_step": { "lora": 4.496876959291761e-05, "row_tokens": 4.496876959291761e-05 }, "learning_rates_after_step": { "lora": 4.478546812128118e-05, "row_tokens": 4.478546812128118e-05 } }, { "update_id": 547, "row_count": 9, "row_ids_sha256": "741ef6f249c2f10af29cac45a1eac1fec62c96e48c3418ef44938f682f7939e6", "input_ids_vector_sha256": "1502ea039aa17094858d21acb807deb4098567483a8161aaaaa53eec01c3833b", "labels_vector_sha256": "652f20cde849f1f6cc1136bfa353a90c40bb853bd713d0eabe65b34b725164c1", "planned_active_tokens": 70574, "realized_active_tokens": 70574, "cumulative_start": 35850098, "cumulative_end": 35920672, "loss_sum": 28602.174194335938, "token_normalized_loss": 0.40527919905823584, "grad_norm_before_clip": 0.15666046738624573, "learning_rates_at_step": { "lora": 4.478546812128118e-05, "row_tokens": 4.478546812128118e-05 }, "learning_rates_after_step": { "lora": 4.462588561849964e-05, "row_tokens": 4.462588561849964e-05 } }, { "update_id": 548, "row_count": 10, "row_ids_sha256": "57c07c3637546f7f52b42be8a37eb8b02aa1c0b3e889d5cacf7c31b967e6433d", "input_ids_vector_sha256": "5580d703a5ee7d0f810aa3e667c95daba0e68eca99074564b99f115e799cb40f", "labels_vector_sha256": "bc6d11d58d0562dcddaf5eaac9532ddc1dafc24be9a8169ccf4cc40be6ef7997", "planned_active_tokens": 61464, "realized_active_tokens": 61464, "cumulative_start": 35920672, "cumulative_end": 35982136, "loss_sum": 24322.631958007812, "token_normalized_loss": 0.3957215924444848, "grad_norm_before_clip": 0.15205591917037964, "learning_rates_at_step": { "lora": 4.462588561849964e-05, "row_tokens": 4.462588561849964e-05 }, "learning_rates_after_step": { "lora": 4.444598562324153e-05, "row_tokens": 4.444598562324153e-05 } }, { "update_id": 549, "row_count": 12, "row_ids_sha256": "503969de8dc19ef66e1327f986ed2b4983c1e0fc36392452e327e517f2bb82eb", "input_ids_vector_sha256": "0df1d8072a90755760cebd487d0417f6754593d4b983b0ab81f0a210c479aa73", "labels_vector_sha256": "82ce50cf8e92b3f707447a378b7f14e742aa15e7407dab8bb1bb20fd440bafcb", "planned_active_tokens": 69315, "realized_active_tokens": 69315, "cumulative_start": 35982136, "cumulative_end": 36051451, "loss_sum": 29059.79998779297, "token_normalized_loss": 0.41924258800826614, "grad_norm_before_clip": 0.14533141255378723, "learning_rates_at_step": { "lora": 4.444598562324153e-05, "row_tokens": 4.444598562324153e-05 }, "learning_rates_after_step": { "lora": 4.429278210246813e-05, "row_tokens": 4.429278210246813e-05 } }, { "update_id": 550, "row_count": 8, "row_ids_sha256": "56e3d4243dd031ff6d419c7e01781265e94c05288a56bf0bbc1fa403ea99576e", "input_ids_vector_sha256": "d3afe159a79e4ef508c7e5aca773544c874f467d46fd6fefdf22f3955e301f5f", "labels_vector_sha256": "5a2701a7b271fb5ccb2071888a5efdb94c3a81655315f1b3ea840153ebfdbc64", "planned_active_tokens": 59051, "realized_active_tokens": 59051, "cumulative_start": 36051451, "cumulative_end": 36110502, "loss_sum": 28575.88671875, "token_normalized_loss": 0.48391876037238996, "grad_norm_before_clip": 0.1681520789861679, "learning_rates_at_step": { "lora": 4.429278210246813e-05, "row_tokens": 4.429278210246813e-05 }, "learning_rates_after_step": { "lora": 4.410842417752191e-05, "row_tokens": 4.410842417752191e-05 } }, { "update_id": 551, "row_count": 12, "row_ids_sha256": "330f8be9f1b9dcd797383ae628ee3a953249291eb0540c6af01194e90af1a602", "input_ids_vector_sha256": "fc32129385c12899cd41923a7e7ca005a848ff8717fe7f17959283381f2af87d", "labels_vector_sha256": "a65251da005075613e75e4382c1b2fb7f52f42907e6894878a4fdc13cd3d446b", "planned_active_tokens": 71087, "realized_active_tokens": 71087, "cumulative_start": 36110502, "cumulative_end": 36181589, "loss_sum": 29693.199920654297, "token_normalized_loss": 0.41770225105369896, "grad_norm_before_clip": 0.15570475161075592, "learning_rates_at_step": { "lora": 4.410842417752191e-05, "row_tokens": 4.410842417752191e-05 }, "learning_rates_after_step": { "lora": 4.394880809793489e-05, "row_tokens": 4.394880809793489e-05 } }, { "update_id": 552, "row_count": 10, "row_ids_sha256": "da4de8381632e689aa39f118a43fcbf2034887f20f2efcc47e6d311f8ad32958", "input_ids_vector_sha256": "bd7edde5dc876352017cef0b3fbf9908245c6e5a90fed3fb9b1913c2bf6d1c3c", "labels_vector_sha256": "5d988c53e9dc083ee302ebcf01d55d3f4916f3a67441d1da9eee9a33ee5355d6", "planned_active_tokens": 61572, "realized_active_tokens": 61572, "cumulative_start": 36181589, "cumulative_end": 36243161, "loss_sum": 22701.644104003906, "token_normalized_loss": 0.36870077476781504, "grad_norm_before_clip": 0.15520843863487244, "learning_rates_at_step": { "lora": 4.394880809793489e-05, "row_tokens": 4.394880809793489e-05 }, "learning_rates_after_step": { "lora": 4.3762365417567555e-05, "row_tokens": 4.3762365417567555e-05 } }, { "update_id": 553, "row_count": 11, "row_ids_sha256": "fb3e7ab4120ccb0526039be0f38470a5d14a7c5425774ae43705eebf8c94e7cc", "input_ids_vector_sha256": "2d8af506b107fc0ad1851818f67608f698a58fae1da5963dd7c4966db94aecd9", "labels_vector_sha256": "eeb78b2888cb078f6ffa2048b8906b6f5d1925d7af0a6a3c31f303af6feed16c", "planned_active_tokens": 71951, "realized_active_tokens": 71951, "cumulative_start": 36243161, "cumulative_end": 36315112, "loss_sum": 30421.820556640625, "token_normalized_loss": 0.4228130332676492, "grad_norm_before_clip": 0.15224657952785492, "learning_rates_at_step": { "lora": 4.3762365417567555e-05, "row_tokens": 4.3762365417567555e-05 }, "learning_rates_after_step": { "lora": 4.359624229122313e-05, "row_tokens": 4.359624229122313e-05 } }, { "update_id": 554, "row_count": 10, "row_ids_sha256": "5457fea63877d5e98e1ddf0021bc21634cc8ce728f0f15ff0b16734f17f3e630", "input_ids_vector_sha256": "9956f9b457fc755c16ffd8b269c93f5e36a8b7c43b7c462bdafcdbdeb9b4858f", "labels_vector_sha256": "7697974f16d55b36a9794754ecf7add9bd08de9a190552a2026a4ac0f0a5c8a3", "planned_active_tokens": 64138, "realized_active_tokens": 64138, "cumulative_start": 36315112, "cumulative_end": 36379250, "loss_sum": 25226.01611328125, "token_normalized_loss": 0.39330843046682545, "grad_norm_before_clip": 0.1597280502319336, "learning_rates_at_step": { "lora": 4.359624229122313e-05, "row_tokens": 4.359624229122313e-05 }, "learning_rates_after_step": { "lora": 4.342962414340776e-05, "row_tokens": 4.342962414340776e-05 } }, { "update_id": 555, "row_count": 11, "row_ids_sha256": "6692e73b799d9012bf9cf1ce6042787b4e76c98deec7ef14fd164088c8785da7", "input_ids_vector_sha256": "9e8e18fec50df815fd7b0dfa2182ca2bc75f51ec74a1cf2712b175f8a4d8d5c7", "labels_vector_sha256": "5d1169261080240bb6f8124c23878d3de6003cd12c12b0bb944e2dbd47459e83", "planned_active_tokens": 64357, "realized_active_tokens": 64357, "cumulative_start": 36379250, "cumulative_end": 36443607, "loss_sum": 24568.32830810547, "token_normalized_loss": 0.38175067682001135, "grad_norm_before_clip": 0.15307162702083588, "learning_rates_at_step": { "lora": 4.342962414340776e-05, "row_tokens": 4.342962414340776e-05 }, "learning_rates_after_step": { "lora": 4.3254017261058735e-05, "row_tokens": 4.3254017261058735e-05 } }, { "update_id": 556, "row_count": 7, "row_ids_sha256": "24d8ba54ee42d15e63ff020173de9e6bca5ca25514e47aaae6779b50169a1cfb", "input_ids_vector_sha256": "e9260762fccd98874c9221b260dd32eea74ddb4318f5fd42f7e5cd1bbc81d19e", "labels_vector_sha256": "7f55a66b92bb1d16f5fa1b75c007b9dbe54bb4b786e90a983243591d7405b282", "planned_active_tokens": 67860, "realized_active_tokens": 67860, "cumulative_start": 36443607, "cumulative_end": 36511467, "loss_sum": 31035.427978515625, "token_normalized_loss": 0.45734494515938146, "grad_norm_before_clip": 0.1655304729938507, "learning_rates_at_step": { "lora": 4.3254017261058735e-05, "row_tokens": 4.3254017261058735e-05 }, "learning_rates_after_step": { "lora": 4.309599688667441e-05, "row_tokens": 4.309599688667441e-05 } }, { "update_id": 557, "row_count": 10, "row_ids_sha256": "2e12558dfbf94f684ec77e90f44c3ca409329592727027d01941ca1ebf4f4b0f", "input_ids_vector_sha256": "9b8d1a5c0533a710edc03a4354cf131d7cee053160a65e3abcb5480cb3ffc463", "labels_vector_sha256": "9163381c240e0cd5f518e1843f147c648b3ef967b260b084bfd49963ddfb7cf7", "planned_active_tokens": 61092, "realized_active_tokens": 61092, "cumulative_start": 36511467, "cumulative_end": 36572559, "loss_sum": 24706.33282470703, "token_normalized_loss": 0.4044119168582962, "grad_norm_before_clip": 0.17342741787433624, "learning_rates_at_step": { "lora": 4.309599688667441e-05, "row_tokens": 4.309599688667441e-05 }, "learning_rates_after_step": { "lora": 4.29330140886058e-05, "row_tokens": 4.29330140886058e-05 } }, { "update_id": 558, "row_count": 11, "row_ids_sha256": "0d7fbca02409f76d0f891c6adb4eec1f732d786df63aa63d2187e46ddb561be1", "input_ids_vector_sha256": "a7b7ad62c02a4b6406f81609e9a37f675e63cd66ef363880c80b86f7bc41f621", "labels_vector_sha256": "c787b8dc8af216450d9f4ac69dc4cc6928b7e2d703a8ae8e81f8b5701fd51784", "planned_active_tokens": 63039, "realized_active_tokens": 63039, "cumulative_start": 36572559, "cumulative_end": 36635598, "loss_sum": 22847.777587890625, "token_normalized_loss": 0.3624387694584404, "grad_norm_before_clip": 0.15218116343021393, "learning_rates_at_step": { "lora": 4.29330140886058e-05, "row_tokens": 4.29330140886058e-05 }, "learning_rates_after_step": { "lora": 4.2761013737493496e-05, "row_tokens": 4.2761013737493496e-05 } }, { "update_id": 559, "row_count": 9, "row_ids_sha256": "d129745bfbc47a648e374cec4b0cacab705ba09a8f5b398560b59e1bf7dde6d4", "input_ids_vector_sha256": "a26bb639469fb5bfb0a713eb9bdfbdefcb67f2182760df059dfdc5523142588b", "labels_vector_sha256": "d72a1ee90607233f95aaa2e9992e9bb680e6dbb6fda129b8a8b7405e355fb465", "planned_active_tokens": 66559, "realized_active_tokens": 66559, "cumulative_start": 36635598, "cumulative_end": 36702157, "loss_sum": 24165.32861328125, "token_normalized_loss": 0.3630662812434269, "grad_norm_before_clip": 0.15084625780582428, "learning_rates_at_step": { "lora": 4.2761013737493496e-05, "row_tokens": 4.2761013737493496e-05 }, "learning_rates_after_step": { "lora": 4.2584920288690486e-05, "row_tokens": 4.2584920288690486e-05 } }, { "update_id": 560, "row_count": 12, "row_ids_sha256": "1057629a5fd329e392811070431873a9e9cd845dab1c033b087625ec786ec9d3", "input_ids_vector_sha256": "c72a390c2ac1c1c0af5791b449fcc83f474f310b1ac55ce3ed2df9ef2443c368", "labels_vector_sha256": "20f441ecee322a5542d6182284871c831ec393a529e46d08a91cfd736caa3f0a", "planned_active_tokens": 68178, "realized_active_tokens": 68178, "cumulative_start": 36702157, "cumulative_end": 36770335, "loss_sum": 26156.89404296875, "token_normalized_loss": 0.3836559306956606, "grad_norm_before_clip": 0.14955028891563416, "learning_rates_at_step": { "lora": 4.2584920288690486e-05, "row_tokens": 4.2584920288690486e-05 }, "learning_rates_after_step": { "lora": 4.241817560491406e-05, "row_tokens": 4.241817560491406e-05 } }, { "update_id": 561, "row_count": 11, "row_ids_sha256": "5ac61f1cb1b1b81933ec954011ecaab76a82fcbafa083ef79804cdd87dd2e0d8", "input_ids_vector_sha256": "2627521ef6b31e3a9d90687a98d1f5233754dff4be64e3169fd4ddb5e04fac32", "labels_vector_sha256": "fdbbfa19b90af0748aa9bc503966b4f40b35b25cea5ccfdcdbc86342bcf45d52", "planned_active_tokens": 64592, "realized_active_tokens": 64592, "cumulative_start": 36770335, "cumulative_end": 36834927, "loss_sum": 24391.947967529297, "token_normalized_loss": 0.3776310993238992, "grad_norm_before_clip": 0.15327569842338562, "learning_rates_at_step": { "lora": 4.241817560491406e-05, "row_tokens": 4.241817560491406e-05 }, "learning_rates_after_step": { "lora": 4.2253464706398196e-05, "row_tokens": 4.2253464706398196e-05 } }, { "update_id": 562, "row_count": 10, "row_ids_sha256": "b50b0570f3b40692b2c3e548f617b585e266febfc63bbbbdc6edf814b059cebe", "input_ids_vector_sha256": "340162b940f3e0aab09542832f75a42cf36ef8cdd44991c0fab9e755b880739b", "labels_vector_sha256": "13609b6f8ecbfb9683f1dcf09dc86397eb21a3c03bad206a329d9281c2134495", "planned_active_tokens": 63837, "realized_active_tokens": 63837, "cumulative_start": 36834927, "cumulative_end": 36898764, "loss_sum": 21665.113891601562, "token_normalized_loss": 0.3393817674953642, "grad_norm_before_clip": 0.15214373171329498, "learning_rates_at_step": { "lora": 4.2253464706398196e-05, "row_tokens": 4.2253464706398196e-05 }, "learning_rates_after_step": { "lora": 4.207533843615233e-05, "row_tokens": 4.207533843615233e-05 } }, { "update_id": 563, "row_count": 12, "row_ids_sha256": "3183ba51324511eba27cfb5ac7f1b9a474d3f7a1fa38181fc8cfbe83b332f4b6", "input_ids_vector_sha256": "ae09b94aad84fe2e126ca349c1b3942fefbbc481103db5163c3898ef2a5919ea", "labels_vector_sha256": "35f27c9cca2b65b65a447df91027fe7104bb8e1e5ea629ed01a800c2003556f0", "planned_active_tokens": 69074, "realized_active_tokens": 69074, "cumulative_start": 36898764, "cumulative_end": 36967838, "loss_sum": 27581.470703125, "token_normalized_loss": 0.39930322122832035, "grad_norm_before_clip": 0.16483938694000244, "learning_rates_at_step": { "lora": 4.207533843615233e-05, "row_tokens": 4.207533843615233e-05 }, "learning_rates_after_step": { "lora": 4.1919829786177564e-05, "row_tokens": 4.1919829786177564e-05 } }, { "update_id": 564, "row_count": 9, "row_ids_sha256": "0509045b8fd29b547ffdc7115dd433e9b6a8d07557017887e2e2e5b1f0db0562", "input_ids_vector_sha256": "7a52344854a6c5e40beeb32f0deb4acb31da818e75afa35ab27f61fce5d09474", "labels_vector_sha256": "f2f99ceed19751fa6790f4d64af0b353475016d5f2db94fbcb8618e32c8fbec1", "planned_active_tokens": 60336, "realized_active_tokens": 60336, "cumulative_start": 36967838, "cumulative_end": 37028174, "loss_sum": 26792.17205810547, "token_normalized_loss": 0.44404952363606254, "grad_norm_before_clip": 0.16291451454162598, "learning_rates_at_step": { "lora": 4.1919829786177564e-05, "row_tokens": 4.1919829786177564e-05 }, "learning_rates_after_step": { "lora": 4.174593906771501e-05, "row_tokens": 4.174593906771501e-05 } }, { "update_id": 565, "row_count": 13, "row_ids_sha256": "1706e044a11628d8ccb060c800df38031cda94d290d4f343022c43a32fd91105", "input_ids_vector_sha256": "a2d1b6821ea62529754e2709f8c3d30fbf8cdf18d7ef78736d2c055ac17ddf6e", "labels_vector_sha256": "b80b777d38afdec1fad4f58ce130407c23b69f7dd7bd8ca226eac5182319c046", "planned_active_tokens": 67505, "realized_active_tokens": 67505, "cumulative_start": 37028174, "cumulative_end": 37095679, "loss_sum": 19149.710083007812, "token_normalized_loss": 0.28367839542267703, "grad_norm_before_clip": 0.1389259397983551, "learning_rates_at_step": { "lora": 4.174593906771501e-05, "row_tokens": 4.174593906771501e-05 }, "learning_rates_after_step": { "lora": 4.158149352334598e-05, "row_tokens": 4.158149352334598e-05 } }, { "update_id": 566, "row_count": 11, "row_ids_sha256": "efaf4db3ee4912abd785e7eb19905dd9d7e1876bebcefe753a65aeb7316b2857", "input_ids_vector_sha256": "44e1c9daccb81f5eb3427d29257eaa4e93732a3a32551a95c9755c97b4f29066", "labels_vector_sha256": "988026a0c9e54dae3b2871f32b0e61682b93cb4a7848230b2b710bda46bfea96", "planned_active_tokens": 63875, "realized_active_tokens": 63875, "cumulative_start": 37095679, "cumulative_end": 37159554, "loss_sum": 24664.668029785156, "token_normalized_loss": 0.38613961690466, "grad_norm_before_clip": 0.15865391492843628, "learning_rates_at_step": { "lora": 4.158149352334598e-05, "row_tokens": 4.158149352334598e-05 }, "learning_rates_after_step": { "lora": 4.1403681220356474e-05, "row_tokens": 4.1403681220356474e-05 } }, { "update_id": 567, "row_count": 11, "row_ids_sha256": "793292541bc13a3eeccad4c16594da709c092d38181b8592f4dfced09c20643d", "input_ids_vector_sha256": "2e6816f6d7e973dd19574d77a34c685f4a0188ee182033c971dfb9e9ba245ef1", "labels_vector_sha256": "d47c54c728009bd1492ac9048d3e8713dd3e139c82d49afe2015ead3b8387cf7", "planned_active_tokens": 69108, "realized_active_tokens": 69108, "cumulative_start": 37159554, "cumulative_end": 37228662, "loss_sum": 26450.288940429688, "token_normalized_loss": 0.38273845199441003, "grad_norm_before_clip": 0.15719184279441833, "learning_rates_at_step": { "lora": 4.1403681220356474e-05, "row_tokens": 4.1403681220356474e-05 }, "learning_rates_after_step": { "lora": 4.124270519371966e-05, "row_tokens": 4.124270519371966e-05 } }, { "update_id": 568, "row_count": 10, "row_ids_sha256": "afbfcaf6b07b4bf2544128ad0e17fbd35bacc235dcfd272f94760aaa162f58f3", "input_ids_vector_sha256": "29b2f7455080ac855f9330987b26546080e8820dd57013f9b64ac88d101d3fd9", "labels_vector_sha256": "74326c400c3f0b5ea74749e98529123c883b7b2f45dd70943df53adfb6fa112e", "planned_active_tokens": 62602, "realized_active_tokens": 62602, "cumulative_start": 37228662, "cumulative_end": 37291264, "loss_sum": 24318.971771240234, "token_normalized_loss": 0.3884695660081185, "grad_norm_before_clip": 0.15748414397239685, "learning_rates_at_step": { "lora": 4.124270519371966e-05, "row_tokens": 4.124270519371966e-05 }, "learning_rates_after_step": { "lora": 4.106974536679426e-05, "row_tokens": 4.106974536679426e-05 } }, { "update_id": 569, "row_count": 13, "row_ids_sha256": "3bb34bfb4918fc76330c83c4472996f7164a485a918a0dff2fb156bd67e42df4", "input_ids_vector_sha256": "6f030d17d7adce04c32c9823c2fe2484f096b3f04f8c0b13b488e4f2dd886ecd", "labels_vector_sha256": "82ef16102cf46c59974ea719bfa13e3f850aa9e246f739263a2d0ce05f8a9a5f", "planned_active_tokens": 67303, "realized_active_tokens": 67303, "cumulative_start": 37291264, "cumulative_end": 37358567, "loss_sum": 26452.45443725586, "token_normalized_loss": 0.3930352946712013, "grad_norm_before_clip": 0.17026911675930023, "learning_rates_at_step": { "lora": 4.106974536679426e-05, "row_tokens": 4.106974536679426e-05 }, "learning_rates_after_step": { "lora": 4.087634461843608e-05, "row_tokens": 4.087634461843608e-05 } }, { "update_id": 570, "row_count": 11, "row_ids_sha256": "7c86ec8dcbff034c8ef9bb26a43b1fa9f35e6309b21bd98d67dd1de09ad86752", "input_ids_vector_sha256": "c99ed980b03957b1cca6edee6873cb8825fc2add199932e43d809b783d176903", "labels_vector_sha256": "72c48aede109115fab8d4277d2aed609c9022f3df235d29e9628da2dee25a1f3", "planned_active_tokens": 75308, "realized_active_tokens": 75308, "cumulative_start": 37358567, "cumulative_end": 37433875, "loss_sum": 29737.40948486328, "token_normalized_loss": 0.394877164243683, "grad_norm_before_clip": 0.15418741106987, "learning_rates_at_step": { "lora": 4.087634461843608e-05, "row_tokens": 4.087634461843608e-05 }, "learning_rates_after_step": { "lora": 4.072865651321741e-05, "row_tokens": 4.072865651321741e-05 } }, { "update_id": 571, "row_count": 11, "row_ids_sha256": "78385d6613c1a7d06d3b46172e7954118293d7e157c70cd454d2c32f727c46ec", "input_ids_vector_sha256": "9500b5e3fb64e78ce7cca9deec166376dcd1c1f0c5fa4f2c810506ef67292a3b", "labels_vector_sha256": "905ebf2925885041a66cb23c728cfde9d5ac3bb62abbab1ce19f4e0f5c1c9724", "planned_active_tokens": 57545, "realized_active_tokens": 57545, "cumulative_start": 37433875, "cumulative_end": 37491420, "loss_sum": 20671.35952758789, "token_normalized_loss": 0.3592207755250307, "grad_norm_before_clip": 0.15943990647792816, "learning_rates_at_step": { "lora": 4.072865651321741e-05, "row_tokens": 4.072865651321741e-05 }, "learning_rates_after_step": { "lora": 4.057148237886293e-05, "row_tokens": 4.057148237886293e-05 } }, { "update_id": 572, "row_count": 12, "row_ids_sha256": "7f8e855d46fcfe833f299eb5b44de665352a1d79415d1f19e4e2ec7835249545", "input_ids_vector_sha256": "4e5a3badc6744bbd28b911e78b603c1e02285dd4d47557f06f0be05ec4fc3ec7", "labels_vector_sha256": "92b6f09ad79ce026f168ee00ba69f4c8bcf60a2872dd08db49775f444f752a45", "planned_active_tokens": 61277, "realized_active_tokens": 61277, "cumulative_start": 37491420, "cumulative_end": 37552697, "loss_sum": 20627.744049072266, "token_normalized_loss": 0.33663110219286624, "grad_norm_before_clip": 0.154272198677063, "learning_rates_at_step": { "lora": 4.057148237886293e-05, "row_tokens": 4.057148237886293e-05 }, "learning_rates_after_step": { "lora": 4.039621863511472e-05, "row_tokens": 4.039621863511472e-05 } }, { "update_id": 573, "row_count": 10, "row_ids_sha256": "3f5b177c83641478d8fcdbfb057f6f6f0dc3ab8ab2f2d8005476cc5342e6290d", "input_ids_vector_sha256": "b52bd7f39195ee1cfc25b6d3847c71eecb20c9e144a206d76b0d7cf56e5eac24", "labels_vector_sha256": "bb7bc48a9d49163bdd4f2ecdc5ecc564302dfca7a45e9973f1857ea36ad90a24", "planned_active_tokens": 68374, "realized_active_tokens": 68374, "cumulative_start": 37552697, "cumulative_end": 37621071, "loss_sum": 27279.216720581055, "token_normalized_loss": 0.39897061339955325, "grad_norm_before_clip": 0.15159516036510468, "learning_rates_at_step": { "lora": 4.039621863511472e-05, "row_tokens": 4.039621863511472e-05 }, "learning_rates_after_step": { "lora": 4.021992249387121e-05, "row_tokens": 4.021992249387121e-05 } }, { "update_id": 574, "row_count": 10, "row_ids_sha256": "07a6743dd19efc63094b415dc52fd1d814ab38190f2ac4e4034e3a5888b90abd", "input_ids_vector_sha256": "859cad442be05e4fe8fee0e59923d71382136c3941ba90c2153de160ffd38f77", "labels_vector_sha256": "6c1b424b720a4255a9dcaf0f38b84c1b679321292c297d1a0c99672b87543bfd", "planned_active_tokens": 68825, "realized_active_tokens": 68825, "cumulative_start": 37621071, "cumulative_end": 37689896, "loss_sum": 26468.205627441406, "token_normalized_loss": 0.38457254816478614, "grad_norm_before_clip": 0.1591263860464096, "learning_rates_at_step": { "lora": 4.021992249387121e-05, "row_tokens": 4.021992249387121e-05 }, "learning_rates_after_step": { "lora": 4.00691905482261e-05, "row_tokens": 4.00691905482261e-05 } }, { "update_id": 575, "row_count": 10, "row_ids_sha256": "fc480c53f3a9341a6acdc8923bcc6d478f02b64f73bf3ad01207e1227d22bae9", "input_ids_vector_sha256": "01dca05072c12c3f35f86fb53c7f90ac8ba0cd1d40b3d5d202d157311ce400e6", "labels_vector_sha256": "24e3037b9c4304571ce6a9180e320615bcebbc92f4e014c9d6949624408bad25", "planned_active_tokens": 58884, "realized_active_tokens": 58884, "cumulative_start": 37689896, "cumulative_end": 37748780, "loss_sum": 21131.43829345703, "token_normalized_loss": 0.35886553721651093, "grad_norm_before_clip": 0.1685124784708023, "learning_rates_at_step": { "lora": 4.00691905482261e-05, "row_tokens": 4.00691905482261e-05 }, "learning_rates_after_step": { "lora": 3.9892918391580304e-05, "row_tokens": 3.9892918391580304e-05 } }, { "update_id": 576, "row_count": 10, "row_ids_sha256": "756f802e0750f6e43845ccf6a9edaa6fdbbad7730957dbbd24bde500e2dc2a96", "input_ids_vector_sha256": "7b05f002525860ec5df5a21d79601326cf0211de85b704d764a9c96d520e62ac", "labels_vector_sha256": "b1b880cf57471331921ecc66e2d5f4bde6f39b41a10f7b3dc284d819b237e259", "planned_active_tokens": 68908, "realized_active_tokens": 68908, "cumulative_start": 37748780, "cumulative_end": 37817688, "loss_sum": 24474.7548828125, "token_normalized_loss": 0.35518016605927466, "grad_norm_before_clip": 0.1641455441713333, "learning_rates_at_step": { "lora": 3.9892918391580304e-05, "row_tokens": 3.9892918391580304e-05 }, "learning_rates_after_step": { "lora": 3.9715826568288724e-05, "row_tokens": 3.9715826568288724e-05 } }, { "update_id": 577, "row_count": 14, "row_ids_sha256": "97abc0ab65154af04af0ccc63ae1c955bd87d004bdabe06afdb0472ddb3f0f32", "input_ids_vector_sha256": "5af66bbe4ac6c55bd53f1eef802c41170bf32e82623e52ef1b2c6ef915d9986e", "labels_vector_sha256": "33f691ed2b2ad5257f98df28c66a0ab02942cfd3c26d08c04ceee8807e0f93be", "planned_active_tokens": 69280, "realized_active_tokens": 69280, "cumulative_start": 37817688, "cumulative_end": 37886968, "loss_sum": 24619.48321533203, "token_normalized_loss": 0.35536205564855705, "grad_norm_before_clip": 0.14976951479911804, "learning_rates_at_step": { "lora": 3.9715826568288724e-05, "row_tokens": 3.9715826568288724e-05 }, "learning_rates_after_step": { "lora": 3.956499824950597e-05, "row_tokens": 3.956499824950597e-05 } }, { "update_id": 578, "row_count": 9, "row_ids_sha256": "2dad2fddc834096b14c7d41f04760c7cbb8f87980b2bc6505b69c5341cce9a53", "input_ids_vector_sha256": "1e44e4c1fbca53035bedea2f3d273b0f2abb64eb1a0d868b72576072455e0370", "labels_vector_sha256": "03a66fd21622146813ec1fd74471636bf7669c4d95590983915b9c2f434fdcde", "planned_active_tokens": 59047, "realized_active_tokens": 59047, "cumulative_start": 37886968, "cumulative_end": 37946015, "loss_sum": 24015.070922851562, "token_normalized_loss": 0.40671111018089934, "grad_norm_before_clip": 0.16029740869998932, "learning_rates_at_step": { "lora": 3.956499824950597e-05, "row_tokens": 3.956499824950597e-05 }, "learning_rates_after_step": { "lora": 3.9383069848873165e-05, "row_tokens": 3.9383069848873165e-05 } }, { "update_id": 579, "row_count": 8, "row_ids_sha256": "3be4bb416de29c05d77fb67f9af47afa59ce277d08af9568c842555702a7fb16", "input_ids_vector_sha256": "6c6a3a39b32285c6d4a13e65c614a2e8fb929f88edbf52653424668d5fd19de8", "labels_vector_sha256": "b379499654ca129e334558e79aee13deea01f6a43077dfe3df9f4bd20554feb5", "planned_active_tokens": 71274, "realized_active_tokens": 71274, "cumulative_start": 37946015, "cumulative_end": 38017289, "loss_sum": 33539.525634765625, "token_normalized_loss": 0.4705716759935688, "grad_norm_before_clip": 0.15709666907787323, "learning_rates_at_step": { "lora": 3.9383069848873165e-05, "row_tokens": 3.9383069848873165e-05 }, "learning_rates_after_step": { "lora": 3.92306724780301e-05, "row_tokens": 3.92306724780301e-05 } }, { "update_id": 580, "row_count": 9, "row_ids_sha256": "23a4224026f395a0a244e18591a2cc5ad20917aed0bd9a81a3fd7d08e107e41a", "input_ids_vector_sha256": "6b9509fe387cd3712e52eb0c45380e765a343af9fbdae5d814af92a421e50c3d", "labels_vector_sha256": "68ff5600027b3e4997940d13ab4ea0220251581378dde8781e5ce4cd0d8edf9e", "planned_active_tokens": 59749, "realized_active_tokens": 59749, "cumulative_start": 38017289, "cumulative_end": 38077038, "loss_sum": 26604.400451660156, "token_normalized_loss": 0.4452693844526294, "grad_norm_before_clip": 0.17055445909500122, "learning_rates_at_step": { "lora": 3.92306724780301e-05, "row_tokens": 3.92306724780301e-05 }, "learning_rates_after_step": { "lora": 3.903400620122691e-05, "row_tokens": 3.903400620122691e-05 } }, { "update_id": 581, "row_count": 10, "row_ids_sha256": "24f0cada38b3c32a35959182844db107643bb8be2f779547ab3a0c0cec4a3685", "input_ids_vector_sha256": "c0d385a82df579b375feb92714d66417bd4c0f8d98bcf051b3501bc875e97c7e", "labels_vector_sha256": "c6460bd11db5dcc72855c565e534a3c80b26a9699dc64c566bfeec28fc5f0756", "planned_active_tokens": 77166, "realized_active_tokens": 77166, "cumulative_start": 38077038, "cumulative_end": 38154204, "loss_sum": 35580.048583984375, "token_normalized_loss": 0.46108452665661526, "grad_norm_before_clip": 0.153239905834198, "learning_rates_at_step": { "lora": 3.903400620122691e-05, "row_tokens": 3.903400620122691e-05 }, "learning_rates_after_step": { "lora": 3.889300667389938e-05, "row_tokens": 3.889300667389938e-05 } }, { "update_id": 582, "row_count": 9, "row_ids_sha256": "986b38de5bb674a30f3aa3abb82c281e020bb7896d38b9dec01db27110326f48", "input_ids_vector_sha256": "6bfd45a5039cfcb3a4682180ab6565b23b36da3825f875dff08505dec73856ac", "labels_vector_sha256": "2c32929d5110121009f88c684f089d89b2ad947950b47d16d2ab4642927c8507", "planned_active_tokens": 55367, "realized_active_tokens": 55367, "cumulative_start": 38154204, "cumulative_end": 38209571, "loss_sum": 22446.906005859375, "token_normalized_loss": 0.4054203046193468, "grad_norm_before_clip": 0.17590759694576263, "learning_rates_at_step": { "lora": 3.889300667389938e-05, "row_tokens": 3.889300667389938e-05 }, "learning_rates_after_step": { "lora": 3.871967269353259e-05, "row_tokens": 3.871967269353259e-05 } }, { "update_id": 583, "row_count": 12, "row_ids_sha256": "9a3acd08a66b02977f9055ee977823aeb019da301953e46ec354824a41acd59b", "input_ids_vector_sha256": "0d9ddf6483c50a5e840ae77286d33736dbdf8f4c328905c67ddb87a01e3ea2bc", "labels_vector_sha256": "ce9846f4aab7d6f06d82455bb96283fbaac957fdfee81e6672d69a97448b1c2e", "planned_active_tokens": 68114, "realized_active_tokens": 68114, "cumulative_start": 38209571, "cumulative_end": 38277685, "loss_sum": 26778.537719726562, "token_normalized_loss": 0.3931429327264081, "grad_norm_before_clip": 0.15898986160755157, "learning_rates_at_step": { "lora": 3.871967269353259e-05, "row_tokens": 3.871967269353259e-05 }, "learning_rates_after_step": { "lora": 3.854854268697218e-05, "row_tokens": 3.854854268697218e-05 } }, { "update_id": 584, "row_count": 12, "row_ids_sha256": "622aea2bf1bbb7debbd74f9a3e8a7acbde77fa1d8cfec77341ed3cf7bce3d102", "input_ids_vector_sha256": "4510f084eef22f0633697ea649644d153bd7ee02e778d5e0a277553241459401", "labels_vector_sha256": "1f60fa3dc8f8e853c6ddccb245b0f640f5281dd030c3d283685befbf1678cfa3", "planned_active_tokens": 67303, "realized_active_tokens": 67303, "cumulative_start": 38277685, "cumulative_end": 38344988, "loss_sum": 27356.558380126953, "token_normalized_loss": 0.406468632603702, "grad_norm_before_clip": 0.15182337164878845, "learning_rates_at_step": { "lora": 3.854854268697218e-05, "row_tokens": 3.854854268697218e-05 }, "learning_rates_after_step": { "lora": 3.839768334215078e-05, "row_tokens": 3.839768334215078e-05 } }, { "update_id": 585, "row_count": 10, "row_ids_sha256": "0760309b51450c87a946fac83c036d28d2d4106bbcf30ae4d4f861d62f3e9e85", "input_ids_vector_sha256": "66af9d5ccee153c05c2957e14c458dcd730cc6c4cc12fe01fa432627b9ae8125", "labels_vector_sha256": "87e837bfb05e6c0828cf364ec980de4904b2d974f4d0075a5d1ae641267d815c", "planned_active_tokens": 59377, "realized_active_tokens": 59377, "cumulative_start": 38344988, "cumulative_end": 38404365, "loss_sum": 22721.234313964844, "token_normalized_loss": 0.3826605304068047, "grad_norm_before_clip": 0.16029970347881317, "learning_rates_at_step": { "lora": 3.839768334215078e-05, "row_tokens": 3.839768334215078e-05 }, "learning_rates_after_step": { "lora": 3.823053899100369e-05, "row_tokens": 3.823053899100369e-05 } }, { "update_id": 586, "row_count": 11, "row_ids_sha256": "087d9dfb26b233038a82e0990ec062500b4cff1ade918f524fc30b10b145d0ae", "input_ids_vector_sha256": "416c02242874f770bb6526e26e25af4310c9e10b585bb66b7585eea1052193a7", "labels_vector_sha256": "c5787a224884106bcd6b6be38f2f270495e14479afdff92e9e7b88473c3be599", "planned_active_tokens": 65838, "realized_active_tokens": 65838, "cumulative_start": 38404365, "cumulative_end": 38470203, "loss_sum": 25234.0517578125, "token_normalized_loss": 0.3832748831649275, "grad_norm_before_clip": 0.17498159408569336, "learning_rates_at_step": { "lora": 3.823053899100369e-05, "row_tokens": 3.823053899100369e-05 }, "learning_rates_after_step": { "lora": 3.806427160583045e-05, "row_tokens": 3.806427160583045e-05 } }, { "update_id": 587, "row_count": 12, "row_ids_sha256": "018a157b8645f84118111221f7ec6c64f84cded94471a5b2bf42fe434315ac65", "input_ids_vector_sha256": "12754c7aee71ca4863d192d82a18026591e91e0e6559215b3d6dad90e86489a9", "labels_vector_sha256": "219a336ba15341800b395592fce148babd1e28b7928b35178f0d2ea764a5fc1e", "planned_active_tokens": 65547, "realized_active_tokens": 65547, "cumulative_start": 38470203, "cumulative_end": 38535750, "loss_sum": 24944.819580078125, "token_normalized_loss": 0.38056386379358514, "grad_norm_before_clip": 0.15563952922821045, "learning_rates_at_step": { "lora": 3.806427160583045e-05, "row_tokens": 3.806427160583045e-05 }, "learning_rates_after_step": { "lora": 3.789953237333473e-05, "row_tokens": 3.789953237333473e-05 } }, { "update_id": 588, "row_count": 12, "row_ids_sha256": "f6fc7d106b2e04b92075ae441d8947181ee957f06dd59470e5b135bcfc91c4b8", "input_ids_vector_sha256": "12c768097c5b89e05e7ac63a330fc5d482890ad1d37ceb78afb54ae0f80d6734", "labels_vector_sha256": "35ee5812afade96c00df04d49322c567121d3f15a296cd923b38a1689d49a79b", "planned_active_tokens": 64999, "realized_active_tokens": 64999, "cumulative_start": 38535750, "cumulative_end": 38600749, "loss_sum": 23910.130767822266, "token_normalized_loss": 0.3678538249484187, "grad_norm_before_clip": 0.15111473202705383, "learning_rates_at_step": { "lora": 3.789953237333473e-05, "row_tokens": 3.789953237333473e-05 }, "learning_rates_after_step": { "lora": 3.772770340606945e-05, "row_tokens": 3.772770340606945e-05 } }, { "update_id": 589, "row_count": 12, "row_ids_sha256": "a9d3bde9ab23cfab6cff90d4cbb98824e4c61a2aae5a0854e387f82780a75c59", "input_ids_vector_sha256": "18c1e4b0cfe95bbe083a2ff1df081e2549694beccdf6dfbb23583465b2d45a00", "labels_vector_sha256": "15d9477578a9b395dcc711704520d9ccd4dcf9fe97269a4c82f5515afbe6af4f", "planned_active_tokens": 67855, "realized_active_tokens": 67855, "cumulative_start": 38600749, "cumulative_end": 38668604, "loss_sum": 28646.7421875, "token_normalized_loss": 0.4221758483162626, "grad_norm_before_clip": 0.15779374539852142, "learning_rates_at_step": { "lora": 3.772770340606945e-05, "row_tokens": 3.772770340606945e-05 }, "learning_rates_after_step": { "lora": 3.755546711866088e-05, "row_tokens": 3.755546711866088e-05 } }, { "update_id": 590, "row_count": 11, "row_ids_sha256": "5bfcfa91ffe8e2841b8f73968899f350440e90945827181489d9ca9c2bcdc876", "input_ids_vector_sha256": "720dabc3c181e2a0d49c144c9812e74d5c6b982cb3673598a9cc237c5ee208c9", "labels_vector_sha256": "f0bdec7ad9f5daf6abf4007d8ade5bbf9c343c72bf5153fa24fcdafd06ab46fc", "planned_active_tokens": 68077, "realized_active_tokens": 68077, "cumulative_start": 38668604, "cumulative_end": 38736681, "loss_sum": 26747.345825195312, "token_normalized_loss": 0.3928984212758393, "grad_norm_before_clip": 0.1550821214914322, "learning_rates_at_step": { "lora": 3.755546711866088e-05, "row_tokens": 3.755546711866088e-05 }, "learning_rates_after_step": { "lora": 3.7399854336367905e-05, "row_tokens": 3.7399854336367905e-05 } }, { "update_id": 591, "row_count": 11, "row_ids_sha256": "03b3e24935411c93622e8a8603654b119ea3732dc51df21eeb69daea0edd8d7a", "input_ids_vector_sha256": "e66a6514e238aa77fbc61f162a9dcd930e70bb2d7fe4e59474606ebf4761f322", "labels_vector_sha256": "9f8a2d210a04c9007f0612755f92d111fd5afee48145c0d39aeb1f94b987e826", "planned_active_tokens": 61560, "realized_active_tokens": 61560, "cumulative_start": 38736681, "cumulative_end": 38798241, "loss_sum": 21684.914184570312, "token_normalized_loss": 0.3522565657012721, "grad_norm_before_clip": 0.18181347846984863, "learning_rates_at_step": { "lora": 3.7399854336367905e-05, "row_tokens": 3.7399854336367905e-05 }, "learning_rates_after_step": { "lora": 3.722008127992073e-05, "row_tokens": 3.722008127992073e-05 } }, { "update_id": 592, "row_count": 11, "row_ids_sha256": "b0e05d964e96d2cd268a1e8d86cba5bc9330cf83ead527b9e2e1ea17e7a37c5e", "input_ids_vector_sha256": "25e479d29d3682bd3c4a2acbdbebad0cd168e9b060baf999e955f7e1c5ab23cd", "labels_vector_sha256": "0bb2aaae3fdbfeb5c8f4cc4c37cae3ecf21dabc7578c794db4fb13830aba80ab", "planned_active_tokens": 71182, "realized_active_tokens": 71182, "cumulative_start": 38798241, "cumulative_end": 38869423, "loss_sum": 24371.427215576172, "token_normalized_loss": 0.34238188327914604, "grad_norm_before_clip": 0.14169183373451233, "learning_rates_at_step": { "lora": 3.722008127992073e-05, "row_tokens": 3.722008127992073e-05 }, "learning_rates_after_step": { "lora": 3.705185347893059e-05, "row_tokens": 3.705185347893059e-05 } }, { "update_id": 593, "row_count": 11, "row_ids_sha256": "a2f716bc3ed5b463ae4aadae77eac52691951fa99d4823dd3409023536447d63", "input_ids_vector_sha256": "b35a2ea38f82be7bf5e029d2c4216892b274393e92cc5feedcfd4c58f7a1becb", "labels_vector_sha256": "47d328fdc7db4a583131121769fabb303e6415d47e32617683beedcac5917363", "planned_active_tokens": 66674, "realized_active_tokens": 66674, "cumulative_start": 38869423, "cumulative_end": 38936097, "loss_sum": 25779.841796875, "token_normalized_loss": 0.3866550948926868, "grad_norm_before_clip": 0.1702173948287964, "learning_rates_at_step": { "lora": 3.705185347893059e-05, "row_tokens": 3.705185347893059e-05 }, "learning_rates_after_step": { "lora": 3.689654234656318e-05, "row_tokens": 3.689654234656318e-05 } }, { "update_id": 594, "row_count": 10, "row_ids_sha256": "c0efc45bcd10c9f80d02e727c8edd6c9cbbff45be3b4a71d184603f18f2e1d47", "input_ids_vector_sha256": "c4b3aac5a45e4dd211edf29a3384f05eb21523f0824c3109a60918fde596041e", "labels_vector_sha256": "b6c898da9582e4353e3fcae9bf24b8284a183a323823aaf3d6d8b943f7f017b1", "planned_active_tokens": 61610, "realized_active_tokens": 61610, "cumulative_start": 38936097, "cumulative_end": 38997707, "loss_sum": 21597.676025390625, "token_normalized_loss": 0.35055471555576406, "grad_norm_before_clip": 0.15921761095523834, "learning_rates_at_step": { "lora": 3.689654234656318e-05, "row_tokens": 3.689654234656318e-05 }, "learning_rates_after_step": { "lora": 3.673493962580941e-05, "row_tokens": 3.673493962580941e-05 } }, { "update_id": 595, "row_count": 11, "row_ids_sha256": "58d8672c61175b42ca9b2c3e47c0dbe6ed8cd53cafd2bd59b33b567e6cec44a6", "input_ids_vector_sha256": "e62919a35835bb01d56e968b4d4a5980a4cb76e89cdd8a2525218586b513c34b", "labels_vector_sha256": "77c646e0fc1c47ac02983be5b4c0cfff65541eb17368ee6fc4bf3e2017320dcf", "planned_active_tokens": 64163, "realized_active_tokens": 64163, "cumulative_start": 38997707, "cumulative_end": 39061870, "loss_sum": 26585.49542236328, "token_normalized_loss": 0.4143430859274548, "grad_norm_before_clip": 0.16837157309055328, "learning_rates_at_step": { "lora": 3.673493962580941e-05, "row_tokens": 3.673493962580941e-05 }, "learning_rates_after_step": { "lora": 3.657196669286718e-05, "row_tokens": 3.657196669286718e-05 } }, { "update_id": 596, "row_count": 12, "row_ids_sha256": "c5ea5b8778471c6f09bca1602c0502846c75aea2264b30d7abc30733a1234231", "input_ids_vector_sha256": "ae0a05dfb40bee21ecb71a04948339a57b4c6f3d4ffb412b007cb024df7f8999", "labels_vector_sha256": "421a8c198f794f783902a8d5cbd1485cd13d4ef2fd7b0489c0cb154e70f63721", "planned_active_tokens": 64767, "realized_active_tokens": 64767, "cumulative_start": 39061870, "cumulative_end": 39126637, "loss_sum": 22100.02764892578, "token_normalized_loss": 0.341223580664934, "grad_norm_before_clip": 0.15713629126548767, "learning_rates_at_step": { "lora": 3.657196669286718e-05, "row_tokens": 3.657196669286718e-05 }, "learning_rates_after_step": { "lora": 3.6410828388863e-05, "row_tokens": 3.6410828388863e-05 } }, { "update_id": 597, "row_count": 10, "row_ids_sha256": "83345dc016d61809e97596320d47e0610ad764000c9ea701bc876a876bd89d09", "input_ids_vector_sha256": "c014407a50c5b3be3ce15ed710a4cbbaf66ff3917d52e3cb8d3b879bdf15e553", "labels_vector_sha256": "74eb60a316931fdfdb39c0df2d3b38070b077202a597755ea4dc192030410190", "planned_active_tokens": 64098, "realized_active_tokens": 64098, "cumulative_start": 39126637, "cumulative_end": 39190735, "loss_sum": 26056.973999023438, "token_normalized_loss": 0.4065177384477431, "grad_norm_before_clip": 0.16365717351436615, "learning_rates_at_step": { "lora": 3.6410828388863e-05, "row_tokens": 3.6410828388863e-05 }, "learning_rates_after_step": { "lora": 3.623432398398461e-05, "row_tokens": 3.623432398398461e-05 } }, { "update_id": 598, "row_count": 14, "row_ids_sha256": "5ca8e6daf97071aa4dd2b2e1938e1d7ebca16dc912dbcbf95dffd395686517b8", "input_ids_vector_sha256": "b4bffc9408285ce25db12770cd7aec59e3f35963540fe8884a4dc9a1939c2135", "labels_vector_sha256": "27fd81be5d49d38a3d4881bfb441db230663263cd0eae4ed19e6c49843d284bc", "planned_active_tokens": 70280, "realized_active_tokens": 70280, "cumulative_start": 39190735, "cumulative_end": 39261015, "loss_sum": 22687.252166748047, "token_normalized_loss": 0.32281235297023403, "grad_norm_before_clip": 0.14398837089538574, "learning_rates_at_step": { "lora": 3.623432398398461e-05, "row_tokens": 3.623432398398461e-05 }, "learning_rates_after_step": { "lora": 3.6065542642715147e-05, "row_tokens": 3.6065542642715147e-05 } }, { "update_id": 599, "row_count": 11, "row_ids_sha256": "37c3f381a415a2ad6453e92bc8a1f489b7aa31ee95b6d504b1c304c5e551f567", "input_ids_vector_sha256": "f3c334c3ea38a6d44f68f62428abfb3c0f76a18ca2b779636ecf552ff8f7184e", "labels_vector_sha256": "a5b33d4ac30c20866210153032e75f8f4aa818aee9919b8a78d867fdf7c730bb", "planned_active_tokens": 67274, "realized_active_tokens": 67274, "cumulative_start": 39261015, "cumulative_end": 39328289, "loss_sum": 26888.391845703125, "token_normalized_loss": 0.3996847496165402, "grad_norm_before_clip": 0.16329120099544525, "learning_rates_at_step": { "lora": 3.6065542642715147e-05, "row_tokens": 3.6065542642715147e-05 }, "learning_rates_after_step": { "lora": 3.590376711466007e-05, "row_tokens": 3.590376711466007e-05 } }, { "update_id": 600, "row_count": 12, "row_ids_sha256": "be5b74654a4f1bef3ce71bfc5f8215a716a9a8eeb53c2aa9c787a2dbf24af7b9", "input_ids_vector_sha256": "e3da52acc0d02488e399b5c5b313b9dad05473b8a2c4a4b96036e23abf27ac06", "labels_vector_sha256": "eb42614735d5d96e0c1f57395179f60a243ccf34f4f3842c8fa7850a00cf1fd0", "planned_active_tokens": 64546, "realized_active_tokens": 64546, "cumulative_start": 39328289, "cumulative_end": 39392835, "loss_sum": 20821.56544494629, "token_normalized_loss": 0.3225849075844559, "grad_norm_before_clip": 0.1467917412519455, "learning_rates_at_step": { "lora": 3.590376711466007e-05, "row_tokens": 3.590376711466007e-05 }, "learning_rates_after_step": { "lora": 3.574255466054085e-05, "row_tokens": 3.574255466054085e-05 } }, { "update_id": 601, "row_count": 10, "row_ids_sha256": "b954aca1aa6254e3fff96f1b8a1b4641acaac8132e56d6dd48649b39e5a697ec", "input_ids_vector_sha256": "34b74f39992ffe7d0395404842f016dfd4d59e59b6bd22c167cbe51ba967743c", "labels_vector_sha256": "ad59d4bc62357b9097181bccfedf50ac095a8fd339eff09dbdbde73eb7198855", "planned_active_tokens": 64385, "realized_active_tokens": 64385, "cumulative_start": 39392835, "cumulative_end": 39457220, "loss_sum": 25983.568603515625, "token_normalized_loss": 0.40356556035591556, "grad_norm_before_clip": 0.16055220365524292, "learning_rates_at_step": { "lora": 3.574255466054085e-05, "row_tokens": 3.574255466054085e-05 }, "learning_rates_after_step": { "lora": 3.557515820874333e-05, "row_tokens": 3.557515820874333e-05 } }, { "update_id": 602, "row_count": 12, "row_ids_sha256": "396efe9922537763846030731127bab9b4d900aa9b741d5d21360e6f8de06b62", "input_ids_vector_sha256": "ab596b8bcb5ec5b8255de59bd41136cc7058806491f112cc8cb9e3ae2d304821", "labels_vector_sha256": "e6aea0a9c81ebd8c0916c8aeddc66c61b9d948b3807e860de34761140e382bcb", "planned_active_tokens": 66923, "realized_active_tokens": 66923, "cumulative_start": 39457220, "cumulative_end": 39524143, "loss_sum": 24181.643920898438, "token_normalized_loss": 0.3613353244908094, "grad_norm_before_clip": 0.15464922785758972, "learning_rates_at_step": { "lora": 3.557515820874333e-05, "row_tokens": 3.557515820874333e-05 }, "learning_rates_after_step": { "lora": 3.542410424394174e-05, "row_tokens": 3.542410424394174e-05 } }, { "update_id": 603, "row_count": 10, "row_ids_sha256": "ce563c367ad6649f26bc212534626b1d93c33d072184870b0df9e545189199cb", "input_ids_vector_sha256": "e3cd7ce18d2870df60cab55b9ad64ac6ee6ed42013412d85cd4792c6aff226de", "labels_vector_sha256": "f5091280c5f34e1c4a33915b7dd8879af6c1ab7a948c0cd7fa7d98d6bbdc8ea7", "planned_active_tokens": 60450, "realized_active_tokens": 60450, "cumulative_start": 39524143, "cumulative_end": 39584593, "loss_sum": 23417.54412841797, "token_normalized_loss": 0.3873869996429771, "grad_norm_before_clip": 0.17539389431476593, "learning_rates_at_step": { "lora": 3.542410424394174e-05, "row_tokens": 3.542410424394174e-05 }, "learning_rates_after_step": { "lora": 3.525551047199552e-05, "row_tokens": 3.525551047199552e-05 } }, { "update_id": 604, "row_count": 10, "row_ids_sha256": "dbeb436542b2d472ac12c52a25846a9c1e616ad83f18141c7c1aedd048029301", "input_ids_vector_sha256": "ed68785477a2c34e8671a575ccdcb90305093d7b2186737415abd211285b0050", "labels_vector_sha256": "a1a5f19f8dc857265af70e2bf9e67c2a8c5c6217fee3c9b9161bab64db8d5f88", "planned_active_tokens": 67538, "realized_active_tokens": 67538, "cumulative_start": 39584593, "cumulative_end": 39652131, "loss_sum": 30214.01318359375, "token_normalized_loss": 0.4473631612365446, "grad_norm_before_clip": 0.17270968854427338, "learning_rates_at_step": { "lora": 3.525551047199552e-05, "row_tokens": 3.525551047199552e-05 }, "learning_rates_after_step": { "lora": 3.508569700512337e-05, "row_tokens": 3.508569700512337e-05 } }, { "update_id": 605, "row_count": 16, "row_ids_sha256": "9bb2fe356015ccc6cad5e18c657ebb050b8a58393fc8f52a942c92795fde25a9", "input_ids_vector_sha256": "646dfa084aacd07973520cd6f96c923d3a744860428b97342443350be1281945", "labels_vector_sha256": "54d17d82c7b4d05e771327144c7d87599ea3e209d69049735f508aaab79394c5", "planned_active_tokens": 68101, "realized_active_tokens": 68101, "cumulative_start": 39652131, "cumulative_end": 39720232, "loss_sum": 26863.278411865234, "token_normalized_loss": 0.39446231937659115, "grad_norm_before_clip": 0.15336138010025024, "learning_rates_at_step": { "lora": 3.508569700512337e-05, "row_tokens": 3.508569700512337e-05 }, "learning_rates_after_step": { "lora": 3.4925798514686605e-05, "row_tokens": 3.4925798514686605e-05 } }, { "update_id": 606, "row_count": 10, "row_ids_sha256": "a10cf1fdb008f7ffd359be0a269b546a56302f4e4c92c51e08fb0e6d4365cac6", "input_ids_vector_sha256": "ee436d95f478ba781205387ed88d13b1487c45a2ac52db6079564ef7b7699e76", "labels_vector_sha256": "967e9bab473b14a6319fd0eee02589c7736586783087f68d5a2e5ed71af94fce", "planned_active_tokens": 64194, "realized_active_tokens": 64194, "cumulative_start": 39720232, "cumulative_end": 39784426, "loss_sum": 27736.948974609375, "token_normalized_loss": 0.43208008497070405, "grad_norm_before_clip": 0.1675432175397873, "learning_rates_at_step": { "lora": 3.4925798514686605e-05, "row_tokens": 3.4925798514686605e-05 }, "learning_rates_after_step": { "lora": 3.476788238061451e-05, "row_tokens": 3.476788238061451e-05 } }, { "update_id": 607, "row_count": 10, "row_ids_sha256": "af839e48802b6eb39e40e80f444a28a794bb667a6f421966c315838bad5080f7", "input_ids_vector_sha256": "0149850ed812ec28bb4ca3e01db8776589aa23824c4367c956f7a10c5c5db1b5", "labels_vector_sha256": "86d6060b173079303c3b820b5a20fedf9dae735189ac6d57f78d299c18aad4e1", "planned_active_tokens": 63465, "realized_active_tokens": 63465, "cumulative_start": 39784426, "cumulative_end": 39847891, "loss_sum": 24480.517578125, "token_normalized_loss": 0.3857325703635862, "grad_norm_before_clip": 0.1627979874610901, "learning_rates_at_step": { "lora": 3.476788238061451e-05, "row_tokens": 3.476788238061451e-05 }, "learning_rates_after_step": { "lora": 3.4607470433619606e-05, "row_tokens": 3.4607470433619606e-05 } }, { "update_id": 608, "row_count": 9, "row_ids_sha256": "54ccea9d35fb7a4252299fd88f84b14be52b68605b8075eed53e76b1d4e910e5", "input_ids_vector_sha256": "d66d95d06f53579f1116914f781133c8f666d276ed563b335d7c2890abb6410e", "labels_vector_sha256": "d63e1de1598bf321a21cca40b814d1b0c4a5b5ca5aa6394a7a56aa0eee8e8daa", "planned_active_tokens": 64537, "realized_active_tokens": 64537, "cumulative_start": 39847891, "cumulative_end": 39912428, "loss_sum": 27666.685302734375, "token_normalized_loss": 0.42869493937949354, "grad_norm_before_clip": 0.17490077018737793, "learning_rates_at_step": { "lora": 3.4607470433619606e-05, "row_tokens": 3.4607470433619606e-05 }, "learning_rates_after_step": { "lora": 3.443885102272911e-05, "row_tokens": 3.443885102272911e-05 } }, { "update_id": 609, "row_count": 9, "row_ids_sha256": "be1cbe89ef527bb131baa0b71e7893da975297de8145e50ba22a5af9daced939", "input_ids_vector_sha256": "608cbf3631ee36aab49db53b18d7f0391500ec96a5fb811cfa21a0ee3a6c25ee", "labels_vector_sha256": "8d0d0549cbd2fc9dcc7b7bcc89fed7f8231d3a885bd1e1e4ccc8c4125d401f6a", "planned_active_tokens": 67915, "realized_active_tokens": 67915, "cumulative_start": 39912428, "cumulative_end": 39980343, "loss_sum": 27177.334106445312, "token_normalized_loss": 0.4001668866442658, "grad_norm_before_clip": 0.15982800722122192, "learning_rates_at_step": { "lora": 3.443885102272911e-05, "row_tokens": 3.443885102272911e-05 }, "learning_rates_after_step": { "lora": 3.428265910088574e-05, "row_tokens": 3.428265910088574e-05 } }, { "update_id": 610, "row_count": 12, "row_ids_sha256": "a6d4aa3efd231ac26e89a7e0bec7cac4485566a40d2f012cd6da64f8f40aea80", "input_ids_vector_sha256": "fd61b147d469007d2f67bce08707ff5ecb332e36259ee94e24f6259054836f22", "labels_vector_sha256": "2a0b611ad66632c042e98c7701fbe58af9e3f38343e425077143e37870e3468a", "planned_active_tokens": 62980, "realized_active_tokens": 62980, "cumulative_start": 39980343, "cumulative_end": 40043323, "loss_sum": 25051.72021484375, "token_normalized_loss": 0.39777262964185056, "grad_norm_before_clip": 0.1602238416671753, "learning_rates_at_step": { "lora": 3.428265910088574e-05, "row_tokens": 3.428265910088574e-05 }, "learning_rates_after_step": { "lora": 3.410889552588076e-05, "row_tokens": 3.410889552588076e-05 } }, { "update_id": 611, "row_count": 11, "row_ids_sha256": "c3103c6756c740b80ef5e3accb780a89533eb5225155fd658a0da993aa208a01", "input_ids_vector_sha256": "b617be9139d2ae38b7340f26ff02dc870b5cafbbf91da732bb2e8364c5ad680e", "labels_vector_sha256": "417826d188a9deb0e6bdd99ed5e3ae3ee0adaa8a1d52195d8e10e8ff54337bee", "planned_active_tokens": 70146, "realized_active_tokens": 70146, "cumulative_start": 40043323, "cumulative_end": 40113469, "loss_sum": 24419.130981445312, "token_normalized_loss": 0.3481186522602189, "grad_norm_before_clip": 0.14469794929027557, "learning_rates_at_step": { "lora": 3.410889552588076e-05, "row_tokens": 3.410889552588076e-05 }, "learning_rates_after_step": { "lora": 3.395261240862787e-05, "row_tokens": 3.395261240862787e-05 } }, { "update_id": 612, "row_count": 13, "row_ids_sha256": "5cdc04963a93c297424c47069f379a471ba6eaaef1716ce0ca1fbd2ed9b456c1", "input_ids_vector_sha256": "0542bcc0019906e2fafbd123304eb64e69028713a64d4197fda96da7c67a191e", "labels_vector_sha256": "3e63db89046bb6100e60d13c9a752132a89bf892304930eb35eebdaa26a9b4b0", "planned_active_tokens": 63163, "realized_active_tokens": 63163, "cumulative_start": 40113469, "cumulative_end": 40176632, "loss_sum": 24314.997619628906, "token_normalized_loss": 0.3849563450062363, "grad_norm_before_clip": 0.17755551636219025, "learning_rates_at_step": { "lora": 3.395261240862787e-05, "row_tokens": 3.395261240862787e-05 }, "learning_rates_after_step": { "lora": 3.378938021567763e-05, "row_tokens": 3.378938021567763e-05 } }, { "update_id": 613, "row_count": 12, "row_ids_sha256": "d863164476b1660ee165e289157b3253c8de85eaacc39c6b664208a0105d432a", "input_ids_vector_sha256": "2351d706f63bff26a0931928d1e3b83aaf5ca6e35efaf0e0128c1dccade178fa", "labels_vector_sha256": "18fb9ebd803961e7d1072c8ad6bb6d866662ece1e8176dfceb44edc3d73bd9db", "planned_active_tokens": 66047, "realized_active_tokens": 66047, "cumulative_start": 40176632, "cumulative_end": 40242679, "loss_sum": 22307.274047851562, "token_normalized_loss": 0.33774848286601306, "grad_norm_before_clip": 0.1581232249736786, "learning_rates_at_step": { "lora": 3.378938021567763e-05, "row_tokens": 3.378938021567763e-05 }, "learning_rates_after_step": { "lora": 3.3628085086835734e-05, "row_tokens": 3.3628085086835734e-05 } }, { "update_id": 614, "row_count": 13, "row_ids_sha256": "d217ed655271768cd9fc380b35e6b759bb59b28692d0c4ba4aa9b90d0bc5371d", "input_ids_vector_sha256": "19e24db8f3eef4cdabf9ea052285e7bd3eca81d54d440fc8c944c1bb91f3c169", "labels_vector_sha256": "10bb8fdffb748aee9351372f42872ee415430c38e47e42301051d1d1c48a6b5b", "planned_active_tokens": 65340, "realized_active_tokens": 65340, "cumulative_start": 40242679, "cumulative_end": 40308019, "loss_sum": 24757.010833740234, "token_normalized_loss": 0.3788951765188282, "grad_norm_before_clip": 0.17087972164154053, "learning_rates_at_step": { "lora": 3.3628085086835734e-05, "row_tokens": 3.3628085086835734e-05 }, "learning_rates_after_step": { "lora": 3.346448192609794e-05, "row_tokens": 3.346448192609794e-05 } }, { "update_id": 615, "row_count": 12, "row_ids_sha256": "34185479f8d2ac9f9d412eb8f55a672b087a0ed2bd7c0875eda2568e053a2782", "input_ids_vector_sha256": "265446f17d20880ab0ee9ff11efef01f86e9891cbb36ffb6b961c578a056b0ec", "labels_vector_sha256": "daa198cc739724165177d2f6a2f5538d4b0bb31107e9e1ad496acb53ffcedf89", "planned_active_tokens": 66354, "realized_active_tokens": 66354, "cumulative_start": 40308019, "cumulative_end": 40374373, "loss_sum": 22963.972457885742, "token_normalized_loss": 0.3460827148007014, "grad_norm_before_clip": 0.15597490966320038, "learning_rates_at_step": { "lora": 3.346448192609794e-05, "row_tokens": 3.346448192609794e-05 }, "learning_rates_after_step": { "lora": 3.3312465358642384e-05, "row_tokens": 3.3312465358642384e-05 } }, { "update_id": 616, "row_count": 10, "row_ids_sha256": "94dc918ad039588d3fe1e49b8236a74b14c8f9b7d53e0dddffc76411b636d629", "input_ids_vector_sha256": "219f033c6b3209173d9f6ab54c101128dc15ef948b9cc53b05d002242b126099", "labels_vector_sha256": "cc75adcdc2057103133c6ca7268404039ba1b76cf2cb79fadbd0ae3704755ef3", "planned_active_tokens": 61727, "realized_active_tokens": 61727, "cumulative_start": 40374373, "cumulative_end": 40436100, "loss_sum": 23535.087341308594, "token_normalized_loss": 0.3812770317901177, "grad_norm_before_clip": 0.17229624092578888, "learning_rates_at_step": { "lora": 3.3312465358642384e-05, "row_tokens": 3.3312465358642384e-05 }, "learning_rates_after_step": { "lora": 3.315153833144073e-05, "row_tokens": 3.315153833144073e-05 } }, { "update_id": 617, "row_count": 11, "row_ids_sha256": "6b329bbb25b9b86208b6a93347c4deeba5c5e160940659326bc6a6d97865208c", "input_ids_vector_sha256": "7143eb030346f0364ffbb838e26facdefccda1a38cea542da2f4b0ea9b17d71c", "labels_vector_sha256": "2b46e52a0abbf20af0715307b7e404ff424fd54c8dfdf7f238b2360d364a78c3", "planned_active_tokens": 65422, "realized_active_tokens": 65422, "cumulative_start": 40436100, "cumulative_end": 40501522, "loss_sum": 19991.587829589844, "token_normalized_loss": 0.3055789769433806, "grad_norm_before_clip": 0.14333921670913696, "learning_rates_at_step": { "lora": 3.315153833144073e-05, "row_tokens": 3.315153833144073e-05 }, "learning_rates_after_step": { "lora": 3.298746140677211e-05, "row_tokens": 3.298746140677211e-05 } }, { "update_id": 618, "row_count": 11, "row_ids_sha256": "d7f5e88584ae4d22d5ac4d5255e05bec9a04137ed4538d221bf2cf26acc654c3", "input_ids_vector_sha256": "79a18a6151e7092703281e571e2ba1e21a76e5e19291ed44a2a280577a280512", "labels_vector_sha256": "85aa320d09262f3db0aa599827e77010259c5b6c84b7a72dbf6210fe3639e7b9", "planned_active_tokens": 66785, "realized_active_tokens": 66785, "cumulative_start": 40501522, "cumulative_end": 40568307, "loss_sum": 23274.143981933594, "token_normalized_loss": 0.3484935836180818, "grad_norm_before_clip": 0.154941126704216, "learning_rates_at_step": { "lora": 3.298746140677211e-05, "row_tokens": 3.298746140677211e-05 }, "learning_rates_after_step": { "lora": 3.282584003492962e-05, "row_tokens": 3.282584003492962e-05 } }, { "update_id": 619, "row_count": 12, "row_ids_sha256": "cb83683a19d659aa17f4c70137d326bc68e5d4dbc3bcfe1c0da50ff5603253f4", "input_ids_vector_sha256": "d5cd2150df5d66e2827b2b8b36cb0e516a0c8efca557fea005af412725e7e6ed", "labels_vector_sha256": "71cc8c9b62c7acf3ec012a6f471cc8cb2e80630ebbfaa18fea64ed32878fdef9", "planned_active_tokens": 65868, "realized_active_tokens": 65868, "cumulative_start": 40568307, "cumulative_end": 40634175, "loss_sum": 24368.091186523438, "token_normalized_loss": 0.3699534096454035, "grad_norm_before_clip": 0.19809138774871826, "learning_rates_at_step": { "lora": 3.282584003492962e-05, "row_tokens": 3.282584003492962e-05 }, "learning_rates_after_step": { "lora": 3.266576151008124e-05, "row_tokens": 3.266576151008124e-05 } }, { "update_id": 620, "row_count": 12, "row_ids_sha256": "3f4623919776f813138ca2ac9bcb4f2d79ab668d7af9b2af6d5c5441d3316b0c", "input_ids_vector_sha256": "08b07ec205391f439806a99aa732a116c4255223ff9e1fe2ee7b048cbe4aea4f", "labels_vector_sha256": "e61c96dd87b436fe4f560513c60cda5797c50f9f618a85c24967f610196dbae3", "planned_active_tokens": 65321, "realized_active_tokens": 65321, "cumulative_start": 40634175, "cumulative_end": 40699496, "loss_sum": 22957.174255371094, "token_normalized_loss": 0.35145166570277697, "grad_norm_before_clip": 0.16146372258663177, "learning_rates_at_step": { "lora": 3.266576151008124e-05, "row_tokens": 3.266576151008124e-05 }, "learning_rates_after_step": { "lora": 3.248312913457253e-05, "row_tokens": 3.248312913457253e-05 } }, { "update_id": 621, "row_count": 11, "row_ids_sha256": "56387962fc36254b8abb16d8cbd6439955a891420a2b3e0552856ac0f86ecca5", "input_ids_vector_sha256": "515b2dd815d53aa62981e203cc391204d28e5399bfd3e982b5de3737a2e62768", "labels_vector_sha256": "bcfb870bccd4d534f3428d9341df913cf4d30ab4229baae0fe79312776a33e96", "planned_active_tokens": 74625, "realized_active_tokens": 74625, "cumulative_start": 40699496, "cumulative_end": 40774121, "loss_sum": 28520.853790283203, "token_normalized_loss": 0.38218899551468277, "grad_norm_before_clip": 0.2635558545589447, "learning_rates_at_step": { "lora": 3.248312913457253e-05, "row_tokens": 3.248312913457253e-05 }, "learning_rates_after_step": { "lora": 3.23455445045504e-05, "row_tokens": 3.23455445045504e-05 } }, { "update_id": 622, "row_count": 11, "row_ids_sha256": "022e6346af56bf6d0d076e702ac95a4dba5f27f716ce8abecc512efe287989d9", "input_ids_vector_sha256": "e1e04dc35d141d3c3122d23e1556be110c93c809c326ac6d925cb63cba0acafb", "labels_vector_sha256": "89ec0512efdc79a84dc9484e57f65dbc2858f0edfbdcff867a1d5b44a9eaf389", "planned_active_tokens": 56290, "realized_active_tokens": 56290, "cumulative_start": 40774121, "cumulative_end": 40830411, "loss_sum": 21777.915161132812, "token_normalized_loss": 0.3868878159732246, "grad_norm_before_clip": 0.18383847177028656, "learning_rates_at_step": { "lora": 3.23455445045504e-05, "row_tokens": 3.23455445045504e-05 }, "learning_rates_after_step": { "lora": 3.218269368915269e-05, "row_tokens": 3.218269368915269e-05 } }, { "update_id": 623, "row_count": 12, "row_ids_sha256": "270fe923e559492897c57cbffbb249597366746f77bfb97a3640665487a0b0e9", "input_ids_vector_sha256": "dc9846ac75daa7958a54b19151448f806464afb6e373c2c08d1a8cfffb04d61e", "labels_vector_sha256": "5e978309c08e575be86dc44bef135940575435075e016fc1803adec6d64153a1", "planned_active_tokens": 66708, "realized_active_tokens": 66708, "cumulative_start": 40830411, "cumulative_end": 40897119, "loss_sum": 25734.686950683594, "token_normalized_loss": 0.38578111996587505, "grad_norm_before_clip": 0.15659673511981964, "learning_rates_at_step": { "lora": 3.218269368915269e-05, "row_tokens": 3.218269368915269e-05 }, "learning_rates_after_step": { "lora": 3.20220910430724e-05, "row_tokens": 3.20220910430724e-05 } }, { "update_id": 624, "row_count": 10, "row_ids_sha256": "6e658d69b5954803039a6fbc6c50abbc713b582cde4d2df34596b2988cb7e570", "input_ids_vector_sha256": "98881c424ba9d56428cf9d55ab883e7b9c51fb8da5d9b992fa2813319b3f27f0", "labels_vector_sha256": "78d8556a0f19cf2c3ce494f64f4c90ef11a9cef269b7dda41a11b71fe0fc86c5", "planned_active_tokens": 65874, "realized_active_tokens": 65874, "cumulative_start": 40897119, "cumulative_end": 40962993, "loss_sum": 26175.952423095703, "token_normalized_loss": 0.3973639436362708, "grad_norm_before_clip": 0.15828663110733032, "learning_rates_at_step": { "lora": 3.20220910430724e-05, "row_tokens": 3.20220910430724e-05 }, "learning_rates_after_step": { "lora": 3.1868521519676356e-05, "row_tokens": 3.1868521519676356e-05 } }, { "update_id": 625, "row_count": 11, "row_ids_sha256": "39ccb54df106754058f45eb3a0eade38718ffab9c6633b748f5db2b223766631", "input_ids_vector_sha256": "83175c4501763fe33628d5e325715421af0500a7a4b40249d718aa5207bb1d3d", "labels_vector_sha256": "71b495cc693bb916a5cf2f22f09cf7a8edc2b78b7da2fd8ac54f8b4fd8d50082", "planned_active_tokens": 63071, "realized_active_tokens": 63071, "cumulative_start": 40962993, "cumulative_end": 41026064, "loss_sum": 23859.716430664062, "token_normalized_loss": 0.3782993203003609, "grad_norm_before_clip": 0.1619059294462204, "learning_rates_at_step": { "lora": 3.1868521519676356e-05, "row_tokens": 3.1868521519676356e-05 }, "learning_rates_after_step": { "lora": 3.167717591151847e-05, "row_tokens": 3.167717591151847e-05 } }, { "update_id": 626, "row_count": 13, "row_ids_sha256": "69b1fe6b95cd66978b59eacf91fe505182a7d5dfbe502333bf2028c7f0e94ae3", "input_ids_vector_sha256": "3056dd9bcbca1479faf1b580573bd5ade1f3495dfc6eb4a5136a81f14b163f82", "labels_vector_sha256": "2c0703adff03045a97ea1cc6d5e840aa7934c9fbbfae9fe6cefe1cb1e304f170", "planned_active_tokens": 78699, "realized_active_tokens": 78699, "cumulative_start": 41026064, "cumulative_end": 41104763, "loss_sum": 30050.442260742188, "token_normalized_loss": 0.3818402045863631, "grad_norm_before_clip": 0.20379625260829926, "learning_rates_at_step": { "lora": 3.167717591151847e-05, "row_tokens": 3.167717591151847e-05 }, "learning_rates_after_step": { "lora": 3.1546556340585084e-05, "row_tokens": 3.1546556340585084e-05 } }, { "update_id": 627, "row_count": 9, "row_ids_sha256": "bf9ac940298607b3ce898f994a69f4b22cd83305bdc2224b0352af9773842a3b", "input_ids_vector_sha256": "0ea546ac60245ca5436124827e575b573aaf8c9f395a210d51b00c743e5fed4c", "labels_vector_sha256": "8a7b73e6e2e96df43eb29b332786ee5e4947ff285891593ce61680843b7c8443", "planned_active_tokens": 53796, "realized_active_tokens": 53796, "cumulative_start": 41104763, "cumulative_end": 41158559, "loss_sum": 21888.630493164062, "token_normalized_loss": 0.4068821193613663, "grad_norm_before_clip": 0.18337449431419373, "learning_rates_at_step": { "lora": 3.1546556340585084e-05, "row_tokens": 3.1546556340585084e-05 }, "learning_rates_after_step": { "lora": 3.137803691263782e-05, "row_tokens": 3.137803691263782e-05 } }, { "update_id": 628, "row_count": 12, "row_ids_sha256": "fa7cafb1f45af9d34e24987386701b29d7a9a278b574caff665378ac74bf117d", "input_ids_vector_sha256": "6a0c2296cad4acc08d331daba43d48d745cfa939faf808c32ef4f72f9cb52104", "labels_vector_sha256": "61fe809f6074f310677c8449c5ba767fd280aa728e223d69810f3bb7ebebeef4", "planned_active_tokens": 69494, "realized_active_tokens": 69494, "cumulative_start": 41158559, "cumulative_end": 41228053, "loss_sum": 27192.50665283203, "token_normalized_loss": 0.3912928692093135, "grad_norm_before_clip": 0.15976664423942566, "learning_rates_at_step": { "lora": 3.137803691263782e-05, "row_tokens": 3.137803691263782e-05 }, "learning_rates_after_step": { "lora": 3.122283440312476e-05, "row_tokens": 3.122283440312476e-05 } }, { "update_id": 629, "row_count": 14, "row_ids_sha256": "504822296db259947658197f0801a2e9ebd498c6399740809ca2dec0bc98e5e1", "input_ids_vector_sha256": "80e30c17732ebdd9a6582c20037de57a78bb5a506fb65c7388256b87008f8c16", "labels_vector_sha256": "8ec14af628fc4328f064804c01f112bbdc88d366084385a001dbbb3946a30ace", "planned_active_tokens": 64092, "realized_active_tokens": 64092, "cumulative_start": 41228053, "cumulative_end": 41292145, "loss_sum": 24435.756561279297, "token_normalized_loss": 0.3812606341084581, "grad_norm_before_clip": 0.15961623191833496, "learning_rates_at_step": { "lora": 3.122283440312476e-05, "row_tokens": 3.122283440312476e-05 }, "learning_rates_after_step": { "lora": 3.106905780393976e-05, "row_tokens": 3.106905780393976e-05 } }, { "update_id": 630, "row_count": 12, "row_ids_sha256": "c4d7c752a3725ea8425a80ebd8c787b2ed0087ce35113a74ffd678b7bc43eeb2", "input_ids_vector_sha256": "44f859cd53f751f0a81c25553e24ad8ea31a53ac0809e0d558bca4d9fc8869af", "labels_vector_sha256": "9a3918e3a36759cb2cfea51e691d1bddf23580513b9746f577d87ddce92319f5", "planned_active_tokens": 63589, "realized_active_tokens": 63589, "cumulative_start": 41292145, "cumulative_end": 41355734, "loss_sum": 25483.462615966797, "token_normalized_loss": 0.400752687036544, "grad_norm_before_clip": 0.16294701397418976, "learning_rates_at_step": { "lora": 3.106905780393976e-05, "row_tokens": 3.106905780393976e-05 }, "learning_rates_after_step": { "lora": 3.0908175308735854e-05, "row_tokens": 3.0908175308735854e-05 } }, { "update_id": 631, "row_count": 8, "row_ids_sha256": "9b8c0a0accac16ca110f974dd57c37417f357c8b7c961d7121f1ad699615cca0", "input_ids_vector_sha256": "bd1bca9e2133726a4f67b6704087ade0674efd22bde3d4dfbc89a8d4ae395b57", "labels_vector_sha256": "9627fbf49f10ee1905f1da89152ed0c11fb8e0a8d14af2d7a5d5f4fa5478388e", "planned_active_tokens": 66620, "realized_active_tokens": 66620, "cumulative_start": 41355734, "cumulative_end": 41422354, "loss_sum": 30560.656677246094, "token_normalized_loss": 0.45873096183197376, "grad_norm_before_clip": 0.16938303411006927, "learning_rates_at_step": { "lora": 3.0908175308735854e-05, "row_tokens": 3.0908175308735854e-05 }, "learning_rates_after_step": { "lora": 3.074122024693854e-05, "row_tokens": 3.074122024693854e-05 } }, { "update_id": 632, "row_count": 11, "row_ids_sha256": "931fe3f42569d3f7367636e8023fbc71fe3b28afbcd32922d0823afaae8c8d17", "input_ids_vector_sha256": "7b9d4d8a3054fffef538e44afb5276b33ed71c20e304717ee5a7e1b0a4c55734", "labels_vector_sha256": "e05ff007055fe910137e5dd921b6051db3563420f5ae3ceb745d8fb7ec2b772b", "planned_active_tokens": 69236, "realized_active_tokens": 69236, "cumulative_start": 41422354, "cumulative_end": 41491590, "loss_sum": 28596.41973876953, "token_normalized_loss": 0.4130281896523417, "grad_norm_before_clip": 0.15296177566051483, "learning_rates_at_step": { "lora": 3.074122024693854e-05, "row_tokens": 3.074122024693854e-05 }, "learning_rates_after_step": { "lora": 3.059700022580828e-05, "row_tokens": 3.059700022580828e-05 } }, { "update_id": 633, "row_count": 10, "row_ids_sha256": "c69651d3d95f627d2cf6515077290098a167de0f553144d0e71b0da65be4e31e", "input_ids_vector_sha256": "f15c48e2314dc51f628cbd1d8465d7ef991b65176713953c0e7dcc7a9c2aae20", "labels_vector_sha256": "4b1c7e65ade005877c36dfe9d523aacf42e1477fee616ae7d349365696dc3088", "planned_active_tokens": 59892, "realized_active_tokens": 59892, "cumulative_start": 41491590, "cumulative_end": 41551482, "loss_sum": 25248.302795410156, "token_normalized_loss": 0.42156386154094294, "grad_norm_before_clip": 0.17081157863140106, "learning_rates_at_step": { "lora": 3.059700022580828e-05, "row_tokens": 3.059700022580828e-05 }, "learning_rates_after_step": { "lora": 3.044161048280264e-05, "row_tokens": 3.044161048280264e-05 } }, { "update_id": 634, "row_count": 10, "row_ids_sha256": "d7101d9a41655bac2f3cbe4a50dfb02b1e3c630c0aa298667f19cb53492709b1", "input_ids_vector_sha256": "f0b19fbf79e9eb109bb9a1d341ac2086ba6c5c0c9eac4650cfb687b7f92686c2", "labels_vector_sha256": "403726fb23bbf3cfb1f218714eca082251d14c0a5afc30d23f24fd0f294c8377", "planned_active_tokens": 64619, "realized_active_tokens": 64619, "cumulative_start": 41551482, "cumulative_end": 41616101, "loss_sum": 27332.06524658203, "token_normalized_loss": 0.42297258154075473, "grad_norm_before_clip": 0.17325465381145477, "learning_rates_at_step": { "lora": 3.044161048280264e-05, "row_tokens": 3.044161048280264e-05 }, "learning_rates_after_step": { "lora": 3.0270396610000294e-05, "row_tokens": 3.0270396610000294e-05 } }, { "update_id": 635, "row_count": 15, "row_ids_sha256": "6563fa7fd8022da3f3f2dc21bd3574b5fbba94a220dfb992b924aa3947272be2", "input_ids_vector_sha256": "91dc80c1a8186404861ffab3e5fc8c53c028049f192009ca51d44a1a5707009a", "labels_vector_sha256": "836729e4f90c4549d531013825432f21df3eeb08f530303583cb64865c0427c0", "planned_active_tokens": 71307, "realized_active_tokens": 71307, "cumulative_start": 41616101, "cumulative_end": 41687408, "loss_sum": 24400.679138183594, "token_normalized_loss": 0.3421919185799935, "grad_norm_before_clip": 0.1474788784980774, "learning_rates_at_step": { "lora": 3.0270396610000294e-05, "row_tokens": 3.0270396610000294e-05 }, "learning_rates_after_step": { "lora": 3.0127403743147443e-05, "row_tokens": 3.0127403743147443e-05 } }, { "update_id": 636, "row_count": 14, "row_ids_sha256": "85a95178e5ed720a63dbd1ec9a7e543185e11bed3bbf05bb21a27af147a92c8c", "input_ids_vector_sha256": "ab3cc9125d001caa5a36c7ac53abc6725d0d95b3b074fdaf07158487e4e93a46", "labels_vector_sha256": "6e21dd6054a48ba38ba3168a60569904be4eeb18cf142d6d4d9405abea05746b", "planned_active_tokens": 59641, "realized_active_tokens": 59641, "cumulative_start": 41687408, "cumulative_end": 41747049, "loss_sum": 20466.355010986328, "token_normalized_loss": 0.34315915244523615, "grad_norm_before_clip": 0.16029572486877441, "learning_rates_at_step": { "lora": 3.0127403743147443e-05, "row_tokens": 3.0127403743147443e-05 }, "learning_rates_after_step": { "lora": 2.9954160905796484e-05, "row_tokens": 2.9954160905796484e-05 } }, { "update_id": 637, "row_count": 12, "row_ids_sha256": "6bbf494f726feef6326b3ee65bcc1f9f98b7458e2f5bdcea4adb1a8c46b24f4e", "input_ids_vector_sha256": "695ae6cde4544cfd4f1d7ae57f0f282608c7b464cf562f9aa62e4823e9f58d33", "labels_vector_sha256": "f73b3165b0e0ba52706d924bdf5699a3c110937917d726566cc9eee96e3f90bc", "planned_active_tokens": 72366, "realized_active_tokens": 72366, "cumulative_start": 41747049, "cumulative_end": 41819415, "loss_sum": 26819.993560791016, "token_normalized_loss": 0.3706159461734933, "grad_norm_before_clip": 0.1498851478099823, "learning_rates_at_step": { "lora": 2.9954160905796484e-05, "row_tokens": 2.9954160905796484e-05 }, "learning_rates_after_step": { "lora": 2.981164194505931e-05, "row_tokens": 2.981164194505931e-05 } }, { "update_id": 638, "row_count": 12, "row_ids_sha256": "1cc88a0a0ce6fd9004a828d6e5923f130428d4ea4d138e25d62671fdc7b85069", "input_ids_vector_sha256": "d54a33b01bd6c98a77aa4c46b1a529c9cb7d83128125f0349d417ada75628811", "labels_vector_sha256": "70131d18cbddc619956eb0589c223f3dfb8a06421c047a15bff12515975456ef", "planned_active_tokens": 59622, "realized_active_tokens": 59622, "cumulative_start": 41819415, "cumulative_end": 41879037, "loss_sum": 20369.57192993164, "token_normalized_loss": 0.3416452304507001, "grad_norm_before_clip": 0.16618596017360687, "learning_rates_at_step": { "lora": 2.981164194505931e-05, "row_tokens": 2.981164194505931e-05 }, "learning_rates_after_step": { "lora": 2.9646199184760788e-05, "row_tokens": 2.9646199184760788e-05 } }, { "update_id": 639, "row_count": 14, "row_ids_sha256": "b3f338616c02a999232559d30f6f0a8920e7b8f55b6f5a1413bf47cb0b1dc09f", "input_ids_vector_sha256": "9e7f4bbc973a26af9932f92db6bb0ccda10eaaf32b74b79560482602b589c0d2", "labels_vector_sha256": "201346e6891548a3754f3a79fb72e54d9ada4ea3c5ff95d0270c67f84699741a", "planned_active_tokens": 69315, "realized_active_tokens": 69315, "cumulative_start": 41879037, "cumulative_end": 41948352, "loss_sum": 22628.33660888672, "token_normalized_loss": 0.3264565621999094, "grad_norm_before_clip": 0.15259520709514618, "learning_rates_at_step": { "lora": 2.9646199184760788e-05, "row_tokens": 2.9646199184760788e-05 }, "learning_rates_after_step": { "lora": 2.9497670342875005e-05, "row_tokens": 2.9497670342875005e-05 } }, { "update_id": 640, "row_count": 11, "row_ids_sha256": "da345bc1fae16e4cb257de07fef5e45a94f56788700d09bc4ab32050541dd290", "input_ids_vector_sha256": "6794ea403630fc0751da7c3b5ddce7d13505c13cb33773c73813cabf2a7dc0d6", "labels_vector_sha256": "5287eeca3fdcf1e234ae67d0b578a1d0c0dc3f404212cd4df09f1accd416046c", "planned_active_tokens": 62324, "realized_active_tokens": 62324, "cumulative_start": 41948352, "cumulative_end": 42010676, "loss_sum": 25210.345733642578, "token_normalized_loss": 0.40450461673901833, "grad_norm_before_clip": 0.20715992152690887, "learning_rates_at_step": { "lora": 2.9497670342875005e-05, "row_tokens": 2.9497670342875005e-05 }, "learning_rates_after_step": { "lora": 2.932945493155329e-05, "row_tokens": 2.932945493155329e-05 } }, { "update_id": 641, "row_count": 8, "row_ids_sha256": "bdcd28ad03115b8237717e055345f5dd4b0cb5b31da1b542e9a939e3bac67186", "input_ids_vector_sha256": "141a98906df1d5c809d6d5782e9e1ea52343e23ea0f5c34dd09238f8e66f1a62", "labels_vector_sha256": "77803aea6697cdf976a4b6828e8d6b9ce14fedf2abd92b179f2233fd3aa083b2", "planned_active_tokens": 70695, "realized_active_tokens": 70695, "cumulative_start": 42010676, "cumulative_end": 42081371, "loss_sum": 34832.46728515625, "token_normalized_loss": 0.49271472218906925, "grad_norm_before_clip": 0.23978407680988312, "learning_rates_at_step": { "lora": 2.932945493155329e-05, "row_tokens": 2.932945493155329e-05 }, "learning_rates_after_step": { "lora": 2.9175266923832112e-05, "row_tokens": 2.9175266923832112e-05 } }, { "update_id": 642, "row_count": 9, "row_ids_sha256": "42e58d0e14a86eef0bc5c3e85be13ed6ec425909371e8a6ea96885a7d1786863", "input_ids_vector_sha256": "93a4c6b3c555f2f0d6ac53e956f32448d5e3ecef08b1909ecd4a1c9baf6c98da", "labels_vector_sha256": "530cde0d0beb33671b8f6a19cafcc8a87a6d6ca2175837e1ba6ad1670a923e7b", "planned_active_tokens": 64904, "realized_active_tokens": 64904, "cumulative_start": 42081371, "cumulative_end": 42146275, "loss_sum": 25740.392822265625, "token_normalized_loss": 0.39659177896994985, "grad_norm_before_clip": 0.2577567994594574, "learning_rates_at_step": { "lora": 2.9175266923832112e-05, "row_tokens": 2.9175266923832112e-05 }, "learning_rates_after_step": { "lora": 2.9033169326761926e-05, "row_tokens": 2.9033169326761926e-05 } }, { "update_id": 643, "row_count": 8, "row_ids_sha256": "98badedb1d63843cee130d2700788c7e99dd314853590dbdf80ec4d916d5d3ee", "input_ids_vector_sha256": "c390e497d4a889991967a9c6044b3b8702c8facf18ddfb83a8f20c41e509f962", "labels_vector_sha256": "953e0cdf4920f71450c4dee0f2b25f93a9b8289ff10f5423f5906f2281799bec", "planned_active_tokens": 59904, "realized_active_tokens": 59904, "cumulative_start": 42146275, "cumulative_end": 42206179, "loss_sum": 21961.885498046875, "token_normalized_loss": 0.36661801378951114, "grad_norm_before_clip": 0.14813905954360962, "learning_rates_at_step": { "lora": 2.9033169326761926e-05, "row_tokens": 2.9033169326761926e-05 }, "learning_rates_after_step": { "lora": 2.8874219842850804e-05, "row_tokens": 2.8874219842850804e-05 } }, { "update_id": 644, "row_count": 9, "row_ids_sha256": "f7aa2800b6224594f2e4b45acc185d426a38ba9fc75e8bedb40b8d922a456a92", "input_ids_vector_sha256": "581ea9e0122216c4859dabaa795ef5c32d68426f029c5425f7b7b52139cdb550", "labels_vector_sha256": "841df4102951a6d5646cebb6abd94f827cb6dd87562857dc16b0b1e18c9099eb", "planned_active_tokens": 67111, "realized_active_tokens": 67111, "cumulative_start": 42206179, "cumulative_end": 42273290, "loss_sum": 32574.580108642578, "token_normalized_loss": 0.48538361980364736, "grad_norm_before_clip": 0.16448554396629333, "learning_rates_at_step": { "lora": 2.8874219842850804e-05, "row_tokens": 2.8874219842850804e-05 }, "learning_rates_after_step": { "lora": 2.8719546412591684e-05, "row_tokens": 2.8719546412591684e-05 } }, { "update_id": 645, "row_count": 8, "row_ids_sha256": "b0ea2226b983976984f7789b63e2867b9f92b2574f9f37962195c4bc0d2df3ab", "input_ids_vector_sha256": "7e2531bcd9d546384f361477ad14fb485a29624c775696c9fe36adf6c681723a", "labels_vector_sha256": "d19e6d02ed73191ef895dc747cbc7c2e1a03c0af38065a677f561a2922ff9788", "planned_active_tokens": 65411, "realized_active_tokens": 65411, "cumulative_start": 42273290, "cumulative_end": 42338701, "loss_sum": 29049.956329345703, "token_normalized_loss": 0.4441142365862883, "grad_norm_before_clip": 0.15708191692829132, "learning_rates_at_step": { "lora": 2.8719546412591684e-05, "row_tokens": 2.8719546412591684e-05 }, "learning_rates_after_step": { "lora": 2.8559905811981803e-05, "row_tokens": 2.8559905811981803e-05 } }, { "update_id": 646, "row_count": 9, "row_ids_sha256": "2cbe960a292dab89cfdf4fc9f6f3d63ffc58ceef7c817a78f29a12d9d9cb9235", "input_ids_vector_sha256": "5bdc74adf43c83ac4c511216fd2d49d20670c4546db390997f3bd5ac5cd488eb", "labels_vector_sha256": "25de18b8f4fe4f8e245f10f8ec63d199bb037304854dea308b673f513b69fa97", "planned_active_tokens": 67622, "realized_active_tokens": 67622, "cumulative_start": 42338701, "cumulative_end": 42406323, "loss_sum": 30006.745971679688, "token_normalized_loss": 0.44374236153440727, "grad_norm_before_clip": 0.14671561121940613, "learning_rates_at_step": { "lora": 2.8559905811981803e-05, "row_tokens": 2.8559905811981803e-05 }, "learning_rates_after_step": { "lora": 2.839813066150886e-05, "row_tokens": 2.839813066150886e-05 } }, { "update_id": 647, "row_count": 8, "row_ids_sha256": "103bcface6de2b655697edc6c61550882ac4ebc23df6b5307be1631066f9203b", "input_ids_vector_sha256": "de841ad9badd2765cd5e16e2124049eea8f2e2f8ef25e4f5fe5f1e11af05b7ad", "labels_vector_sha256": "b516c85675f176d99beb2a988245edc0bcb4edf753e8418a2af9fcae8a7965f9", "planned_active_tokens": 68642, "realized_active_tokens": 68642, "cumulative_start": 42406323, "cumulative_end": 42474965, "loss_sum": 26360.6142578125, "token_normalized_loss": 0.384030393313314, "grad_norm_before_clip": 0.14176779985427856, "learning_rates_at_step": { "lora": 2.839813066150886e-05, "row_tokens": 2.839813066150886e-05 }, "learning_rates_after_step": { "lora": 2.8258875887663982e-05, "row_tokens": 2.8258875887663982e-05 } }, { "update_id": 648, "row_count": 7, "row_ids_sha256": "997a9f14f219e212466f9eca793b7eb0a47d187276d0aa0a333b332a1aad473d", "input_ids_vector_sha256": "07f6a6b7fcb7e52c9c937cef3d9af14c1c9889c43bc633adb3303dd1a2cf8318", "labels_vector_sha256": "324119434e52d2ece4b5687c2901fed5342485d728f2eafba66da9c037815c2d", "planned_active_tokens": 59181, "realized_active_tokens": 59181, "cumulative_start": 42474965, "cumulative_end": 42534146, "loss_sum": 22477.487548828125, "token_normalized_loss": 0.37980918789523876, "grad_norm_before_clip": 0.14949609339237213, "learning_rates_at_step": { "lora": 2.8258875887663982e-05, "row_tokens": 2.8258875887663982e-05 }, "learning_rates_after_step": { "lora": 2.8087592588661908e-05, "row_tokens": 2.8087592588661908e-05 } }, { "update_id": 649, "row_count": 9, "row_ids_sha256": "acc365653f34497b5e80d862e71af8282e4d4c44c382fa0c2103387b9d47bc28", "input_ids_vector_sha256": "bbed7c5d356a70d8fa741550e18af271e24d0cbb3fd37945672a64a5fa6b7db3", "labels_vector_sha256": "455f73c729b0b6f592fb79c02abe4626cc18786804ad17c9324623bb201eaff0", "planned_active_tokens": 72914, "realized_active_tokens": 72914, "cumulative_start": 42534146, "cumulative_end": 42607060, "loss_sum": 31103.227172851562, "token_normalized_loss": 0.4265741445106778, "grad_norm_before_clip": 0.14210253953933716, "learning_rates_at_step": { "lora": 2.8087592588661908e-05, "row_tokens": 2.8087592588661908e-05 }, "learning_rates_after_step": { "lora": 2.7933998766058317e-05, "row_tokens": 2.7933998766058317e-05 } }, { "update_id": 650, "row_count": 8, "row_ids_sha256": "42d37b9c03e236f841b4685803eb51305bcb9e05b1b4a5cf89a6100aedda1103", "input_ids_vector_sha256": "4b75e05414729bce34e5e02c4d34832b4f1d420a2a38f708369dcedec4127036", "labels_vector_sha256": "fbb27c68673c79b91d90bfc2148e068a5b2a097d926f9b3bb3862ab314f5fc59", "planned_active_tokens": 65499, "realized_active_tokens": 65499, "cumulative_start": 42607060, "cumulative_end": 42672559, "loss_sum": 26425.118896484375, "token_normalized_loss": 0.40344308915379434, "grad_norm_before_clip": 0.15502671897411346, "learning_rates_at_step": { "lora": 2.7933998766058317e-05, "row_tokens": 2.7933998766058317e-05 }, "learning_rates_after_step": { "lora": 2.7792955686278166e-05, "row_tokens": 2.7792955686278166e-05 } }, { "update_id": 651, "row_count": 8, "row_ids_sha256": "afe133bc8fc918255144f930adc73a8e683eec164f89ea18b5edba0afbdf1e1a", "input_ids_vector_sha256": "65eb4d932f4a529eb4b8303374b0b47f4cae0c69f2f6ead00ab5efc54db93165", "labels_vector_sha256": "d3e184ea3e8f2b863c8da511d4acc4d3d4afe98208a5e0c5072a16a2e024e065", "planned_active_tokens": 60244, "realized_active_tokens": 60244, "cumulative_start": 42672559, "cumulative_end": 42732803, "loss_sum": 25586.841796875, "token_normalized_loss": 0.42472016793166123, "grad_norm_before_clip": 0.15813373029232025, "learning_rates_at_step": { "lora": 2.7792955686278166e-05, "row_tokens": 2.7792955686278166e-05 }, "learning_rates_after_step": { "lora": 2.7640150968560925e-05, "row_tokens": 2.7640150968560925e-05 } }, { "update_id": 652, "row_count": 10, "row_ids_sha256": "642b7142333b7c66da74a884d95e939edb5fb70a50a02fc681d0d53eaf990612", "input_ids_vector_sha256": "445c96675e48aa35208631865d81ad926e3a00b64d938d9c892bb3dfd035928f", "labels_vector_sha256": "636005dfa00711ec7951b547983904297d0774ccf34444d7f5ad00de7a8da84a", "planned_active_tokens": 65374, "realized_active_tokens": 65374, "cumulative_start": 42732803, "cumulative_end": 42798177, "loss_sum": 27180.955017089844, "token_normalized_loss": 0.4157762262839943, "grad_norm_before_clip": 0.1542394459247589, "learning_rates_at_step": { "lora": 2.7640150968560925e-05, "row_tokens": 2.7640150968560925e-05 }, "learning_rates_after_step": { "lora": 2.7466197816503837e-05, "row_tokens": 2.7466197816503837e-05 } }, { "update_id": 653, "row_count": 8, "row_ids_sha256": "aa6b6a7de8670b04152aeb74bf9e160169845728512db4b5fe87f0470858f981", "input_ids_vector_sha256": "e72b476499593ab4130c0639117f77ee3954f89015042932c7c33be9988585f1", "labels_vector_sha256": "e6a9e0380a9732a5ceeb2586dbc4b7a699f645ae3222072a38e3fc17dc4335c5", "planned_active_tokens": 74558, "realized_active_tokens": 74558, "cumulative_start": 42798177, "cumulative_end": 42872735, "loss_sum": 28766.20654296875, "token_normalized_loss": 0.38582320532965947, "grad_norm_before_clip": 0.146868497133255, "learning_rates_at_step": { "lora": 2.7466197816503837e-05, "row_tokens": 2.7466197816503837e-05 }, "learning_rates_after_step": { "lora": 2.734000091938258e-05, "row_tokens": 2.734000091938258e-05 } }, { "update_id": 654, "row_count": 7, "row_ids_sha256": "8b2266761cbbf8f0f4f657d1ca85c65adc1c7b356fccaddacd09b7e5153f1ca3", "input_ids_vector_sha256": "8f325c9218f93199d185698c13fdbf1b07a254546300f56acb89489a6d510937", "labels_vector_sha256": "a030471dd5d49220d709bb8b4a27da643ba5ccfe2d21c7a75c241c5c982fd55b", "planned_active_tokens": 54181, "realized_active_tokens": 54181, "cumulative_start": 42872735, "cumulative_end": 42926916, "loss_sum": 22954.300415039062, "token_normalized_loss": 0.4236595931237715, "grad_norm_before_clip": 0.1772884577512741, "learning_rates_at_step": { "lora": 2.734000091938258e-05, "row_tokens": 2.734000091938258e-05 }, "learning_rates_after_step": { "lora": 2.71829009078417e-05, "row_tokens": 2.71829009078417e-05 } }, { "update_id": 655, "row_count": 9, "row_ids_sha256": "4745ab58adf27b2f3769c17a6245e6d5ef1592c1d8720db04b0e9b885b7ddf70", "input_ids_vector_sha256": "794851b481b47f649e247fb031f0d3ab6e823f37ec086dd47ca5288495ac994a", "labels_vector_sha256": "fa4fa748c1cd0e3a3ebe83d87bcfbc677403f97874679cc8f5f96f76717c9b38", "planned_active_tokens": 67558, "realized_active_tokens": 67558, "cumulative_start": 42926916, "cumulative_end": 42994474, "loss_sum": 25540.257568359375, "token_normalized_loss": 0.3780493437988007, "grad_norm_before_clip": 0.14780302345752716, "learning_rates_at_step": { "lora": 2.71829009078417e-05, "row_tokens": 2.71829009078417e-05 }, "learning_rates_after_step": { "lora": 2.702637940954903e-05, "row_tokens": 2.702637940954903e-05 } }, { "update_id": 656, "row_count": 9, "row_ids_sha256": "fb284ab2faa1250d6d037990ac478d68bc9b438a57a0a4a493b8033191846e01", "input_ids_vector_sha256": "57076f466ec1e7011ef702b484221a20cec7a74cefd7c121bcb588f2ab75fb62", "labels_vector_sha256": "0623db3966d980ff2926b22f364be63ff690bc11f904479e9ed39cb733f961ef", "planned_active_tokens": 67431, "realized_active_tokens": 67431, "cumulative_start": 42994474, "cumulative_end": 43061905, "loss_sum": 25591.302734375, "token_normalized_loss": 0.3795183629840133, "grad_norm_before_clip": 0.15041965246200562, "learning_rates_at_step": { "lora": 2.702637940954903e-05, "row_tokens": 2.702637940954903e-05 }, "learning_rates_after_step": { "lora": 2.6878428073418403e-05, "row_tokens": 2.6878428073418403e-05 } }, { "update_id": 657, "row_count": 13, "row_ids_sha256": "81b479201bb954df02bae1c3c4f0c282e530d767fcc4e4b3c747b6be4611d790", "input_ids_vector_sha256": "2466254c63fc7f46c5425ee3f4d46a90b99023bb34da51f5c16b46eeee5bcd9e", "labels_vector_sha256": "9fab3fc4bddbcb76e07a00f9d286f36d0eb5a4be2441bcfc824e548d62c667b7", "planned_active_tokens": 63852, "realized_active_tokens": 63852, "cumulative_start": 43061905, "cumulative_end": 43125757, "loss_sum": 22427.57598876953, "token_normalized_loss": 0.3512431245500459, "grad_norm_before_clip": 0.36644142866134644, "learning_rates_at_step": { "lora": 2.6878428073418403e-05, "row_tokens": 2.6878428073418403e-05 }, "learning_rates_after_step": { "lora": 2.672465365400023e-05, "row_tokens": 2.672465365400023e-05 } }, { "update_id": 658, "row_count": 13, "row_ids_sha256": "8a7013f4b8f172e4ec66811919f158ebfc3a7d57640e55ec8f43ca83cc276279", "input_ids_vector_sha256": "dc0ce3fa1445e57b74f867f1662e7dfc36b5cab14d685fed8b52bfb902df1d4d", "labels_vector_sha256": "5ec2b73f0c6eef16ca046b0d657846e86d429e6296f9bd175b0d3a79c791fcb1", "planned_active_tokens": 66483, "realized_active_tokens": 66483, "cumulative_start": 43125757, "cumulative_end": 43192240, "loss_sum": 26775.76303100586, "token_normalized_loss": 0.4027460107246343, "grad_norm_before_clip": 0.17189888656139374, "learning_rates_at_step": { "lora": 2.672465365400023e-05, "row_tokens": 2.672465365400023e-05 }, "learning_rates_after_step": { "lora": 2.6576832024365804e-05, "row_tokens": 2.6576832024365804e-05 } }, { "update_id": 659, "row_count": 11, "row_ids_sha256": "51e4a67bc6f582dde17675d154efffc05ff410abe5c3d92bef3c6d451e65d819", "input_ids_vector_sha256": "9363b3907d62b63de6513e7448b72bc753670896ce5a4bab8f3f2456bb67c129", "labels_vector_sha256": "779a11ddaa6bfe06afbfb5401d4ae9464a49dc0bd4e8694f59be1046c0456934", "planned_active_tokens": 64024, "realized_active_tokens": 64024, "cumulative_start": 43192240, "cumulative_end": 43256264, "loss_sum": 25399.283599853516, "token_normalized_loss": 0.3967150381084205, "grad_norm_before_clip": 0.1623651385307312, "learning_rates_at_step": { "lora": 2.6576832024365804e-05, "row_tokens": 2.6576832024365804e-05 }, "learning_rates_after_step": { "lora": 2.642847088603685e-05, "row_tokens": 2.642847088603685e-05 } }, { "update_id": 660, "row_count": 14, "row_ids_sha256": "faf3959d543df05e846c68da8a105731fdf83e12dcef3ac3b8e1cb48fe763fb1", "input_ids_vector_sha256": "4edd6fd7ea38164738d4b844c94daed0d7e5f90a8e446926148ba67ebf1bedaf", "labels_vector_sha256": "db2db282cc55ee2f84bf6d8f140ce1977d4aef9d44d44aa64efcc3d4bbb2de46", "planned_active_tokens": 64372, "realized_active_tokens": 64372, "cumulative_start": 43256264, "cumulative_end": 43320636, "loss_sum": 22592.223510742188, "token_normalized_loss": 0.3509635169132882, "grad_norm_before_clip": 0.1578895002603531, "learning_rates_at_step": { "lora": 2.642847088603685e-05, "row_tokens": 2.642847088603685e-05 }, "learning_rates_after_step": { "lora": 2.626925886877962e-05, "row_tokens": 2.626925886877962e-05 } }, { "update_id": 661, "row_count": 14, "row_ids_sha256": "6a682369dd7d9fb65eb0f190a35e418d473b12dd05d81cf73f9a69b389330ce0", "input_ids_vector_sha256": "8b37e0f3cf7731364ddc2d0a72026b849c7854a99d7519cab85913ddc8ced69f", "labels_vector_sha256": "fed1cd756116a7ce1deed9fc89c66d9a750c09afb82b1e769ec340382fe01ec3", "planned_active_tokens": 69209, "realized_active_tokens": 69209, "cumulative_start": 43320636, "cumulative_end": 43389845, "loss_sum": 23557.771514892578, "token_normalized_loss": 0.34038595435409524, "grad_norm_before_clip": 0.22984150052070618, "learning_rates_at_step": { "lora": 2.626925886877962e-05, "row_tokens": 2.626925886877962e-05 }, "learning_rates_after_step": { "lora": 2.610815717154365e-05, "row_tokens": 2.610815717154365e-05 } }, { "update_id": 662, "row_count": 13, "row_ids_sha256": "b08bc6fda99135d05a99c2c10a5a6dc19c286f8644403001a25f6cd930af5752", "input_ids_vector_sha256": "2facc38d8b83ac26bfc774fe55fd73f1a4419454719c912163009a19fd595267", "labels_vector_sha256": "fdf98b178dd390d2ca91523b6f5a5065f2f015c4e19e2bd5b1298cf56de1ebaf", "planned_active_tokens": 70168, "realized_active_tokens": 70168, "cumulative_start": 43389845, "cumulative_end": 43460013, "loss_sum": 26492.450927734375, "token_normalized_loss": 0.37755744680957665, "grad_norm_before_clip": 0.1603647619485855, "learning_rates_at_step": { "lora": 2.610815717154365e-05, "row_tokens": 2.610815717154365e-05 }, "learning_rates_after_step": { "lora": 2.5970636643080465e-05, "row_tokens": 2.5970636643080465e-05 } }, { "update_id": 663, "row_count": 12, "row_ids_sha256": "a9c86305fa33f8a2302088ddeecb93d4f8b594b94dbea0a76a72f31f0f4cbc13", "input_ids_vector_sha256": "0ef51306e5e93a899fd4ba838c6e0a39b2c36803622b23c8f9d3d8d25821f5ee", "labels_vector_sha256": "8ec9bf403d3c0b74b5eda9c8de0c5c47d4bd08c4e86b18bafa9c5cf6558a398b", "planned_active_tokens": 60008, "realized_active_tokens": 60008, "cumulative_start": 43460013, "cumulative_end": 43520021, "loss_sum": 22178.331420898438, "token_normalized_loss": 0.36958957840452, "grad_norm_before_clip": 0.17170126736164093, "learning_rates_at_step": { "lora": 2.5970636643080465e-05, "row_tokens": 2.5970636643080465e-05 }, "learning_rates_after_step": { "lora": 2.5826117860139227e-05, "row_tokens": 2.5826117860139227e-05 } }, { "update_id": 664, "row_count": 13, "row_ids_sha256": "aa9da56a17c832d298946f29f3b5789221f4c48ec6c50ae6670a134bcec1b691", "input_ids_vector_sha256": "c1c179d6ed5872127c8bc64c1b1509f55f9d51562dc4ffc0f5140734f3fa5efb", "labels_vector_sha256": "40dfef71a12ea06054f486434e4ad804f1e821315f28cd24eabe95f68f5bf81b", "planned_active_tokens": 63173, "realized_active_tokens": 63173, "cumulative_start": 43520021, "cumulative_end": 43583194, "loss_sum": 22408.65234375, "token_normalized_loss": 0.3547188251903503, "grad_norm_before_clip": 0.15799084305763245, "learning_rates_at_step": { "lora": 2.5826117860139227e-05, "row_tokens": 2.5826117860139227e-05 }, "learning_rates_after_step": { "lora": 2.5660221392261062e-05, "row_tokens": 2.5660221392261062e-05 } }, { "update_id": 665, "row_count": 13, "row_ids_sha256": "86d204595c54dedf231b0e0d06c7a9f0d9d9b16a83c0fa268deff89014c96bc2", "input_ids_vector_sha256": "1de3a64a48d1d57ad1819aeeb6d5ad2b99650ecb0eaa01d30c0c9a94651a1447", "labels_vector_sha256": "929ea331b1332610b47740e924b16686e25b06e6c44cb6e5acdb192b4f3c0caa", "planned_active_tokens": 72660, "realized_active_tokens": 72660, "cumulative_start": 43583194, "cumulative_end": 43655854, "loss_sum": 28394.328002929688, "token_normalized_loss": 0.3907834847636896, "grad_norm_before_clip": 0.15719208121299744, "learning_rates_at_step": { "lora": 2.5660221392261062e-05, "row_tokens": 2.5660221392261062e-05 }, "learning_rates_after_step": { "lora": 2.552188446968693e-05, "row_tokens": 2.552188446968693e-05 } }, { "update_id": 666, "row_count": 9, "row_ids_sha256": "a22bb98f1345ae7cb69d6770a60338c9d399ad3ce89f5b0d05da5e5b36a17adf", "input_ids_vector_sha256": "dcd5b969c54a1e7ae3569b8550ce2995c4f18c1f464cdf059efb859898e53e31", "labels_vector_sha256": "e99d8f19962b48f0b4fc97299683805c8de15915a0cd69493511799d2f0cb1ef", "planned_active_tokens": 60707, "realized_active_tokens": 60707, "cumulative_start": 43655854, "cumulative_end": 43716561, "loss_sum": 24646.192749023438, "token_normalized_loss": 0.4059860106581356, "grad_norm_before_clip": 0.17060741782188416, "learning_rates_at_step": { "lora": 2.552188446968693e-05, "row_tokens": 2.552188446968693e-05 }, "learning_rates_after_step": { "lora": 2.537007689012901e-05, "row_tokens": 2.537007689012901e-05 } }, { "update_id": 667, "row_count": 12, "row_ids_sha256": "931dcb1445a492ccfb6d1e3ae23afcd6a0012fc7e0b2a6cc0b3a24e6c58fb18b", "input_ids_vector_sha256": "d47eaf746f7b3455c504ce76ec9f85878bbc73775965cac6ff029face8ef7f55", "labels_vector_sha256": "aae983ab24225a108dbabd46d8690a0034ceb1c8499f8c4b49fdd57b4207f221", "planned_active_tokens": 66743, "realized_active_tokens": 66743, "cumulative_start": 43716561, "cumulative_end": 43783304, "loss_sum": 23186.811767578125, "token_normalized_loss": 0.3474043984774152, "grad_norm_before_clip": 0.1554347574710846, "learning_rates_at_step": { "lora": 2.537007689012901e-05, "row_tokens": 2.537007689012901e-05 }, "learning_rates_after_step": { "lora": 2.5231362108478595e-05, "row_tokens": 2.5231362108478595e-05 } }, { "update_id": 668, "row_count": 13, "row_ids_sha256": "d63ceaacd25fceabd547580fd134831cac1690d830fce1ed14ae9c562d856a85", "input_ids_vector_sha256": "35cdeeb8f1034f6a80689e8b250ab584ee68bf7abc9bc1d2c8efcfce6c81f29f", "labels_vector_sha256": "a899945597d4f760f9817797b27f0d43381f51dc469c2761006ea8576648f797", "planned_active_tokens": 61102, "realized_active_tokens": 61102, "cumulative_start": 43783304, "cumulative_end": 43844406, "loss_sum": 19204.993255615234, "token_normalized_loss": 0.3143103868222846, "grad_norm_before_clip": 0.15382209420204163, "learning_rates_at_step": { "lora": 2.5231362108478595e-05, "row_tokens": 2.5231362108478595e-05 }, "learning_rates_after_step": { "lora": 2.507583073235723e-05, "row_tokens": 2.507583073235723e-05 } }, { "update_id": 669, "row_count": 13, "row_ids_sha256": "33e7acef3e25c72b598c77928871fda08c06ca457b7643b92d1b4bf2da266e2a", "input_ids_vector_sha256": "a2ca994ff25b81c664dfc904097e8c2c72ce82725796c171389e2642e5b84ded", "labels_vector_sha256": "bb198759b5a00d70bc4077fa6636a70724b73af156f8772c0229888a0f919fa8", "planned_active_tokens": 68642, "realized_active_tokens": 68642, "cumulative_start": 43844406, "cumulative_end": 43913048, "loss_sum": 27357.683349609375, "token_normalized_loss": 0.3985560349291888, "grad_norm_before_clip": 0.16899657249450684, "learning_rates_at_step": { "lora": 2.507583073235723e-05, "row_tokens": 2.507583073235723e-05 }, "learning_rates_after_step": { "lora": 2.4927918228024727e-05, "row_tokens": 2.4927918228024727e-05 } }, { "update_id": 670, "row_count": 12, "row_ids_sha256": "0ec555ab15bff57a8b678579336c4c1117e3e3b0dc60810c32480d74679fe202", "input_ids_vector_sha256": "11f920a117a460c6bcc7f2bded9dba9d698854e18132a0af2489005f4da06c4b", "labels_vector_sha256": "d845845a477ae1c510631d180d97aa9489dafa1d833b7ee56a1d9b5d99c212e6", "planned_active_tokens": 65411, "realized_active_tokens": 65411, "cumulative_start": 43913048, "cumulative_end": 43978459, "loss_sum": 22416.585388183594, "token_normalized_loss": 0.34270360318881526, "grad_norm_before_clip": 0.15754207968711853, "learning_rates_at_step": { "lora": 2.4927918228024727e-05, "row_tokens": 2.4927918228024727e-05 }, "learning_rates_after_step": { "lora": 2.47783097619832e-05, "row_tokens": 2.47783097619832e-05 } }, { "update_id": 671, "row_count": 12, "row_ids_sha256": "b625a411c6bc9a3cb1103df05088735a2860718622b8568123637141cc80218b", "input_ids_vector_sha256": "b7ebf0c23fbdd6382012336e2643a4db7219978e9d352ec29706113ab99beea1", "labels_vector_sha256": "156b375059999f0b9e8aaf4f314eb4d495d83be985656de1cd62ccb11bd04a6c", "planned_active_tokens": 66293, "realized_active_tokens": 66293, "cumulative_start": 43978459, "cumulative_end": 44044752, "loss_sum": 24385.91082763672, "token_normalized_loss": 0.367850464266766, "grad_norm_before_clip": 0.16129928827285767, "learning_rates_at_step": { "lora": 2.47783097619832e-05, "row_tokens": 2.47783097619832e-05 }, "learning_rates_after_step": { "lora": 2.4632830793315003e-05, "row_tokens": 2.4632830793315003e-05 } }, { "update_id": 672, "row_count": 12, "row_ids_sha256": "9b466dbbe01913a7d5f397ea45036bcadcb19cfb6eed24b7c44fbee0cad97beb", "input_ids_vector_sha256": "5eadebdcdfc9e5501aaca72ba10c2056b51c6d4250547ae4dc4a5c9b45ece91a", "labels_vector_sha256": "1e35e5cfa62aaf57b5d0c994abef8f408485ec00d9ffb527f7f470bbc1cc338c", "planned_active_tokens": 64592, "realized_active_tokens": 64592, "cumulative_start": 44044752, "cumulative_end": 44109344, "loss_sum": 22173.532165527344, "token_normalized_loss": 0.34328604417772085, "grad_norm_before_clip": 0.15464681386947632, "learning_rates_at_step": { "lora": 2.4632830793315003e-05, "row_tokens": 2.4632830793315003e-05 }, "learning_rates_after_step": { "lora": 2.4491040301452046e-05, "row_tokens": 2.4491040301452046e-05 } }, { "update_id": 673, "row_count": 13, "row_ids_sha256": "1c7f8fff801fb1a04da7f00ccbd68064594b0353c365e9f1e5e441780e0fa765", "input_ids_vector_sha256": "834d95926fd017c7f27303125e5969e2617ff7d86c8e306742d901cc3660f1d0", "labels_vector_sha256": "33236dabce026529f6b442142f0e43a85220545ee2d9a4f1fd56f8b245ad1cd5", "planned_active_tokens": 63078, "realized_active_tokens": 63078, "cumulative_start": 44109344, "cumulative_end": 44172422, "loss_sum": 23850.10986328125, "token_normalized_loss": 0.3781050423805645, "grad_norm_before_clip": 0.5486661791801453, "learning_rates_at_step": { "lora": 2.4491040301452046e-05, "row_tokens": 2.4491040301452046e-05 }, "learning_rates_after_step": { "lora": 2.432774027189455e-05, "row_tokens": 2.432774027189455e-05 } }, { "update_id": 674, "row_count": 13, "row_ids_sha256": "7e3c635e5f52ad9e419c12139b15d4ed74618e4189a2054d8d4d491a4e086872", "input_ids_vector_sha256": "bdc0c955845deeda8179238aa0b37911e0fa61ddf85c212c39e7757ef3458df5", "labels_vector_sha256": "47a3485d76d0b9dc6fb9055a2db29422e059f86acffaa709708989a677e61e12", "planned_active_tokens": 72800, "realized_active_tokens": 72800, "cumulative_start": 44172422, "cumulative_end": 44245222, "loss_sum": 29835.21661376953, "token_normalized_loss": 0.40982440403529574, "grad_norm_before_clip": 0.1604851484298706, "learning_rates_at_step": { "lora": 2.432774027189455e-05, "row_tokens": 2.432774027189455e-05 }, "learning_rates_after_step": { "lora": 2.4196960236670617e-05, "row_tokens": 2.4196960236670617e-05 } }, { "update_id": 675, "row_count": 13, "row_ids_sha256": "4d31c7b23f2b53271f24ca92549a2404072d2e9fce83bd8ad1699f38fd1e1cf5", "input_ids_vector_sha256": "0f8a154cc33b8a3be19b23e3bede2637c16a95f647f4c163dd4eb335aad19bea", "labels_vector_sha256": "3c4864aae686ae63d11f212d672d2f687bc67d08fcbf21efac18d8bd17401c55", "planned_active_tokens": 58422, "realized_active_tokens": 58422, "cumulative_start": 44245222, "cumulative_end": 44303644, "loss_sum": 19314.117126464844, "token_normalized_loss": 0.3305966438407594, "grad_norm_before_clip": 0.16837580502033234, "learning_rates_at_step": { "lora": 2.4196960236670617e-05, "row_tokens": 2.4196960236670617e-05 }, "learning_rates_after_step": { "lora": 2.405159230874442e-05, "row_tokens": 2.405159230874442e-05 } }, { "update_id": 676, "row_count": 13, "row_ids_sha256": "c6ad2ab97163c022ac69823a615cc48e1b062d80867b4cc5c9dd7b97fe16fec6", "input_ids_vector_sha256": "fd6a81fcef7e8e18742579c8b698702c9bbdea1ec8dbdc42838ba3abe456cb76", "labels_vector_sha256": "7f8fdc6319b3eafc760e8f3bcf7377669a0f5ef100580a09392b3b07e1e48e5d", "planned_active_tokens": 65065, "realized_active_tokens": 65065, "cumulative_start": 44303644, "cumulative_end": 44368709, "loss_sum": 22364.55792236328, "token_normalized_loss": 0.343726395487025, "grad_norm_before_clip": 0.157933309674263, "learning_rates_at_step": { "lora": 2.405159230874442e-05, "row_tokens": 2.405159230874442e-05 }, "learning_rates_after_step": { "lora": 2.3895132335899584e-05, "row_tokens": 2.3895132335899584e-05 } }, { "update_id": 677, "row_count": 16, "row_ids_sha256": "d4d89716d091d1d9b0979faf845a2fe5abc0eea8e4aadc4b05cfd1d9c45d8787", "input_ids_vector_sha256": "791c19fcbc02e2f8269e8c1420b41109294e8f4f7259fce5fb4614a973b23ad5", "labels_vector_sha256": "6e6d2e59bf52a30f577a0daf75f209dbee0d4f3d2c8b2fa9a374040e63b9b938", "planned_active_tokens": 70180, "realized_active_tokens": 70180, "cumulative_start": 44368709, "cumulative_end": 44438889, "loss_sum": 22118.921966552734, "token_normalized_loss": 0.31517415170351576, "grad_norm_before_clip": 0.14980752766132355, "learning_rates_at_step": { "lora": 2.3895132335899584e-05, "row_tokens": 2.3895132335899584e-05 }, "learning_rates_after_step": { "lora": 2.376045659196341e-05, "row_tokens": 2.376045659196341e-05 } }, { "update_id": 678, "row_count": 12, "row_ids_sha256": "400af7adabc33b44f5718def74aead3fe4807edc1114960f2703e456f66ed742", "input_ids_vector_sha256": "6bc11ce9372c9aaa6d495ece0f2d9b8b856f7bdf2fee89abc371bc47506b4765", "labels_vector_sha256": "a0596d8685a114d80b80b2596c89d5957b6430d96f84d5f050fd166a01f758b2", "planned_active_tokens": 60535, "realized_active_tokens": 60535, "cumulative_start": 44438889, "cumulative_end": 44499424, "loss_sum": 23369.99627685547, "token_normalized_loss": 0.38605759109367255, "grad_norm_before_clip": 0.17404904961585999, "learning_rates_at_step": { "lora": 2.376045659196341e-05, "row_tokens": 2.376045659196341e-05 }, "learning_rates_after_step": { "lora": 2.359967754777907e-05, "row_tokens": 2.359967754777907e-05 } }, { "update_id": 679, "row_count": 13, "row_ids_sha256": "b18b6eb9c9deefc8a2abec2b78fa8f3f41c3431828f2fe30eeb0b309a63bd115", "input_ids_vector_sha256": "6ad995731d5101cfdaa21a7c5659c1d5bc731dedf1fbcba2313497a4dcb66b78", "labels_vector_sha256": "f4391e934c79d80711ee6105bf88510f8399af7d9fd1db58e0e5fd9025321d17", "planned_active_tokens": 72423, "realized_active_tokens": 72423, "cumulative_start": 44499424, "cumulative_end": 44571847, "loss_sum": 23415.344665527344, "token_normalized_loss": 0.3233136526452556, "grad_norm_before_clip": 0.15084517002105713, "learning_rates_at_step": { "lora": 2.359967754777907e-05, "row_tokens": 2.359967754777907e-05 }, "learning_rates_after_step": { "lora": 2.3466635112499046e-05, "row_tokens": 2.3466635112499046e-05 } }, { "update_id": 680, "row_count": 10, "row_ids_sha256": "4c2f11cc44c51433b2678918002b6f443fcd32a19f2a3cd4b6c7468a8011aea5", "input_ids_vector_sha256": "fc419392d62b45ee3579178f7fa44dbf7c62d868045015e84d5e41f663965ba0", "labels_vector_sha256": "417e84c93ab0faad63f6af2c0a8d28d0b0420d1b880d8f3262bcce30e6a7d584", "planned_active_tokens": 60058, "realized_active_tokens": 60058, "cumulative_start": 44571847, "cumulative_end": 44631905, "loss_sum": 18815.36883544922, "token_normalized_loss": 0.3132866368418732, "grad_norm_before_clip": 0.16421367228031158, "learning_rates_at_step": { "lora": 2.3466635112499046e-05, "row_tokens": 2.3466635112499046e-05 }, "learning_rates_after_step": { "lora": 2.3325370558070737e-05, "row_tokens": 2.3325370558070737e-05 } }, { "update_id": 681, "row_count": 11, "row_ids_sha256": "ff192d16b7ba312d4fff7f6ec150e676d8b747bd18be80bdd2e417350bd9065e", "input_ids_vector_sha256": "483ff13edc17e859eadff06e2132b2e397bd9d68e3cb7df5bc768dcce220d660", "labels_vector_sha256": "d269309fb1ac8e4cf39f9702abd9fc225233a4dd1f9c7ce60d0edc20eb26a683", "planned_active_tokens": 63899, "realized_active_tokens": 63899, "cumulative_start": 44631905, "cumulative_end": 44695804, "loss_sum": 21273.341674804688, "token_normalized_loss": 0.33292135518247057, "grad_norm_before_clip": 0.1586654782295227, "learning_rates_at_step": { "lora": 2.3325370558070737e-05, "row_tokens": 2.3325370558070737e-05 }, "learning_rates_after_step": { "lora": 2.3169679075359317e-05, "row_tokens": 2.3169679075359317e-05 } }, { "update_id": 682, "row_count": 14, "row_ids_sha256": "7ae62cc2edffb3d1d8a4c76567c854a70e86a5be03cba92137055ec52380d7d9", "input_ids_vector_sha256": "99310b121d0e39fca9b680915fc3f66dd9351d11cab314af764c9f4efa602de3", "labels_vector_sha256": "c3c654d57128bb94e9f6484ef18a5f0074c4d3c02611f806992881a6d86a10af", "planned_active_tokens": 70581, "realized_active_tokens": 70581, "cumulative_start": 44695804, "cumulative_end": 44766385, "loss_sum": 23962.37191772461, "token_normalized_loss": 0.3395017344288776, "grad_norm_before_clip": 0.15352767705917358, "learning_rates_at_step": { "lora": 2.3169679075359317e-05, "row_tokens": 2.3169679075359317e-05 }, "learning_rates_after_step": { "lora": 2.303005498370036e-05, "row_tokens": 2.303005498370036e-05 } }, { "update_id": 683, "row_count": 12, "row_ids_sha256": "639b91e04e51f386bef8a36b8546cb3951b7c2434cb4483ac518ac2e95a34f21", "input_ids_vector_sha256": "cc87683fe8226800198957849e21ef99edb966dbb706e35fb249050cecabb483", "labels_vector_sha256": "8792de5374df6cdce1392e3dd05cdf1d45003d477176ab8623e9b5edc22492e7", "planned_active_tokens": 63438, "realized_active_tokens": 63438, "cumulative_start": 44766385, "cumulative_end": 44829823, "loss_sum": 21815.574249267578, "token_normalized_loss": 0.3438881151560197, "grad_norm_before_clip": 0.16266803443431854, "learning_rates_at_step": { "lora": 2.303005498370036e-05, "row_tokens": 2.303005498370036e-05 }, "learning_rates_after_step": { "lora": 2.288122777625951e-05, "row_tokens": 2.288122777625951e-05 } }, { "update_id": 684, "row_count": 10, "row_ids_sha256": "91e06ba57432a9c9cf8396b0b2a0779d6dfc4b732daf04b7dfed20ad727c654b", "input_ids_vector_sha256": "ad22cec9e5d59f6d74dff8b8748f59d1ba30b3a9d9a15cd7733df14d6b5d1c51", "labels_vector_sha256": "0e34592ec51f4a93d5441964373baad2af5e4a908bf627fa26e15b23ed7d2ef1", "planned_active_tokens": 67768, "realized_active_tokens": 67768, "cumulative_start": 44829823, "cumulative_end": 44897591, "loss_sum": 28630.83367919922, "token_normalized_loss": 0.4224830846299023, "grad_norm_before_clip": 0.17610393464565277, "learning_rates_at_step": { "lora": 2.288122777625951e-05, "row_tokens": 2.288122777625951e-05 }, "learning_rates_after_step": { "lora": 2.2745518520227528e-05, "row_tokens": 2.2745518520227528e-05 } }, { "update_id": 685, "row_count": 11, "row_ids_sha256": "b4a0e03328e236df01c94d68cb541e2a6ed969fc836da2db109660030a06a903", "input_ids_vector_sha256": "114e5a75946c349b9ab3139b43e4013bdf8ef020718abb009459a135feb4847e", "labels_vector_sha256": "57d1f1f9af2f0adb0ed81399893920e79927eab662bf95f52a8422f33ee05ff7", "planned_active_tokens": 61930, "realized_active_tokens": 61930, "cumulative_start": 44897591, "cumulative_end": 44959521, "loss_sum": 21064.088500976562, "token_normalized_loss": 0.3401273777002513, "grad_norm_before_clip": 0.16538406908512115, "learning_rates_at_step": { "lora": 2.2745518520227528e-05, "row_tokens": 2.2745518520227528e-05 }, "learning_rates_after_step": { "lora": 2.2593708891832393e-05, "row_tokens": 2.2593708891832393e-05 } }, { "update_id": 686, "row_count": 15, "row_ids_sha256": "2d6615d4e7b679e2a2a7deb978cc74ec3bb5209e388525e810f2931262024bd1", "input_ids_vector_sha256": "331255e3a9cd7952ff005174d6345916368f159fc64b562dea6ff89600e1f329", "labels_vector_sha256": "8f9027cc3f94a85d23413301535be9c3dd48d4ce94ddae36d5c3ba0315998522", "planned_active_tokens": 69432, "realized_active_tokens": 69432, "cumulative_start": 44959521, "cumulative_end": 45028953, "loss_sum": 19874.456756591797, "token_normalized_loss": 0.2862434721251267, "grad_norm_before_clip": 0.36798956990242004, "learning_rates_at_step": { "lora": 2.2593708891832393e-05, "row_tokens": 2.2593708891832393e-05 }, "learning_rates_after_step": { "lora": 2.245604106557884e-05, "row_tokens": 2.245604106557884e-05 } }, { "update_id": 687, "row_count": 14, "row_ids_sha256": "df04b45a9baf877ef75ffa9adb0096f0d63b6a31b9c5e22535c9768d39e266dc", "input_ids_vector_sha256": "99b4f17de5e03907a26ed3a314482bb99ae131d49fae2fe002c97b0c17809518", "labels_vector_sha256": "c97fbc5dcb2ac691dec70585aa2cfa487562e0647d0d96be388b8e1c35cb15d7", "planned_active_tokens": 63107, "realized_active_tokens": 63107, "cumulative_start": 45028953, "cumulative_end": 45092060, "loss_sum": 20140.210327148438, "token_normalized_loss": 0.31914384025779136, "grad_norm_before_clip": 0.16249269247055054, "learning_rates_at_step": { "lora": 2.245604106557884e-05, "row_tokens": 2.245604106557884e-05 }, "learning_rates_after_step": { "lora": 2.2312238713019996e-05, "row_tokens": 2.2312238713019996e-05 } }, { "update_id": 688, "row_count": 10, "row_ids_sha256": "6cac316ec6806afd2e2101b11f41b136efe197fc7258d86f8daabdaef9ff1459", "input_ids_vector_sha256": "bd733c6fd92fddeb62678eeeda411419095fee51f3d235df139d8b8271054f95", "labels_vector_sha256": "fbdd756c56bb8475deba0ffcd714b1094ca73c2ceb2449d84f59b1eefdc161b8", "planned_active_tokens": 66066, "realized_active_tokens": 66066, "cumulative_start": 45092060, "cumulative_end": 45158126, "loss_sum": 26646.235137939453, "token_normalized_loss": 0.4033275079154096, "grad_norm_before_clip": 0.16460034251213074, "learning_rates_at_step": { "lora": 2.2312238713019996e-05, "row_tokens": 2.2312238713019996e-05 }, "learning_rates_after_step": { "lora": 2.2168674812197886e-05, "row_tokens": 2.2168674812197886e-05 } }, { "update_id": 689, "row_count": 12, "row_ids_sha256": "41743c8b7dfa35a628b044621ba3a10ea87587c36bfe64c25c25459c4dd3bc6d", "input_ids_vector_sha256": "ade48a10eab6e4aa9778221b5b33e2711b0c895c0a59b681b541a07668823e40", "labels_vector_sha256": "fba02d90271b1b43bcc90610f3eb967d206444fd1cee4580136a82f526301406", "planned_active_tokens": 66108, "realized_active_tokens": 66108, "cumulative_start": 45158126, "cumulative_end": 45224234, "loss_sum": 23616.043334960938, "token_normalized_loss": 0.35723427323411594, "grad_norm_before_clip": 0.17032089829444885, "learning_rates_at_step": { "lora": 2.2168674812197886e-05, "row_tokens": 2.2168674812197886e-05 }, "learning_rates_after_step": { "lora": 2.203298069861684e-05, "row_tokens": 2.203298069861684e-05 } }, { "update_id": 690, "row_count": 11, "row_ids_sha256": "f378f01d4a951da940d8b07c35d6eb83f223ceb5157119235f0b116b36c81607", "input_ids_vector_sha256": "84c81c76eb6dc8d29697ad15c1ccb4024caaa32d3d733b4bf0142a0a4938fd55", "labels_vector_sha256": "d233e5d3c119de4026cdf616df96ba8fe1ce1340376ac0de470c610e99fa5e3e", "planned_active_tokens": 62625, "realized_active_tokens": 62625, "cumulative_start": 45224234, "cumulative_end": 45286859, "loss_sum": 22157.200897216797, "token_normalized_loss": 0.35380759915715443, "grad_norm_before_clip": 0.1661108285188675, "learning_rates_at_step": { "lora": 2.203298069861684e-05, "row_tokens": 2.203298069861684e-05 }, "learning_rates_after_step": { "lora": 2.189059330854306e-05, "row_tokens": 2.189059330854306e-05 } }, { "update_id": 691, "row_count": 14, "row_ids_sha256": "d5dab035622a0d88f78b5b108d707523fc6e13eb0ac635b2f08bc8798571a8ce", "input_ids_vector_sha256": "bff285d3593ec2d167a5b85d2df900d6ecdb90ce2fd2b1dca150db8b58515f83", "labels_vector_sha256": "b9fe1b2559df4d96cf6382e03cb9309d7ed16661fc713a6fdf49988792afd468", "planned_active_tokens": 65863, "realized_active_tokens": 65863, "cumulative_start": 45286859, "cumulative_end": 45352722, "loss_sum": 20738.799362182617, "token_normalized_loss": 0.31487784282803116, "grad_norm_before_clip": 0.15629006922245026, "learning_rates_at_step": { "lora": 2.189059330854306e-05, "row_tokens": 2.189059330854306e-05 }, "learning_rates_after_step": { "lora": 2.1749438940664853e-05, "row_tokens": 2.1749438940664853e-05 } }, { "update_id": 692, "row_count": 18, "row_ids_sha256": "ccbb3c0c13f1318331763101eb5521e986c1176b6df3e0dba9e9475b31c12438", "input_ids_vector_sha256": "b43480c94f616f7471d4ff55d59f2273bbc23217a6ab0e395a8332a4b5518e50", "labels_vector_sha256": "3758c6a4e3c846ac036ce7717bc0c8c9b58c9f5ee336e379a6b6585aa55e57d6", "planned_active_tokens": 65445, "realized_active_tokens": 65445, "cumulative_start": 45352722, "cumulative_end": 45418167, "loss_sum": 20062.098571777344, "token_normalized_loss": 0.30654898879635334, "grad_norm_before_clip": 0.14643511176109314, "learning_rates_at_step": { "lora": 2.1749438940664853e-05, "row_tokens": 2.1749438940664853e-05 }, "learning_rates_after_step": { "lora": 2.160875208944828e-05, "row_tokens": 2.160875208944828e-05 } }, { "update_id": 693, "row_count": 14, "row_ids_sha256": "29a6147a085213b58524037387e2e2d9d7aa7fc8b5382d4d6af86da2e8c463ea", "input_ids_vector_sha256": "6d6b77065cf05c42a84ee93b31ae92598bf5200ffad03f50064fb70eb7fc52cc", "labels_vector_sha256": "89223debdc96ca48573bad65458c4b8943d596308a3a1bbcff5b29887c6b99a6", "planned_active_tokens": 65381, "realized_active_tokens": 65381, "cumulative_start": 45418167, "cumulative_end": 45483548, "loss_sum": 20619.837860107422, "token_normalized_loss": 0.31537966473604595, "grad_norm_before_clip": 0.15344010293483734, "learning_rates_at_step": { "lora": 2.160875208944828e-05, "row_tokens": 2.160875208944828e-05 }, "learning_rates_after_step": { "lora": 2.1464125106681653e-05, "row_tokens": 2.1464125106681653e-05 } }, { "update_id": 694, "row_count": 15, "row_ids_sha256": "bd420ed165d36790f6ec7e91581b0648dab7ef0d727fa1f772e5aacc238e6217", "input_ids_vector_sha256": "0411cbbfa7ea5364aa8c689886443a65a472f887feab8901f7828ffd6548e1a0", "labels_vector_sha256": "0fa57ad3caef4acbdb22e0e3703386e96da1300d403ad83278ac62217117e55f", "planned_active_tokens": 67373, "realized_active_tokens": 67373, "cumulative_start": 45483548, "cumulative_end": 45550921, "loss_sum": 21893.473693847656, "token_normalized_loss": 0.3249591630749359, "grad_norm_before_clip": 0.15275202691555023, "learning_rates_at_step": { "lora": 2.1464125106681653e-05, "row_tokens": 2.1464125106681653e-05 }, "learning_rates_after_step": { "lora": 2.133003714096417e-05, "row_tokens": 2.133003714096417e-05 } }, { "update_id": 695, "row_count": 17, "row_ids_sha256": "d5c54c3e725781165daafdaf343937ace0cb5801104878226cc588b157ee3439", "input_ids_vector_sha256": "eedcf74425d7c6b4adc0e258ed8a9c5e22932670ec60fd150f738263ed9ea14e", "labels_vector_sha256": "d1e4d0ec7b8516364f0afb2fa42ca4d909d759ecde65fca14bb9d9e6ca15be8c", "planned_active_tokens": 62611, "realized_active_tokens": 62611, "cumulative_start": 45550921, "cumulative_end": 45613532, "loss_sum": 16806.70167541504, "token_normalized_loss": 0.2684304942488547, "grad_norm_before_clip": 0.1437930315732956, "learning_rates_at_step": { "lora": 2.133003714096417e-05, "row_tokens": 2.133003714096417e-05 }, "learning_rates_after_step": { "lora": 2.1189513948318518e-05, "row_tokens": 2.1189513948318518e-05 } }, { "update_id": 696, "row_count": 14, "row_ids_sha256": "e6cd4cbf38d8d7e416133b0ec0915e5f7cfe5d38d8b1bafd803185ae20e5c218", "input_ids_vector_sha256": "252199782134e499d83e483cbed6334e743d488a40b5d24dac712bb8159a1a39", "labels_vector_sha256": "7a20ef479393eaf262b08fd5ee01a39f3be3da7161e7ea5905eeb11a4340d178", "planned_active_tokens": 65770, "realized_active_tokens": 65770, "cumulative_start": 45613532, "cumulative_end": 45679302, "loss_sum": 25009.8145904541, "token_normalized_loss": 0.3802617392497203, "grad_norm_before_clip": 0.1630038619041443, "learning_rates_at_step": { "lora": 2.1189513948318518e-05, "row_tokens": 2.1189513948318518e-05 }, "learning_rates_after_step": { "lora": 2.104712731707671e-05, "row_tokens": 2.104712731707671e-05 } }, { "update_id": 697, "row_count": 15, "row_ids_sha256": "55a996b565bce653b626b7f47d4fac1b3d7d02c91426c62cade8f31884d7492f", "input_ids_vector_sha256": "5d0c9f27cb3761654250b086b3b5ece143b060a48425df862dfc7949207898f4", "labels_vector_sha256": "9a93e7936119b36e331a3223d8afbe29ecce910daad4ad314b8bc792b10fc2fa", "planned_active_tokens": 66805, "realized_active_tokens": 66805, "cumulative_start": 45679302, "cumulative_end": 45746107, "loss_sum": 23264.75405883789, "token_normalized_loss": 0.34824869484077375, "grad_norm_before_clip": 0.15516144037246704, "learning_rates_at_step": { "lora": 2.104712731707671e-05, "row_tokens": 2.104712731707671e-05 }, "learning_rates_after_step": { "lora": 2.0902007754452663e-05, "row_tokens": 2.0902007754452663e-05 } }, { "update_id": 698, "row_count": 16, "row_ids_sha256": "ff1b9acf8973634232eb91bced2772abd951ae289ec29b41df4ccd569d60c75b", "input_ids_vector_sha256": "ca8c3107460bdbffee0b2bb35f5be4a2054a885f6853c7e60d2df9c075585842", "labels_vector_sha256": "aa05a341133cc4a70e8bf91352c05aff57d976a64f4445c42b58da14aecbad2e", "planned_active_tokens": 68258, "realized_active_tokens": 68258, "cumulative_start": 45746107, "cumulative_end": 45814365, "loss_sum": 21941.027542114258, "token_normalized_loss": 0.32144257877632304, "grad_norm_before_clip": 0.15624718368053436, "learning_rates_at_step": { "lora": 2.0902007754452663e-05, "row_tokens": 2.0902007754452663e-05 }, "learning_rates_after_step": { "lora": 2.0763160825735122e-05, "row_tokens": 2.0763160825735122e-05 } }, { "update_id": 699, "row_count": 17, "row_ids_sha256": "d76934bafc151b19a631d83f950f70309ad15ec60b5745d8a0f0aea6e432e734", "input_ids_vector_sha256": "658a2b887dea8ac114381c1a349ce7ed18958f3189191be4149c856aca345960", "labels_vector_sha256": "ead7f6de93e99e10bf8829c3f3cbb26b5bc43c4ba5f7e0b7e6012e39d3d6229e", "planned_active_tokens": 65471, "realized_active_tokens": 65471, "cumulative_start": 45814365, "cumulative_end": 45879836, "loss_sum": 21268.923461914062, "token_normalized_loss": 0.3248602199739436, "grad_norm_before_clip": 0.15392109751701355, "learning_rates_at_step": { "lora": 2.0763160825735122e-05, "row_tokens": 2.0763160825735122e-05 }, "learning_rates_after_step": { "lora": 2.062871890853393e-05, "row_tokens": 2.062871890853393e-05 } }, { "update_id": 700, "row_count": 14, "row_ids_sha256": "5010d0ef10e2ec0ad1c855a2ef470af43d7617c8447fd62fc9ad917d0ce79392", "input_ids_vector_sha256": "4ef1d33e76a728e36a14b370dc5a4f182548f79d621da8bbfd79331fc33447b6", "labels_vector_sha256": "fc804daf937b16210a573da3eec11eb202801d08e608ceb73c8972c3381db04e", "planned_active_tokens": 63548, "realized_active_tokens": 63548, "cumulative_start": 45879836, "cumulative_end": 45943384, "loss_sum": 20688.423950195312, "token_normalized_loss": 0.32555586250071306, "grad_norm_before_clip": 0.15603378415107727, "learning_rates_at_step": { "lora": 2.062871890853393e-05, "row_tokens": 2.062871890853393e-05 }, "learning_rates_after_step": { "lora": 2.0491782182966008e-05, "row_tokens": 2.0491782182966008e-05 } }, { "update_id": 701, "row_count": 16, "row_ids_sha256": "140c9040129764fca04afd022f33eb975fdc87584b67a0bf5ec67e9fecf1c543", "input_ids_vector_sha256": "aa15d8f5613064e248a578b2081314ba4e9c7d270567a5f2c948ca18fb0b5692", "labels_vector_sha256": "f85b40c9f68af5931f4c63bbd38cb89a94b1b899fbed8749d9d97b08a89b917d", "planned_active_tokens": 64885, "realized_active_tokens": 64885, "cumulative_start": 45943384, "cumulative_end": 46008269, "loss_sum": 20847.549072265625, "token_normalized_loss": 0.32129997799592547, "grad_norm_before_clip": 0.15429964661598206, "learning_rates_at_step": { "lora": 2.0491782182966008e-05, "row_tokens": 2.0491782182966008e-05 }, "learning_rates_after_step": { "lora": 2.0350281163722103e-05, "row_tokens": 2.0350281163722103e-05 } }, { "update_id": 702, "row_count": 14, "row_ids_sha256": "c8e5b1f61e8e9659276794bf3ff9f4db14c45efd1f68cd4edb673a727a88f699", "input_ids_vector_sha256": "49f50a8814682d8365056d00c9a5f67b91a27772de412784c52975833dbb3ceb", "labels_vector_sha256": "e729a917ae1414fd49a22310e97bba59ac78166f58ac0220745bf5084295a69c", "planned_active_tokens": 67217, "realized_active_tokens": 67217, "cumulative_start": 46008269, "cumulative_end": 46075486, "loss_sum": 21680.30743408203, "token_normalized_loss": 0.322542027077704, "grad_norm_before_clip": 0.15364769101142883, "learning_rates_at_step": { "lora": 2.0350281163722103e-05, "row_tokens": 2.0350281163722103e-05 }, "learning_rates_after_step": { "lora": 2.021183384756371e-05, "row_tokens": 2.021183384756371e-05 } }, { "update_id": 703, "row_count": 16, "row_ids_sha256": "7d85b678fffcfd90cabae024b24efa41c930112e214dcbfc160cda7326e4b73b", "input_ids_vector_sha256": "af7a921cc477223a5ca6e56733d4c9173ebc31483d7f85865ad1fdc956a39296", "labels_vector_sha256": "2b68c56b4648449b63dabcff1da1a497007e51873adb0030157a8083a134401d", "planned_active_tokens": 65935, "realized_active_tokens": 65935, "cumulative_start": 46075486, "cumulative_end": 46141421, "loss_sum": 20350.6951751709, "token_normalized_loss": 0.3086478376457253, "grad_norm_before_clip": 0.15216238796710968, "learning_rates_at_step": { "lora": 2.021183384756371e-05, "row_tokens": 2.021183384756371e-05 }, "learning_rates_after_step": { "lora": 2.0077569744998024e-05, "row_tokens": 2.0077569744998024e-05 } }, { "update_id": 704, "row_count": 13, "row_ids_sha256": "dd99ed2fbcf869245f7e40037aebad1eb1bd7b2ec2c973c0412f0cecf73f0c77", "input_ids_vector_sha256": "9b444cc4bcee72ae55a33963734312d1b8fb35a3a1d2f8c9390077cd50b5b474", "labels_vector_sha256": "7091776584e9b60b8267e53d0a1e1f34937331dcdafd23fbc2e2086e153b56be", "planned_active_tokens": 64104, "realized_active_tokens": 64104, "cumulative_start": 46141421, "cumulative_end": 46205525, "loss_sum": 19948.125122070312, "token_normalized_loss": 0.3111837813875938, "grad_norm_before_clip": 0.15024733543395996, "learning_rates_at_step": { "lora": 2.0077569744998024e-05, "row_tokens": 2.0077569744998024e-05 }, "learning_rates_after_step": { "lora": 1.9938378764633425e-05, "row_tokens": 1.9938378764633425e-05 } }, { "update_id": 705, "row_count": 12, "row_ids_sha256": "2ab487a4c548335fc9d2b1d8c497897e458c4b20a4e3a7a98da1e8ea9390df7c", "input_ids_vector_sha256": "9ecf1e6a0938b808213c44d611302dec53875d421f3373420f0342a70420481f", "labels_vector_sha256": "d8b22a199d6329278e25efe909ea1ba84b8187c87900b6495b1af3e748e9f7b1", "planned_active_tokens": 66626, "realized_active_tokens": 66626, "cumulative_start": 46205525, "cumulative_end": 46272151, "loss_sum": 23768.981811523438, "token_normalized_loss": 0.356752346103975, "grad_norm_before_clip": 0.16304564476013184, "learning_rates_at_step": { "lora": 1.9938378764633425e-05, "row_tokens": 1.9938378764633425e-05 }, "learning_rates_after_step": { "lora": 1.9805574266169107e-05, "row_tokens": 1.9805574266169107e-05 } }, { "update_id": 706, "row_count": 11, "row_ids_sha256": "1314db89d3998c852584df03883ff643fc9f719068a50dcd2b0a8a95dda7a7f5", "input_ids_vector_sha256": "83c0445ceb198d4417e91613a5fc94c4aa57adf8fa0596f12a5229baf55aadc0", "labels_vector_sha256": "86988ee13ec3f06ff8dc8c9afafeb2919ea3fef4c87a626f63110a9aa058b2f6", "planned_active_tokens": 63732, "realized_active_tokens": 63732, "cumulative_start": 46272151, "cumulative_end": 46335883, "loss_sum": 21967.00457763672, "token_normalized_loss": 0.34467778474921107, "grad_norm_before_clip": 0.1699618697166443, "learning_rates_at_step": { "lora": 1.9805574266169107e-05, "row_tokens": 1.9805574266169107e-05 }, "learning_rates_after_step": { "lora": 1.9658547843445675e-05, "row_tokens": 1.9658547843445675e-05 } }, { "update_id": 707, "row_count": 13, "row_ids_sha256": "1de277b98194139c3771f860504426b5fab31b45e2b9c3fbd16b6cee1f8ed0a2", "input_ids_vector_sha256": "a69a089d0b1204d033130cf57abab441388956a3589d7e3eddddf12b27de0b73", "labels_vector_sha256": "2ce0578d7636fdf86c33a402a54fc6d590481be1f8aa2b93dbaaca6c65c69087", "planned_active_tokens": 70745, "realized_active_tokens": 70745, "cumulative_start": 46335883, "cumulative_end": 46406628, "loss_sum": 24790.904998779297, "token_normalized_loss": 0.3504262491876358, "grad_norm_before_clip": 0.15385238826274872, "learning_rates_at_step": { "lora": 1.9658547843445675e-05, "row_tokens": 1.9658547843445675e-05 }, "learning_rates_after_step": { "lora": 1.9533692310230862e-05, "row_tokens": 1.9533692310230862e-05 } }, { "update_id": 708, "row_count": 14, "row_ids_sha256": "ff3a251c95b35d0262167ae9a753ab10dd161b6b60076ba1a639da55dab4b271", "input_ids_vector_sha256": "0461cac3ab6dfe2ea815681a58a3c18f6d0368913c796bee87ce65aa05c93648", "labels_vector_sha256": "a75497677c1fca9f8b55168b4a01f1365682ebfba423dd4b727d2da9084d1c3e", "planned_active_tokens": 60234, "realized_active_tokens": 60234, "cumulative_start": 46406628, "cumulative_end": 46466862, "loss_sum": 18018.690826416016, "token_normalized_loss": 0.29914484886303444, "grad_norm_before_clip": 0.1519758552312851, "learning_rates_at_step": { "lora": 1.9533692310230862e-05, "row_tokens": 1.9533692310230862e-05 }, "learning_rates_after_step": { "lora": 1.9401697372991988e-05, "row_tokens": 1.9401697372991988e-05 } }, { "update_id": 709, "row_count": 16, "row_ids_sha256": "1444352bd044393058ac289350586ae5c51c2c4c155eb96a9354fb882306356e", "input_ids_vector_sha256": "ed0ab7c4273b52957101b6589603866b096e006fe2e081877d2189761dc86837", "labels_vector_sha256": "139d74b5fbfa883fc0b23044c32f9dcaa4be6db8f38be05bcf8990c05094ef97", "planned_active_tokens": 63837, "realized_active_tokens": 63837, "cumulative_start": 46466862, "cumulative_end": 46530699, "loss_sum": 17365.962677001953, "token_normalized_loss": 0.27203600853739923, "grad_norm_before_clip": 0.1440221667289734, "learning_rates_at_step": { "lora": 1.9401697372991988e-05, "row_tokens": 1.9401697372991988e-05 }, "learning_rates_after_step": { "lora": 1.925642975824572e-05, "row_tokens": 1.925642975824572e-05 } }, { "update_id": 710, "row_count": 12, "row_ids_sha256": "94d748d10b3e697b168fbd49184539e72e0618088792211c110177820cfed7ac", "input_ids_vector_sha256": "99041f1d895f728ac6600feb928e938dde47a01784f8f586a80b8e602ccbc9fb", "labels_vector_sha256": "3d3f6b5464bf7bde06c4d2165fb4a4a22ceb76fda19d13bc558ccf7d72ee9719", "planned_active_tokens": 70447, "realized_active_tokens": 70447, "cumulative_start": 46530699, "cumulative_end": 46601146, "loss_sum": 23115.771484375, "token_normalized_loss": 0.3281299627290729, "grad_norm_before_clip": 0.14516660571098328, "learning_rates_at_step": { "lora": 1.925642975824572e-05, "row_tokens": 1.925642975824572e-05 }, "learning_rates_after_step": { "lora": 1.9128834353490222e-05, "row_tokens": 1.9128834353490222e-05 } }, { "update_id": 711, "row_count": 10, "row_ids_sha256": "6539c99922475ff72ab28a01723e692a499ff177cdfab8847ec33ababc078a00", "input_ids_vector_sha256": "ca416be97987e73a3e6d5cb571b8ca3b0d33b94fed58aaab6bf4beb538dd539c", "labels_vector_sha256": "0e24970b7bb3fa5c3a53b47019d62f0bdf260ced4576a2b5d6666e0027756fd2", "planned_active_tokens": 62044, "realized_active_tokens": 62044, "cumulative_start": 46601146, "cumulative_end": 46663190, "loss_sum": 19634.431579589844, "token_normalized_loss": 0.3164597959446497, "grad_norm_before_clip": 0.15410427749156952, "learning_rates_at_step": { "lora": 1.9128834353490222e-05, "row_tokens": 1.9128834353490222e-05 }, "learning_rates_after_step": { "lora": 1.899551360858132e-05, "row_tokens": 1.899551360858132e-05 } }, { "update_id": 712, "row_count": 14, "row_ids_sha256": "9cecf97b511edcaad88079404c60f811712c7a71231c4e0b55d0a7d8ca4354e3", "input_ids_vector_sha256": "41ef28ed9911266dd48c882538c1c3a9c775cfad80b6c74d711afe91cfce0708", "labels_vector_sha256": "eec384ecfc3526f1a6d85779a660c09be8bed1de6961e551bc513da336f0baf4", "planned_active_tokens": 64997, "realized_active_tokens": 64997, "cumulative_start": 46663190, "cumulative_end": 46728187, "loss_sum": 21318.246795654297, "token_normalized_loss": 0.32798816554078336, "grad_norm_before_clip": 0.14830587804317474, "learning_rates_at_step": { "lora": 1.899551360858132e-05, "row_tokens": 1.899551360858132e-05 }, "learning_rates_after_step": { "lora": 1.885447909006764e-05, "row_tokens": 1.885447909006764e-05 } }, { "update_id": 713, "row_count": 13, "row_ids_sha256": "c793f2a362b0d270ae7955df0112c27df403df47466170723e2923443e8e8a30", "input_ids_vector_sha256": "1642a837fcdd57e0f87ce7c0cad1b042c39f39d5050e08f9d7019d54830f2513", "labels_vector_sha256": "a244acee0e8f3ca974b6078d7089eb6b22675df52415ef80d30e1f8a6642e787", "planned_active_tokens": 68948, "realized_active_tokens": 68948, "cumulative_start": 46728187, "cumulative_end": 46797135, "loss_sum": 21852.572692871094, "token_normalized_loss": 0.31694280751974085, "grad_norm_before_clip": 0.14518842101097107, "learning_rates_at_step": { "lora": 1.885447909006764e-05, "row_tokens": 1.885447909006764e-05 }, "learning_rates_after_step": { "lora": 1.8723578752026914e-05, "row_tokens": 1.8723578752026914e-05 } }, { "update_id": 714, "row_count": 13, "row_ids_sha256": "43eabad491a3a391cf57bbf3f02d7e285a029c1c76acdd0066915d1a4da51ac3", "input_ids_vector_sha256": "6ebf1cde930d13f809c8c04be916871417a4e301804129b9b0e0260a0879faba", "labels_vector_sha256": "6526bebbbe543476279623679cbe4a5f17f5fb47f5f8418b3b22318c55ca16c6", "planned_active_tokens": 64171, "realized_active_tokens": 64171, "cumulative_start": 46797135, "cumulative_end": 46861306, "loss_sum": 21051.7041015625, "token_normalized_loss": 0.32805635102402175, "grad_norm_before_clip": 0.15581201016902924, "learning_rates_at_step": { "lora": 1.8723578752026914e-05, "row_tokens": 1.8723578752026914e-05 }, "learning_rates_after_step": { "lora": 1.8593498948323863e-05, "row_tokens": 1.8593498948323863e-05 } }, { "update_id": 715, "row_count": 14, "row_ids_sha256": "b46ed462b5c8794c77397d10b5233a583236ec6b1a63366c348bf6b88846af0b", "input_ids_vector_sha256": "e206684c36f22c7e5f7f6c0c5b3039f5efface7b70008cf195fceb2576b722c3", "labels_vector_sha256": "3783ad7fd7660311d5b3abe321b96f726170c5853e63725f2eb627cf91439d81", "planned_active_tokens": 63940, "realized_active_tokens": 63940, "cumulative_start": 46861306, "cumulative_end": 46925246, "loss_sum": 18531.988082885742, "token_normalized_loss": 0.28983403320121587, "grad_norm_before_clip": 0.14569997787475586, "learning_rates_at_step": { "lora": 1.8593498948323863e-05, "row_tokens": 1.8593498948323863e-05 }, "learning_rates_after_step": { "lora": 1.8463027714693448e-05, "row_tokens": 1.8463027714693448e-05 } }, { "update_id": 716, "row_count": 17, "row_ids_sha256": "e0d39fb1ccda0b33c2bc86bb9fd45e7aacdf2734151c9c0c3d98deedc20eedb0", "input_ids_vector_sha256": "8af6674537c4b04891c690afb38b557e4159ab359a57c9b94e69f99b66019d49", "labels_vector_sha256": "78b5569c749c52359cb10ee9d7abf7c2f1a95858716773030bb4d14db55ab44e", "planned_active_tokens": 64306, "realized_active_tokens": 64306, "cumulative_start": 46925246, "cumulative_end": 46989552, "loss_sum": 18577.37481689453, "token_normalized_loss": 0.28889022512509765, "grad_norm_before_clip": 0.14649884402751923, "learning_rates_at_step": { "lora": 1.8463027714693448e-05, "row_tokens": 1.8463027714693448e-05 }, "learning_rates_after_step": { "lora": 1.8330477348236946e-05, "row_tokens": 1.8330477348236946e-05 } }, { "update_id": 717, "row_count": 13, "row_ids_sha256": "ef9573820c381457acb5585efd9afe19f3d1e227d927ba5be84465178326dcd5", "input_ids_vector_sha256": "140881ba8e4280abd422b23daddcedead3c726dd34a491d9c4a567a4a4f17a19", "labels_vector_sha256": "4ee2c8ccda403e369517c0aa9f86fa717a2fa628057a015a17062286dd2ad9b0", "planned_active_tokens": 65511, "realized_active_tokens": 65511, "cumulative_start": 46989552, "cumulative_end": 47055063, "loss_sum": 24449.295989990234, "token_normalized_loss": 0.3732090181800039, "grad_norm_before_clip": 0.1611449122428894, "learning_rates_at_step": { "lora": 1.8330477348236946e-05, "row_tokens": 1.8330477348236946e-05 }, "learning_rates_after_step": { "lora": 1.8194677105322493e-05, "row_tokens": 1.8194677105322493e-05 } }, { "update_id": 718, "row_count": 16, "row_ids_sha256": "d3c0ac038b921d0557a63ec02adb3a4e43b4aea524dd252fa88921d371595b39", "input_ids_vector_sha256": "138fa2f409d06ae2d1c0900edfffefb0b9be0753d1dbe49f5df81fcf92a89a87", "labels_vector_sha256": "5eabe7d3b9a259b41de5c5fa8341238ed235c1466038943c36454d22793a1811", "planned_active_tokens": 67308, "realized_active_tokens": 67308, "cumulative_start": 47055063, "cumulative_end": 47122371, "loss_sum": 20824.848037719727, "token_normalized_loss": 0.30939632789147986, "grad_norm_before_clip": 0.14544445276260376, "learning_rates_at_step": { "lora": 1.8194677105322493e-05, "row_tokens": 1.8194677105322493e-05 }, "learning_rates_after_step": { "lora": 1.8061911481563232e-05, "row_tokens": 1.8061911481563232e-05 } }, { "update_id": 719, "row_count": 14, "row_ids_sha256": "0f8244db511f1e223cad6ba211550c75482066fdf63c51c5eafdf4e58a27d6de", "input_ids_vector_sha256": "6f0a89d71d1ce85303202ec70cf01e6bf66b9c32db8b3f31a1dcbecd9d7fc5a5", "labels_vector_sha256": "c220c3492be34f7a646b37d4a71b98283dbb84afe9d1724e78d703006fa0db54", "planned_active_tokens": 65993, "realized_active_tokens": 65993, "cumulative_start": 47122371, "cumulative_end": 47188364, "loss_sum": 20404.119049072266, "token_normalized_loss": 0.3091861113916971, "grad_norm_before_clip": 0.14590425789356232, "learning_rates_at_step": { "lora": 1.8061911481563232e-05, "row_tokens": 1.8061911481563232e-05 }, "learning_rates_after_step": { "lora": 1.792603575002116e-05, "row_tokens": 1.792603575002116e-05 } }, { "update_id": 720, "row_count": 13, "row_ids_sha256": "57ee3551b0468220b7adc5df2c645b48a9834c2583f24f1f079139943bb52432", "input_ids_vector_sha256": "8a4fcda8e611ca158e396f662076d1555c859fcd523ade8d807eb25b32e7faca", "labels_vector_sha256": "8c179e6ab147b4e56fd8d2393497cc6688a757ff1b17d2c84112f801ed69dfc0", "planned_active_tokens": 67735, "realized_active_tokens": 67735, "cumulative_start": 47188364, "cumulative_end": 47256099, "loss_sum": 21221.801559448242, "token_normalized_loss": 0.31330629009298355, "grad_norm_before_clip": 0.15863408148288727, "learning_rates_at_step": { "lora": 1.792603575002116e-05, "row_tokens": 1.792603575002116e-05 }, "learning_rates_after_step": { "lora": 1.779975686990909e-05, "row_tokens": 1.779975686990909e-05 } }, { "update_id": 721, "row_count": 15, "row_ids_sha256": "0f9f281a64cbcf965cdc6b8eb82aa0d1375cd29e5227985a151dd33345b1a562", "input_ids_vector_sha256": "0e1ec80edb260c501b88c920d9e3f1f12c1610c3db6dc839f62097a42002c2cc", "labels_vector_sha256": "2fc7de89e1a21d51da5e761f92ac91a83cb03077d488873ea10db2ea87ff5e3e", "planned_active_tokens": 63131, "realized_active_tokens": 63131, "cumulative_start": 47256099, "cumulative_end": 47319230, "loss_sum": 19154.19613647461, "token_normalized_loss": 0.30340397168545735, "grad_norm_before_clip": 0.14893217384815216, "learning_rates_at_step": { "lora": 1.779975686990909e-05, "row_tokens": 1.779975686990909e-05 }, "learning_rates_after_step": { "lora": 1.7673347903124493e-05, "row_tokens": 1.7673347903124493e-05 } }, { "update_id": 722, "row_count": 16, "row_ids_sha256": "0eb94a3b0a41dbc757ad2a5e3c1340448318eca0eb82010a4f9e7ce4a55c3137", "input_ids_vector_sha256": "787e421b53d54f6b64c4a2ff3ef495488fc8a218ccaf4483712144fca59fe9c7", "labels_vector_sha256": "16d8decba5563a43e15c9046d5a9da57dc4ce73368ee69b0875619b9e88c05c7", "planned_active_tokens": 63372, "realized_active_tokens": 63372, "cumulative_start": 47319230, "cumulative_end": 47382602, "loss_sum": 19828.3565826416, "token_normalized_loss": 0.31288828792907913, "grad_norm_before_clip": 0.16211891174316406, "learning_rates_at_step": { "lora": 1.7673347903124493e-05, "row_tokens": 1.7673347903124493e-05 }, "learning_rates_after_step": { "lora": 1.751684306503133e-05, "row_tokens": 1.751684306503133e-05 } }, { "update_id": 723, "row_count": 17, "row_ids_sha256": "472c8cc28ab2996873ab868bdaf890ea303222a44a6a3127977148d8b1c34278", "input_ids_vector_sha256": "b8659941ee449c2b122e764a5fc1d1d64693f341dac2f07b9d207533b8a7edf2", "labels_vector_sha256": "12955f0cd9f6c2106b775a4482a03e8aeed7584366bcafc4ab91670804602caf", "planned_active_tokens": 78707, "realized_active_tokens": 78707, "cumulative_start": 47382602, "cumulative_end": 47461309, "loss_sum": 23339.822204589844, "token_normalized_loss": 0.2965406152513734, "grad_norm_before_clip": 0.1349639594554901, "learning_rates_at_step": { "lora": 1.751684306503133e-05, "row_tokens": 1.751684306503133e-05 }, "learning_rates_after_step": { "lora": 1.7403576648824366e-05, "row_tokens": 1.7403576648824366e-05 } }, { "update_id": 724, "row_count": 13, "row_ids_sha256": "9dd9b40407e70d0db4fc0dce7e74ad2b6ee623b9ac64130a2d094d46a2842fd9", "input_ids_vector_sha256": "44bb313c5238cfcd84dfd9663e4cb4507cbc73d5adf7c29feb61614fb0a8ba08", "labels_vector_sha256": "551c93bd65f490f5f9f89d2671afe092deded102e72fc24e0cc02edfffa2eedb", "planned_active_tokens": 57135, "realized_active_tokens": 57135, "cumulative_start": 47461309, "cumulative_end": 47518444, "loss_sum": 19022.220275878906, "token_normalized_loss": 0.3329346333399651, "grad_norm_before_clip": 0.1677071452140808, "learning_rates_at_step": { "lora": 1.7403576648824366e-05, "row_tokens": 1.7403576648824366e-05 }, "learning_rates_after_step": { "lora": 1.7275274613358278e-05, "row_tokens": 1.7275274613358278e-05 } }, { "update_id": 725, "row_count": 15, "row_ids_sha256": "b40294e3605969ad58172b5ce1711e21e87d7f6da4094ab86cc90b763e1cd8e9", "input_ids_vector_sha256": "3f738aeb3d06729e16b95a520999fdf7534ebeb7e2ac97e9b65eef47bccf3047", "labels_vector_sha256": "6739b99794204b991a962d6369e38693b5c38bcdd84fc363e2412fcd33f92295", "planned_active_tokens": 64897, "realized_active_tokens": 64897, "cumulative_start": 47518444, "cumulative_end": 47583341, "loss_sum": 20286.70233154297, "token_normalized_loss": 0.3125984611236724, "grad_norm_before_clip": 0.14647795259952545, "learning_rates_at_step": { "lora": 1.7275274613358278e-05, "row_tokens": 1.7275274613358278e-05 }, "learning_rates_after_step": { "lora": 1.714849203119714e-05, "row_tokens": 1.714849203119714e-05 } }, { "update_id": 726, "row_count": 11, "row_ids_sha256": "3f535fd4ff849e8ce949ff8b8b6fe7211344db1f2bd9ad1cf2376a2051572e75", "input_ids_vector_sha256": "44e8aea0e0de22f1a0344a5084863cb897a078d11cb9acdd826b1da074879877", "labels_vector_sha256": "9437fd299372b560305c23b6823fe9bbf91b78ed791e1001526758b447e33814", "planned_active_tokens": 64316, "realized_active_tokens": 64316, "cumulative_start": 47583341, "cumulative_end": 47647657, "loss_sum": 26479.883026123047, "token_normalized_loss": 0.41171532785190385, "grad_norm_before_clip": 0.18072468042373657, "learning_rates_at_step": { "lora": 1.714849203119714e-05, "row_tokens": 1.714849203119714e-05 }, "learning_rates_after_step": { "lora": 1.701490341911947e-05, "row_tokens": 1.701490341911947e-05 } }, { "update_id": 727, "row_count": 11, "row_ids_sha256": "745beb04213efdfc71230b58355612109a7807d0bcc9478478d0f754e6de4bf7", "input_ids_vector_sha256": "5208bb8e79318f88f11e94c391b3dec9841aa246f09f19942ee98e79bf09203b", "labels_vector_sha256": "3ee113102deaf8b57de83ca4bebdcf4bd2895035301964857759239258a57481", "planned_active_tokens": 67973, "realized_active_tokens": 67973, "cumulative_start": 47647657, "cumulative_end": 47715630, "loss_sum": 22506.008544921875, "token_normalized_loss": 0.3311021809383413, "grad_norm_before_clip": 0.15517757833003998, "learning_rates_at_step": { "lora": 1.701490341911947e-05, "row_tokens": 1.701490341911947e-05 }, "learning_rates_after_step": { "lora": 1.6887544452324756e-05, "row_tokens": 1.6887544452324756e-05 } }, { "update_id": 728, "row_count": 16, "row_ids_sha256": "5909eb4d3971ab99b5ab7e76f90522b76a5b9dcc35ca458ce97f03ff55434061", "input_ids_vector_sha256": "69721b00c5c6762ae3da8d8cdd525e20d4322e9736bf9ec4b862f0a5192fcd2b", "labels_vector_sha256": "191b86db92724ee27207d8f8e7ade629b8bd759f61b1ac7f7150d0cd8b63aeda", "planned_active_tokens": 65001, "realized_active_tokens": 65001, "cumulative_start": 47715630, "cumulative_end": 47780631, "loss_sum": 20898.32781982422, "token_normalized_loss": 0.32150778941592006, "grad_norm_before_clip": 0.1560608446598053, "learning_rates_at_step": { "lora": 1.6887544452324756e-05, "row_tokens": 1.6887544452324756e-05 }, "learning_rates_after_step": { "lora": 1.6753296071008934e-05, "row_tokens": 1.6753296071008934e-05 } }, { "update_id": 729, "row_count": 17, "row_ids_sha256": "76702153379f847ea8b1a42b83ef8e27b8a5a98e43a4cb21934ae4fdefa52995", "input_ids_vector_sha256": "dfbc45594c8b0951da99b39591bece991d5c9ce97b88397f1041b2b9915f8912", "labels_vector_sha256": "4a37fedaebb75ca75c1b136fa0b0a4ab0065973d86006464aefc631f139dfed3", "planned_active_tokens": 68729, "realized_active_tokens": 68729, "cumulative_start": 47780631, "cumulative_end": 47849360, "loss_sum": 19888.476928710938, "token_normalized_loss": 0.28937532815421346, "grad_norm_before_clip": 0.145072340965271, "learning_rates_at_step": { "lora": 1.6753296071008934e-05, "row_tokens": 1.6753296071008934e-05 }, "learning_rates_after_step": { "lora": 1.6627378845405756e-05, "row_tokens": 1.6627378845405756e-05 } }, { "update_id": 730, "row_count": 11, "row_ids_sha256": "1ba158272120acb5c41500693cf12e8b1c203c71359d0712d77a112a5a2f4d9a", "input_ids_vector_sha256": "91eb9ca33bb9e9f28702e15ea344d17c069a76b76909c0391c531d0427b306c1", "labels_vector_sha256": "ff96516a4769476fd4ea6b144fa8abf30cef0e492576b593ae5bd4928ba960ab", "planned_active_tokens": 64664, "realized_active_tokens": 64664, "cumulative_start": 47849360, "cumulative_end": 47914024, "loss_sum": 23890.93603515625, "token_normalized_loss": 0.3694627000364384, "grad_norm_before_clip": 0.2938993275165558, "learning_rates_at_step": { "lora": 1.6627378845405756e-05, "row_tokens": 1.6627378845405756e-05 }, "learning_rates_after_step": { "lora": 1.6499101327118034e-05, "row_tokens": 1.6499101327118034e-05 } }, { "update_id": 731, "row_count": 13, "row_ids_sha256": "1e4bd7b5b058820c178f5a58ddaf6b810f0098058c590e6ba5aee59d0b38e0d9", "input_ids_vector_sha256": "2d470aabcd4160e757e7d891b1d6626cf66a4ac22e34a6c89242cb61ef71777e", "labels_vector_sha256": "0ce7baecf8eca87dc98ba63dd50f82f6d6756d7ae95c5fd52513b3a3e6ba638e", "planned_active_tokens": 66078, "realized_active_tokens": 66078, "cumulative_start": 47914024, "cumulative_end": 47980102, "loss_sum": 21560.593292236328, "token_normalized_loss": 0.32629004044063575, "grad_norm_before_clip": 0.1529369205236435, "learning_rates_at_step": { "lora": 1.6499101327118034e-05, "row_tokens": 1.6499101327118034e-05 }, "learning_rates_after_step": { "lora": 1.637934858867784e-05, "row_tokens": 1.637934858867784e-05 } }, { "update_id": 732, "row_count": 13, "row_ids_sha256": "ccd7765c9949039925039f7150d37d329412e0ac323fd9f699fc5b81c0464705", "input_ids_vector_sha256": "41b9b680248e8971eebb260f2bca79d16fcab3e5b00e2c5a9f2ce939db951f80", "labels_vector_sha256": "6685444d103add13a9d1081415c1445813bcdcb77a11191748900225c4851ee0", "planned_active_tokens": 61873, "realized_active_tokens": 61873, "cumulative_start": 47980102, "cumulative_end": 48041975, "loss_sum": 20226.604248046875, "token_normalized_loss": 0.3269051807419533, "grad_norm_before_clip": 0.17526742815971375, "learning_rates_at_step": { "lora": 1.637934858867784e-05, "row_tokens": 1.637934858867784e-05 }, "learning_rates_after_step": { "lora": 1.6251546236260218e-05, "row_tokens": 1.6251546236260218e-05 } }, { "update_id": 733, "row_count": 15, "row_ids_sha256": "5820cbf263f58a623ae73a96e3a558e84f0622a02ce940970411673e8608b62d", "input_ids_vector_sha256": "c43267f82ce1d77f979fb62a9ca119ee9d0603d4755525f390016591d6b3eef6", "labels_vector_sha256": "a725fef1af92250ad78a3e9705eecd21437c31953f432b52cce4dc5c3e10e078", "planned_active_tokens": 66233, "realized_active_tokens": 66233, "cumulative_start": 48041975, "cumulative_end": 48108208, "loss_sum": 21773.16845703125, "token_normalized_loss": 0.32873595423778557, "grad_norm_before_clip": 0.1728605031967163, "learning_rates_at_step": { "lora": 1.6251546236260218e-05, "row_tokens": 1.6251546236260218e-05 }, "learning_rates_after_step": { "lora": 1.6128052049127095e-05, "row_tokens": 1.6128052049127095e-05 } }, { "update_id": 734, "row_count": 12, "row_ids_sha256": "262687543220f9697f28383e7923fb3e1f93cb153748b64d2d48cb1b497e3746", "input_ids_vector_sha256": "5a434ac49066629ed23027ec26e12bbb777842b2762d14e4c9ecda26be151a54", "labels_vector_sha256": "bce8d61c4465f579c3f18d090e96cfe9eddf4fea6bf223f4db85639df7476172", "planned_active_tokens": 64200, "realized_active_tokens": 64200, "cumulative_start": 48108208, "cumulative_end": 48172408, "loss_sum": 21833.24594116211, "token_normalized_loss": 0.3400817124791606, "grad_norm_before_clip": 0.160012885928154, "learning_rates_at_step": { "lora": 1.6128052049127095e-05, "row_tokens": 1.6128052049127095e-05 }, "learning_rates_after_step": { "lora": 1.6007580924424272e-05, "row_tokens": 1.6007580924424272e-05 } }, { "update_id": 735, "row_count": 14, "row_ids_sha256": "8f8eca43539a06896a6170e45b129ed562026c00b7cd09238db8f7809e7ac05e", "input_ids_vector_sha256": "bca3450285a3e73cb26e4af4de3b5b4d1ce55050895d4c558e2278203b7a064c", "labels_vector_sha256": "d037e4e045cb7413fef417b4c4fe5a8b37c6a72f8b26b47bdcaa06bf44caccf8", "planned_active_tokens": 62820, "realized_active_tokens": 62820, "cumulative_start": 48172408, "cumulative_end": 48235228, "loss_sum": 19871.59405517578, "token_normalized_loss": 0.3163259161919099, "grad_norm_before_clip": 0.155572310090065, "learning_rates_at_step": { "lora": 1.6007580924424272e-05, "row_tokens": 1.6007580924424272e-05 }, "learning_rates_after_step": { "lora": 1.5869439933263786e-05, "row_tokens": 1.5869439933263786e-05 } }, { "update_id": 736, "row_count": 16, "row_ids_sha256": "d7f3b457f1247b35ce1ff3bc7fd97d185fefffe3eb890bd73b7b1bee28d19a84", "input_ids_vector_sha256": "19a9a33bc23ff7c5603dd322510dfffac21587b8396f996a214e34ed3cc9a8bb", "labels_vector_sha256": "500295a2bbc94b1f3ef12a80b00df9dac389c9b88b8115bb6c92675f4562abd0", "planned_active_tokens": 72270, "realized_active_tokens": 72270, "cumulative_start": 48235228, "cumulative_end": 48307498, "loss_sum": 23367.648193359375, "token_normalized_loss": 0.3233381512848952, "grad_norm_before_clip": 0.14482280611991882, "learning_rates_at_step": { "lora": 1.5869439933263786e-05, "row_tokens": 1.5869439933263786e-05 }, "learning_rates_after_step": { "lora": 1.5742647146029438e-05, "row_tokens": 1.5742647146029438e-05 } }, { "update_id": 737, "row_count": 9, "row_ids_sha256": "bd77b1907f3a261d6e18592b7a1cca4dabc5f7abd3d2d6d53e21f643bbc3173e", "input_ids_vector_sha256": "aae551f8b5859aa4042a2743d83b732498eb5beed464cb355bc937278bd51529", "labels_vector_sha256": "8648c8e9789c0457a7a6c66ecdc725e2b331be80aee8c4f6896689f2d51749c2", "planned_active_tokens": 66558, "realized_active_tokens": 66558, "cumulative_start": 48307498, "cumulative_end": 48374056, "loss_sum": 25959.843231201172, "token_normalized_loss": 0.3900334029147687, "grad_norm_before_clip": 0.16636419296264648, "learning_rates_at_step": { "lora": 1.5742647146029438e-05, "row_tokens": 1.5742647146029438e-05 }, "learning_rates_after_step": { "lora": 1.5631904923009888e-05, "row_tokens": 1.5631904923009888e-05 } }, { "update_id": 738, "row_count": 10, "row_ids_sha256": "2d93d2ef098c1e61f9a23bb88eb79eea4f09f3d01c157a832dd8a9d924ba3ece", "input_ids_vector_sha256": "09885bffb9829123b914d2b6fa83856955ccdf975a4e0184313c8e1aece38540", "labels_vector_sha256": "3d36bb4302330145659d66f9f34a4b35398448a06e70b094e489740bc3e92a45", "planned_active_tokens": 58311, "realized_active_tokens": 58311, "cumulative_start": 48374056, "cumulative_end": 48432367, "loss_sum": 23477.085723876953, "token_normalized_loss": 0.4026184720529052, "grad_norm_before_clip": 0.17204487323760986, "learning_rates_at_step": { "lora": 1.5631904923009888e-05, "row_tokens": 1.5631904923009888e-05 }, "learning_rates_after_step": { "lora": 1.5497883821430624e-05, "row_tokens": 1.5497883821430624e-05 } }, { "update_id": 739, "row_count": 12, "row_ids_sha256": "cc9eea20000b2f0dc42f07739f0faeec169de34609dc9f2d0ef0cc0b1161871e", "input_ids_vector_sha256": "0cca2efcac07226b8557afae801224cb825122a9ac2705ccfa110d393d9a0e54", "labels_vector_sha256": "08f8d1f4cc9a1e650e635e0505abcc47ef1f4f0b7f4b92d6ddadbf2221545861", "planned_active_tokens": 70794, "realized_active_tokens": 70794, "cumulative_start": 48432367, "cumulative_end": 48503161, "loss_sum": 26823.634216308594, "token_normalized_loss": 0.37889699997610804, "grad_norm_before_clip": 0.22115574777126312, "learning_rates_at_step": { "lora": 1.5497883821430624e-05, "row_tokens": 1.5497883821430624e-05 }, "learning_rates_after_step": { "lora": 1.5371875011584215e-05, "row_tokens": 1.5371875011584215e-05 } }, { "update_id": 740, "row_count": 11, "row_ids_sha256": "b0874b3ba03c887d9341ee7cc581d2cae6b8179433230527de095cc9f80e1245", "input_ids_vector_sha256": "11eeaf0ae461caea5a2d61a787e2b2051ddab4e7a3575d28bf080289862ecfb2", "labels_vector_sha256": "009ffd84639b80a335e02f8ba6c1ff47388cca3dca0258e0c32b6170999372a3", "planned_active_tokens": 66790, "realized_active_tokens": 66790, "cumulative_start": 48503161, "cumulative_end": 48569951, "loss_sum": 24812.216995239258, "token_normalized_loss": 0.3714959873519877, "grad_norm_before_clip": 0.15931998193264008, "learning_rates_at_step": { "lora": 1.5371875011584215e-05, "row_tokens": 1.5371875011584215e-05 }, "learning_rates_after_step": { "lora": 1.5256818007121326e-05, "row_tokens": 1.5256818007121326e-05 } }, { "update_id": 741, "row_count": 14, "row_ids_sha256": "9fec0e914e118b4f6940025a34259af567f1c6c4dc5c5490c73654a5803d9ba5", "input_ids_vector_sha256": "21c522151abbd43cbe22d0d1940c80282762e612b42213e0a4cdd631f1cae728", "labels_vector_sha256": "894de7c05f297cb6b96149283322ff83b7dc9983b7ecc575821cdf0d52d8dbb7", "planned_active_tokens": 61181, "realized_active_tokens": 61181, "cumulative_start": 48569951, "cumulative_end": 48631132, "loss_sum": 17319.647857666016, "token_normalized_loss": 0.2830886689930863, "grad_norm_before_clip": 0.14257831871509552, "learning_rates_at_step": { "lora": 1.5256818007121326e-05, "row_tokens": 1.5256818007121326e-05 }, "learning_rates_after_step": { "lora": 1.51299802485457e-05, "row_tokens": 1.51299802485457e-05 } }, { "update_id": 742, "row_count": 14, "row_ids_sha256": "05d89fac4855965df72eb7e08c086f59b953a41a2a7edf94f1ebdebe4378cf6c", "input_ids_vector_sha256": "01d46fd9c89fbe335858961809d2159a591ee373dc859cf99f8bec6c98ff8571", "labels_vector_sha256": "2f14f95a7f34db0d9b8e2233312b6d925ccf9f67a8dfdb70f4884d1f57d75ff0", "planned_active_tokens": 67665, "realized_active_tokens": 67665, "cumulative_start": 48631132, "cumulative_end": 48698797, "loss_sum": 24120.435485839844, "token_normalized_loss": 0.35646841773206006, "grad_norm_before_clip": 0.16169756650924683, "learning_rates_at_step": { "lora": 1.51299802485457e-05, "row_tokens": 1.51299802485457e-05 }, "learning_rates_after_step": { "lora": 1.5008264503076808e-05, "row_tokens": 1.5008264503076808e-05 } }, { "update_id": 743, "row_count": 11, "row_ids_sha256": "50390f2d7c2cdd7138abb4526722b2264bb2bc92dbb8d7ca34035fb66d3aedf9", "input_ids_vector_sha256": "328f0ba280a929018bc3754d769649d4253da6951b5fe727050585ae8e467fc4", "labels_vector_sha256": "df79b49f9fd014532f35c1d5f3cfe8d94afda7449861dbe4fd72e1e073d7a871", "planned_active_tokens": 65152, "realized_active_tokens": 65152, "cumulative_start": 48698797, "cumulative_end": 48763949, "loss_sum": 26494.378967285156, "token_normalized_loss": 0.4066548834615232, "grad_norm_before_clip": 0.1603900045156479, "learning_rates_at_step": { "lora": 1.5008264503076808e-05, "row_tokens": 1.5008264503076808e-05 }, "learning_rates_after_step": { "lora": 1.4894412276951663e-05, "row_tokens": 1.4894412276951663e-05 } }, { "update_id": 744, "row_count": 13, "row_ids_sha256": "8decb66f94d761c35dcd79fda18d7a3477a6e40d36686d60a974a2f820b41643", "input_ids_vector_sha256": "8687d6e80cd0c57f6837e4b8aeeb3229ef6acd01a7c3a744481bb32a5ed89a0d", "labels_vector_sha256": "c57807602ed9afd52169601b68de45ae9e19223cb8114f25fc9f98e4cce5b9dc", "planned_active_tokens": 61140, "realized_active_tokens": 61140, "cumulative_start": 48763949, "cumulative_end": 48825089, "loss_sum": 21333.057220458984, "token_normalized_loss": 0.3489214461965814, "grad_norm_before_clip": 0.15731921792030334, "learning_rates_at_step": { "lora": 1.4894412276951663e-05, "row_tokens": 1.4894412276951663e-05 }, "learning_rates_after_step": { "lora": 1.4768748899992035e-05, "row_tokens": 1.4768748899992035e-05 } }, { "update_id": 745, "row_count": 12, "row_ids_sha256": "d12c48e1e4aa21a86edf148b188ca9863a97f9eb9150a5be0d6bdde14f257982", "input_ids_vector_sha256": "3a243f5c10af74ff0e6fbcace585a284bdee9ef1124dfc53422849848c3d32fe", "labels_vector_sha256": "2dc4ae0b1aaf6c0d66881248a4d0739eb87316766446a9877aea245bb211274e", "planned_active_tokens": 67707, "realized_active_tokens": 67707, "cumulative_start": 48825089, "cumulative_end": 48892796, "loss_sum": 28834.801330566406, "token_normalized_loss": 0.4258762215216507, "grad_norm_before_clip": 0.17164269089698792, "learning_rates_at_step": { "lora": 1.4768748899992035e-05, "row_tokens": 1.4768748899992035e-05 }, "learning_rates_after_step": { "lora": 1.46381372435982e-05, "row_tokens": 1.46381372435982e-05 } }, { "update_id": 746, "row_count": 14, "row_ids_sha256": "160722a3f0664b904419a96f377eef0686cf285a053524feb5cb4270ede1480f", "input_ids_vector_sha256": "441218eb2e405f4657591fc761f7ca19900139557c4ede360c17c147c3caca47", "labels_vector_sha256": "816f98f1be81923e7d9d4d178a28037cc116a70d5b985b7fe662bc6479147e68", "planned_active_tokens": 70626, "realized_active_tokens": 70626, "cumulative_start": 48892796, "cumulative_end": 48963422, "loss_sum": 23261.701873779297, "token_normalized_loss": 0.3293645665021281, "grad_norm_before_clip": 0.14433446526527405, "learning_rates_at_step": { "lora": 1.46381372435982e-05, "row_tokens": 1.46381372435982e-05 }, "learning_rates_after_step": { "lora": 1.4529823499061806e-05, "row_tokens": 1.4529823499061806e-05 } }, { "update_id": 747, "row_count": 14, "row_ids_sha256": "4d629b140ca8dbadb45e210c9683a838f3bbdcbe2c5165ca28d400619b70f682", "input_ids_vector_sha256": "6076493b13d4d1cda09cd319958bedb4bd35175c69999a9bf79f4d651074dd21", "labels_vector_sha256": "df0651cb05ef0f692aa6e3a599b3f4bd75fd5fad3be6688f55e3e5a6b00df6fe", "planned_active_tokens": 58767, "realized_active_tokens": 58767, "cumulative_start": 48963422, "cumulative_end": 49022189, "loss_sum": 19235.65411376953, "token_normalized_loss": 0.3273206751028559, "grad_norm_before_clip": 0.16089992225170135, "learning_rates_at_step": { "lora": 1.4529823499061806e-05, "row_tokens": 1.4529823499061806e-05 }, "learning_rates_after_step": { "lora": 1.440989729511365e-05, "row_tokens": 1.440989729511365e-05 } }, { "update_id": 748, "row_count": 13, "row_ids_sha256": "0e16dac42c3328fb55afade3d05f78fee92519fe3190a03f7f1abec18eac4d3c", "input_ids_vector_sha256": "da5813593fd12f5fae0525d3d9054cc02386fb353e3c2ddc52c61b4c52ee7e7e", "labels_vector_sha256": "f9d99678cb048645dd2e5225f48e4d0e905d162617d8bddad526fb73d69101d3", "planned_active_tokens": 65280, "realized_active_tokens": 65280, "cumulative_start": 49022189, "cumulative_end": 49087469, "loss_sum": 20699.99673461914, "token_normalized_loss": 0.31709553821414127, "grad_norm_before_clip": 0.1519448310136795, "learning_rates_at_step": { "lora": 1.440989729511365e-05, "row_tokens": 1.440989729511365e-05 }, "learning_rates_after_step": { "lora": 1.4284884068741834e-05, "row_tokens": 1.4284884068741834e-05 } }, { "update_id": 749, "row_count": 14, "row_ids_sha256": "dd5c26802bdfee3e40f286236fb61bccab43aa28b6518c69b1a22dbe6af6a1fa", "input_ids_vector_sha256": "eb3515739b0ab0b4179c3719e5d9a464b1e23a1a4b3d69a6789090ecb052d05b", "labels_vector_sha256": "9d88737c25f83620cf7b730420eeb6483e7918506d8f4ea660e168f90ca4854f", "planned_active_tokens": 68290, "realized_active_tokens": 68290, "cumulative_start": 49087469, "cumulative_end": 49155759, "loss_sum": 25393.704650878906, "token_normalized_loss": 0.37185099796278964, "grad_norm_before_clip": 0.15569493174552917, "learning_rates_at_step": { "lora": 1.4284884068741834e-05, "row_tokens": 1.4284884068741834e-05 }, "learning_rates_after_step": { "lora": 1.4170279937433728e-05, "row_tokens": 1.4170279937433728e-05 } }, { "update_id": 750, "row_count": 13, "row_ids_sha256": "d33d96273cc719db78d899504deb52feb7b9aa4bc594be27a8ec7f4b360177c7", "input_ids_vector_sha256": "3acf9c8c1b40d5bfd6e82fa89503503138618ea0969de6a3ca01c729614f8ff2", "labels_vector_sha256": "ebc884b65c2a48d9611ba6e39788233d4e546c17a2cbd6963224d0a584b3445c", "planned_active_tokens": 62823, "realized_active_tokens": 62823, "cumulative_start": 49155759, "cumulative_end": 49218582, "loss_sum": 21810.665557861328, "token_normalized_loss": 0.34717644107828866, "grad_norm_before_clip": 0.15734566748142242, "learning_rates_at_step": { "lora": 1.4170279937433728e-05, "row_tokens": 1.4170279937433728e-05 }, "learning_rates_after_step": { "lora": 1.404013111022841e-05, "row_tokens": 1.404013111022841e-05 } }, { "update_id": 751, "row_count": 14, "row_ids_sha256": "9d5d067558cc68d1656ad59914ce07b510bc3c52ca3e6af04f2950e9b426915a", "input_ids_vector_sha256": "9d5ab1c06c125dcc860f8608292da481ffc6539871493c69e180f28c70a6581c", "labels_vector_sha256": "6277b634464ed7c5644979d745278fb354abca96c66b8526a4de3c03f5fed5a9", "planned_active_tokens": 71602, "realized_active_tokens": 71602, "cumulative_start": 49218582, "cumulative_end": 49290184, "loss_sum": 24793.530700683594, "token_normalized_loss": 0.3462686894316303, "grad_norm_before_clip": 0.1522652804851532, "learning_rates_at_step": { "lora": 1.404013111022841e-05, "row_tokens": 1.404013111022841e-05 }, "learning_rates_after_step": { "lora": 1.393056831788785e-05, "row_tokens": 1.393056831788785e-05 } }, { "update_id": 752, "row_count": 9, "row_ids_sha256": "ad41e87afe4e13d9490be57ef30c5907467f7e527ae4746590c150b6b9339175", "input_ids_vector_sha256": "6e5d6ac707413ec7376e029d7e6bcda9c1e33666a3e1b249a7fc323252e01890", "labels_vector_sha256": "af966812f1d088f80cb53cf994c3a0f04b8438c3d1907b2a0ae685a837204359", "planned_active_tokens": 60492, "realized_active_tokens": 60492, "cumulative_start": 49290184, "cumulative_end": 49350676, "loss_sum": 25606.507080078125, "token_normalized_loss": 0.4233040249963322, "grad_norm_before_clip": 0.16595615446567535, "learning_rates_at_step": { "lora": 1.393056831788785e-05, "row_tokens": 1.393056831788785e-05 }, "learning_rates_after_step": { "lora": 1.3801784284547859e-05, "row_tokens": 1.3801784284547859e-05 } }, { "update_id": 753, "row_count": 16, "row_ids_sha256": "38687f11875bceabe482330ff69d11fccc7344f8524145a52b3bfa0cebb811a3", "input_ids_vector_sha256": "0e443701086f1d6c2662269c0d6acfd67971daadde01c2f121f3e83f2f89c9bf", "labels_vector_sha256": "d9fda4f6beb022505d053df959575a75639096f4f7afd5eba4e0dd7692faf9f4", "planned_active_tokens": 71360, "realized_active_tokens": 71360, "cumulative_start": 49350676, "cumulative_end": 49422036, "loss_sum": 23505.36358642578, "token_normalized_loss": 0.32939130586359, "grad_norm_before_clip": 0.14863541722297668, "learning_rates_at_step": { "lora": 1.3801784284547859e-05, "row_tokens": 1.3801784284547859e-05 }, "learning_rates_after_step": { "lora": 1.3690589364020106e-05, "row_tokens": 1.3690589364020106e-05 } }, { "update_id": 754, "row_count": 12, "row_ids_sha256": "0d6fd675d0bed5f12cafd9c8332e11df5dde612b5d051385028dec7540b2c9e7", "input_ids_vector_sha256": "879349cd44b61524522d89edb425aa273b9244816b255c6e53f0cb1dcf7d9fd5", "labels_vector_sha256": "a81192d417beb6517d7f4c000cdac0d2a1417daa4498096ff8cabd2383f0889e", "planned_active_tokens": 61839, "realized_active_tokens": 61839, "cumulative_start": 49422036, "cumulative_end": 49483875, "loss_sum": 24218.577758789062, "token_normalized_loss": 0.39163922053702455, "grad_norm_before_clip": 0.1933688521385193, "learning_rates_at_step": { "lora": 1.3690589364020106e-05, "row_tokens": 1.3690589364020106e-05 }, "learning_rates_after_step": { "lora": 1.3570656123872732e-05, "row_tokens": 1.3570656123872732e-05 } }, { "update_id": 755, "row_count": 12, "row_ids_sha256": "577af44dc2c80e279eec7fde2012171436da2c3e17ec99069ebdb83397365142", "input_ids_vector_sha256": "d7cbdc2fd585b8e5e857eb2ee29de5cdc38db29b567760dab425459deb0297bd", "labels_vector_sha256": "fb678f79cb45b733d76cba10459600b4d9d7d0300f948f9fbb9a5cb85823697a", "planned_active_tokens": 66936, "realized_active_tokens": 66936, "cumulative_start": 49483875, "cumulative_end": 49550811, "loss_sum": 23718.854598999023, "token_normalized_loss": 0.3543512399754844, "grad_norm_before_clip": 0.15687865018844604, "learning_rates_at_step": { "lora": 1.3570656123872732e-05, "row_tokens": 1.3570656123872732e-05 }, "learning_rates_after_step": { "lora": 1.3456622472534148e-05, "row_tokens": 1.3456622472534148e-05 } }, { "update_id": 756, "row_count": 14, "row_ids_sha256": "524c7c4addf83955c9782ba29d4cc9a579297cb7886b9bbd34cb7e7911cdc75f", "input_ids_vector_sha256": "abeacb95afb6cff19a3a1d46b7cbcbe244754a62c6c297afea36a2e3355b843b", "labels_vector_sha256": "ce96b6e82e823d81764135e75218b28cc69bb06e32ad6d08c423649c469e72f1", "planned_active_tokens": 63875, "realized_active_tokens": 63875, "cumulative_start": 49550811, "cumulative_end": 49614686, "loss_sum": 20407.757354736328, "token_normalized_loss": 0.319495222774737, "grad_norm_before_clip": 0.15781962871551514, "learning_rates_at_step": { "lora": 1.3456622472534148e-05, "row_tokens": 1.3456622472534148e-05 }, "learning_rates_after_step": { "lora": 1.3343821125715671e-05, "row_tokens": 1.3343821125715671e-05 } }, { "update_id": 757, "row_count": 13, "row_ids_sha256": "cafa21e645c9a84e5765f06f8439a59e4211203f3ebde8d48ee2f8fc43258eb5", "input_ids_vector_sha256": "1410ce32f97884f2003e644b4adad6ed489f377fdcd97639de767521a98b3e59", "labels_vector_sha256": "2fde8360a0d9ecd67eb74cf18b8ce206f81abf777bd7938268b992f21e8ea8f7", "planned_active_tokens": 63410, "realized_active_tokens": 63410, "cumulative_start": 49614686, "cumulative_end": 49678096, "loss_sum": 22141.440490722656, "token_normalized_loss": 0.3491790015884349, "grad_norm_before_clip": 0.15814828872680664, "learning_rates_at_step": { "lora": 1.3343821125715671e-05, "row_tokens": 1.3343821125715671e-05 }, "learning_rates_after_step": { "lora": 1.323025569012077e-05, "row_tokens": 1.323025569012077e-05 } }, { "update_id": 758, "row_count": 12, "row_ids_sha256": "729da5fab8f8ba36995ae37b0c3d91be0881a46b41982f314b2c86c23e46dc87", "input_ids_vector_sha256": "4641dbe5323c765651433f3c417d0325075b1a4a42180632d047acf5137eeab6", "labels_vector_sha256": "d94f6629ebe893742220141092c7cb2c1a2f0494dbf67af83ea408dfcef1db4e", "planned_active_tokens": 64069, "realized_active_tokens": 64069, "cumulative_start": 49678096, "cumulative_end": 49742165, "loss_sum": 23850.99594116211, "token_normalized_loss": 0.3722704574936726, "grad_norm_before_clip": 0.1673370599746704, "learning_rates_at_step": { "lora": 1.323025569012077e-05, "row_tokens": 1.323025569012077e-05 }, "learning_rates_after_step": { "lora": 1.3107076069976371e-05, "row_tokens": 1.3107076069976371e-05 } }, { "update_id": 759, "row_count": 14, "row_ids_sha256": "9bb722e39636a3de87f382c4f7f8b989694451be59337c45076c088d04ceb370", "input_ids_vector_sha256": "5f97204910de195ba7d16bbadd9350cc55375fbed9b1c05b86116767f431d792", "labels_vector_sha256": "f01ea5deb93ecbbba96e8c6a2e91c48d3b2b94fe6640245eecff1f45ef8c38cb", "planned_active_tokens": 69757, "realized_active_tokens": 69757, "cumulative_start": 49742165, "cumulative_end": 49811922, "loss_sum": 25013.59356689453, "token_normalized_loss": 0.35858184220787204, "grad_norm_before_clip": 0.15417376160621643, "learning_rates_at_step": { "lora": 1.3107076069976371e-05, "row_tokens": 1.3107076069976371e-05 }, "learning_rates_after_step": { "lora": 1.2993416627009514e-05, "row_tokens": 1.2993416627009514e-05 } }, { "update_id": 760, "row_count": 15, "row_ids_sha256": "8e55b00768dbbe08ef853abf4f057962b85d74186dca899e066f2ccb5c2ea6f2", "input_ids_vector_sha256": "e06a29e79e88ff57189f26602252d38e1183a53185cdc13f9e1e2d6a5245d56a", "labels_vector_sha256": "c3d799c93df846dff736780cd35b4fafa18e04afe86161eda1534a0f2b9b2b42", "planned_active_tokens": 64613, "realized_active_tokens": 64613, "cumulative_start": 49811922, "cumulative_end": 49876535, "loss_sum": 19443.162963867188, "token_normalized_loss": 0.30091719876599426, "grad_norm_before_clip": 0.1506611704826355, "learning_rates_at_step": { "lora": 1.2993416627009514e-05, "row_tokens": 1.2993416627009514e-05 }, "learning_rates_after_step": { "lora": 1.2883553070440735e-05, "row_tokens": 1.2883553070440735e-05 } }, { "update_id": 761, "row_count": 14, "row_ids_sha256": "3cc86410b5aad7703ba1a8558b51a34c1b57d83ce1fc95b31cac666c8c937f8d", "input_ids_vector_sha256": "60d7a1e35afc10f4d47120d051af8b5124845a9740c9a25fc2bda284352eef8c", "labels_vector_sha256": "e3c2d2aefc32430ae0dca9d638ac8b6b6914c800a0c744153f665f246a49ce2a", "planned_active_tokens": 62684, "realized_active_tokens": 62684, "cumulative_start": 49876535, "cumulative_end": 49939219, "loss_sum": 21784.517822265625, "token_normalized_loss": 0.34752915931123773, "grad_norm_before_clip": 0.15923532843589783, "learning_rates_at_step": { "lora": 1.2883553070440735e-05, "row_tokens": 1.2883553070440735e-05 }, "learning_rates_after_step": { "lora": 1.2768295349687875e-05, "row_tokens": 1.2768295349687875e-05 } }, { "update_id": 762, "row_count": 14, "row_ids_sha256": "775e6446b389140136f06943630793985e8c8c0d7fda1a024e069e9456bc5154", "input_ids_vector_sha256": "2efcbf0f9e5766fae0b1ff6555f23c820a95753410d976721a2188e4dfc852d6", "labels_vector_sha256": "182cfac6f189b51b23536ebd78f1beefa3b6d70a5d6c23528ee2ef9f4787b5ea", "planned_active_tokens": 66007, "realized_active_tokens": 66007, "cumulative_start": 49939219, "cumulative_end": 50005226, "loss_sum": 20674.58807373047, "token_normalized_loss": 0.3132181143474248, "grad_norm_before_clip": 0.15099018812179565, "learning_rates_at_step": { "lora": 1.2768295349687875e-05, "row_tokens": 1.2768295349687875e-05 }, "learning_rates_after_step": { "lora": 1.264769245242785e-05, "row_tokens": 1.264769245242785e-05 } }, { "update_id": 763, "row_count": 19, "row_ids_sha256": "de4ff8e590a36aef8c452d2ad210df3c05dbe04f9ded57491d89eaa644b7429c", "input_ids_vector_sha256": "cdc9a485b2e7236e5e12407809587182b0eccaf782d19df6df6b74bce2bd788b", "labels_vector_sha256": "1e91fa6e39eec9dd7ec101c1266b87bb1f1625f40218ad3467d3ea0d8c5e3915", "planned_active_tokens": 69341, "realized_active_tokens": 69341, "cumulative_start": 50005226, "cumulative_end": 50074567, "loss_sum": 21067.17481994629, "token_normalized_loss": 0.30381988751166394, "grad_norm_before_clip": 0.14147184789180756, "learning_rates_at_step": { "lora": 1.264769245242785e-05, "row_tokens": 1.264769245242785e-05 }, "learning_rates_after_step": { "lora": 1.2539225956738493e-05, "row_tokens": 1.2539225956738493e-05 } }, { "update_id": 764, "row_count": 14, "row_ids_sha256": "723901f443e3ba49d849d8687be15c5763afadad56805d4812d5f5c2a935d45d", "input_ids_vector_sha256": "82c7921d90d201f34bb68814d395d97c7d63df61d6f3ba6ab7529cbc582592fa", "labels_vector_sha256": "29a018df51ed7f45ee64b760b4776eea1969401b0743a5f1f007dfa1a4b8b09d", "planned_active_tokens": 62605, "realized_active_tokens": 62605, "cumulative_start": 50074567, "cumulative_end": 50137172, "loss_sum": 17915.909057617188, "token_normalized_loss": 0.28617377298326313, "grad_norm_before_clip": 0.14317536354064941, "learning_rates_at_step": { "lora": 1.2539225956738493e-05, "row_tokens": 1.2539225956738493e-05 }, "learning_rates_after_step": { "lora": 1.24271439213062e-05, "row_tokens": 1.24271439213062e-05 } }, { "update_id": 765, "row_count": 15, "row_ids_sha256": "ea6dc333e56324114bee55547d5490c689bfc445c79ece82e5059a7f83ac3944", "input_ids_vector_sha256": "f85c6233be3a613be0acfc5de8beb394caf56fa530afb95bc0637cb898be3245", "labels_vector_sha256": "c7a00f34a37ff15e81e1ce049a751537b5ae4c8d9b3831d4301e9f9b5fb0330c", "planned_active_tokens": 64936, "realized_active_tokens": 64936, "cumulative_start": 50137172, "cumulative_end": 50202108, "loss_sum": 20783.63735961914, "token_normalized_loss": 0.32006340642508224, "grad_norm_before_clip": 0.15530814230442047, "learning_rates_at_step": { "lora": 1.24271439213062e-05, "row_tokens": 1.24271439213062e-05 }, "learning_rates_after_step": { "lora": 1.2309496959605898e-05, "row_tokens": 1.2309496959605898e-05 } }, { "update_id": 766, "row_count": 16, "row_ids_sha256": "f4fcf568585bba582beb94696421c3802da4a07530f494011a4b22cfaa1d20c9", "input_ids_vector_sha256": "a0660484dd44e34c3d1131c56de1e65a26f7eac15d6d2e7db4be87c08f9adfa4", "labels_vector_sha256": "32a9aac56f30c907e84a25d919bdaafd211446e8c432125212b5057f1eda1b08", "planned_active_tokens": 68431, "realized_active_tokens": 68431, "cumulative_start": 50202108, "cumulative_end": 50270539, "loss_sum": 22549.704971313477, "token_normalized_loss": 0.3295247032969484, "grad_norm_before_clip": 0.18050333857536316, "learning_rates_at_step": { "lora": 1.2309496959605898e-05, "row_tokens": 1.2309496959605898e-05 }, "learning_rates_after_step": { "lora": 1.219589064388102e-05, "row_tokens": 1.219589064388102e-05 } }, { "update_id": 767, "row_count": 9, "row_ids_sha256": "22c80605eee4bfab1ba7417c3edb5b60347ae845bd3adce2e169567633b661d6", "input_ids_vector_sha256": "d0424e4a7bec75fb79664d4de976c147a2fde0634d57e3cb044bc413f14b3cca", "labels_vector_sha256": "b60c669ca384a9e797b3fc7001e49de1727f5491620f13acdd4f953841e217f1", "planned_active_tokens": 66348, "realized_active_tokens": 66348, "cumulative_start": 50270539, "cumulative_end": 50336887, "loss_sum": 26657.233612060547, "token_normalized_loss": 0.4017790078383756, "grad_norm_before_clip": 0.16716600954532623, "learning_rates_at_step": { "lora": 1.219589064388102e-05, "row_tokens": 1.219589064388102e-05 }, "learning_rates_after_step": { "lora": 1.2085066594797773e-05, "row_tokens": 1.2085066594797773e-05 } }, { "update_id": 768, "row_count": 13, "row_ids_sha256": "0f991435589d6863a20765ace92aaa87761b6e9154fc7e13c22a411a31927772", "input_ids_vector_sha256": "4cbe93ef127c2060b2309af93a72cd80102890939c8b2755118f8e34f3cf31de", "labels_vector_sha256": "371387e05e8f018b125c47ca5eb3a83edd1e2e23e8e02ba631eadb03e4d452fc", "planned_active_tokens": 64980, "realized_active_tokens": 64980, "cumulative_start": 50336887, "cumulative_end": 50401867, "loss_sum": 22964.279235839844, "token_normalized_loss": 0.3534053437340696, "grad_norm_before_clip": 0.9240944981575012, "learning_rates_at_step": { "lora": 1.2085066594797773e-05, "row_tokens": 1.2085066594797773e-05 }, "learning_rates_after_step": { "lora": 1.1978015915950103e-05, "row_tokens": 1.1978015915950103e-05 } }, { "update_id": 769, "row_count": 13, "row_ids_sha256": "8ff5f57108694c23b6ac1e2358b1cb35318c50c308f7c651bb084fc55122f852", "input_ids_vector_sha256": "f8c442fce56510ae332d136dbee9aabbe04123ea7f1ed41b2e189a963963627a", "labels_vector_sha256": "d628570272d0164a2c18717ea83a67730b3001d11231b308571083fc71757cb6", "planned_active_tokens": 63012, "realized_active_tokens": 63012, "cumulative_start": 50401867, "cumulative_end": 50464879, "loss_sum": 20478.262634277344, "token_normalized_loss": 0.324989885010432, "grad_norm_before_clip": 0.152865469455719, "learning_rates_at_step": { "lora": 1.1978015915950103e-05, "row_tokens": 1.1978015915950103e-05 }, "learning_rates_after_step": { "lora": 1.186664282096695e-05, "row_tokens": 1.186664282096695e-05 } }, { "update_id": 770, "row_count": 16, "row_ids_sha256": "dce0035416830881cd930d1ee6749f5f1a8471cdcf2a151162ab1bf8fa5c5b5d", "input_ids_vector_sha256": "b7f517c3446c81289c58c4d1d270d171da40fcf671f28aa21e36f7796a251409", "labels_vector_sha256": "d8faa2410a3cc9cffa96d8ed8b6cbc2b0361a6d135abe3d3c11c8316b8e430d4", "planned_active_tokens": 65815, "realized_active_tokens": 65815, "cumulative_start": 50464879, "cumulative_end": 50530694, "loss_sum": 21795.541900634766, "token_normalized_loss": 0.33116374535645016, "grad_norm_before_clip": 0.1545730084180832, "learning_rates_at_step": { "lora": 1.186664282096695e-05, "row_tokens": 1.186664282096695e-05 }, "learning_rates_after_step": { "lora": 1.1756796633658129e-05, "row_tokens": 1.1756796633658129e-05 } }, { "update_id": 771, "row_count": 16, "row_ids_sha256": "00c6b40d4e0e8cdc463b5239376ab8b4c2d349906ed0763fb1ae797780592b49", "input_ids_vector_sha256": "a7d684925363e6d4cdd21a5e9eb10f7628387c46f410b66a0124509a08fc97cd", "labels_vector_sha256": "4405b7c4097a556eb3b9135aaabbac45ea98693bc644670eae97aa40ad85550d", "planned_active_tokens": 65175, "realized_active_tokens": 65175, "cumulative_start": 50530694, "cumulative_end": 50595869, "loss_sum": 18746.97833251953, "token_normalized_loss": 0.28764063417751484, "grad_norm_before_clip": 0.14398057758808136, "learning_rates_at_step": { "lora": 1.1756796633658129e-05, "row_tokens": 1.1756796633658129e-05 }, "learning_rates_after_step": { "lora": 1.1645791999602861e-05, "row_tokens": 1.1645791999602861e-05 } }, { "update_id": 772, "row_count": 12, "row_ids_sha256": "8171d77e7efc1881d819c1fad4b8c2025740f15a912e8fc98ef48f1396f753d9", "input_ids_vector_sha256": "570ae041438934bd68465f574fedd24665d79170e18907b9c9e41b5a8ea80919", "labels_vector_sha256": "24900e06425858fd669ae66e8fe96c18a6842d96bdd5b0ae027a35f62012f383", "planned_active_tokens": 66131, "realized_active_tokens": 66131, "cumulative_start": 50595869, "cumulative_end": 50662000, "loss_sum": 23958.244720458984, "token_normalized_loss": 0.362284627791187, "grad_norm_before_clip": 0.15863971412181854, "learning_rates_at_step": { "lora": 1.1645791999602861e-05, "row_tokens": 1.1645791999602861e-05 }, "learning_rates_after_step": { "lora": 1.1538599690710417e-05, "row_tokens": 1.1538599690710417e-05 } }, { "update_id": 773, "row_count": 15, "row_ids_sha256": "60cf5baafa06ffb64e963e7ed84d7ce8b65428415b57914111350e3a97dc546c", "input_ids_vector_sha256": "116a27844a6b5be079f4cc48fd1d53ff63ecf250b210020a1fd3a8534706bb23", "labels_vector_sha256": "84c189a7239b3eef0d457af3697cbfe416105771a4e6bf8a9c5d1f40fcd04c5b", "planned_active_tokens": 64120, "realized_active_tokens": 64120, "cumulative_start": 50662000, "cumulative_end": 50726120, "loss_sum": 21266.59881591797, "token_normalized_loss": 0.33166872763440375, "grad_norm_before_clip": 0.1554347276687622, "learning_rates_at_step": { "lora": 1.1538599690710417e-05, "row_tokens": 1.1538599690710417e-05 }, "learning_rates_after_step": { "lora": 1.1425086518437888e-05, "row_tokens": 1.1425086518437888e-05 } }, { "update_id": 774, "row_count": 16, "row_ids_sha256": "ef6d4c2f5d491c03101117b471f14e80577afacb2e2fda557cad5f940fdbebba", "input_ids_vector_sha256": "da9624a81a428b7340a070935f9403c98da5ddb59b9d8c9a016d9d49972a2874", "labels_vector_sha256": "e81926def0f4769277771185170f702f151ac16aac38e7e5d50e4520257061c8", "planned_active_tokens": 68184, "realized_active_tokens": 68184, "cumulative_start": 50726120, "cumulative_end": 50794304, "loss_sum": 21525.255615234375, "token_normalized_loss": 0.31569364682673906, "grad_norm_before_clip": 0.14648805558681488, "learning_rates_at_step": { "lora": 1.1425086518437888e-05, "row_tokens": 1.1425086518437888e-05 }, "learning_rates_after_step": { "lora": 1.1319046699051033e-05, "row_tokens": 1.1319046699051033e-05 } }, { "update_id": 775, "row_count": 11, "row_ids_sha256": "9a37d1da735088f130e5e2505b8414cffb624c684784b5ac8c157c4df8a6d0cb", "input_ids_vector_sha256": "9a533fce9c6f042bef37e6b538745bf53acf16c4d60fc549bedee9de064778d9", "labels_vector_sha256": "6f63e838db77e7a3489b9829bec6bd9a2e7c692182763d546441d50502dc1365", "planned_active_tokens": 63962, "realized_active_tokens": 63962, "cumulative_start": 50794304, "cumulative_end": 50858266, "loss_sum": 22850.557067871094, "token_normalized_loss": 0.3572520726035942, "grad_norm_before_clip": 0.15996015071868896, "learning_rates_at_step": { "lora": 1.1319046699051033e-05, "row_tokens": 1.1319046699051033e-05 }, "learning_rates_after_step": { "lora": 1.1211098755485738e-05, "row_tokens": 1.1211098755485738e-05 } }, { "update_id": 776, "row_count": 15, "row_ids_sha256": "1a2b5c2cf09b69ee370311c3d27de71bc0f27f09a9a69b45eb72f6e0572bb95e", "input_ids_vector_sha256": "f83bf4045a22bc15a8f44774ddb9e976ce118a761997f31d8e676c979a20e943", "labels_vector_sha256": "68156e13d04654c24b6f30b62e4f01ff32708f966dc33fdc4373c0fe06593514", "planned_active_tokens": 65382, "realized_active_tokens": 65382, "cumulative_start": 50858266, "cumulative_end": 50923648, "loss_sum": 22466.30093383789, "token_normalized_loss": 0.34361599421611283, "grad_norm_before_clip": 0.1534494012594223, "learning_rates_at_step": { "lora": 1.1211098755485738e-05, "row_tokens": 1.1211098755485738e-05 }, "learning_rates_after_step": { "lora": 1.1104086987651024e-05, "row_tokens": 1.1104086987651024e-05 } }, { "update_id": 777, "row_count": 14, "row_ids_sha256": "40cb78cd9af3d408fd1bd5c160cc10d1031c96302bebdce83c7ec52712476e29", "input_ids_vector_sha256": "9f5dcadf44fe317fb1eea49a4d536e6851b4cae29d789a55ed409c6862a1ec8b", "labels_vector_sha256": "afa78641cb874a6d0f36ba464ce02bb3a7ec8c930933d0ecd7cb14f2416aabd5", "planned_active_tokens": 65087, "realized_active_tokens": 65087, "cumulative_start": 50923648, "cumulative_end": 50988735, "loss_sum": 21019.218322753906, "token_normalized_loss": 0.32294034634802504, "grad_norm_before_clip": 0.1683865338563919, "learning_rates_at_step": { "lora": 1.1104086987651024e-05, "row_tokens": 1.1104086987651024e-05 }, "learning_rates_after_step": { "lora": 1.0999202503284995e-05, "row_tokens": 1.0999202503284995e-05 } }, { "update_id": 778, "row_count": 14, "row_ids_sha256": "1f938cf7e2715e25b62d0d90755401ea52b8614f61845b5d9ae8b55ac780c93e", "input_ids_vector_sha256": "7994b6e0172f598bda76b300a95fc29d41934bf4550d33497c29dcc57632bde1", "labels_vector_sha256": "60645ca26b68bffc45d4ca72c02188ff50d23e40ce62f729a2808ba5bdddd9f0", "planned_active_tokens": 64060, "realized_active_tokens": 64060, "cumulative_start": 50988735, "cumulative_end": 51052795, "loss_sum": 22527.749633789062, "token_normalized_loss": 0.35166640077722544, "grad_norm_before_clip": 0.15647900104522705, "learning_rates_at_step": { "lora": 1.0999202503284995e-05, "row_tokens": 1.0999202503284995e-05 }, "learning_rates_after_step": { "lora": 1.0889543543401393e-05, "row_tokens": 1.0889543543401393e-05 } }, { "update_id": 779, "row_count": 12, "row_ids_sha256": "c4f64388818f7df60a085e954631d3863ca086c1df38e49f122772d9b83ce805", "input_ids_vector_sha256": "9d4bd8d3ffe3522eea34953c4911508b08e2353fd961f24bf92db8380c838c34", "labels_vector_sha256": "37f3b0d070f6b7b8dd892e99a1f0966620380eef2f549172448007769271b40c", "planned_active_tokens": 67263, "realized_active_tokens": 67263, "cumulative_start": 51052795, "cumulative_end": 51120058, "loss_sum": 21564.79217529297, "token_normalized_loss": 0.32060407914147404, "grad_norm_before_clip": 0.15216785669326782, "learning_rates_at_step": { "lora": 1.0889543543401393e-05, "row_tokens": 1.0889543543401393e-05 }, "learning_rates_after_step": { "lora": 1.0781100780711007e-05, "row_tokens": 1.0781100780711007e-05 } }, { "update_id": 780, "row_count": 15, "row_ids_sha256": "3423864c7fbfd5b6d1d8304ed6473b0714541e5851d8760abe0bb66feaab38ab", "input_ids_vector_sha256": "0f9a71faa40919d0a6e2bfcae3bf834326305e87c32f57fd1cadbfa81b5394a4", "labels_vector_sha256": "424f8b27b3f757da7c5a70580e247199047e9cbe2383484718fdac0014941fdf", "planned_active_tokens": 66810, "realized_active_tokens": 66810, "cumulative_start": 51120058, "cumulative_end": 51186868, "loss_sum": 20279.0, "token_normalized_loss": 0.30353240532854364, "grad_norm_before_clip": 0.17202144861221313, "learning_rates_at_step": { "lora": 1.0781100780711007e-05, "row_tokens": 1.0781100780711007e-05 }, "learning_rates_after_step": { "lora": 1.0680219824762611e-05, "row_tokens": 1.0680219824762611e-05 } }, { "update_id": 781, "row_count": 11, "row_ids_sha256": "aefa47ed2c20874cb06c440d605c7cb1e9d62e9dd67834e0e5efa83444ea266d", "input_ids_vector_sha256": "36174495c1063073c58facb53e2d8d9c4b27e6f676cda85c522ea2f73a3e8491", "labels_vector_sha256": "980caabebc85ae387f4a641b7d785d0bde4215ed719755bd57448e8bb1dfcb7d", "planned_active_tokens": 62417, "realized_active_tokens": 62417, "cumulative_start": 51186868, "cumulative_end": 51249285, "loss_sum": 22384.912155151367, "token_normalized_loss": 0.35863486157859825, "grad_norm_before_clip": 0.16960836946964264, "learning_rates_at_step": { "lora": 1.0680219824762611e-05, "row_tokens": 1.0680219824762611e-05 }, "learning_rates_after_step": { "lora": 1.055646842495095e-05, "row_tokens": 1.055646842495095e-05 } }, { "update_id": 782, "row_count": 13, "row_ids_sha256": "021a0464581c0777613c0ccb57193bb314324855fa45604e4b520eaa15425ae6", "input_ids_vector_sha256": "61abe8fae5aa0d0326f809480b6bf1fe4d972cf3356b6a6a9861e3f81509f2bb", "labels_vector_sha256": "df0c10a307af7489ad4dcbafaa650d2c50373834df0b42865168d324730d2bca", "planned_active_tokens": 76923, "realized_active_tokens": 76923, "cumulative_start": 51249285, "cumulative_end": 51326208, "loss_sum": 27249.978546142578, "token_normalized_loss": 0.35425007534992886, "grad_norm_before_clip": 0.146048903465271, "learning_rates_at_step": { "lora": 1.055646842495095e-05, "row_tokens": 1.055646842495095e-05 }, "learning_rates_after_step": { "lora": 1.0462455295043133e-05, "row_tokens": 1.0462455295043133e-05 } }, { "update_id": 783, "row_count": 11, "row_ids_sha256": "0a2dfd71f4d37ea03d5ef46ab8612e4c03f29ab0da1b1af8e707cbe0e3926e13", "input_ids_vector_sha256": "a24fc43db8a4063ec0b1521a41dd7f16e9de52a1e170b2db3f919cbf26919ed4", "labels_vector_sha256": "ad6124a5a2a7d4142e7ea250008f275bb3c20ff1bbd59b3179382426e27295f3", "planned_active_tokens": 58704, "realized_active_tokens": 58704, "cumulative_start": 51326208, "cumulative_end": 51384912, "loss_sum": 19408.425354003906, "token_normalized_loss": 0.3306150407809333, "grad_norm_before_clip": 0.16660617291927338, "learning_rates_at_step": { "lora": 1.0462455295043133e-05, "row_tokens": 1.0462455295043133e-05 }, "learning_rates_after_step": { "lora": 1.0364294535895391e-05, "row_tokens": 1.0364294535895391e-05 } }, { "update_id": 784, "row_count": 14, "row_ids_sha256": "5becf7d7c21e9a8d19cdaf45d0e6c1296cabc7a043f410b795e252c11502027c", "input_ids_vector_sha256": "aee400dd30d5d272f5002f0c4688f25b6c67a2b22c63e58e006674c84b8c69ba", "labels_vector_sha256": "173b91d0d0f45d267c406543eae67eb724e6256182051e095e6453f468dc3d70", "planned_active_tokens": 61543, "realized_active_tokens": 61543, "cumulative_start": 51384912, "cumulative_end": 51446455, "loss_sum": 18776.011108398438, "token_normalized_loss": 0.30508768029505284, "grad_norm_before_clip": 0.18964697420597076, "learning_rates_at_step": { "lora": 1.0364294535895391e-05, "row_tokens": 1.0364294535895391e-05 }, "learning_rates_after_step": { "lora": 1.0255159234987527e-05, "row_tokens": 1.0255159234987527e-05 } }, { "update_id": 785, "row_count": 13, "row_ids_sha256": "7f8b3b194a776f5b3021b8c82d4232a3bdd74024b6366d25156bc6e62f2fd9c3", "input_ids_vector_sha256": "d192ca515db5784f2cf88b002cf106ef54e07ea7eb7957367c2085e8c9e8a3ae", "labels_vector_sha256": "e02962ea1fb5b591607c41804759c5f16f381a4075bed75d0f26eef998bd407c", "planned_active_tokens": 68727, "realized_active_tokens": 68727, "cumulative_start": 51446455, "cumulative_end": 51515182, "loss_sum": 22777.626861572266, "token_normalized_loss": 0.3314218118290085, "grad_norm_before_clip": 0.1571395993232727, "learning_rates_at_step": { "lora": 1.0255159234987527e-05, "row_tokens": 1.0255159234987527e-05 }, "learning_rates_after_step": { "lora": 1.015515456715821e-05, "row_tokens": 1.015515456715821e-05 } }, { "update_id": 786, "row_count": 11, "row_ids_sha256": "183ec48bbea79b94729b1f30063d7c137c3fc6aba84b4f5181086c28f900ad5f", "input_ids_vector_sha256": "ce6d7fc221305d22702feae320fcf02117c8faba462660fefb37ee245e7741c9", "labels_vector_sha256": "df2c91d8d78a496e14047e6806511835d490513e2f38344f50826b68b53411f4", "planned_active_tokens": 63262, "realized_active_tokens": 63262, "cumulative_start": 51515182, "cumulative_end": 51578444, "loss_sum": 23279.43211364746, "token_normalized_loss": 0.36798444743522907, "grad_norm_before_clip": 0.16091087460517883, "learning_rates_at_step": { "lora": 1.015515456715821e-05, "row_tokens": 1.015515456715821e-05 }, "learning_rates_after_step": { "lora": 1.0051300875692171e-05, "row_tokens": 1.0051300875692171e-05 } }, { "update_id": 787, "row_count": 13, "row_ids_sha256": "3a1c0c41fe6c15972e48c5cb5aa7e00296d9a8bcc811023926d29f3cca41e3da", "input_ids_vector_sha256": "09c90c041ba0b9ee4804126aeb6ba4e870e0654f94ed58ba2233b6f331f6b27b", "labels_vector_sha256": "df8e5a47f6176066bf0af4fb77422cb7761831166cc7d6d9c5354944c7f6b9a3", "planned_active_tokens": 65990, "realized_active_tokens": 65990, "cumulative_start": 51578444, "cumulative_end": 51644434, "loss_sum": 23156.444122314453, "token_normalized_loss": 0.3509083819111146, "grad_norm_before_clip": 0.15922312438488007, "learning_rates_at_step": { "lora": 1.0051300875692171e-05, "row_tokens": 1.0051300875692171e-05 }, "learning_rates_after_step": { "lora": 9.948357662411578e-06, "row_tokens": 9.948357662411578e-06 } }, { "update_id": 788, "row_count": 14, "row_ids_sha256": "175a5337d5a178cca3406143c71413af961e36a22dd049438b2a1366ff6b9d2f", "input_ids_vector_sha256": "fb0b2d5c32fe8962c1c755e0e1074e1ef9aad65e1804b73634f6360bd585c8d5", "labels_vector_sha256": "300307a4c46b7bfc11602d7b8fa02cbab2e432c0b24b60235ef007f334b9ff3a", "planned_active_tokens": 65711, "realized_active_tokens": 65711, "cumulative_start": 51644434, "cumulative_end": 51710145, "loss_sum": 21886.10774230957, "token_normalized_loss": 0.33306611894978877, "grad_norm_before_clip": 0.15281789004802704, "learning_rates_at_step": { "lora": 9.948357662411578e-06, "row_tokens": 9.948357662411578e-06 }, "learning_rates_after_step": { "lora": 9.843138626380232e-06, "row_tokens": 9.843138626380232e-06 } }, { "update_id": 789, "row_count": 14, "row_ids_sha256": "10574bd1a6500227c2add07664d899fd01e41fd5649a65c1eeb003cad0fd61b9", "input_ids_vector_sha256": "b8a2ecf67dd00b8f5fc8946673be7a9c8238a5967c20884a37b626b5a083df7c", "labels_vector_sha256": "b36e7ab7ed8b0d7c8b7b3f65108f6d2c90e313af4d623622eb4c5df2293469fd", "planned_active_tokens": 67477, "realized_active_tokens": 67477, "cumulative_start": 51710145, "cumulative_end": 51777622, "loss_sum": 22826.503051757812, "token_normalized_loss": 0.33828568329590547, "grad_norm_before_clip": 0.15016986429691315, "learning_rates_at_step": { "lora": 9.843138626380232e-06, "row_tokens": 9.843138626380232e-06 }, "learning_rates_after_step": { "lora": 9.745166474836692e-06, "row_tokens": 9.745166474836692e-06 } }, { "update_id": 790, "row_count": 16, "row_ids_sha256": "a064a2716e6f2f11aa429370bf50cf2a5c9be4352a50151a0000b0485eae46da", "input_ids_vector_sha256": "98d14252637c6ca0e9ee04837c198f8bda11b08bb4920c7aaf90127af3381899", "labels_vector_sha256": "4b3bc91f6283cf1725cb6a51b6a91234d4d70775fbf1ee26ca5190346c83c612", "planned_active_tokens": 63119, "realized_active_tokens": 63119, "cumulative_start": 51777622, "cumulative_end": 51840741, "loss_sum": 16528.975158691406, "token_normalized_loss": 0.2618700416465946, "grad_norm_before_clip": 0.14503325521945953, "learning_rates_at_step": { "lora": 9.745166474836692e-06, "row_tokens": 9.745166474836692e-06 }, "learning_rates_after_step": { "lora": 9.645092501238589e-06, "row_tokens": 9.645092501238589e-06 } }, { "update_id": 791, "row_count": 15, "row_ids_sha256": "08ddd0584456e263666c3f222e80f45029e8ffe50b93e1555d65a12a95030f86", "input_ids_vector_sha256": "7767d10014bce807f193578f421974eb647111b5f39da79cde898957c05cee58", "labels_vector_sha256": "426296b9cf2c9370f9525d9c92ce7433ca0e0e0095c4c4bc06754274f90b3388", "planned_active_tokens": 64766, "realized_active_tokens": 64766, "cumulative_start": 51840741, "cumulative_end": 51905507, "loss_sum": 18878.265991210938, "token_normalized_loss": 0.29148420453958773, "grad_norm_before_clip": 0.14770588278770447, "learning_rates_at_step": { "lora": 9.645092501238589e-06, "row_tokens": 9.645092501238589e-06 }, "learning_rates_after_step": { "lora": 9.544083820948035e-06, "row_tokens": 9.544083820948035e-06 } }, { "update_id": 792, "row_count": 14, "row_ids_sha256": "1d934524590b011fe2d3d034dc183d534ff2514985905d1b9c6622d3a6cd98a7", "input_ids_vector_sha256": "9f2a6ee2809d9dbacc370688c4a4deb1586af328cf324c75d884b356c1642ddd", "labels_vector_sha256": "e81b7a9f7bbe0ef999e34d30d997bd0b15ade6fa3a91b81192f4240e5b4ddffb", "planned_active_tokens": 65676, "realized_active_tokens": 65676, "cumulative_start": 51905507, "cumulative_end": 51971183, "loss_sum": 21301.019958496094, "token_normalized_loss": 0.3243349162326587, "grad_norm_before_clip": 0.15054814517498016, "learning_rates_at_step": { "lora": 9.544083820948035e-06, "row_tokens": 9.544083820948035e-06 }, "learning_rates_after_step": { "lora": 9.444578772950447e-06, "row_tokens": 9.444578772950447e-06 } }, { "update_id": 793, "row_count": 15, "row_ids_sha256": "5287f1831081e9f069fe82a76aff3818a3297ddbb0ff6c2fcf296e6644e93751", "input_ids_vector_sha256": "855f39874f50bd324d1a4289dbd0ce1e996f3337b56ac26ff7e0497fc0a1f18c", "labels_vector_sha256": "6664a0ae620b88903fdaceb56628cee3053ddeb66dd7f0bd9cc142a9c6bd4d4a", "planned_active_tokens": 65003, "realized_active_tokens": 65003, "cumulative_start": 51971183, "cumulative_end": 52036186, "loss_sum": 18025.62045288086, "token_normalized_loss": 0.27730443907020996, "grad_norm_before_clip": 0.14403004944324493, "learning_rates_at_step": { "lora": 9.444578772950447e-06, "row_tokens": 9.444578772950447e-06 }, "learning_rates_after_step": { "lora": 9.345595750565428e-06, "row_tokens": 9.345595750565428e-06 } }, { "update_id": 794, "row_count": 16, "row_ids_sha256": "d4695c8c47112fb515eddc664dcffc306b68038552ba96dc3cd2add99ba3aee2", "input_ids_vector_sha256": "081519495208d819a8e95585d8865d41dd3933a71e79ea1a2c0aacde674079ef", "labels_vector_sha256": "97ff70d7e1e4d24f2e9208cea7bc19a3fc64e05dea109a32165cf9ccdf50602b", "planned_active_tokens": 64967, "realized_active_tokens": 64967, "cumulative_start": 52036186, "cumulative_end": 52101153, "loss_sum": 17305.863815307617, "token_normalized_loss": 0.2663792974172675, "grad_norm_before_clip": 0.14135007560253143, "learning_rates_at_step": { "lora": 9.345595750565428e-06, "row_tokens": 9.345595750565428e-06 }, "learning_rates_after_step": { "lora": 9.234492129187677e-06, "row_tokens": 9.234492129187677e-06 } }, { "update_id": 795, "row_count": 13, "row_ids_sha256": "0695929bfea516c1aa693edfd02d85df00fa66adea36f35123a9b1b1f695de76", "input_ids_vector_sha256": "5c415f685bcee48704aa080326d4ffef1296203e97cf51c01f604f1a25ca36ee", "labels_vector_sha256": "40c2e906a926578b9679bd2eb13670fb9f53cc931b870e35f47d4fb138dd599f", "planned_active_tokens": 73291, "realized_active_tokens": 73291, "cumulative_start": 52101153, "cumulative_end": 52174444, "loss_sum": 27722.063049316406, "token_normalized_loss": 0.3782464838700032, "grad_norm_before_clip": 0.15601441264152527, "learning_rates_at_step": { "lora": 9.234492129187677e-06, "row_tokens": 9.234492129187677e-06 }, "learning_rates_after_step": { "lora": 9.146129117438179e-06, "row_tokens": 9.146129117438179e-06 } }, { "update_id": 796, "row_count": 13, "row_ids_sha256": "063ac543b5485a83948973cee82324a9be957eb0a8fd5eb4f725a8364e256ea6", "input_ids_vector_sha256": "00ecd075454dce67e42e4449fa4c23e25f8c46f3d4e7c862997f508eb12c7153", "labels_vector_sha256": "32073a425ce59dbbb72549ff50daee16c9677cbc6a072453583653193bf0522f", "planned_active_tokens": 58573, "realized_active_tokens": 58573, "cumulative_start": 52174444, "cumulative_end": 52233017, "loss_sum": 18396.868438720703, "token_normalized_loss": 0.3140844491270842, "grad_norm_before_clip": 0.1634213775396347, "learning_rates_at_step": { "lora": 9.146129117438179e-06, "row_tokens": 9.146129117438179e-06 }, "learning_rates_after_step": { "lora": 9.043475899610382e-06, "row_tokens": 9.043475899610382e-06 } }, { "update_id": 797, "row_count": 19, "row_ids_sha256": "1131984dc6989f5a8e21f64c31daeec1e23091d4fdf997de3797d21bf4eb2944", "input_ids_vector_sha256": "51b707a5aac560a3e1613fc433353a8a1867a77192bf2d65117242144c1ca889", "labels_vector_sha256": "1acf11520c89d4a84891dbcd1a05eb769e6c9e8b0f7af07b849ad3b80b4dfb2e", "planned_active_tokens": 68366, "realized_active_tokens": 68366, "cumulative_start": 52233017, "cumulative_end": 52301383, "loss_sum": 17443.07015991211, "token_normalized_loss": 0.2551424708175425, "grad_norm_before_clip": 0.13739779591560364, "learning_rates_at_step": { "lora": 9.043475899610382e-06, "row_tokens": 9.043475899610382e-06 }, "learning_rates_after_step": { "lora": 8.948918657661282e-06, "row_tokens": 8.948918657661282e-06 } }, { "update_id": 798, "row_count": 12, "row_ids_sha256": "68fb2c894d6537d4587a23becb5f9f780c7b7987e6779a975a0ac320f70ed518", "input_ids_vector_sha256": "13f970c95f4f90ac937e2daf53be6415cdc9b73491ca0daa51d902107a9c38cf", "labels_vector_sha256": "e6b64f36f3bf57644d4abcf12044eff91a7e490c82f63494c8904bfa0d486a43", "planned_active_tokens": 63284, "realized_active_tokens": 63284, "cumulative_start": 52301383, "cumulative_end": 52364667, "loss_sum": 22634.057586669922, "token_normalized_loss": 0.35765845374296695, "grad_norm_before_clip": 0.1560109406709671, "learning_rates_at_step": { "lora": 8.948918657661282e-06, "row_tokens": 8.948918657661282e-06 }, "learning_rates_after_step": { "lora": 8.845390040711549e-06, "row_tokens": 8.845390040711549e-06 } }, { "update_id": 799, "row_count": 15, "row_ids_sha256": "9ab6da16108f8ad57e4ca82d0604ba5549ce1209fc38fafc66bd26910a82c4f0", "input_ids_vector_sha256": "ff717c81ea2dc1f635dd8c65985b3cc25bb63b57eb71ce1b7617ff3e7daa37cc", "labels_vector_sha256": "55cd69213c64c9b48dd2183a70bd39ac5c4d2feafdfff8d7965383cfb3977cef", "planned_active_tokens": 69635, "realized_active_tokens": 69635, "cumulative_start": 52364667, "cumulative_end": 52434302, "loss_sum": 23693.400329589844, "token_normalized_loss": 0.34025131513735685, "grad_norm_before_clip": 0.15504874289035797, "learning_rates_at_step": { "lora": 8.845390040711549e-06, "row_tokens": 8.845390040711549e-06 }, "learning_rates_after_step": { "lora": 8.75050951553485e-06, "row_tokens": 8.75050951553485e-06 } }, { "update_id": 800, "row_count": 13, "row_ids_sha256": "679e8cf7df3d5eb4fe7332eebdf48911af801fec2b97e21581fba2e81c82b4ec", "input_ids_vector_sha256": "b9d0801abfc14fb641b19e7c5bc1220139c75813836baba73d6a16897746866f", "labels_vector_sha256": "7a25a78572378c8fae4601394eff32503591e0ad3ae2ba507fcae707e42d3155", "planned_active_tokens": 64142, "realized_active_tokens": 64142, "cumulative_start": 52434302, "cumulative_end": 52498444, "loss_sum": 19748.644287109375, "token_normalized_loss": 0.30788943729708107, "grad_norm_before_clip": 0.15266476571559906, "learning_rates_at_step": { "lora": 8.75050951553485e-06, "row_tokens": 8.75050951553485e-06 }, "learning_rates_after_step": { "lora": 8.653349015416057e-06, "row_tokens": 8.653349015416057e-06 } }, { "update_id": 801, "row_count": 18, "row_ids_sha256": "0a002df0fba6929b2ebf4f4c50b18a5242c89d55a546141849361d7e3113f288", "input_ids_vector_sha256": "ebfd334065a9503b7069d29c6a7f5d78c4a30cb2d0166f053f7b761e0dd8b902", "labels_vector_sha256": "e42607a4e616d20c834c0ae9a4dc3f30da59f320123feb2c350d7ae12168c0a3", "planned_active_tokens": 66010, "realized_active_tokens": 66010, "cumulative_start": 52498444, "cumulative_end": 52564454, "loss_sum": 18464.382690429688, "token_normalized_loss": 0.2797209921289151, "grad_norm_before_clip": 0.15095944702625275, "learning_rates_at_step": { "lora": 8.653349015416057e-06, "row_tokens": 8.653349015416057e-06 }, "learning_rates_after_step": { "lora": 8.557559197220899e-06, "row_tokens": 8.557559197220899e-06 } }, { "update_id": 802, "row_count": 13, "row_ids_sha256": "0873728be5810c2d9e1d3b1df3d5cc0716a1167c0277fff2547c22ef90d6840a", "input_ids_vector_sha256": "6a34f1acbf9f5390a132ea8e24346852b77ffcfab561287c1b7636d3781445e7", "labels_vector_sha256": "837a06d23678ffa98f706d1997bd0020570ffbd16b29d0278a7b526dcf9dcdc1", "planned_active_tokens": 65408, "realized_active_tokens": 65408, "cumulative_start": 52564454, "cumulative_end": 52629862, "loss_sum": 20620.93685913086, "token_normalized_loss": 0.31526628025823844, "grad_norm_before_clip": 0.1584305316209793, "learning_rates_at_step": { "lora": 8.557559197220899e-06, "row_tokens": 8.557559197220899e-06 }, "learning_rates_after_step": { "lora": 8.466692096753842e-06, "row_tokens": 8.466692096753842e-06 } }, { "update_id": 803, "row_count": 17, "row_ids_sha256": "8636da7a6043666fe7c08f10c418482438e4405b849ad87ab6b2fd287ee72ed3", "input_ids_vector_sha256": "8362f311111fb720df25bbc36ce874b2b17d694c37b7dcfe5aec13acf82e7415", "labels_vector_sha256": "50dd5272c2a2d0b84808f0a1468fa7b6fef7281e728a2bb9847ed4346c8b1a97", "planned_active_tokens": 62354, "realized_active_tokens": 62354, "cumulative_start": 52629862, "cumulative_end": 52692216, "loss_sum": 15665.562957763672, "token_normalized_loss": 0.2512358943734752, "grad_norm_before_clip": 0.14050127565860748, "learning_rates_at_step": { "lora": 8.466692096753842e-06, "row_tokens": 8.466692096753842e-06 }, "learning_rates_after_step": { "lora": 8.3647490517688e-06, "row_tokens": 8.3647490517688e-06 } }, { "update_id": 804, "row_count": 18, "row_ids_sha256": "dff5a0c50ff81edb98d7dfe2b22e6d64e5b504b779d991608c555c1243673eb8", "input_ids_vector_sha256": "9ce2ae5aefe96431fd8eaf6ada29e35ee6403397d593afa728820973c8f26bc0", "labels_vector_sha256": "c37a371caba47d39283b1a4befb9e55032f0cdb31a12ed4eb550dcc9a6e81bf2", "planned_active_tokens": 70317, "realized_active_tokens": 70317, "cumulative_start": 52692216, "cumulative_end": 52762533, "loss_sum": 21464.61605834961, "token_normalized_loss": 0.3052550031763245, "grad_norm_before_clip": 0.14163395762443542, "learning_rates_at_step": { "lora": 8.3647490517688e-06, "row_tokens": 8.3647490517688e-06 }, "learning_rates_after_step": { "lora": 8.277399814843146e-06, "row_tokens": 8.277399814843146e-06 } }, { "update_id": 805, "row_count": 14, "row_ids_sha256": "35233694771643be86500c700ad3a617415ef627a0d71256e638b7d49ee9b741", "input_ids_vector_sha256": "19d939531efb1e80220becc21544e56ebd4d7a7c46345e1b13d4471a6638c0e8", "labels_vector_sha256": "26d5dbd43c34aae530313fb3f494d79e804d57cbf114ae632d7eb3e8a2434d98", "planned_active_tokens": 60561, "realized_active_tokens": 60561, "cumulative_start": 52762533, "cumulative_end": 52823094, "loss_sum": 20745.647674560547, "token_normalized_loss": 0.34255787841284896, "grad_norm_before_clip": 0.16567137837409973, "learning_rates_at_step": { "lora": 8.277399814843146e-06, "row_tokens": 8.277399814843146e-06 }, "learning_rates_after_step": { "lora": 8.184526078568627e-06, "row_tokens": 8.184526078568627e-06 } }, { "update_id": 806, "row_count": 16, "row_ids_sha256": "2c27ec21f12d3cab1f49a560d55aea8b8168baaf0cebc27c345d4946433d811b", "input_ids_vector_sha256": "d8d7555a85858f7cc126ac9a8e6bf451fa3e8d27a3ef9aeea80f0fdedf806324", "labels_vector_sha256": "5fb805e24ee74886511e8363c7fc87c10996853010aa62db1e46fd8e6181fae3", "planned_active_tokens": 64711, "realized_active_tokens": 64711, "cumulative_start": 52823094, "cumulative_end": 52887805, "loss_sum": 17749.749908447266, "token_normalized_loss": 0.2742926227140249, "grad_norm_before_clip": 0.14610996842384338, "learning_rates_at_step": { "lora": 8.184526078568627e-06, "row_tokens": 8.184526078568627e-06 }, "learning_rates_after_step": { "lora": 8.086811505641595e-06, "row_tokens": 8.086811505641595e-06 } }, { "update_id": 807, "row_count": 14, "row_ids_sha256": "39ea444a78b9f1e40769c904254119beb18646d75c74843428a2d1a4f31e8e3e", "input_ids_vector_sha256": "709c9c12ec2a8ae21c22f98f34059cf6fe35b3b9f7c1e5721315d035662a8857", "labels_vector_sha256": "f28fd65e2469b228200687ab81f7a1f85bb5694e637a6ebed1ad320dbb2d11fb", "planned_active_tokens": 68446, "realized_active_tokens": 68446, "cumulative_start": 52887805, "cumulative_end": 52956251, "loss_sum": 21415.26593017578, "token_normalized_loss": 0.312878267980244, "grad_norm_before_clip": 0.15306420624256134, "learning_rates_at_step": { "lora": 8.086811505641595e-06, "row_tokens": 8.086811505641595e-06 }, "learning_rates_after_step": { "lora": 7.996696207396064e-06, "row_tokens": 7.996696207396064e-06 } }, { "update_id": 808, "row_count": 13, "row_ids_sha256": "a259ff75a3b084f48008a48ad5e98516ba956657ab4ab7aa70e4beb109006d36", "input_ids_vector_sha256": "f4840b4a28cd5763899a1e639ee3a9e800eea8966437b22485b313d99f5df549", "labels_vector_sha256": "c73a77eef716306e13c7fa55cc58ad1b88768457d9246f8d97b2128b0b3a281b", "planned_active_tokens": 63458, "realized_active_tokens": 63458, "cumulative_start": 52956251, "cumulative_end": 53019709, "loss_sum": 21989.482208251953, "token_normalized_loss": 0.34652025289564675, "grad_norm_before_clip": 0.21037279069423676, "learning_rates_at_step": { "lora": 7.996696207396064e-06, "row_tokens": 7.996696207396064e-06 }, "learning_rates_after_step": { "lora": 7.904184605056276e-06, "row_tokens": 7.904184605056276e-06 } }, { "update_id": 809, "row_count": 10, "row_ids_sha256": "71f047774828524f49f073e6087842878d3f1d913a9c3c3c331ece4309335865", "input_ids_vector_sha256": "633bea76f13eeedad75f613e207046f0349939ff3a24769ba4e906d8ae0fdeeb", "labels_vector_sha256": "a290768586a8c0b34b2860643f1a41f319c0dd6c4a7ee8c610d6a6f9032b1059", "planned_active_tokens": 65486, "realized_active_tokens": 65486, "cumulative_start": 53019709, "cumulative_end": 53085195, "loss_sum": 25976.90936279297, "token_normalized_loss": 0.39667882238635693, "grad_norm_before_clip": 0.1603388488292694, "learning_rates_at_step": { "lora": 7.904184605056276e-06, "row_tokens": 7.904184605056276e-06 }, "learning_rates_after_step": { "lora": 7.81206719477084e-06, "row_tokens": 7.81206719477084e-06 } }, { "update_id": 810, "row_count": 10, "row_ids_sha256": "6fd90492b40a81f72b9804d39d0869ebb36a419a0ac6812845e35b5ea90b95bf", "input_ids_vector_sha256": "ded7a6c99a1cf2e72b59f616e19aa19ae08587f2f4ec07a75b04f1024b790c89", "labels_vector_sha256": "adfb58944e3e33fb0a362b9f837a1e894534583c0d7522aa8fc4a90c632faccb", "planned_active_tokens": 65556, "realized_active_tokens": 65556, "cumulative_start": 53085195, "cumulative_end": 53150751, "loss_sum": 24637.152954101562, "token_normalized_loss": 0.3758184293444012, "grad_norm_before_clip": 0.1607435792684555, "learning_rates_at_step": { "lora": 7.81206719477084e-06, "row_tokens": 7.81206719477084e-06 }, "learning_rates_after_step": { "lora": 7.716647780239744e-06, "row_tokens": 7.716647780239744e-06 } }, { "update_id": 811, "row_count": 13, "row_ids_sha256": "dcf5728d28773395ed75f67f9c4a2d46c49c01f7e221ce08ecee6c242a3f4016", "input_ids_vector_sha256": "71de22aa0c7bdb750ef3492ba778c05331d3d96e5feae13152ab8e26cd3ccc9b", "labels_vector_sha256": "2fc6d3e018a7b6afc1177f8af219593147901cc27eebf01c002863ce70875ee7", "planned_active_tokens": 68280, "realized_active_tokens": 68280, "cumulative_start": 53150751, "cumulative_end": 53219031, "loss_sum": 27125.55206298828, "token_normalized_loss": 0.39726936237534094, "grad_norm_before_clip": 0.15770860016345978, "learning_rates_at_step": { "lora": 7.716647780239744e-06, "row_tokens": 7.716647780239744e-06 }, "learning_rates_after_step": { "lora": 7.624997610198681e-06, "row_tokens": 7.624997610198681e-06 } }, { "update_id": 812, "row_count": 16, "row_ids_sha256": "65bb63d9159371222d16bab6a521dadc57852ac35d1d6773c8f1c3dd733a958d", "input_ids_vector_sha256": "68bbedd7090473828493652cb84b60839bb18ec0aa40feffe8d16aa143d8d1b2", "labels_vector_sha256": "35e940e2369a0bc7e481392d5a3102b84ed08f94c1be2bbbedf61744e053ab00", "planned_active_tokens": 65948, "realized_active_tokens": 65948, "cumulative_start": 53219031, "cumulative_end": 53284979, "loss_sum": 20061.958267211914, "token_normalized_loss": 0.3042087442714247, "grad_norm_before_clip": 0.16913187503814697, "learning_rates_at_step": { "lora": 7.624997610198681e-06, "row_tokens": 7.624997610198681e-06 }, "learning_rates_after_step": { "lora": 7.528740082304475e-06, "row_tokens": 7.528740082304475e-06 } }, { "update_id": 813, "row_count": 15, "row_ids_sha256": "1f25e59a80f028cf39399f8211ac892c43b5b21c186653df3f7cc72d94a9bed5", "input_ids_vector_sha256": "72fd498ea06d184b2e94f9295685a5e13148586b667f1803d039a2ef415bb8e8", "labels_vector_sha256": "a035bb722456a3cb24a0d58be2eb0bbd45f147591338701b5c7d7526685590bc", "planned_active_tokens": 69656, "realized_active_tokens": 69656, "cumulative_start": 53284979, "cumulative_end": 53354635, "loss_sum": 23720.816650390625, "token_normalized_loss": 0.3405423316066186, "grad_norm_before_clip": 0.14685188233852386, "learning_rates_at_step": { "lora": 7.528740082304475e-06, "row_tokens": 7.528740082304475e-06 }, "learning_rates_after_step": { "lora": 7.4474967775788605e-06, "row_tokens": 7.4474967775788605e-06 } }, { "update_id": 814, "row_count": 12, "row_ids_sha256": "5d11809c8ef43abad3a306ee91e31c3a6f7ce11e0fec7e4494744482cdae64e8", "input_ids_vector_sha256": "17f65275397122b71ede59517cdfb130b6262e2e1e4dd226f591fcaca12dcf45", "labels_vector_sha256": "8a41f46ebf2c799d7e9f97f282b3d954360683ba1fb32cf77e49e783e360827d", "planned_active_tokens": 59110, "realized_active_tokens": 59110, "cumulative_start": 53354635, "cumulative_end": 53413745, "loss_sum": 20364.428649902344, "token_normalized_loss": 0.3445174868871992, "grad_norm_before_clip": 0.16942541301250458, "learning_rates_at_step": { "lora": 7.4474967775788605e-06, "row_tokens": 7.4474967775788605e-06 }, "learning_rates_after_step": { "lora": 7.352089618313118e-06, "row_tokens": 7.352089618313118e-06 } }, { "update_id": 815, "row_count": 15, "row_ids_sha256": "544dabb96261c2cd27d5ed5914c4743c1e6dbc68c096561dacaed60afc7663ba", "input_ids_vector_sha256": "d168c939f5304934987626601765389ce9e61cb052e9857b7a3074125d386833", "labels_vector_sha256": "492f923d3ee667f97243b962f215bc29d6d9ae2fcc73794c8f122cdb1a52f83a", "planned_active_tokens": 69795, "realized_active_tokens": 69795, "cumulative_start": 53413745, "cumulative_end": 53483540, "loss_sum": 21966.624450683594, "token_normalized_loss": 0.3147306318602134, "grad_norm_before_clip": 0.14658188819885254, "learning_rates_at_step": { "lora": 7.352089618313118e-06, "row_tokens": 7.352089618313118e-06 }, "learning_rates_after_step": { "lora": 7.2643930249786055e-06, "row_tokens": 7.2643930249786055e-06 } }, { "update_id": 816, "row_count": 14, "row_ids_sha256": "7f60d0168e5f6364e312e65faf58777d4800cf8bb2cbe05055c8bb59fb650fe3", "input_ids_vector_sha256": "fcae4970d1d815f0aa168a45fd5c6c4de8d7e7678524b0220ed42d9e08636b36", "labels_vector_sha256": "38821855367b61224a18000a30c6cde9bf68c281bedf9bab35e46d1ab70b5d89", "planned_active_tokens": 64523, "realized_active_tokens": 64523, "cumulative_start": 53483540, "cumulative_end": 53548063, "loss_sum": 19804.759841918945, "token_normalized_loss": 0.30694108832383715, "grad_norm_before_clip": 0.14941944181919098, "learning_rates_at_step": { "lora": 7.2643930249786055e-06, "row_tokens": 7.2643930249786055e-06 }, "learning_rates_after_step": { "lora": 7.181077439904194e-06, "row_tokens": 7.181077439904194e-06 } }, { "update_id": 817, "row_count": 12, "row_ids_sha256": "e61347f51b43db71696b5483f95aa3d5721ff4882f9bdab6ff1b6a85bfff8d75", "input_ids_vector_sha256": "cc4ef0732bf792a2691bf9ba4d6046d7d02c811772aad1fa6b94501f9f8580ce", "labels_vector_sha256": "53c231eae55bf7bb20a82aaa87d7a50bf96db238e34656c4ba3daaca83cb9a1e", "planned_active_tokens": 61633, "realized_active_tokens": 61633, "cumulative_start": 53548063, "cumulative_end": 53609696, "loss_sum": 25662.204498291016, "token_normalized_loss": 0.41637117288288766, "grad_norm_before_clip": 0.1736212968826294, "learning_rates_at_step": { "lora": 7.181077439904194e-06, "row_tokens": 7.181077439904194e-06 }, "learning_rates_after_step": { "lora": 7.08934796508236e-06, "row_tokens": 7.08934796508236e-06 } }, { "update_id": 818, "row_count": 13, "row_ids_sha256": "a6e163c00f4c74dc5cd7334ca1b6e829ca79e8ecf520b7707e90c8cd52a297e1", "input_ids_vector_sha256": "e15550bd5d65d6bc67c1002d8742f16625ece2ca6a8ff212d9f43a5a19a83c71", "labels_vector_sha256": "2ac528cc20f55091a0bc4452c494c3b8bcc409b15b8b6c9d8f7acb88c859fd07", "planned_active_tokens": 68240, "realized_active_tokens": 68240, "cumulative_start": 53609696, "cumulative_end": 53677936, "loss_sum": 24010.60565185547, "token_normalized_loss": 0.3518552997047988, "grad_norm_before_clip": 0.15411022305488586, "learning_rates_at_step": { "lora": 7.08934796508236e-06, "row_tokens": 7.08934796508236e-06 }, "learning_rates_after_step": { "lora": 7.006893392785768e-06, "row_tokens": 7.006893392785768e-06 } }, { "update_id": 819, "row_count": 11, "row_ids_sha256": "b970a8a3006662ff568355cd4f8bfabab51b12ff8957af54b3b5d1a8cb97f732", "input_ids_vector_sha256": "6d8734530a3fa99fb722f41b74537c6c51c06a4e8c3396e6f41f426481888263", "labels_vector_sha256": "cd28ee7ae8c6750d897d32e7f99658253689365a42e7f21bb4e45c213ec9c312", "planned_active_tokens": 61689, "realized_active_tokens": 61689, "cumulative_start": 53677936, "cumulative_end": 53739625, "loss_sum": 20794.49722290039, "token_normalized_loss": 0.33708598328551914, "grad_norm_before_clip": 0.29595592617988586, "learning_rates_at_step": { "lora": 7.006893392785768e-06, "row_tokens": 7.006893392785768e-06 }, "learning_rates_after_step": { "lora": 6.919148185227742e-06, "row_tokens": 6.919148185227742e-06 } }, { "update_id": 820, "row_count": 12, "row_ids_sha256": "57c96ed3155e4ab9817e6b7bbacb9a315fcb018e3cbb38540a3af4879709fb79", "input_ids_vector_sha256": "e3a762512d4133bf967af1a1056331b76eca7c3334f847c26236671eef85a653", "labels_vector_sha256": "4d87a5aab6706d79f460f7e82f268dfab5e55e3cb71b75172f145793a1a83820", "planned_active_tokens": 66017, "realized_active_tokens": 66017, "cumulative_start": 53739625, "cumulative_end": 53805642, "loss_sum": 25036.20443725586, "token_normalized_loss": 0.3792387481596537, "grad_norm_before_clip": 0.16157786548137665, "learning_rates_at_step": { "lora": 6.919148185227742e-06, "row_tokens": 6.919148185227742e-06 }, "learning_rates_after_step": { "lora": 6.830804387695527e-06, "row_tokens": 6.830804387695527e-06 } }, { "update_id": 821, "row_count": 12, "row_ids_sha256": "faf916b47bd95e21f3b4f2af3707dde24efbd5015783df0532f3776ad48b18a0", "input_ids_vector_sha256": "b7c8df99c97d835fba5f66f96e7d1113d8e5912fae60f5874f1fded2e33006b5", "labels_vector_sha256": "0cdf82e80984c185cff57009965983f8a27399e610834d5e4e052e02dbaf930a", "planned_active_tokens": 66860, "realized_active_tokens": 66860, "cumulative_start": 53805642, "cumulative_end": 53872502, "loss_sum": 23100.842834472656, "token_normalized_loss": 0.34551066159845434, "grad_norm_before_clip": 0.15862016379833221, "learning_rates_at_step": { "lora": 6.830804387695527e-06, "row_tokens": 6.830804387695527e-06 }, "learning_rates_after_step": { "lora": 6.740221411258146e-06, "row_tokens": 6.740221411258146e-06 } }, { "update_id": 822, "row_count": 13, "row_ids_sha256": "09a1d0d6a89412f19b4f4a7630d25bc9da80c445300c47e07ecb5a098a3867f1", "input_ids_vector_sha256": "26911f2050692b9cfa1d012a07e69239f5cc38791f6b7778e47966d87fe6712b", "labels_vector_sha256": "2ee3c1b82a33ce1f8d99f54c4e36fcb808007f614d0117aedd8e214b16973f54", "planned_active_tokens": 68972, "realized_active_tokens": 68972, "cumulative_start": 53872502, "cumulative_end": 53941474, "loss_sum": 23495.700286865234, "token_normalized_loss": 0.34065563253008807, "grad_norm_before_clip": 0.1529323011636734, "learning_rates_at_step": { "lora": 6.740221411258146e-06, "row_tokens": 6.740221411258146e-06 }, "learning_rates_after_step": { "lora": 6.66062278444769e-06, "row_tokens": 6.66062278444769e-06 } }, { "update_id": 823, "row_count": 13, "row_ids_sha256": "d21c1c49bb3acb1538cebc6ebfe2f5d5a4e3e24d887f75f22469e3b5418ac79d", "input_ids_vector_sha256": "7af22d23dc92337776a038fb461efa084767d4931e21a6f43df970b229d0e8ee", "labels_vector_sha256": "27b926334bd46db522d98f5feca7d07210116512b3395c1c2a17adfdcb7b3168", "planned_active_tokens": 60964, "realized_active_tokens": 60964, "cumulative_start": 53941474, "cumulative_end": 54002438, "loss_sum": 22983.641708374023, "token_normalized_loss": 0.3770035054847783, "grad_norm_before_clip": 0.16452203691005707, "learning_rates_at_step": { "lora": 6.66062278444769e-06, "row_tokens": 6.66062278444769e-06 }, "learning_rates_after_step": { "lora": 6.572429508867395e-06, "row_tokens": 6.572429508867395e-06 } }, { "update_id": 824, "row_count": 12, "row_ids_sha256": "4c79225dfd42a65bc0549266d2c0b3e0351a9f5bc909bfd7453714bcef6f2449", "input_ids_vector_sha256": "a2a861430816b4ed6450cdde8e4ccea61f70d3456521a9c2af4ddbd1f8622cf8", "labels_vector_sha256": "715cf240135fc7509f4c7a3f5a13b388a5ddd3efdeb7b070756d23a5f9172302", "planned_active_tokens": 67943, "realized_active_tokens": 67943, "cumulative_start": 54002438, "cumulative_end": 54070381, "loss_sum": 24505.233154296875, "token_normalized_loss": 0.36067340497618405, "grad_norm_before_clip": 0.15543919801712036, "learning_rates_at_step": { "lora": 6.572429508867395e-06, "row_tokens": 6.572429508867395e-06 }, "learning_rates_after_step": { "lora": 6.482407932618906e-06, "row_tokens": 6.482407932618906e-06 } }, { "update_id": 825, "row_count": 15, "row_ids_sha256": "af18340c25d7aadc15cff6e47f0986492cfe27538664992af25911cb84a01955", "input_ids_vector_sha256": "8afcbf45b1d13deeda456aa9e9b2a7bb055d427495028a09a35b86eaa47e2156", "labels_vector_sha256": "f56bf9829f86ff678e918a07d957c32a1d6911e8a9cc2ca7e97a80633ce9d45e", "planned_active_tokens": 69790, "realized_active_tokens": 69790, "cumulative_start": 54070381, "cumulative_end": 54140171, "loss_sum": 23324.869995117188, "token_normalized_loss": 0.33421507372284265, "grad_norm_before_clip": 0.14609394967556, "learning_rates_at_step": { "lora": 6.482407932618906e-06, "row_tokens": 6.482407932618906e-06 }, "learning_rates_after_step": { "lora": 6.40358930756067e-06, "row_tokens": 6.40358930756067e-06 } }, { "update_id": 826, "row_count": 14, "row_ids_sha256": "32e166e7d556f3fab3e6d0b1f2558b429f587bb8f1bdb938b96c3c0238217137", "input_ids_vector_sha256": "a64e6da9bada7a8b73910d8466e7ecc6f256430e7866583d2054d9a736d98a1f", "labels_vector_sha256": "298e1ccdb1d0539412d1f2873832d69aa5482f1245f657065dea6009a708fa85", "planned_active_tokens": 61476, "realized_active_tokens": 61476, "cumulative_start": 54140171, "cumulative_end": 54201647, "loss_sum": 17634.185516357422, "token_normalized_loss": 0.28684666400477293, "grad_norm_before_clip": 0.14518745243549347, "learning_rates_at_step": { "lora": 6.40358930756067e-06, "row_tokens": 6.40358930756067e-06 }, "learning_rates_after_step": { "lora": 6.324158636641103e-06, "row_tokens": 6.324158636641103e-06 } }, { "update_id": 827, "row_count": 13, "row_ids_sha256": "59cae3bcf7bae837c379c4c21da722c9f8ae81bb43a45819702661f7ca02d5a0", "input_ids_vector_sha256": "3738df9e94708adea5e833985f17ed80acf0472901be16912508140b9bce5949", "labels_vector_sha256": "eb47b6284a2b036941b248af8aed56853be28772512d018340152063c99e7808", "planned_active_tokens": 62311, "realized_active_tokens": 62311, "cumulative_start": 54201647, "cumulative_end": 54263958, "loss_sum": 19885.473236083984, "token_normalized_loss": 0.319132628846977, "grad_norm_before_clip": 0.15686260163784027, "learning_rates_at_step": { "lora": 6.324158636641103e-06, "row_tokens": 6.324158636641103e-06 }, "learning_rates_after_step": { "lora": 6.238690718674883e-06, "row_tokens": 6.238690718674883e-06 } }, { "update_id": 828, "row_count": 15, "row_ids_sha256": "ef7b36ef6d2b19f4e898d937bd2540cc8e1ae36a5196b5e6e67a80ccb0710959", "input_ids_vector_sha256": "8a6d68d5931c8f602e285a485ce72bbafd98b620db6844eaed5e829697e18d27", "labels_vector_sha256": "a7e0aefb9f01395a6d19c27dacb732f988486d9e4ffc5d59522f219a84e42b7f", "planned_active_tokens": 67456, "realized_active_tokens": 67456, "cumulative_start": 54263958, "cumulative_end": 54331414, "loss_sum": 20790.954391479492, "token_normalized_loss": 0.3082150496839346, "grad_norm_before_clip": 0.14004965126514435, "learning_rates_at_step": { "lora": 6.238690718674883e-06, "row_tokens": 6.238690718674883e-06 }, "learning_rates_after_step": { "lora": 6.15468823332696e-06, "row_tokens": 6.15468823332696e-06 } }, { "update_id": 829, "row_count": 14, "row_ids_sha256": "aead79c5deeeb4fc22c643a760e8466a6930a94f2fc118a3ecd3f2e2d247fe32", "input_ids_vector_sha256": "8f9830913ef0ba97a31de532b8851d5809143a4f769d7345bea2373cd3b89062", "labels_vector_sha256": "fb88cc0529897c4b717e12c639ce119d66e157701634c6bfde05b08a6305fe61", "planned_active_tokens": 66721, "realized_active_tokens": 66721, "cumulative_start": 54331414, "cumulative_end": 54398135, "loss_sum": 22013.45001220703, "token_normalized_loss": 0.32993285490635677, "grad_norm_before_clip": 0.15490853786468506, "learning_rates_at_step": { "lora": 6.15468823332696e-06, "row_tokens": 6.15468823332696e-06 }, "learning_rates_after_step": { "lora": 6.071255431548906e-06, "row_tokens": 6.071255431548906e-06 } }, { "update_id": 830, "row_count": 14, "row_ids_sha256": "e33ed5936b84da9b16aa8282866e76881940151429d9eab4b04b8f76570734a4", "input_ids_vector_sha256": "64f067b3883e7c40ba64c320913fefffe6a5a3acb95e1a6440ac2c292f562ddd", "labels_vector_sha256": "0a914a67cc954e9c766a75fb4f7a6a449b3292f3274b600405ee65c7c8123ba3", "planned_active_tokens": 66691, "realized_active_tokens": 66691, "cumulative_start": 54398135, "cumulative_end": 54464826, "loss_sum": 19895.65838623047, "token_normalized_loss": 0.298325986808272, "grad_norm_before_clip": 0.14651483297348022, "learning_rates_at_step": { "lora": 6.071255431548906e-06, "row_tokens": 6.071255431548906e-06 }, "learning_rates_after_step": { "lora": 5.9907494975347255e-06, "row_tokens": 5.9907494975347255e-06 } }, { "update_id": 831, "row_count": 14, "row_ids_sha256": "b1fe6b16b224a0c1b206d6e28ba501e9aff8bff009d5c6be8b9d403a62216a7a", "input_ids_vector_sha256": "4f1ebce91fd2216337b8377da58f43317ef49bfa5e6de2a8914a0c8397c69724", "labels_vector_sha256": "21b366c68057a1146b90fcb9b097d32ea1768191eaad8122d916b7f6b6260899", "planned_active_tokens": 64759, "realized_active_tokens": 64759, "cumulative_start": 54464826, "cumulative_end": 54529585, "loss_sum": 18821.887100219727, "token_normalized_loss": 0.29064511651229524, "grad_norm_before_clip": 0.14874088764190674, "learning_rates_at_step": { "lora": 5.9907494975347255e-06, "row_tokens": 5.9907494975347255e-06 }, "learning_rates_after_step": { "lora": 5.911660672650715e-06, "row_tokens": 5.911660672650715e-06 } }, { "update_id": 832, "row_count": 14, "row_ids_sha256": "33b609397e141e65fe857b2c7ef48e551e5597d384183d98e5cad185e6ff6ee5", "input_ids_vector_sha256": "87c501f7caff5c67c9249e82a1acdc72a7be6b7fc63fc4ef7d67dcfac9523bb3", "labels_vector_sha256": "21160f9ebb6576b08c6b6288c361039b75d0e924ea624104394a25a71572b06f", "planned_active_tokens": 64017, "realized_active_tokens": 64017, "cumulative_start": 54529585, "cumulative_end": 54593602, "loss_sum": 18735.519744873047, "token_normalized_loss": 0.2926647569375798, "grad_norm_before_clip": 0.15052740275859833, "learning_rates_at_step": { "lora": 5.911660672650715e-06, "row_tokens": 5.911660672650715e-06 }, "learning_rates_after_step": { "lora": 5.830117801497509e-06, "row_tokens": 5.830117801497509e-06 } }, { "update_id": 833, "row_count": 13, "row_ids_sha256": "48268f7fdfc28f9112e7bd4894da882e9004e390adc5538dfb3ce06d08dc7db6", "input_ids_vector_sha256": "b9b3560ab728320a6c01be67e39408f6e075e682031e2d252ee188f49cc795a4", "labels_vector_sha256": "0414fb067f405921346ecdbb6f61f09da3e8c1c9ed0b44dce2c16db3952b7710", "planned_active_tokens": 66425, "realized_active_tokens": 66425, "cumulative_start": 54593602, "cumulative_end": 54660027, "loss_sum": 23432.801177978516, "token_normalized_loss": 0.35277081186267994, "grad_norm_before_clip": 0.156503826379776, "learning_rates_at_step": { "lora": 5.830117801497509e-06, "row_tokens": 5.830117801497509e-06 }, "learning_rates_after_step": { "lora": 5.752171273314105e-06, "row_tokens": 5.752171273314105e-06 } }, { "update_id": 834, "row_count": 14, "row_ids_sha256": "1842ae49a34c5969d29ad9109786caa07007c708836302b303de08775a2294f8", "input_ids_vector_sha256": "b043e79213426943618bf5ac4ec1b09e4e0903d2c2323940e09b48de46a7ab26", "labels_vector_sha256": "ebc1700bdead18cc25ccbac9efce49741907eacdb29e5c07f90fa6056b840b3c", "planned_active_tokens": 63904, "realized_active_tokens": 63904, "cumulative_start": 54660027, "cumulative_end": 54723931, "loss_sum": 22290.404724121094, "token_normalized_loss": 0.3488107899993912, "grad_norm_before_clip": 0.16447532176971436, "learning_rates_at_step": { "lora": 5.752171273314105e-06, "row_tokens": 5.752171273314105e-06 }, "learning_rates_after_step": { "lora": 5.6730539632055375e-06, "row_tokens": 5.6730539632055375e-06 } }, { "update_id": 835, "row_count": 14, "row_ids_sha256": "3646e7ebdba86753ca4ea5ec46516718a2ba64b8ac1d5e5d5f9db2b8372ca5b9", "input_ids_vector_sha256": "cda1834c2f6409eabc5137de863bea75fc0643fc3e468d30a82f2258e2de2494", "labels_vector_sha256": "957fa8d7c1e9abd6b993de1bca87d417718786126f4c1c12d4b250e918877bce", "planned_active_tokens": 65281, "realized_active_tokens": 65281, "cumulative_start": 54723931, "cumulative_end": 54789212, "loss_sum": 21353.195053100586, "token_normalized_loss": 0.32709662923516164, "grad_norm_before_clip": 0.1516164243221283, "learning_rates_at_step": { "lora": 5.6730539632055375e-06, "row_tokens": 5.6730539632055375e-06 }, "learning_rates_after_step": { "lora": 5.595206687498345e-06, "row_tokens": 5.595206687498345e-06 } }, { "update_id": 836, "row_count": 15, "row_ids_sha256": "19116d2226f602cd7b9cb24cea7fb8a587d2cd9ef9221c6f537b9b7fc7dd1067", "input_ids_vector_sha256": "a0dc28224470004002e6bccfa0ac9154fa71ef49b224e6f8dd8e4bf5a66107f8", "labels_vector_sha256": "5c41fac88e4d3042dc735f2ddc7ca742472c2490892d6fef1127f1f13869b40e", "planned_active_tokens": 64652, "realized_active_tokens": 64652, "cumulative_start": 54789212, "cumulative_end": 54853864, "loss_sum": 19415.913162231445, "token_normalized_loss": 0.3003141923255498, "grad_norm_before_clip": 0.14837297797203064, "learning_rates_at_step": { "lora": 5.595206687498345e-06, "row_tokens": 5.595206687498345e-06 }, "learning_rates_after_step": { "lora": 5.51367877997912e-06, "row_tokens": 5.51367877997912e-06 } }, { "update_id": 837, "row_count": 13, "row_ids_sha256": "64f0d0079c59b61afd0a50cbb9a7e34da1028fd87ed970459f419070e80bf51d", "input_ids_vector_sha256": "62aa4558ee8f3777c8e0b1c363ace6eff10dc397765b5f47f81936fa1809f568", "labels_vector_sha256": "32bb5499b33304a9064e7d56fed9bf5226842117a8b219a0c29349a6803b3a08", "planned_active_tokens": 68164, "realized_active_tokens": 68164, "cumulative_start": 54853864, "cumulative_end": 54922028, "loss_sum": 25144.383697509766, "token_normalized_loss": 0.36888069505178345, "grad_norm_before_clip": 0.15071064233779907, "learning_rates_at_step": { "lora": 5.51367877997912e-06, "row_tokens": 5.51367877997912e-06 }, "learning_rates_after_step": { "lora": 5.4328885362949335e-06, "row_tokens": 5.4328885362949335e-06 } }, { "update_id": 838, "row_count": 15, "row_ids_sha256": "882da889a0813529137f1beebb52a91130e3522f5d1619a6c5dc7706bdd9db3d", "input_ids_vector_sha256": "56771111216e65eb744e7abced53b2f72f05232e75751452bc2d392efa6c627a", "labels_vector_sha256": "dcf8224a39fd91c0eebd1071d4b40fec77a85b85e11a31b08780663255ce5ed4", "planned_active_tokens": 68017, "realized_active_tokens": 68017, "cumulative_start": 54922028, "cumulative_end": 54990045, "loss_sum": 21418.97479248047, "token_normalized_loss": 0.314906196869613, "grad_norm_before_clip": 0.15084034204483032, "learning_rates_at_step": { "lora": 5.4328885362949335e-06, "row_tokens": 5.4328885362949335e-06 }, "learning_rates_after_step": { "lora": 5.3587507048198755e-06, "row_tokens": 5.3587507048198755e-06 } }, { "update_id": 839, "row_count": 14, "row_ids_sha256": "ccd41209f55ad3ce53366c76b37005802a41f13474850cd69fae6d68c645974e", "input_ids_vector_sha256": "cef9d2cd5be4bf41ba25aafa6d4f28714ead0761d5afaa4986e65c69499b60be", "labels_vector_sha256": "d9774f80df1bb27fab0b8e9657f980f04e90342d811768c185159b8d7065ba9d", "planned_active_tokens": 62837, "realized_active_tokens": 62837, "cumulative_start": 54990045, "cumulative_end": 55052882, "loss_sum": 19997.692260742188, "token_normalized_loss": 0.3182470878740581, "grad_norm_before_clip": 0.16540805995464325, "learning_rates_at_step": { "lora": 5.3587507048198755e-06, "row_tokens": 5.3587507048198755e-06 }, "learning_rates_after_step": { "lora": 5.284620372032423e-06, "row_tokens": 5.284620372032423e-06 } }, { "update_id": 840, "row_count": 14, "row_ids_sha256": "046763ebfdbf8107d66d47d4a16259ecb9ee18414f4e04fc5589269775f4cc24", "input_ids_vector_sha256": "07eca24daf9a3e3e84dae4a939b6371cef1d2173400ffbb4c63091747939aef2", "labels_vector_sha256": "dd8815e8ee2cacdae01ba6264222bdd9462a90022cf3fe698db0fa1aab2ce532", "planned_active_tokens": 63242, "realized_active_tokens": 63242, "cumulative_start": 55052882, "cumulative_end": 55116124, "loss_sum": 20926.897338867188, "token_normalized_loss": 0.33090189018163857, "grad_norm_before_clip": 0.16162335872650146, "learning_rates_at_step": { "lora": 5.284620372032423e-06, "row_tokens": 5.284620372032423e-06 }, "learning_rates_after_step": { "lora": 5.205317798567055e-06, "row_tokens": 5.205317798567055e-06 } }, { "update_id": 841, "row_count": 12, "row_ids_sha256": "fe04ff2353953e2565a10066e00b62b580111815fc6250610398b257156be8e9", "input_ids_vector_sha256": "64325abea05ba91156a5c279a2b680e58d5a174547a3e408810c99eb216a35e4", "labels_vector_sha256": "61c4093533308ff02db2a64637d5a8a944a26d4ea90e7b16e798e3076982f861", "planned_active_tokens": 68120, "realized_active_tokens": 68120, "cumulative_start": 55116124, "cumulative_end": 55184244, "loss_sum": 23877.759338378906, "token_normalized_loss": 0.35052494624748837, "grad_norm_before_clip": 0.15500196814537048, "learning_rates_at_step": { "lora": 5.205317798567055e-06, "row_tokens": 5.205317798567055e-06 }, "learning_rates_after_step": { "lora": 5.1249433591421144e-06, "row_tokens": 5.1249433591421144e-06 } }, { "update_id": 842, "row_count": 13, "row_ids_sha256": "93ebedb2aef0e730919239a3008bd40525e9955f2b6eed3d2bc98e41ffdae65f", "input_ids_vector_sha256": "c1b7daf6e28a34ef3588d6012ee9081bd298d61ded6210a874d6b642a3223d43", "labels_vector_sha256": "ec0545d738976591b1398385e17b2dc08e53bf0d7bb39d886f277680b1c4452d", "planned_active_tokens": 69543, "realized_active_tokens": 69543, "cumulative_start": 55184244, "cumulative_end": 55253787, "loss_sum": 24316.030960083008, "token_normalized_loss": 0.34965461599417635, "grad_norm_before_clip": 0.17362810671329498, "learning_rates_at_step": { "lora": 5.1249433591421144e-06, "row_tokens": 5.1249433591421144e-06 }, "learning_rates_after_step": { "lora": 5.054673452757524e-06, "row_tokens": 5.054673452757524e-06 } }, { "update_id": 843, "row_count": 14, "row_ids_sha256": "6c56019495f3289e66e64f2b5ea494838103872b48ca4bc30e611073b814665d", "input_ids_vector_sha256": "de4410140244ed0905536fa458f2062ab322faa1973f4c9fc90512a3e8e5ffc2", "labels_vector_sha256": "a095bae60c0c250cbd3363ccd14c3f975551094e6c78d973387736501c5838c3", "planned_active_tokens": 61224, "realized_active_tokens": 61224, "cumulative_start": 55253787, "cumulative_end": 55315011, "loss_sum": 20050.454040527344, "token_normalized_loss": 0.3274933692755675, "grad_norm_before_clip": 0.15566372871398926, "learning_rates_at_step": { "lora": 5.054673452757524e-06, "row_tokens": 5.054673452757524e-06 }, "learning_rates_after_step": { "lora": 4.978798129750528e-06, "row_tokens": 4.978798129750528e-06 } }, { "update_id": 844, "row_count": 15, "row_ids_sha256": "f0cb388c1c8da73d1fb4733750533b89b77dab2879459cd200cf352b463d5e3b", "input_ids_vector_sha256": "cc71c6b7e1d51ddff76f2db2b21e3913e8c86f1abbb4c55d5d903d0f3407c780", "labels_vector_sha256": "c3828401e2387dae637700bffb996ec2e85bfb3d3ef365204525e4ebadebcf2d", "planned_active_tokens": 66562, "realized_active_tokens": 66562, "cumulative_start": 55315011, "cumulative_end": 55381573, "loss_sum": 22692.72283935547, "token_normalized_loss": 0.3409260965619343, "grad_norm_before_clip": 0.1666572540998459, "learning_rates_at_step": { "lora": 4.978798129750528e-06, "row_tokens": 4.978798129750528e-06 }, "learning_rates_after_step": { "lora": 4.908382248992177e-06, "row_tokens": 4.908382248992177e-06 } }, { "update_id": 845, "row_count": 11, "row_ids_sha256": "7b969792c6c2364cfbc8356da99eadca767c7f3f1e4b797e3da0f2c413c04f93", "input_ids_vector_sha256": "732577834ceeb0c5233179c8b5f0a402832e53caad9298cfd26ad6e7edc51217", "labels_vector_sha256": "512eafd1a6a28806f994aead349f041a0ba9f2b26b13c3b70c1625a39ce31855", "planned_active_tokens": 62204, "realized_active_tokens": 62204, "cumulative_start": 55381573, "cumulative_end": 55443777, "loss_sum": 19809.405853271484, "token_normalized_loss": 0.31845871412242754, "grad_norm_before_clip": 0.1558884084224701, "learning_rates_at_step": { "lora": 4.908382248992177e-06, "row_tokens": 4.908382248992177e-06 }, "learning_rates_after_step": { "lora": 4.834521032731537e-06, "row_tokens": 4.834521032731537e-06 } }, { "update_id": 846, "row_count": 14, "row_ids_sha256": "24d104bddd25c3d5e580fc470ba310b4b3abcc80b53f07d07995eaed90648a56", "input_ids_vector_sha256": "2098d0c21d1c7a726bc917c7d423b345587807524aeee1f3993cd6e38471220f", "labels_vector_sha256": "1d7e83718f9193ef3729620250ffbca26a3c3e5082cc288b6007ebace9420bdc", "planned_active_tokens": 65704, "realized_active_tokens": 65704, "cumulative_start": 55443777, "cumulative_end": 55509481, "loss_sum": 19787.774291992188, "token_normalized_loss": 0.30116544338232354, "grad_norm_before_clip": 0.1446978896856308, "learning_rates_at_step": { "lora": 4.834521032731537e-06, "row_tokens": 4.834521032731537e-06 }, "learning_rates_after_step": { "lora": 4.758210678200681e-06, "row_tokens": 4.758210678200681e-06 } }, { "update_id": 847, "row_count": 15, "row_ids_sha256": "417f343b470c1f60226d3a9254c082f7ef233ae6314506329ceac92bbbc834e8", "input_ids_vector_sha256": "baa7d9e2bf2735e244bfb9b27863acc0fb578f54c9d70f782839a5eadaebf11c", "labels_vector_sha256": "7b8df0719579aea2a792e29039ce1d4bb716600e16f3ca78c5e3c356d3934f46", "planned_active_tokens": 68385, "realized_active_tokens": 68385, "cumulative_start": 55509481, "cumulative_end": 55577866, "loss_sum": 24299.596252441406, "token_normalized_loss": 0.3553351795341289, "grad_norm_before_clip": 0.15433338284492493, "learning_rates_at_step": { "lora": 4.758210678200681e-06, "row_tokens": 4.758210678200681e-06 }, "learning_rates_after_step": { "lora": 4.687242197679365e-06, "row_tokens": 4.687242197679365e-06 } }, { "update_id": 848, "row_count": 16, "row_ids_sha256": "cb6061762e2db54cb5273a2acb8b9b3e78ed0466fa304cb7c80526bc26ddfdf1", "input_ids_vector_sha256": "520bfb69c4b7c9e4e660bd90cca6e6bbe51827ffe7e6bbcfbf9bdfb73e4c8a19", "labels_vector_sha256": "233a323d2bea2b278c80f8ba1f44f94ce81d61dd62f4540d63121896720775aa", "planned_active_tokens": 64067, "realized_active_tokens": 64067, "cumulative_start": 55577866, "cumulative_end": 55641933, "loss_sum": 20233.36801147461, "token_normalized_loss": 0.3158157555601887, "grad_norm_before_clip": 0.15656372904777527, "learning_rates_at_step": { "lora": 4.687242197679365e-06, "row_tokens": 4.687242197679365e-06 }, "learning_rates_after_step": { "lora": 4.615780458316715e-06, "row_tokens": 4.615780458316715e-06 } }, { "update_id": 849, "row_count": 15, "row_ids_sha256": "53408b465bc6a36555e628052270582c2ecc0d941d3329b855623d017847d6f9", "input_ids_vector_sha256": "ffcc82f9f219f269172c02ee82d15c19907a71ee2bd3f011f686a8dd80011f2b", "labels_vector_sha256": "4579577c748295fa71cedbfd1611cd79dfcf7f1b14c4e69b78478454f0eea8ed", "planned_active_tokens": 64980, "realized_active_tokens": 64980, "cumulative_start": 55641933, "cumulative_end": 55706913, "loss_sum": 19397.615493774414, "token_normalized_loss": 0.2985167050442354, "grad_norm_before_clip": 0.14774297177791595, "learning_rates_at_step": { "lora": 4.615780458316715e-06, "row_tokens": 4.615780458316715e-06 }, "learning_rates_after_step": { "lora": 4.5431468368090755e-06, "row_tokens": 4.5431468368090755e-06 } }, { "update_id": 850, "row_count": 17, "row_ids_sha256": "9af430fce3b846fcf8e243f86b6eb3b037562f9b1ff99fffe99e294805669b8c", "input_ids_vector_sha256": "014bd6829681ac366368ed269e3f4194b1b0c72918433bc99794d8423e18c8f3", "labels_vector_sha256": "a451318e502f23635744ce5ab8f38aaf74a99bc17b4550bab1bcd4891a37492d", "planned_active_tokens": 66538, "realized_active_tokens": 66538, "cumulative_start": 55706913, "cumulative_end": 55773451, "loss_sum": 22869.619140625, "token_normalized_loss": 0.343707642860095, "grad_norm_before_clip": 0.153206467628479, "learning_rates_at_step": { "lora": 4.5431468368090755e-06, "row_tokens": 4.5431468368090755e-06 }, "learning_rates_after_step": { "lora": 4.471073900008338e-06, "row_tokens": 4.471073900008338e-06 } }, { "update_id": 851, "row_count": 17, "row_ids_sha256": "88819eb7dd21701e8b301ec8bf6ae4b79346f7ec261a2e467615de12bbaf1de9", "input_ids_vector_sha256": "75ae89f808f58adb8e4d03bc179bbee5c23084c7f43133e341d48430f04248da", "labels_vector_sha256": "ae5857ebb101f6e7e526dbec93362200d6281999787b560cd9fee321b6aa7ceb", "planned_active_tokens": 66527, "realized_active_tokens": 66527, "cumulative_start": 55773451, "cumulative_end": 55839978, "loss_sum": 18604.869735717773, "token_normalized_loss": 0.27965893149725335, "grad_norm_before_clip": 0.14493118226528168, "learning_rates_at_step": { "lora": 4.471073900008338e-06, "row_tokens": 4.471073900008338e-06 }, "learning_rates_after_step": { "lora": 4.4022004241559276e-06, "row_tokens": 4.4022004241559276e-06 } }, { "update_id": 852, "row_count": 18, "row_ids_sha256": "1c48a79d565e3e5530c025bbbf90f0b2bf0b714cc0f103e9ea51edf0a7a65bf9", "input_ids_vector_sha256": "f97219f189847807749210eaa6d2a9474117e071d6488c9f2276954fa98be0bf", "labels_vector_sha256": "35ec447f5b154e198e14723bdb21263571dbc5b25a85c0f15004dbf5b87d530e", "planned_active_tokens": 64053, "realized_active_tokens": 64053, "cumulative_start": 55839978, "cumulative_end": 55904031, "loss_sum": 17753.776428222656, "token_normalized_loss": 0.27717322261600014, "grad_norm_before_clip": 0.15781883895397186, "learning_rates_at_step": { "lora": 4.4022004241559276e-06, "row_tokens": 4.4022004241559276e-06 }, "learning_rates_after_step": { "lora": 4.330126929206918e-06, "row_tokens": 4.330126929206918e-06 } }, { "update_id": 853, "row_count": 14, "row_ids_sha256": "ac37466a30fbbe0412dce3fe571d83574d656d144ece60b4a06e61b428500b58", "input_ids_vector_sha256": "25458c2129c0879daf80db56fe94f2da1b8c1787dbf465b78b2d9a6398a909fb", "labels_vector_sha256": "93b8a0012601b28daf4c823988d573acac4dfe0a943420f47b640a390475b212", "planned_active_tokens": 67543, "realized_active_tokens": 67543, "cumulative_start": 55904031, "cumulative_end": 55971574, "loss_sum": 23065.414916992188, "token_normalized_loss": 0.34149230737444575, "grad_norm_before_clip": 0.15332232415676117, "learning_rates_at_step": { "lora": 4.330126929206918e-06, "row_tokens": 4.330126929206918e-06 }, "learning_rates_after_step": { "lora": 4.261748604064786e-06, "row_tokens": 4.261748604064786e-06 } }, { "update_id": 854, "row_count": 14, "row_ids_sha256": "c426434d30162d6fe58f08f4a37592fb6f9d0527f97fa25631005d9b4074ee8e", "input_ids_vector_sha256": "b8563b469902bbdd9116e712fe8932f9790e8159edadfff15e494268dc8d20bb", "labels_vector_sha256": "9f22af67b8227705176f8263353ee6ef1483b2b284f79d01bd093c09a2738f17", "planned_active_tokens": 64578, "realized_active_tokens": 64578, "cumulative_start": 55971574, "cumulative_end": 56036152, "loss_sum": 19707.123321533203, "token_normalized_loss": 0.30516775560613835, "grad_norm_before_clip": 0.15438812971115112, "learning_rates_at_step": { "lora": 4.261748604064786e-06, "row_tokens": 4.261748604064786e-06 }, "learning_rates_after_step": { "lora": 4.194342648937966e-06, "row_tokens": 4.194342648937966e-06 } }, { "update_id": 855, "row_count": 14, "row_ids_sha256": "2d16bf2063b9a4aa0d6ad1d866c333103de9d083bd8bf9a41870cd732b374613", "input_ids_vector_sha256": "055e4e643ebb1c253f0cc69770690c9913671b8dfad98098df62680d77bccd6c", "labels_vector_sha256": "67d92e727464f067ef771097eae074da071407a7d5291c77318baec044c82338", "planned_active_tokens": 64146, "realized_active_tokens": 64146, "cumulative_start": 56036152, "cumulative_end": 56100298, "loss_sum": 20963.38543701172, "token_normalized_loss": 0.32680736814472794, "grad_norm_before_clip": 0.15759171545505524, "learning_rates_at_step": { "lora": 4.194342648937966e-06, "row_tokens": 4.194342648937966e-06 }, "learning_rates_after_step": { "lora": 4.122987072640505e-06, "row_tokens": 4.122987072640505e-06 } }, { "update_id": 856, "row_count": 18, "row_ids_sha256": "8f77f02207522c28c1b5ab80004a83034532af3de7e7ec3ced5cfd57869702f5", "input_ids_vector_sha256": "dcc820be7f8b04c76e504b16f106de56fb85e05f6d1711d4ac2a2f8174ae67c7", "labels_vector_sha256": "c2d1f61bb920b6506d81a0009b7746fc038048cda9af2562d31701924d321ec3", "planned_active_tokens": 68444, "realized_active_tokens": 68444, "cumulative_start": 56100298, "cumulative_end": 56168742, "loss_sum": 18559.722381591797, "token_normalized_loss": 0.2711665358773859, "grad_norm_before_clip": 0.14155472815036774, "learning_rates_at_step": { "lora": 4.122987072640505e-06, "row_tokens": 4.122987072640505e-06 }, "learning_rates_after_step": { "lora": 4.058809126465391e-06, "row_tokens": 4.058809126465391e-06 } }, { "update_id": 857, "row_count": 11, "row_ids_sha256": "1eed3aa2c9e1eb20c0b8219c5add438ca695980c2b1ef0f6fac44a4723751446", "input_ids_vector_sha256": "1f28909ae60351311ec85c83897db0077950f40bd0de58d64a5c2302ce503cb0", "labels_vector_sha256": "2fac9a3ac64214bf1d9be8899b4f4247defe88d8ae1747b89613201ac6f50326", "planned_active_tokens": 62045, "realized_active_tokens": 62045, "cumulative_start": 56168742, "cumulative_end": 56230787, "loss_sum": 22475.192291259766, "token_normalized_loss": 0.36224018520847395, "grad_norm_before_clip": 0.16057555377483368, "learning_rates_at_step": { "lora": 4.058809126465391e-06, "row_tokens": 4.058809126465391e-06 }, "learning_rates_after_step": { "lora": 3.989230842528158e-06, "row_tokens": 3.989230842528158e-06 } }, { "update_id": 858, "row_count": 16, "row_ids_sha256": "2759e632f860a0d5f5855f1337caf1b7c8fcd85dead18aee5afa5fa3c4ff3611", "input_ids_vector_sha256": "cbb21b9e9eea3709bb44fb5e884a8227ab8bc7eeffd5b77e7593a8f3a5fd8e1e", "labels_vector_sha256": "0b3441b02c926e2e495fd1595bae7e9de0650431e59217166520aad6814a36fb", "planned_active_tokens": 67799, "realized_active_tokens": 67799, "cumulative_start": 56230787, "cumulative_end": 56298586, "loss_sum": 20073.821014404297, "token_normalized_loss": 0.29607842319804567, "grad_norm_before_clip": 0.15502308309078217, "learning_rates_at_step": { "lora": 3.989230842528158e-06, "row_tokens": 3.989230842528158e-06 }, "learning_rates_after_step": { "lora": 3.922980358766698e-06, "row_tokens": 3.922980358766698e-06 } }, { "update_id": 859, "row_count": 17, "row_ids_sha256": "bb37ff10d62aab3f5a36f6eba9cc171ba6f24ec2397190b691ceb2e454d1f897", "input_ids_vector_sha256": "3fb70bd567111cd72ead69bf40c92a153a7d5977cfad7b6916028dfc437c28e9", "labels_vector_sha256": "3efff61d75e5456006d91a9ea6d1406df8978a8ca2db3292011736b5e5b0ecee", "planned_active_tokens": 65085, "realized_active_tokens": 65085, "cumulative_start": 56298586, "cumulative_end": 56363671, "loss_sum": 19540.902069091797, "token_normalized_loss": 0.3002366454496704, "grad_norm_before_clip": 0.20616395771503448, "learning_rates_at_step": { "lora": 3.922980358766698e-06, "row_tokens": 3.922980358766698e-06 }, "learning_rates_after_step": { "lora": 3.858526328817919e-06, "row_tokens": 3.858526328817919e-06 } }, { "update_id": 860, "row_count": 13, "row_ids_sha256": "efad7d4d3704e4217e0e4591885e65ae542a57141629ea10f829d176ecb6c185", "input_ids_vector_sha256": "b3bad7bf3701d2872ea08a74e8bb5aa13dfc09e9d8d78cc0123aef1f90e80cb7", "labels_vector_sha256": "eeeb8eb2215f008f1ee3567b793e1fd6cccaa690b62d70cdda95025c3efa416c", "planned_active_tokens": 63828, "realized_active_tokens": 63828, "cumulative_start": 56363671, "cumulative_end": 56427499, "loss_sum": 20909.45881652832, "token_normalized_loss": 0.32759069399837565, "grad_norm_before_clip": 0.16083881258964539, "learning_rates_at_step": { "lora": 3.858526328817919e-06, "row_tokens": 3.858526328817919e-06 }, "learning_rates_after_step": { "lora": 3.791984198460735e-06, "row_tokens": 3.791984198460735e-06 } }, { "update_id": 861, "row_count": 14, "row_ids_sha256": "5838e9a99bd3865ea306317a0aa0768388aa46f8f1db738da81f29cf13a7d41b", "input_ids_vector_sha256": "4edf846ae3eda6f9d329f589ebc8a8da2899c873666ac30f863681c0787efbaf", "labels_vector_sha256": "30254cbbdc4aebb8f7dd17efb16922f863c9549cf58eac8f6c4ea1094278ec24", "planned_active_tokens": 66435, "realized_active_tokens": 66435, "cumulative_start": 56427499, "cumulative_end": 56493934, "loss_sum": 18480.779388427734, "token_normalized_loss": 0.2781783606296039, "grad_norm_before_clip": 0.1439991593360901, "learning_rates_at_step": { "lora": 3.791984198460735e-06, "row_tokens": 3.791984198460735e-06 }, "learning_rates_after_step": { "lora": 3.726056578618453e-06, "row_tokens": 3.726056578618453e-06 } }, { "update_id": 862, "row_count": 15, "row_ids_sha256": "1bb6e96439117821289cbb98b3bd10c6df536dda205b512c238de8f9e4b2c7a6", "input_ids_vector_sha256": "8c492a417fccce9244b0a8cab64a7474abd5a54cf0dead73dc37e49f41455b66", "labels_vector_sha256": "13344bd45810cf939519ff5407cf0f2b6569bb5519536471b4048bdd5cd0a5d3", "planned_active_tokens": 66376, "realized_active_tokens": 66376, "cumulative_start": 56493934, "cumulative_end": 56560310, "loss_sum": 19287.159088134766, "token_normalized_loss": 0.290574290227413, "grad_norm_before_clip": 0.1532766968011856, "learning_rates_at_step": { "lora": 3.726056578618453e-06, "row_tokens": 3.726056578618453e-06 }, "learning_rates_after_step": { "lora": 3.6624670184323583e-06, "row_tokens": 3.6624670184323583e-06 } }, { "update_id": 863, "row_count": 13, "row_ids_sha256": "55c98bcf2b20bc43dc540ab77e7f0321195d29dee3d9bb11f0d77fe9047c7c76", "input_ids_vector_sha256": "5a1a233dcfebecf005ed1bb8a0c11488969dde8ce4d9d6cc17797251e7fa1be8", "labels_vector_sha256": "d45bee33a03b2c3e9a093b17b74073ac20576e39c6d15cdc4c15c3253c83d245", "planned_active_tokens": 64559, "realized_active_tokens": 64559, "cumulative_start": 56560310, "cumulative_end": 56624869, "loss_sum": 19595.856216430664, "token_normalized_loss": 0.30353407296319124, "grad_norm_before_clip": 0.15065442025661469, "learning_rates_at_step": { "lora": 3.6624670184323583e-06, "row_tokens": 3.6624670184323583e-06 }, "learning_rates_after_step": { "lora": 3.5946576682963584e-06, "row_tokens": 3.5946576682963584e-06 } }, { "update_id": 864, "row_count": 19, "row_ids_sha256": "603eda0bdc8d8798ae680f6e36579c2ca78cc317b0ae1cbdd6d56d4110cc7b5c", "input_ids_vector_sha256": "975841e98500f3eab74d22a1c95fd001a6f8326cd8027e1b0c6d41a997ef5f9b", "labels_vector_sha256": "efdd2463584f1affddfa66674b47661b9d90c756a618b3348af6b07c0e9539f2", "planned_active_tokens": 69440, "realized_active_tokens": 69440, "cumulative_start": 56624869, "cumulative_end": 56694309, "loss_sum": 18095.981048583984, "token_normalized_loss": 0.26059880542315644, "grad_norm_before_clip": 0.1426154524087906, "learning_rates_at_step": { "lora": 3.5946576682963584e-06, "row_tokens": 3.5946576682963584e-06 }, "learning_rates_after_step": { "lora": 3.5321042140953275e-06, "row_tokens": 3.5321042140953275e-06 } }, { "update_id": 865, "row_count": 15, "row_ids_sha256": "b928a77b98b891090a9a3998acef7c7e6efa064284b0f081e3d8b441e42b7d04", "input_ids_vector_sha256": "2a8ad075401bb908f65adc5821eae4d3239f9ea70990dfe2078c744217781a0b", "labels_vector_sha256": "6283ac8fc2563b31f3451477d2a0be82b58ac6944204e35995d9c55335421e5c", "planned_active_tokens": 64619, "realized_active_tokens": 64619, "cumulative_start": 56694309, "cumulative_end": 56758928, "loss_sum": 20458.678955078125, "token_normalized_loss": 0.3166046976133664, "grad_norm_before_clip": 0.30811411142349243, "learning_rates_at_step": { "lora": 3.5321042140953275e-06, "row_tokens": 3.5321042140953275e-06 }, "learning_rates_after_step": { "lora": 3.4732833124321294e-06, "row_tokens": 3.4732833124321294e-06 } }, { "update_id": 866, "row_count": 15, "row_ids_sha256": "01ca54bf461543a54a15fedff96b26436f26d2349d3e525bac8159801468d98c", "input_ids_vector_sha256": "fa45c3ad3b29fbf1599bd593365b0fc03a531a149b268c1aa9ea7cf80be59ee1", "labels_vector_sha256": "c28f33a35634499aff209220baa74a5eccdee2d2f48fef9e80785b34cfd2c75b", "planned_active_tokens": 61268, "realized_active_tokens": 61268, "cumulative_start": 56758928, "cumulative_end": 56820196, "loss_sum": 17921.813110351562, "token_normalized_loss": 0.29251506676163025, "grad_norm_before_clip": 0.1541283279657364, "learning_rates_at_step": { "lora": 3.4732833124321294e-06, "row_tokens": 3.4732833124321294e-06 }, "learning_rates_after_step": { "lora": 3.410371736222118e-06, "row_tokens": 3.410371736222118e-06 } }, { "update_id": 867, "row_count": 16, "row_ids_sha256": "72c381dab6a9a79c9f949eeece62b70dc89c00021126cbb3b6e735e130faac5f", "input_ids_vector_sha256": "860b3d0103b5448692ceaeda9d75834b6612e29ba6abba0220ff3c5a01be2151", "labels_vector_sha256": "9e4b2962a13ab0e7be0b633819abd97d01c54d801c463dac4b1deed6cc807964", "planned_active_tokens": 66085, "realized_active_tokens": 66085, "cumulative_start": 56820196, "cumulative_end": 56886281, "loss_sum": 18454.54493713379, "token_normalized_loss": 0.279254671062023, "grad_norm_before_clip": 0.1493796557188034, "learning_rates_at_step": { "lora": 3.410371736222118e-06, "row_tokens": 3.410371736222118e-06 }, "learning_rates_after_step": { "lora": 3.344085756814941e-06, "row_tokens": 3.344085756814941e-06 } }, { "update_id": 868, "row_count": 15, "row_ids_sha256": "79e5f93bf9d78aa177bc4b166507d01ef7eab67acffbf49c8efe142422117850", "input_ids_vector_sha256": "58e810fd02d228864773a0eee492f75a014db87188e0c382a8a0797229a4cd78", "labels_vector_sha256": "bef933449117ac79d9d69e9f8490a9a54e1aed349dc3d4ca68cd58fcdff754f2", "planned_active_tokens": 70269, "realized_active_tokens": 70269, "cumulative_start": 56886281, "cumulative_end": 56956550, "loss_sum": 18817.46337890625, "token_normalized_loss": 0.2677918197057913, "grad_norm_before_clip": 0.1377699226140976, "learning_rates_at_step": { "lora": 3.344085756814941e-06, "row_tokens": 3.344085756814941e-06 }, "learning_rates_after_step": { "lora": 3.2876617064532267e-06, "row_tokens": 3.2876617064532267e-06 } }, { "update_id": 869, "row_count": 12, "row_ids_sha256": "8c77723019ab698d02b287c92b06461a0d6a63f1520a8bbbf94574da70f4a1c4", "input_ids_vector_sha256": "a05a2a0ad7cd30afda61cf934e046e76084e2a29835357c1cef1048e391bd10d", "labels_vector_sha256": "ea2bef48ec086fc845cbc861260a1b960a8c9faa4dba905134753c3a363a02a0", "planned_active_tokens": 60346, "realized_active_tokens": 60346, "cumulative_start": 56956550, "cumulative_end": 57016896, "loss_sum": 19906.038818359375, "token_normalized_loss": 0.3298650916110326, "grad_norm_before_clip": 0.15885183215141296, "learning_rates_at_step": { "lora": 3.2876617064532267e-06, "row_tokens": 3.2876617064532267e-06 }, "learning_rates_after_step": { "lora": 3.226133463590214e-06, "row_tokens": 3.226133463590214e-06 } }, { "update_id": 870, "row_count": 17, "row_ids_sha256": "38456465a7d8c9beac91c1a5f5dfc7eef708013ffc4d28be84b10c7dd99aa1c4", "input_ids_vector_sha256": "6b557d7175336fa21d9b3801e4cd75f2db08d21fd5198da735a88b33eeacdb07", "labels_vector_sha256": "75ac811076bc877644136780d03cde05e265b3656438acca92b0c40ed32e266e", "planned_active_tokens": 66378, "realized_active_tokens": 66378, "cumulative_start": 57016896, "cumulative_end": 57083274, "loss_sum": 19521.024658203125, "token_normalized_loss": 0.29408877426561697, "grad_norm_before_clip": 0.1495279222726822, "learning_rates_at_step": { "lora": 3.226133463590214e-06, "row_tokens": 3.226133463590214e-06 }, "learning_rates_after_step": { "lora": 3.1662589078419293e-06, "row_tokens": 3.1662589078419293e-06 } }, { "update_id": 871, "row_count": 16, "row_ids_sha256": "5fde859a1eeca790ac83e12680cc3cbf48e55f766f08a0f7b237869d0cfa8cfc", "input_ids_vector_sha256": "99bce3482eebda9723be94be9cbfcc6a1fe522057820c900c6756ecdcbd76feb", "labels_vector_sha256": "45ec4c406a02e8bba3a2b7ed07a8fe49ede69e7e34d9ff19d0fd9907f732d472", "planned_active_tokens": 65184, "realized_active_tokens": 65184, "cumulative_start": 57083274, "cumulative_end": 57148458, "loss_sum": 21276.764190673828, "token_normalized_loss": 0.3264108399403815, "grad_norm_before_clip": 0.15840370953083038, "learning_rates_at_step": { "lora": 3.1662589078419293e-06, "row_tokens": 3.1662589078419293e-06 }, "learning_rates_after_step": { "lora": 3.1061297309219194e-06, "row_tokens": 3.1061297309219194e-06 } }, { "update_id": 872, "row_count": 17, "row_ids_sha256": "33ca9dea51587626e1756d6c412e83bd49b41d9e41fa5c812ecf3500f75a85aa", "input_ids_vector_sha256": "c0702ef210c546e73586556a1a38d6cac5ed79be989176026e3ab4700f8c0f51", "labels_vector_sha256": "a68325fe67c3a274f947faaa415142a7bfd4f6a3132cbe85c361c005004fc326", "planned_active_tokens": 66064, "realized_active_tokens": 66064, "cumulative_start": 57148458, "cumulative_end": 57214522, "loss_sum": 19095.091339111328, "token_normalized_loss": 0.28903928522510486, "grad_norm_before_clip": 0.1468992680311203, "learning_rates_at_step": { "lora": 3.1061297309219194e-06, "row_tokens": 3.1061297309219194e-06 }, "learning_rates_after_step": { "lora": 3.0469867960666032e-06, "row_tokens": 3.0469867960666032e-06 } }, { "update_id": 873, "row_count": 17, "row_ids_sha256": "8aaa2b1c728474b7c3f8b10055458f153a1664f3b4eba16ef61b5980ca009824", "input_ids_vector_sha256": "9d028ff6af862f6b292d97deaa267603099dd2f227b25dd6d259824e6a77b71e", "labels_vector_sha256": "0f2f28032a3d8116c9e87cea073de96952001f302c43511d0e187ed94facaf51", "planned_active_tokens": 65587, "realized_active_tokens": 65587, "cumulative_start": 57214522, "cumulative_end": 57280109, "loss_sum": 19699.43701171875, "token_normalized_loss": 0.3003558176425016, "grad_norm_before_clip": 0.15357200801372528, "learning_rates_at_step": { "lora": 3.0469867960666032e-06, "row_tokens": 3.0469867960666032e-06 }, "learning_rates_after_step": { "lora": 2.98875387552115e-06, "row_tokens": 2.98875387552115e-06 } }, { "update_id": 874, "row_count": 16, "row_ids_sha256": "a206a1018536c6950f8f3572a400bf94435ed4e830645ddf143536a655cb190e", "input_ids_vector_sha256": "98360cc1ebf8608bb18880cafaff076f09493bb211f1f705cedadcb61835a05a", "labels_vector_sha256": "8127421aa58ff94d3150d1fa943fe632d8e55adb622701b32795f46970a75b48", "planned_active_tokens": 65183, "realized_active_tokens": 65183, "cumulative_start": 57280109, "cumulative_end": 57345292, "loss_sum": 18830.700134277344, "token_normalized_loss": 0.28888974325019323, "grad_norm_before_clip": 0.14682966470718384, "learning_rates_at_step": { "lora": 2.98875387552115e-06, "row_tokens": 2.98875387552115e-06 }, "learning_rates_after_step": { "lora": 2.928251151364003e-06, "row_tokens": 2.928251151364003e-06 } }, { "update_id": 875, "row_count": 13, "row_ids_sha256": "098ffc55ec3a8582b099a5a1fe6c17691439db0d045681ce00be4f26f00f7f5d", "input_ids_vector_sha256": "c33439c0b0dbb0ff3be3a41004bf892c22d9657a6e1889206b163b35d4332b6a", "labels_vector_sha256": "8dec65615303e41dda96dec09415b6b39640fd1ca02ce1c6fd5a7bbbc23ef554", "planned_active_tokens": 68379, "realized_active_tokens": 68379, "cumulative_start": 57345292, "cumulative_end": 57413671, "loss_sum": 23775.584411621094, "token_normalized_loss": 0.34770301425322236, "grad_norm_before_clip": 0.1564338356256485, "learning_rates_at_step": { "lora": 2.928251151364003e-06, "row_tokens": 2.928251151364003e-06 }, "learning_rates_after_step": { "lora": 2.8685395141297313e-06, "row_tokens": 2.8685395141297313e-06 } }, { "update_id": 876, "row_count": 14, "row_ids_sha256": "75a72cbc0a559f7a09fc4516d462b6e01faa4b375a53f94f861407745ddaf199", "input_ids_vector_sha256": "3c5ab533c68979b693bd7ccecd88377473be6475e9848cfedea76ec271c4e27e", "labels_vector_sha256": "107fc6042d1e19fce1da70523a6015a0e81159bcc60e4f717896f7a59e99055e", "planned_active_tokens": 68160, "realized_active_tokens": 68160, "cumulative_start": 57413671, "cumulative_end": 57481831, "loss_sum": 23760.682556152344, "token_normalized_loss": 0.34860156332383135, "grad_norm_before_clip": 0.1610657274723053, "learning_rates_at_step": { "lora": 2.8685395141297313e-06, "row_tokens": 2.8685395141297313e-06 }, "learning_rates_after_step": { "lora": 2.816849016798978e-06, "row_tokens": 2.816849016798978e-06 } }, { "update_id": 877, "row_count": 11, "row_ids_sha256": "c707869f217e44e3eea01135e8dd96d101a8e6d3371d42e5f05a04cfc5f84bd7", "input_ids_vector_sha256": "58956da8c0fe4123ad7cff1682af6fb67c4d419d8974bace688f03ceeb9d0b65", "labels_vector_sha256": "895b63f77e455b5514b188378b298176838442f8dd57e607b2bd9481106294bc", "planned_active_tokens": 59562, "realized_active_tokens": 59562, "cumulative_start": 57481831, "cumulative_end": 57541393, "loss_sum": 23757.273315429688, "token_normalized_loss": 0.3988662790945517, "grad_norm_before_clip": 0.169630229473114, "learning_rates_at_step": { "lora": 2.816849016798978e-06, "row_tokens": 2.816849016798978e-06 }, "learning_rates_after_step": { "lora": 2.7608428660932606e-06, "row_tokens": 2.7608428660932606e-06 } }, { "update_id": 878, "row_count": 17, "row_ids_sha256": "5f024e05b197d642843a212ba890c6cb024fa3e5f9dbcb77cc7074ea204f3f8c", "input_ids_vector_sha256": "29a484c51771a57f69ee47234f4e2ab005bcdacb6c576efc13229c7ec5978901", "labels_vector_sha256": "7a53f4cdcdfa72403958325380ff6e8a6cea07152ee0f37c1f058e909bd966c6", "planned_active_tokens": 65137, "realized_active_tokens": 65137, "cumulative_start": 57541393, "cumulative_end": 57606530, "loss_sum": 22660.32534790039, "token_normalized_loss": 0.34788715089581024, "grad_norm_before_clip": 0.16160520911216736, "learning_rates_at_step": { "lora": 2.7608428660932606e-06, "row_tokens": 2.7608428660932606e-06 }, "learning_rates_after_step": { "lora": 2.702674497018698e-06, "row_tokens": 2.702674497018698e-06 } }, { "update_id": 879, "row_count": 13, "row_ids_sha256": "eb8f8b2f0969cc084d86dd8f37723846a3f72158cf673dd3f231773730b9eff4", "input_ids_vector_sha256": "71b6fd19d58d8e450f9727bc7244038446e0ecee73ab6c6bd3123e9bde3c0428", "labels_vector_sha256": "ff1cdbe5d5e68cd3e16aec35ab6a19c68f59f088e825cedd66acd29e792621b7", "planned_active_tokens": 68335, "realized_active_tokens": 68335, "cumulative_start": 57606530, "cumulative_end": 57674865, "loss_sum": 26058.109924316406, "token_normalized_loss": 0.38132889330967157, "grad_norm_before_clip": 0.3367297053337097, "learning_rates_at_step": { "lora": 2.702674497018698e-06, "row_tokens": 2.702674497018698e-06 }, "learning_rates_after_step": { "lora": 2.64821158034802e-06, "row_tokens": 2.64821158034802e-06 } }, { "update_id": 880, "row_count": 15, "row_ids_sha256": "92cdc2a13944cd1722df45e1f9d57f416c2a2a5cb7092a9f6ff94df62a456c17", "input_ids_vector_sha256": "3e7665584de8f3fc48ee0835f84f2506c914196347af4b79fbb9cf63b124b8a4", "labels_vector_sha256": "1db4a21b8418d482be527288beb9b1d1b2884f7fec086fd40c17e3be7cfb80be", "planned_active_tokens": 64633, "realized_active_tokens": 64633, "cumulative_start": 57674865, "cumulative_end": 57739498, "loss_sum": 21590.983947753906, "token_normalized_loss": 0.33405511035777247, "grad_norm_before_clip": 0.1526086926460266, "learning_rates_at_step": { "lora": 2.64821158034802e-06, "row_tokens": 2.64821158034802e-06 }, "learning_rates_after_step": { "lora": 2.593780904940368e-06, "row_tokens": 2.593780904940368e-06 } }, { "update_id": 881, "row_count": 14, "row_ids_sha256": "c4e3dec4a363b1837cd6c4fd54038cb56cec81cc8cbba78cdbc2ed3300a147f7", "input_ids_vector_sha256": "afabc8175c4957fbdf3fdc1b7d666b00a699d811ff21cb8c8fb51f55b0c7e2f1", "labels_vector_sha256": "f12171e3af6ab2946f44a04e7aeb4a401820261c97c8b6388120a15cf5d450df", "planned_active_tokens": 65244, "realized_active_tokens": 65244, "cumulative_start": 57739498, "cumulative_end": 57804742, "loss_sum": 22112.554138183594, "token_normalized_loss": 0.33892088373158596, "grad_norm_before_clip": 0.15977266430854797, "learning_rates_at_step": { "lora": 2.593780904940368e-06, "row_tokens": 2.593780904940368e-06 }, "learning_rates_after_step": { "lora": 2.5357875415430777e-06, "row_tokens": 2.5357875415430777e-06 } }, { "update_id": 882, "row_count": 15, "row_ids_sha256": "2439f5121c8941f381d38c75db173ff041459b53f14fefc6277161bf8c5842a7", "input_ids_vector_sha256": "f5f2c14c12eb1ce58174aada2a2ae7161672d82974d340d839a9b1b907194e17", "labels_vector_sha256": "89ce3e034e067d24f80372b1dfde7309904bca5f505b7741d6ad1820f6138f19", "planned_active_tokens": 70252, "realized_active_tokens": 70252, "cumulative_start": 57804742, "cumulative_end": 57874994, "loss_sum": 21399.788513183594, "token_normalized_loss": 0.30461465172783114, "grad_norm_before_clip": 0.1434837430715561, "learning_rates_at_step": { "lora": 2.5357875415430777e-06, "row_tokens": 2.5357875415430777e-06 }, "learning_rates_after_step": { "lora": 2.48529784076611e-06, "row_tokens": 2.48529784076611e-06 } }, { "update_id": 883, "row_count": 13, "row_ids_sha256": "82d5168f72f4a391e44d824442581a5f77b3d4173661f183d0bc8a3ba3f3c085", "input_ids_vector_sha256": "f910b399115588cada9fe94645e0cc1092a12e848d52d533b17ecbc336b52d35", "labels_vector_sha256": "f29cba95c031c5911b15b30553a270af460bb49dd27edfe5dabdfa7ddc6607f5", "planned_active_tokens": 61802, "realized_active_tokens": 61802, "cumulative_start": 57874994, "cumulative_end": 57936796, "loss_sum": 19611.460342407227, "token_normalized_loss": 0.3173272765024955, "grad_norm_before_clip": 0.15266145765781403, "learning_rates_at_step": { "lora": 2.48529784076611e-06, "row_tokens": 2.48529784076611e-06 }, "learning_rates_after_step": { "lora": 2.430827142833775e-06, "row_tokens": 2.430827142833775e-06 } }, { "update_id": 884, "row_count": 16, "row_ids_sha256": "2b10fb7f031584a0564f839ee22d8a7c95db95868d8b8893f2198c51213a1662", "input_ids_vector_sha256": "fd77614c01c3fc6a78cc5bb2f53c4f044296ea7079e5e7d494664924abf399c0", "labels_vector_sha256": "219359781b7377b69b6179edad6fb6ac6f00fdb37cf63b6c62853a019d4acfc3", "planned_active_tokens": 67365, "realized_active_tokens": 67365, "cumulative_start": 57936796, "cumulative_end": 58004161, "loss_sum": 20815.95864868164, "token_normalized_loss": 0.30900257772851836, "grad_norm_before_clip": 0.1479247808456421, "learning_rates_at_step": { "lora": 2.430827142833775e-06, "row_tokens": 2.430827142833775e-06 }, "learning_rates_after_step": { "lora": 2.380953601643671e-06, "row_tokens": 2.380953601643671e-06 } }, { "update_id": 885, "row_count": 9, "row_ids_sha256": "6c259c3ce580fdaf75a2788e138a24064240f45c5609c72b5cd6059a95640990", "input_ids_vector_sha256": "36b26e7847402aee79a4a41e702e22ac0842b6b511445234ff41b28540d4e2b5", "labels_vector_sha256": "f9b583eb6dd1570a00900b16a8882ffd1896db8b6fe33f2a5c6bc1fca842f639", "planned_active_tokens": 62328, "realized_active_tokens": 62328, "cumulative_start": 58004161, "cumulative_end": 58066489, "loss_sum": 22819.042419433594, "token_normalized_loss": 0.3661122195391091, "grad_norm_before_clip": 0.4194472134113312, "learning_rates_at_step": { "lora": 2.380953601643671e-06, "row_tokens": 2.380953601643671e-06 }, "learning_rates_after_step": { "lora": 2.328983143478769e-06, "row_tokens": 2.328983143478769e-06 } }, { "update_id": 886, "row_count": 8, "row_ids_sha256": "c19dceddde0f0b1712de533db81535fbfb95e1614e457d16b3d62ab2cdebc264", "input_ids_vector_sha256": "445ff2f26e787b20cdf296a8258f18ddccb40d4450ee149f80d8272f0f8a6ed7", "labels_vector_sha256": "5c63a1acd9302c9cd654a740744ece568fdd5e92ec94af5d86a17bdb1272e78b", "planned_active_tokens": 65630, "realized_active_tokens": 65630, "cumulative_start": 58066489, "cumulative_end": 58132119, "loss_sum": 20212.01481628418, "token_normalized_loss": 0.30796914240871825, "grad_norm_before_clip": 0.14789824187755585, "learning_rates_at_step": { "lora": 2.328983143478769e-06, "row_tokens": 2.328983143478769e-06 }, "learning_rates_after_step": { "lora": 2.2747836157616607e-06, "row_tokens": 2.2747836157616607e-06 } }, { "update_id": 887, "row_count": 15, "row_ids_sha256": "5c440b46dc332205cd657231361abe67df2ccb9aca4beec50d6729738efffc8b", "input_ids_vector_sha256": "1c990d2b3c185b62eac1a090c60b651d4a8681b6cb3be5dae63ae0c49ee48553", "labels_vector_sha256": "17b34a3e596245572ed6bd32a399d46c2cc30c71a007aca02a32b93120d9c081", "planned_active_tokens": 69211, "realized_active_tokens": 69211, "cumulative_start": 58132119, "cumulative_end": 58201330, "loss_sum": 21876.80307006836, "token_normalized_loss": 0.31608852740270127, "grad_norm_before_clip": 0.14308501780033112, "learning_rates_at_step": { "lora": 2.2747836157616607e-06, "row_tokens": 2.2747836157616607e-06 }, "learning_rates_after_step": { "lora": 2.2266617930783827e-06, "row_tokens": 2.2266617930783827e-06 } }, { "update_id": 888, "row_count": 7, "row_ids_sha256": "78a137daf6b3973543ea22f314b9029aa2b67fcf1c52129239cc8579caa931c2", "input_ids_vector_sha256": "9c0d4a232ac7099ef477da7cfab8c2a99474769634252e5f017002725f377fa6", "labels_vector_sha256": "08b7d5a873cdb9655c575bda420887dc7b5c6600c6df31ef79486c0c12b05bb2", "planned_active_tokens": 62128, "realized_active_tokens": 62128, "cumulative_start": 58201330, "cumulative_end": 58263458, "loss_sum": 22202.587646484375, "token_normalized_loss": 0.3573684594141832, "grad_norm_before_clip": 0.16203919053077698, "learning_rates_at_step": { "lora": 2.2266617930783827e-06, "row_tokens": 2.2266617930783827e-06 }, "learning_rates_after_step": { "lora": 2.173339038887717e-06, "row_tokens": 2.173339038887717e-06 } }, { "update_id": 889, "row_count": 12, "row_ids_sha256": "f2479a7596c37788b57a97fad750f68fbb58a3bdd49170dc2b6800646d686886", "input_ids_vector_sha256": "6cf7db397e05e6a0d02095bb9aa1bbb7921b3719a14bc6e0dbb1152eea182865", "labels_vector_sha256": "f182135a19d268346bf203d92fcc1f8111b9c8ab25e0031eb9d901ce2683543e", "planned_active_tokens": 69614, "realized_active_tokens": 69614, "cumulative_start": 58263458, "cumulative_end": 58333072, "loss_sum": 23624.28643798828, "token_normalized_loss": 0.3393611405462735, "grad_norm_before_clip": 0.14874377846717834, "learning_rates_at_step": { "lora": 2.173339038887717e-06, "row_tokens": 2.173339038887717e-06 }, "learning_rates_after_step": { "lora": 2.1250751894377584e-06, "row_tokens": 2.1250751894377584e-06 } }, { "update_id": 890, "row_count": 10, "row_ids_sha256": "6eba1c3f9e0b8473821ddbf28f0c7e3395b664f1f70492f9d581d87646bfa1a6", "input_ids_vector_sha256": "581fd0995c90db309a5acfdd30ce6f544e426d69644247008a5b2dc53942809c", "labels_vector_sha256": "0617091c15e2452170f46f93ba9591b5bb2cf494b32439470c7166b80c134a05", "planned_active_tokens": 63733, "realized_active_tokens": 63733, "cumulative_start": 58333072, "cumulative_end": 58396805, "loss_sum": 22041.89697265625, "token_normalized_loss": 0.34584747262260135, "grad_norm_before_clip": 0.1532336175441742, "learning_rates_at_step": { "lora": 2.1250751894377584e-06, "row_tokens": 2.1250751894377584e-06 }, "learning_rates_after_step": { "lora": 2.078324888471922e-06, "row_tokens": 2.078324888471922e-06 } }, { "update_id": 891, "row_count": 7, "row_ids_sha256": "12a1fc75961e4e0491053abcdd921eed9a487733aa8d4bca3b0f9941e58ee3d5", "input_ids_vector_sha256": "019bc845edfaf392d7cd79bc79a7850f3b43db7a2656a431a194daa621e752a0", "labels_vector_sha256": "21dd2ed8f6eb4199d53c0e695c8379fefe7de6635df906e655f09b444a22b056", "planned_active_tokens": 62413, "realized_active_tokens": 62413, "cumulative_start": 58396805, "cumulative_end": 58459218, "loss_sum": 25110.46319580078, "token_normalized_loss": 0.40232745094452727, "grad_norm_before_clip": 0.23205474019050598, "learning_rates_at_step": { "lora": 2.078324888471922e-06, "row_tokens": 2.078324888471922e-06 }, "learning_rates_after_step": { "lora": 2.027615824802631e-06, "row_tokens": 2.027615824802631e-06 } }, { "update_id": 892, "row_count": 9, "row_ids_sha256": "ff9816ec804a0b317138bb510fbedc7eab15123dfa8546bc8a2b7d79db5859c4", "input_ids_vector_sha256": "ab00872dc931f38c1450e950634c6a108b0de82a771e896e7a657445ed0dac6a", "labels_vector_sha256": "a2b356b32f2cc60a88ed88fa4a723b8873cb7ec4e62ec463c8251fd08f61f149", "planned_active_tokens": 68480, "realized_active_tokens": 68480, "cumulative_start": 58459218, "cumulative_end": 58527698, "loss_sum": 23524.397338867188, "token_normalized_loss": 0.34352215740168207, "grad_norm_before_clip": 0.1519113928079605, "learning_rates_at_step": { "lora": 2.027615824802631e-06, "row_tokens": 2.027615824802631e-06 }, "learning_rates_after_step": { "lora": 1.9822532281005058e-06, "row_tokens": 1.9822532281005058e-06 } }, { "update_id": 893, "row_count": 11, "row_ids_sha256": "795d4d7b508dd7cc57fa3b3c499cd19a6fb684ebf272350c4f497f6b55ba24b0", "input_ids_vector_sha256": "2827bbb21a6904b29e3fa3c1a7fe92de832ced60c2964292d89f9847b2a3eaa7", "labels_vector_sha256": "575ddbf8b047ec16569699b9951cf6c3cbe77f630d81a668c4c72237a9da103b", "planned_active_tokens": 61974, "realized_active_tokens": 61974, "cumulative_start": 58527698, "cumulative_end": 58589672, "loss_sum": 26735.26968383789, "token_normalized_loss": 0.43139493471194196, "grad_norm_before_clip": 0.17808881402015686, "learning_rates_at_step": { "lora": 1.9822532281005058e-06, "row_tokens": 1.9822532281005058e-06 }, "learning_rates_after_step": { "lora": 1.9348628818342265e-06, "row_tokens": 1.9348628818342265e-06 } }, { "update_id": 894, "row_count": 10, "row_ids_sha256": "40cada3d5b5cb30750805a766fb4bd08e63cd5d339ee3d8da55652d9c9db0679", "input_ids_vector_sha256": "91966bcf5ec801017aafff37755620a5478b4bd14152742602e8f02422f6ef85", "labels_vector_sha256": "464b5dcff772d0049132959a6b099361a6e4c29aa080729eafa68fb1ec99cd23", "planned_active_tokens": 65491, "realized_active_tokens": 65491, "cumulative_start": 58589672, "cumulative_end": 58655163, "loss_sum": 23679.782470703125, "token_normalized_loss": 0.36157307829630214, "grad_norm_before_clip": 0.1638270914554596, "learning_rates_at_step": { "lora": 1.9348628818342265e-06, "row_tokens": 1.9348628818342265e-06 }, "learning_rates_after_step": { "lora": 1.8848895727136884e-06, "row_tokens": 1.8848895727136884e-06 } }, { "update_id": 895, "row_count": 10, "row_ids_sha256": "4d7cb0ebb1c53f67d847e8796635bd62e4aae4d2c19f7cf2d1964546c677cb0b", "input_ids_vector_sha256": "0225aef9adeae4c7b1c3ba6c8df36c47986b82d6a13edf7dcfc0d1330b5d6510", "labels_vector_sha256": "370244d7ebf09224330e75d7627cb02a0125a1ef531b351959d44f4f7a7bb1b2", "planned_active_tokens": 69918, "realized_active_tokens": 69918, "cumulative_start": 58655163, "cumulative_end": 58725081, "loss_sum": 24932.694549560547, "token_normalized_loss": 0.3565990810601068, "grad_norm_before_clip": 0.15653908252716064, "learning_rates_at_step": { "lora": 1.8848895727136884e-06, "row_tokens": 1.8848895727136884e-06 }, "learning_rates_after_step": { "lora": 1.8403371980216966e-06, "row_tokens": 1.8403371980216966e-06 } }, { "update_id": 896, "row_count": 8, "row_ids_sha256": "43af5903d1a98af1dec69a58e7746a72024ab0418d7ed8434bbc5337b36b49ed", "input_ids_vector_sha256": "e3e9cde0bacccf62157d302000e6ca36dabd1d1019186e14ae11d397029cba88", "labels_vector_sha256": "e449f34b3a45d56026fe6dc56c56105da9c9dda02c0f7de613321bf41ea80f92", "planned_active_tokens": 63104, "realized_active_tokens": 63104, "cumulative_start": 58725081, "cumulative_end": 58788185, "loss_sum": 24379.912231445312, "token_normalized_loss": 0.3863449580287353, "grad_norm_before_clip": 0.17090769112110138, "learning_rates_at_step": { "lora": 1.8403371980216966e-06, "row_tokens": 1.8403371980216966e-06 }, "learning_rates_after_step": { "lora": 1.7957002739872608e-06, "row_tokens": 1.7957002739872608e-06 } }, { "update_id": 897, "row_count": 13, "row_ids_sha256": "04efc0baf5ec40dbdcbe918e345733f914a2dbf677b29fa74e8b104e8939b48d", "input_ids_vector_sha256": "e9780c4daddcacae429bfde90fbc76d926e0eeed40f19ed84361cf289d9cd9c4", "labels_vector_sha256": "4bc6b0be7d434c8938512341b06445c9c90a1a3b3ccd0fcacb23705cd5424cd7", "planned_active_tokens": 63980, "realized_active_tokens": 63980, "cumulative_start": 58788185, "cumulative_end": 58852165, "loss_sum": 22461.076171875, "token_normalized_loss": 0.3510640226926383, "grad_norm_before_clip": 0.1570155769586563, "learning_rates_at_step": { "lora": 1.7957002739872608e-06, "row_tokens": 1.7957002739872608e-06 }, "learning_rates_after_step": { "lora": 1.7497029880175376e-06, "row_tokens": 1.7497029880175376e-06 } }, { "update_id": 898, "row_count": 11, "row_ids_sha256": "f91859f00e613098c715d142ab6b849d700ef628e57a1190cc5fc89247ef4dcf", "input_ids_vector_sha256": "87e182a30f7ec9292f1d93dd5edc1fb60c5cf8a6a01ebe2b92a06792a2d8e88f", "labels_vector_sha256": "d77fdaae18b312c65e43fb9db894c8bfb768417f43f8a8020d5d48b16c4b6364", "planned_active_tokens": 66752, "realized_active_tokens": 66752, "cumulative_start": 58852165, "cumulative_end": 58918917, "loss_sum": 23765.232299804688, "token_normalized_loss": 0.35602277534462917, "grad_norm_before_clip": 0.15637312829494476, "learning_rates_at_step": { "lora": 1.7497029880175376e-06, "row_tokens": 1.7497029880175376e-06 }, "learning_rates_after_step": { "lora": 1.70251280671605e-06, "row_tokens": 1.70251280671605e-06 } }, { "update_id": 899, "row_count": 7, "row_ids_sha256": "78dce10a6c1c43bd0bba8168af3f3823368f5cdd20aa85aa98f12830d5fb0b7f", "input_ids_vector_sha256": "cab65a9932923d0f67b204095b9b7aea0aa5c2b91d53640576bc5afdc4a1b9c0", "labels_vector_sha256": "42fa0cc2c60e492332400ce3a0529ac2730188780fad723ff61f2de8d31a96e8", "planned_active_tokens": 69385, "realized_active_tokens": 69385, "cumulative_start": 58918917, "cumulative_end": 58988302, "loss_sum": 24566.322021484375, "token_normalized_loss": 0.3540581108522645, "grad_norm_before_clip": 0.14540377259254456, "learning_rates_at_step": { "lora": 1.70251280671605e-06, "row_tokens": 1.70251280671605e-06 }, "learning_rates_after_step": { "lora": 1.6624224071738525e-06, "row_tokens": 1.6624224071738525e-06 } }, { "update_id": 900, "row_count": 8, "row_ids_sha256": "18ea5ea0ac86b8452366c8656ff469b0ce0e7e58b85842bd3b12172778c3ed2a", "input_ids_vector_sha256": "a2b21b36d34212b370b75378912b482c0b8ae15c6526b346f5d70b19504c1d3c", "labels_vector_sha256": "852d7f34b16559eaabb9a5b2fa584a58ed9bc531f21ca318ce4a58d57fa060b2", "planned_active_tokens": 59692, "realized_active_tokens": 59692, "cumulative_start": 58988302, "cumulative_end": 59047994, "loss_sum": 23669.591888427734, "token_normalized_loss": 0.3965287121964038, "grad_norm_before_clip": 0.16579602658748627, "learning_rates_at_step": { "lora": 1.6624224071738525e-06, "row_tokens": 1.6624224071738525e-06 }, "learning_rates_after_step": { "lora": 1.6168278509905376e-06, "row_tokens": 1.6168278509905376e-06 } }, { "update_id": 901, "row_count": 10, "row_ids_sha256": "42c0c0f80dc5861e031ca582aba72606ccfdd67cf25ea2a5ff53a909649a234d", "input_ids_vector_sha256": "af17fc3a6e67feedeaf18804b3708186fced0d68ef03a42b7589e6271fc0d290", "labels_vector_sha256": "a71080bcc37917f9773f187e262cc8ae6d8e4dc9d28552bdaffb06eac0c3f344", "planned_active_tokens": 68754, "realized_active_tokens": 68754, "cumulative_start": 59047994, "cumulative_end": 59116748, "loss_sum": 25375.30453491211, "token_normalized_loss": 0.3690738653011041, "grad_norm_before_clip": 0.15205031633377075, "learning_rates_at_step": { "lora": 1.6168278509905376e-06, "row_tokens": 1.6168278509905376e-06 }, "learning_rates_after_step": { "lora": 1.574041511400881e-06, "row_tokens": 1.574041511400881e-06 } }, { "update_id": 902, "row_count": 11, "row_ids_sha256": "6cdbdd6dbbe2ed75858635c25cc8a1a6cd20d09ab1b423b09001dba5d656646d", "input_ids_vector_sha256": "313675a52ca28b430903feab6e7cf61ef5e7dc7f35d0d5aa40f590778eb4fc2d", "labels_vector_sha256": "dcf8dc474d83bd86ee0cae5643346de827d616c3ccbf02867e23c1671a67ed38", "planned_active_tokens": 65392, "realized_active_tokens": 65392, "cumulative_start": 59116748, "cumulative_end": 59182140, "loss_sum": 21543.353607177734, "token_normalized_loss": 0.32944937618023207, "grad_norm_before_clip": 0.15157939493656158, "learning_rates_at_step": { "lora": 1.574041511400881e-06, "row_tokens": 1.574041511400881e-06 }, "learning_rates_after_step": { "lora": 1.532571618256029e-06, "row_tokens": 1.532571618256029e-06 } }, { "update_id": 903, "row_count": 12, "row_ids_sha256": "2d7fb03203e6fd0211ab93ff35636ac38c0a1a89674c3df0e357d090535ce854", "input_ids_vector_sha256": "0517956e1c84a2b5448a3be0b0248295986ac0743e0c1a6e87604e8ae3833130", "labels_vector_sha256": "105cfd720558483568a066a9bd672b90cab03b671ff4b4cf4534bec5b13f3578", "planned_active_tokens": 64220, "realized_active_tokens": 64220, "cumulative_start": 59182140, "cumulative_end": 59246360, "loss_sum": 24287.273239135742, "token_normalized_loss": 0.37818862097688793, "grad_norm_before_clip": 0.15651196241378784, "learning_rates_at_step": { "lora": 1.532571618256029e-06, "row_tokens": 1.532571618256029e-06 }, "learning_rates_after_step": { "lora": 1.4907702291789227e-06, "row_tokens": 1.4907702291789227e-06 } }, { "update_id": 904, "row_count": 14, "row_ids_sha256": "301e40e6a0387e3a3ae580c143ee4b153a1e7e38bcb2e75530dc0ebd7649b054", "input_ids_vector_sha256": "d23eadbb538a097a768c14dd9f10e1be79dc2f438158c020352b5acff632e890", "labels_vector_sha256": "0186ab76324ae8b538795f202c77e6b3217cd1bdc8411e9e631f9121aed272cd", "planned_active_tokens": 65605, "realized_active_tokens": 65605, "cumulative_start": 59246360, "cumulative_end": 59311965, "loss_sum": 23445.509765625, "token_normalized_loss": 0.35737382464179557, "grad_norm_before_clip": 0.15241776406764984, "learning_rates_at_step": { "lora": 1.4907702291789227e-06, "row_tokens": 1.4907702291789227e-06 }, "learning_rates_after_step": { "lora": 1.4463050182563054e-06, "row_tokens": 1.4463050182563054e-06 } }, { "update_id": 905, "row_count": 11, "row_ids_sha256": "af1ff8a7945e55209d056554e9d11b65cd9a8fe3ee518fa4adf2ff797f9144a9", "input_ids_vector_sha256": "e5df30fcbf01e289b551c3b395583742948df038eb3409dbe84e76dcad529d2f", "labels_vector_sha256": "0e460769c78746de825dac9a8bd36620d233a4e0649dce9274a7a3be10d3dc61", "planned_active_tokens": 70788, "realized_active_tokens": 70788, "cumulative_start": 59311965, "cumulative_end": 59382753, "loss_sum": 27420.348754882812, "token_normalized_loss": 0.38735871552922546, "grad_norm_before_clip": 0.15655286610126495, "learning_rates_at_step": { "lora": 1.4463050182563054e-06, "row_tokens": 1.4463050182563054e-06 }, "learning_rates_after_step": { "lora": 1.4085418288811214e-06, "row_tokens": 1.4085418288811214e-06 } }, { "update_id": 906, "row_count": 7, "row_ids_sha256": "81a269d3644decc2d35a3e9b4270603d7cbd41a86c89f20e45d2a8940efca06c", "input_ids_vector_sha256": "26bafd63c94a2382408e72fcd874c54d8ad5bee7666a5e8ebdc19d95894c42da", "labels_vector_sha256": "4c288e707b82e36d024150549cf591a35df861d3d3c414bfb9af49bace05f34b", "planned_active_tokens": 60965, "realized_active_tokens": 60965, "cumulative_start": 59382753, "cumulative_end": 59443718, "loss_sum": 26407.308471679688, "token_normalized_loss": 0.43315522794520933, "grad_norm_before_clip": 0.17312484979629517, "learning_rates_at_step": { "lora": 1.4085418288811214e-06, "row_tokens": 1.4085418288811214e-06 }, "learning_rates_after_step": { "lora": 1.3660974768269164e-06, "row_tokens": 1.3660974768269164e-06 } }, { "update_id": 907, "row_count": 10, "row_ids_sha256": "ed72fc21c2b6f9e489acb9e3ef93a37003fbd01c34449f4f131c039ad5ea9648", "input_ids_vector_sha256": "b34173fcc84669fe9f5f555b73f74cc81711f828c55bf29c4c565a3b6e8b627c", "labels_vector_sha256": "51a58efae56de9e36531428680b672a08b2f8422ed7db87abf4cc7170baa98ba", "planned_active_tokens": 69492, "realized_active_tokens": 69492, "cumulative_start": 59443718, "cumulative_end": 59513210, "loss_sum": 25015.288635253906, "token_normalized_loss": 0.3599736463946052, "grad_norm_before_clip": 0.1541423350572586, "learning_rates_at_step": { "lora": 1.3660974768269164e-06, "row_tokens": 1.3660974768269164e-06 }, "learning_rates_after_step": { "lora": 1.3300268660544736e-06, "row_tokens": 1.3300268660544736e-06 } }, { "update_id": 908, "row_count": 8, "row_ids_sha256": "5ad9d1a62c7cb2c3793c0f5c34e51e6dbc143124eb3134227c1f461f1be5bb71", "input_ids_vector_sha256": "967f9a7eb808a7b5bad1c15ac92c5064e963650bdf968367a1f5750898e63e2d", "labels_vector_sha256": "e76ddd20078dbe0f435dcb1cc5d3363d3623abbf3c422aa22f7eb8d08cfbe129", "planned_active_tokens": 59898, "realized_active_tokens": 59898, "cumulative_start": 59513210, "cumulative_end": 59573108, "loss_sum": 20263.902709960938, "token_normalized_loss": 0.33830683344954654, "grad_norm_before_clip": 0.16342200338840485, "learning_rates_at_step": { "lora": 1.3300268660544736e-06, "row_tokens": 1.3300268660544736e-06 }, "learning_rates_after_step": { "lora": 1.2869584411903669e-06, "row_tokens": 1.2869584411903669e-06 } }, { "update_id": 909, "row_count": 10, "row_ids_sha256": "cb6bdc7be8aeea77a111b8e0a5ae66d9182c5ea0808c29b05dc2a6a0332fe8a7", "input_ids_vector_sha256": "821796a920cb08607da16eacdbc03a051637c211f0b049166e9b60d9bc8f74d4", "labels_vector_sha256": "597cbb81607e965557f7ac9471a3384f50c7ab8debe6136e67a1d271bb8acbaf", "planned_active_tokens": 72578, "realized_active_tokens": 72578, "cumulative_start": 59573108, "cumulative_end": 59645686, "loss_sum": 28610.381713867188, "token_normalized_loss": 0.3942018478584032, "grad_norm_before_clip": 0.15886689722537994, "learning_rates_at_step": { "lora": 1.2869584411903669e-06, "row_tokens": 1.2869584411903669e-06 }, "learning_rates_after_step": { "lora": 1.2486015585086498e-06, "row_tokens": 1.2486015585086498e-06 } }, { "update_id": 910, "row_count": 7, "row_ids_sha256": "14b06bdebda558cc3e6dc39fec5547ed1f598cff285b44fd8c3031e30445d7d8", "input_ids_vector_sha256": "7b96c3e510366455ba78e43a11cd41a5f9e4a6e60dd5d152e18326e31d64a393", "labels_vector_sha256": "fe150373049548a1057a9aca6e078940ed2e77cb2cff0355840e2743d4340d5c", "planned_active_tokens": 65654, "realized_active_tokens": 65654, "cumulative_start": 59645686, "cumulative_end": 59711340, "loss_sum": 25171.800048828125, "token_normalized_loss": 0.3834008597926726, "grad_norm_before_clip": 0.15709081292152405, "learning_rates_at_step": { "lora": 1.2486015585086498e-06, "row_tokens": 1.2486015585086498e-06 }, "learning_rates_after_step": { "lora": 1.2154345365567642e-06, "row_tokens": 1.2154345365567642e-06 } }, { "update_id": 911, "row_count": 8, "row_ids_sha256": "aeceda644e1f251bd7fd44c106a5143803d8a474782234525ee385823dc2f13a", "input_ids_vector_sha256": "020225693eb6bc0e55b5b8f92422e5d69ba1186258734c9fe80b5eb5e99b780f", "labels_vector_sha256": "680d249f528e4f4e563d3dd651570f3dbc23f13e2fa4e302afb3a2a40c08f12a", "planned_active_tokens": 57578, "realized_active_tokens": 57578, "cumulative_start": 59711340, "cumulative_end": 59768918, "loss_sum": 25503.88751220703, "token_normalized_loss": 0.44294500524865454, "grad_norm_before_clip": 0.1817747950553894, "learning_rates_at_step": { "lora": 1.2154345365567642e-06, "row_tokens": 1.2154345365567642e-06 }, "learning_rates_after_step": { "lora": 1.1743183702989824e-06, "row_tokens": 1.1743183702989824e-06 } }, { "update_id": 912, "row_count": 11, "row_ids_sha256": "4c9095c91cfc0d8f2628ca17ac25c1e702002efc05569858d5ec51ebf95e61fc", "input_ids_vector_sha256": "0f775a7c354d6914698b00e954a8c3dda2be24c47ab5adaff8fb1ba902711030", "labels_vector_sha256": "d89869e60bb4c4e3e44aefa172c7447becc2f56d9b95065abeb31502c9003a1a", "planned_active_tokens": 72466, "realized_active_tokens": 72466, "cumulative_start": 59768918, "cumulative_end": 59841384, "loss_sum": 26443.110717773438, "token_normalized_loss": 0.3649036888716562, "grad_norm_before_clip": 0.15176180005073547, "learning_rates_at_step": { "lora": 1.1743183702989824e-06, "row_tokens": 1.1743183702989824e-06 }, "learning_rates_after_step": { "lora": 1.1364152040812037e-06, "row_tokens": 1.1364152040812037e-06 } }, { "update_id": 913, "row_count": 8, "row_ids_sha256": "f54b8cf80b3037dd3550519376f502fff2843715988810eb3e7cd0843833263b", "input_ids_vector_sha256": "822e7531fe5c048b1812821ef358c6b2c620c61b5e7dc55f2890d549327bfa0f", "labels_vector_sha256": "7a1c446dcf2ed6c38fcf27ba1357a795f89cf8c322b5042418be0747ee66938d", "planned_active_tokens": 67922, "realized_active_tokens": 67922, "cumulative_start": 59841384, "cumulative_end": 59909306, "loss_sum": 27080.111938476562, "token_normalized_loss": 0.3986942660474745, "grad_norm_before_clip": 0.15913929045200348, "learning_rates_at_step": { "lora": 1.1364152040812037e-06, "row_tokens": 1.1364152040812037e-06 }, "learning_rates_after_step": { "lora": 1.104691586708978e-06, "row_tokens": 1.104691586708978e-06 } }, { "update_id": 914, "row_count": 8, "row_ids_sha256": "bf249ecbfd177cdf32b76d93cde2c556257f585a6147397fe6066f6ed7120c41", "input_ids_vector_sha256": "1cd080c464084c79754eefbb7c4f21b1972ac2df5b0deb2c89f906a8471d05cf", "labels_vector_sha256": "425f3f96fdf4519ac67de431602e209cdc1d1e5c73f83defbd26422b2d4ca348", "planned_active_tokens": 57714, "realized_active_tokens": 57714, "cumulative_start": 59909306, "cumulative_end": 59967020, "loss_sum": 21829.870727539062, "token_normalized_loss": 0.3782422068742257, "grad_norm_before_clip": 0.17237721383571625, "learning_rates_at_step": { "lora": 1.104691586708978e-06, "row_tokens": 1.104691586708978e-06 }, "learning_rates_after_step": { "lora": 1.0693224517557555e-06, "row_tokens": 1.0693224517557555e-06 } }, { "update_id": 915, "row_count": 7, "row_ids_sha256": "485a1719cc90300ebc2051e0b110c16d416b7b86264bbd908a80562483749a8d", "input_ids_vector_sha256": "915f18fbc978368f29627174da6e57b05054d13c61f73af20e09ff8c6fcd635d", "labels_vector_sha256": "8255d95d2e383b95c6a59a4ae8a4e94680066056509324bd8be77594713d3b55", "planned_active_tokens": 65321, "realized_active_tokens": 65321, "cumulative_start": 59967020, "cumulative_end": 60032341, "loss_sum": 25930.19677734375, "token_normalized_loss": 0.39696570440354173, "grad_norm_before_clip": 0.16061899065971375, "learning_rates_at_step": { "lora": 1.0693224517557555e-06, "row_tokens": 1.0693224517557555e-06 }, "learning_rates_after_step": { "lora": 1.0339842974215364e-06, "row_tokens": 1.0339842974215364e-06 } }, { "update_id": 916, "row_count": 10, "row_ids_sha256": "f50a2b7c5b4c7434afea1d645fc7518b17cf89b125e3e5ef2af3b2ebfe18c17e", "input_ids_vector_sha256": "9ed51f5e055ae53f9c9e661290bf27b801e21b7e09e7bea5b09f00fae08717b5", "labels_vector_sha256": "946695a73051cb00528e4db6e1074fbc6e260879b478f6f1a33e02143fc103da", "planned_active_tokens": 66340, "realized_active_tokens": 66340, "cumulative_start": 60032341, "cumulative_end": 60098681, "loss_sum": 25882.639068603516, "token_normalized_loss": 0.3901513275339692, "grad_norm_before_clip": 0.16874675452709198, "learning_rates_at_step": { "lora": 1.0339842974215364e-06, "row_tokens": 1.0339842974215364e-06 }, "learning_rates_after_step": { "lora": 9.988167808442695e-07, "row_tokens": 9.988167808442695e-07 } }, { "update_id": 917, "row_count": 9, "row_ids_sha256": "77710355a205f90412966a64bf2cf245375b50aff005a0a9506739ef631e6ce2", "input_ids_vector_sha256": "59f23907b5e11d64d817e442b64e1bbff4ece8ce5726b6a7ce111b401f201db7", "labels_vector_sha256": "a67599273657e85a1e0d8247e15b71bd354f3510ed6f7e165cf368ba41b19cb4", "planned_active_tokens": 67143, "realized_active_tokens": 67143, "cumulative_start": 60098681, "cumulative_end": 60165824, "loss_sum": 25522.431518554688, "token_normalized_loss": 0.3801205117220661, "grad_norm_before_clip": 0.15957142412662506, "learning_rates_at_step": { "lora": 9.988167808442695e-07, "row_tokens": 9.988167808442695e-07 }, "learning_rates_after_step": { "lora": 9.641756416179426e-07, "row_tokens": 9.641756416179426e-07 } }, { "update_id": 918, "row_count": 9, "row_ids_sha256": "5c7a578febcad81d0333f195ac9d06a3843ae0f8283497b1cbeace02822f5eea", "input_ids_vector_sha256": "80a3c1c6860ec9eddbb030d7262ef8318f482f77a78aaf299cbecd2485902846", "labels_vector_sha256": "20128bf9804374604318fe42d89c6788ae57566a223b779b8cbd813b9302128d", "planned_active_tokens": 67292, "realized_active_tokens": 67292, "cumulative_start": 60165824, "cumulative_end": 60233116, "loss_sum": 28856.95574951172, "token_normalized_loss": 0.4288318930855335, "grad_norm_before_clip": 0.1625021994113922, "learning_rates_at_step": { "lora": 9.641756416179426e-07, "row_tokens": 9.641756416179426e-07 }, "learning_rates_after_step": { "lora": 9.312767843695614e-07, "row_tokens": 9.312767843695614e-07 } }, { "update_id": 919, "row_count": 9, "row_ids_sha256": "5e938a71e4cf9500b02cb4500b3c9fd511e91c5121595b62c00add2c4935c2b9", "input_ids_vector_sha256": "c0d0fa8f9b9a94e2015defc072b48481521046959a0cbdb51e0addabe3311f27", "labels_vector_sha256": "980eb531ce0d34aa4a614cce7939179b12cb68e1839d073540e18eb14d74b795", "planned_active_tokens": 65025, "realized_active_tokens": 65025, "cumulative_start": 60233116, "cumulative_end": 60298141, "loss_sum": 24222.461059570312, "token_normalized_loss": 0.37250997400338814, "grad_norm_before_clip": 0.16369383037090302, "learning_rates_at_step": { "lora": 9.312767843695614e-07, "row_tokens": 9.312767843695614e-07 }, "learning_rates_after_step": { "lora": 9.005887318478012e-07, "row_tokens": 9.005887318478012e-07 } }, { "update_id": 920, "row_count": 8, "row_ids_sha256": "fc6b2bcdffcec12ef58d43f19a385de3048c2ef0ff68dd2b7cbc32a4ba0d5ce3", "input_ids_vector_sha256": "58042a0007b3ff844c186eac611030df6727dfd2f6a5b8f02b49a89281eebdee", "labels_vector_sha256": "d17c97f917ebc2dfb91acfc4b186b8a0bc3054311fffd0e91b7a195fbffe394d", "planned_active_tokens": 61689, "realized_active_tokens": 61689, "cumulative_start": 60298141, "cumulative_end": 60359830, "loss_sum": 22000.554748535156, "token_normalized_loss": 0.35663659239953893, "grad_norm_before_clip": 0.15735048055648804, "learning_rates_at_step": { "lora": 9.005887318478012e-07, "row_tokens": 9.005887318478012e-07 }, "learning_rates_after_step": { "lora": 8.682578169114774e-07, "row_tokens": 8.682578169114774e-07 } }, { "update_id": 921, "row_count": 11, "row_ids_sha256": "79e4cf6c8ad78e6b4f628a22098a82a42f7f19cfa2b25d2b06999c7fa1dad39d", "input_ids_vector_sha256": "c136581fcebd85fcbd449ecab6fd6891c2eb24d77fbc6b1c4576304612ec24e6", "labels_vector_sha256": "ce11c14177c669ab3fe47f4560a85ec1fbe96ab71f147a838bc6ea6dce52475b", "planned_active_tokens": 66129, "realized_active_tokens": 66129, "cumulative_start": 60359830, "cumulative_end": 60425959, "loss_sum": 21873.696411132812, "token_normalized_loss": 0.3307731314723164, "grad_norm_before_clip": 0.151478573679924, "learning_rates_at_step": { "lora": 8.682578169114774e-07, "row_tokens": 8.682578169114774e-07 }, "learning_rates_after_step": { "lora": 8.361280846728936e-07, "row_tokens": 8.361280846728936e-07 } }, { "update_id": 922, "row_count": 11, "row_ids_sha256": "71aebc53eaf64f3a6479e53508d154a1395428aed5832bd1f461185dc578d0eb", "input_ids_vector_sha256": "b3a81ab8c078fb30508fb4926630350c22a69cc8979904f884abd5c6306633e5", "labels_vector_sha256": "4792d7e22de4d502dafbcb98f26e88567985dec32a85d21710ada03b7c7a0f98", "planned_active_tokens": 66938, "realized_active_tokens": 66938, "cumulative_start": 60425959, "cumulative_end": 60492897, "loss_sum": 25407.90737915039, "token_normalized_loss": 0.37957374554289625, "grad_norm_before_clip": 0.16123776137828827, "learning_rates_at_step": { "lora": 8.361280846728936e-07, "row_tokens": 8.361280846728936e-07 }, "learning_rates_after_step": { "lora": 8.048869533356762e-07, "row_tokens": 8.048869533356762e-07 } }, { "update_id": 923, "row_count": 8, "row_ids_sha256": "d11f40d07d374d714d875e200abba2e9f51135c2520126d1d2e0349a37121f7a", "input_ids_vector_sha256": "f4d89c7cb7eae111376a8b3fb58991ad1841873a67193cdc3f15cffe38cf6efe", "labels_vector_sha256": "9ae634e7864310aac07024d67a21fa60c1d95f6e48bb37c2c76c1b4e5d398a97", "planned_active_tokens": 66321, "realized_active_tokens": 66321, "cumulative_start": 60492897, "cumulative_end": 60559218, "loss_sum": 26242.245361328125, "token_normalized_loss": 0.3956853087457687, "grad_norm_before_clip": 0.16444502770900726, "learning_rates_at_step": { "lora": 8.048869533356762e-07, "row_tokens": 8.048869533356762e-07 }, "learning_rates_after_step": { "lora": 7.755024441912284e-07, "row_tokens": 7.755024441912284e-07 } }, { "update_id": 924, "row_count": 7, "row_ids_sha256": "258f23f3a8d74d89af9b2462e1827f3216d05c3b914bc2a3775839433c554f2b", "input_ids_vector_sha256": "e91abc2b174421ff144f82d2ce7aa2f5df4806ec3ce913f0fd7a0be893ea15cd", "labels_vector_sha256": "1f952d96aa1a92e3cb0cc16c0e692899534cb292d98a609ba67aae4f9e36ae38", "planned_active_tokens": 63555, "realized_active_tokens": 63555, "cumulative_start": 60559218, "cumulative_end": 60622773, "loss_sum": 25379.446411132812, "token_normalized_loss": 0.39933044467206064, "grad_norm_before_clip": 0.165599063038826, "learning_rates_at_step": { "lora": 7.755024441912284e-07, "row_tokens": 7.755024441912284e-07 }, "learning_rates_after_step": { "lora": 7.457253721815826e-07, "row_tokens": 7.457253721815826e-07 } }, { "update_id": 925, "row_count": 13, "row_ids_sha256": "350748526f85886cebfbcb3a45fdefe676beeefcc197c31d3607aaccd9aeda3b", "input_ids_vector_sha256": "d84187fb546f928f813d6e3164ed7e962d63d0b54cbfb318edf2b1260abdad30", "labels_vector_sha256": "fc7174a950d3fa4f0532c9e5ad186d7a396638d5b1d0ed0e78e92b7fbfc1ca55", "planned_active_tokens": 65635, "realized_active_tokens": 65635, "cumulative_start": 60622773, "cumulative_end": 60688408, "loss_sum": 21591.341247558594, "token_normalized_loss": 0.32896078689050956, "grad_norm_before_clip": 0.14654868841171265, "learning_rates_at_step": { "lora": 7.457253721815826e-07, "row_tokens": 7.457253721815826e-07 }, "learning_rates_after_step": { "lora": 7.159482928233041e-07, "row_tokens": 7.159482928233041e-07 } }, { "update_id": 926, "row_count": 10, "row_ids_sha256": "2278722a1e8115eead4c46847e5ceb4f74bac7d61af127f9134f18042b0f2919", "input_ids_vector_sha256": "acff5c7ea5768be096965c4e4cc594812558610cb41a1a07a6b84d2f6cbb986c", "labels_vector_sha256": "a3b7878439da673db833e5d62d57faad581041b05cbb8e15279ffc2533797961", "planned_active_tokens": 66949, "realized_active_tokens": 66949, "cumulative_start": 60688408, "cumulative_end": 60755357, "loss_sum": 25917.401580810547, "token_normalized_loss": 0.3871215638890879, "grad_norm_before_clip": 0.15386569499969482, "learning_rates_at_step": { "lora": 7.159482928233041e-07, "row_tokens": 7.159482928233041e-07 }, "learning_rates_after_step": { "lora": 6.869068770019805e-07, "row_tokens": 6.869068770019805e-07 } }, { "update_id": 927, "row_count": 7, "row_ids_sha256": "f2481af6dec38ebf9b0ed6e1a89c6b4314031dd87de270921d6b0546f9f67fe8", "input_ids_vector_sha256": "fb99a47b19c77f4a0602bcc6c3716c50e55f38930067c68ffa3414f8e5d25daa", "labels_vector_sha256": "219e7f43f8c5adfc140047abf7e6718e1069cfcba061d05b0e80613ab2d1b2b1", "planned_active_tokens": 66640, "realized_active_tokens": 66640, "cumulative_start": 60755357, "cumulative_end": 60821997, "loss_sum": 26109.506591796875, "token_normalized_loss": 0.3917993186043949, "grad_norm_before_clip": 0.15325790643692017, "learning_rates_at_step": { "lora": 6.869068770019805e-07, "row_tokens": 6.869068770019805e-07 }, "learning_rates_after_step": { "lora": 6.563770405169533e-07, "row_tokens": 6.563770405169533e-07 } }, { "update_id": 928, "row_count": 11, "row_ids_sha256": "ea77e6c894e40ca237be9873d36c92151e2925ca1451fe1bdf7b3b0385fd506f", "input_ids_vector_sha256": "6fc00e580fbca1c3e84e179eafad7a09e769864fdefba90043af6b99696c846a", "labels_vector_sha256": "c3ccd0d377f2d96d50022ff760e61313117e95ee11ef3036d9533f42e943bda3", "planned_active_tokens": 71582, "realized_active_tokens": 71582, "cumulative_start": 60821997, "cumulative_end": 60893579, "loss_sum": 27495.592193603516, "token_normalized_loss": 0.38411321552350475, "grad_norm_before_clip": 0.15090516209602356, "learning_rates_at_step": { "lora": 6.563770405169533e-07, "row_tokens": 6.563770405169533e-07 }, "learning_rates_after_step": { "lora": 6.306473992305606e-07, "row_tokens": 6.306473992305606e-07 } }, { "update_id": 929, "row_count": 12, "row_ids_sha256": "19c0ba5ac049121b419c6b96552c8820469f254592b336fe1871c719727b7090", "input_ids_vector_sha256": "0d67788918b5563ceee7e9f55730cdb211bda6af142b861fd7e2c39debf7a92c", "labels_vector_sha256": "49a89503ee3ff7e796e728fb501ad515adda93dcc9bcfd100816ae340965bce3", "planned_active_tokens": 61622, "realized_active_tokens": 61622, "cumulative_start": 60893579, "cumulative_end": 60955201, "loss_sum": 20915.24105834961, "token_normalized_loss": 0.3394119155228589, "grad_norm_before_clip": 0.15104976296424866, "learning_rates_at_step": { "lora": 6.306473992305606e-07, "row_tokens": 6.306473992305606e-07 }, "learning_rates_after_step": { "lora": 6.046105658412293e-07, "row_tokens": 6.046105658412293e-07 } }, { "update_id": 930, "row_count": 10, "row_ids_sha256": "59ef8ace0c944356a65f3159dfd1f36d6e87fa1e4ceb7b86836f8d8a7e1e3ac8", "input_ids_vector_sha256": "b600e85f4d709372ef090792c1a01eaf5c3509a038bc22f331b9ef5f6fb72f42", "labels_vector_sha256": "52cb50f7e22e4e7dd79d1bf04148024b0fa6753a3e50b30b264817f86f60d29b", "planned_active_tokens": 63643, "realized_active_tokens": 63643, "cumulative_start": 60955201, "cumulative_end": 61018844, "loss_sum": 25807.690307617188, "token_normalized_loss": 0.40550713051894455, "grad_norm_before_clip": 0.15467946231365204, "learning_rates_at_step": { "lora": 6.046105658412293e-07, "row_tokens": 6.046105658412293e-07 }, "learning_rates_after_step": { "lora": 5.773514322635454e-07, "row_tokens": 5.773514322635454e-07 } }, { "update_id": 931, "row_count": 15, "row_ids_sha256": "b88e9644de0fd4bf32052ba35e8af364748286ead2bf46203c21ec24ec3b3a2e", "input_ids_vector_sha256": "5f721a480b1e4ebf2d5d4b1e93bd68dc613b062222d14277672236a588f05b53", "labels_vector_sha256": "0cb5ac8cc432e385dc0b719d63b62231399fd407445ad5df006770d2cbdc44fd", "planned_active_tokens": 68108, "realized_active_tokens": 68108, "cumulative_start": 61018844, "cumulative_end": 61086952, "loss_sum": 24291.335403442383, "token_normalized_loss": 0.3566590621284193, "grad_norm_before_clip": 0.15800903737545013, "learning_rates_at_step": { "lora": 5.773514322635454e-07, "row_tokens": 5.773514322635454e-07 }, "learning_rates_after_step": { "lora": 5.533051652714172e-07, "row_tokens": 5.533051652714172e-07 } }, { "update_id": 932, "row_count": 12, "row_ids_sha256": "df952fdab06990094e5b2c30f0c0070e3ed7657b56b8d48bcc36d6ae273b1165", "input_ids_vector_sha256": "a37b788a16d68edae40ba0397b69b2e205ebaeb407011a499dc60421b885a6b5", "labels_vector_sha256": "a196922f4b35e14dd85ec673ab92dbdddb28adf86f2175c4d2d483b6bed18466", "planned_active_tokens": 61420, "realized_active_tokens": 61420, "cumulative_start": 61086952, "cumulative_end": 61148372, "loss_sum": 20099.39324951172, "token_normalized_loss": 0.3272450870972276, "grad_norm_before_clip": 0.14755046367645264, "learning_rates_at_step": { "lora": 5.533051652714172e-07, "row_tokens": 5.533051652714172e-07 }, "learning_rates_after_step": { "lora": 5.273884712613975e-07, "row_tokens": 5.273884712613975e-07 } }, { "update_id": 933, "row_count": 17, "row_ids_sha256": "7bde8114b63b35489c92c3f0b17d3cc002f79745b0d26974e6ee074067e09ec5", "input_ids_vector_sha256": "8c817d3f48a4b1f1408ee70f7586fa9a4682c1180d00c98496d352ee83debc2f", "labels_vector_sha256": "401b72535638edfd2fc7a4104f5b2024a745088e744480e40ec61183919bf49e", "planned_active_tokens": 67703, "realized_active_tokens": 67703, "cumulative_start": 61148372, "cumulative_end": 61216075, "loss_sum": 24962.387008666992, "token_normalized_loss": 0.368704296835694, "grad_norm_before_clip": 0.15918441116809845, "learning_rates_at_step": { "lora": 5.273884712613975e-07, "row_tokens": 5.273884712613975e-07 }, "learning_rates_after_step": { "lora": 5.028725929212053e-07, "row_tokens": 5.028725929212053e-07 } }, { "update_id": 934, "row_count": 12, "row_ids_sha256": "27275fd3c28ada2eeb23970389b56cb8e6dc7a2adabc1b6d9273f6a40b1f897e", "input_ids_vector_sha256": "017521fbcec484f7231cbcfb7e6f14178328608616220e3ed510558b45ab8a1a", "labels_vector_sha256": "af2577b8551bc270015bd9a5c7f9a772704d945f49ad133cbd472c17d78cda1a", "planned_active_tokens": 65584, "realized_active_tokens": 65584, "cumulative_start": 61216075, "cumulative_end": 61281659, "loss_sum": 24150.747268676758, "token_normalized_loss": 0.36824145018109233, "grad_norm_before_clip": 0.15098083019256592, "learning_rates_at_step": { "lora": 5.028725929212053e-07, "row_tokens": 5.028725929212053e-07 }, "learning_rates_after_step": { "lora": 4.790256273274729e-07, "row_tokens": 4.790256273274729e-07 } }, { "update_id": 935, "row_count": 11, "row_ids_sha256": "c0e17fac96bf00b043e998d28defea98aefa1a4f302f5c6b55a04443f66172bc", "input_ids_vector_sha256": "cc4395b7c0065ed738d515700b298ec497274f857642f9ce92462f71e7367c68", "labels_vector_sha256": "a14b8115f62cfa2a9abf942d51231fadd1c2c715053f4d6339f9e3aa70aaad90", "planned_active_tokens": 65339, "realized_active_tokens": 65339, "cumulative_start": 61281659, "cumulative_end": 61346998, "loss_sum": 21261.336547851562, "token_normalized_loss": 0.32540039712654867, "grad_norm_before_clip": 0.14758890867233276, "learning_rates_at_step": { "lora": 4.790256273274729e-07, "row_tokens": 4.790256273274729e-07 }, "learning_rates_after_step": { "lora": 4.557323263647606e-07, "row_tokens": 4.557323263647606e-07 } }, { "update_id": 936, "row_count": 13, "row_ids_sha256": "93e46fed3258d83ef65ed6f1c460c0ba72949a654e75b67378700596d6abe1d6", "input_ids_vector_sha256": "b71d55079cf29627d55f32b387c43295aa3bc38349776c7471869e2c335ce484", "labels_vector_sha256": "70ac58351a7abd65131e7a32351fc4d39f06182ded4fa2ed6206b1455ea14ed0", "planned_active_tokens": 65404, "realized_active_tokens": 65404, "cumulative_start": 61346998, "cumulative_end": 61412402, "loss_sum": 22273.534957885742, "token_normalized_loss": 0.34055310008387474, "grad_norm_before_clip": 0.1520097255706787, "learning_rates_at_step": { "lora": 4.557323263647606e-07, "row_tokens": 4.557323263647606e-07 }, "learning_rates_after_step": { "lora": 4.335297416096229e-07, "row_tokens": 4.335297416096229e-07 } }, { "update_id": 937, "row_count": 15, "row_ids_sha256": "a1c8bd6fcd06b03e64bc7b1235d084bb2023bd5424170305d6fffe32c163a2a2", "input_ids_vector_sha256": "18beae8d76c5b1e1a41558fc6502e07788509e6a9eda02c16fcfc78454eb5275", "labels_vector_sha256": "183aa5239a15040b22f7a8b25860ed2a49003fc7bb0e8ec8151fd0ba73e53e08", "planned_active_tokens": 63909, "realized_active_tokens": 63909, "cumulative_start": 61412402, "cumulative_end": 61476311, "loss_sum": 25144.510864257812, "token_normalized_loss": 0.3934424081781566, "grad_norm_before_clip": 0.1660357415676117, "learning_rates_at_step": { "lora": 4.335297416096229e-07, "row_tokens": 4.335297416096229e-07 }, "learning_rates_after_step": { "lora": 4.111090165209164e-07, "row_tokens": 4.111090165209164e-07 } }, { "update_id": 938, "row_count": 12, "row_ids_sha256": "7e14218d73bcd800a1b97b2732032fa113410fdb58339f938ab841598418dcba", "input_ids_vector_sha256": "c0f8ff7dc082390e5aab5fd10f5fb9f03a153c4322c2eea2af23dffc91785903", "labels_vector_sha256": "bcdecae9c3518cc73a5ef7b59def8b257d3913ce75fd90f5b289d38546831a30", "planned_active_tokens": 66213, "realized_active_tokens": 66213, "cumulative_start": 61476311, "cumulative_end": 61542524, "loss_sum": 22551.548431396484, "token_normalized_loss": 0.34059094787121086, "grad_norm_before_clip": 0.15021254122257233, "learning_rates_at_step": { "lora": 4.111090165209164e-07, "row_tokens": 4.111090165209164e-07 }, "learning_rates_after_step": { "lora": 3.9025601273816046e-07, "row_tokens": 3.9025601273816046e-07 } }, { "update_id": 939, "row_count": 10, "row_ids_sha256": "2dabad13bd9f38e0c042b7fbce0554f430c7f8a2ac65c47a63b2a9436f382321", "input_ids_vector_sha256": "1a1a0bb7f5a4d57fc170c38c31f3232701e05836f10a1e527d8c2d812aa3d7c3", "labels_vector_sha256": "cf2bb0a82d9862f936cc0d303d894c97ebd278abe38831ce769aeb4603eff7e4", "planned_active_tokens": 63217, "realized_active_tokens": 63217, "cumulative_start": 61542524, "cumulative_end": 61605741, "loss_sum": 24153.938446044922, "token_normalized_loss": 0.38207979572021644, "grad_norm_before_clip": 0.18838568031787872, "learning_rates_at_step": { "lora": 3.9025601273816046e-07, "row_tokens": 3.9025601273816046e-07 }, "learning_rates_after_step": { "lora": 3.6786145799749814e-07, "row_tokens": 3.6786145799749814e-07 } }, { "update_id": 940, "row_count": 18, "row_ids_sha256": "e600e052076e14e87d9c28240227f350c62138d548ae93b2bcc18c38a35ee372", "input_ids_vector_sha256": "0cfe43cf4517342ad7621c703f78be8c5050351b55372166170a8562082b55f5", "labels_vector_sha256": "40c34eb47cfda60b1cd6daf4f3acfa3ee7e3a71f61846f2455d87704b2773f4a", "planned_active_tokens": 69794, "realized_active_tokens": 69794, "cumulative_start": 61605741, "cumulative_end": 61675535, "loss_sum": 22022.90850830078, "token_normalized_loss": 0.3155415724603946, "grad_norm_before_clip": 0.14112840592861176, "learning_rates_at_step": { "lora": 3.6786145799749814e-07, "row_tokens": 3.6786145799749814e-07 }, "learning_rates_after_step": { "lora": 3.475396668480346e-07, "row_tokens": 3.475396668480346e-07 } }, { "update_id": 941, "row_count": 11, "row_ids_sha256": "89ff9a9fd65330b0c1f513f82c7d8f9cd9982a8bb30efa86382fe8608e56d16a", "input_ids_vector_sha256": "c0cd83f1f473075bb95f2f30210507f53b43932cb58b1bce78662f0b7c018ebb", "labels_vector_sha256": "0342fe4af7431cb878a4d6f0f11d05bb8132bc9cf4da4434559ad49c7c10420c", "planned_active_tokens": 65190, "realized_active_tokens": 65190, "cumulative_start": 61675535, "cumulative_end": 61740725, "loss_sum": 25488.542907714844, "token_normalized_loss": 0.39098853977166503, "grad_norm_before_clip": 0.1557544320821762, "learning_rates_at_step": { "lora": 3.475396668480346e-07, "row_tokens": 3.475396668480346e-07 }, "learning_rates_after_step": { "lora": 3.2746444627119176e-07, "row_tokens": 3.2746444627119176e-07 } }, { "update_id": 942, "row_count": 9, "row_ids_sha256": "759a47b89b3dcbdf079e6b33e17d8a3b2600653c59fd23d08d56b884f1a31b86", "input_ids_vector_sha256": "6f982e0a8ff09c4ac342fa1342e485e64728b9f73f110646f79c3fc0700aec99", "labels_vector_sha256": "8ee7155344d866aeb3fe3682a1f424bb0418bb0dd636d379e576d3fc180b5ce7", "planned_active_tokens": 66292, "realized_active_tokens": 66292, "cumulative_start": 61740725, "cumulative_end": 61807017, "loss_sum": 26285.4541015625, "token_normalized_loss": 0.3965101988409235, "grad_norm_before_clip": 0.15415890514850616, "learning_rates_at_step": { "lora": 3.2746444627119176e-07, "row_tokens": 3.2746444627119176e-07 }, "learning_rates_after_step": { "lora": 3.0926248244588784e-07, "row_tokens": 3.0926248244588784e-07 } }, { "update_id": 943, "row_count": 11, "row_ids_sha256": "7e55d64695d4be114f16967d46a7f00708cc365bdcc116256e0d2a3e5a9eb9d4", "input_ids_vector_sha256": "d2848283327164e8005a0175b39ecefe403d31ee04e4cb545b25feb36e6eb732", "labels_vector_sha256": "0b69f6a033ce4e6e06463e079e38178e43f405978c6b0835ce7b5836e927bc17", "planned_active_tokens": 61880, "realized_active_tokens": 61880, "cumulative_start": 61807017, "cumulative_end": 61868897, "loss_sum": 26202.42611694336, "token_normalized_loss": 0.4234393360850575, "grad_norm_before_clip": 0.16768725216388702, "learning_rates_at_step": { "lora": 3.0926248244588784e-07, "row_tokens": 3.0926248244588784e-07 }, "learning_rates_after_step": { "lora": 2.906217113261611e-07, "row_tokens": 2.906217113261611e-07 } }, { "update_id": 944, "row_count": 14, "row_ids_sha256": "5215baf8f144e5ed88ab2e7bfe5531a71ec8a093a3e4861dc5f3b7166bbe9857", "input_ids_vector_sha256": "48a9e283ce0480ab1edea6ef2582077fa7ee7aa4ba3efaaf4617a8ac163bf5d4", "labels_vector_sha256": "a05b83c9b939b7ca8b5d39b90fa9e397507c554139f643e86afe435b68c520ae", "planned_active_tokens": 65284, "realized_active_tokens": 65284, "cumulative_start": 61868897, "cumulative_end": 61934181, "loss_sum": 25501.272705078125, "token_normalized_loss": 0.39062056101155146, "grad_norm_before_clip": 0.15158990025520325, "learning_rates_at_step": { "lora": 2.906217113261611e-07, "row_tokens": 2.906217113261611e-07 }, "learning_rates_after_step": { "lora": 2.721624232619069e-07, "row_tokens": 2.721624232619069e-07 } }, { "update_id": 945, "row_count": 11, "row_ids_sha256": "c68c32491fd6693865a6b1e5194e04281dcbab0868b4ec75047b3a6b3784eaed", "input_ids_vector_sha256": "f1f2edf9bbcbbd083cd255705554ef4fb484e2a8b8b06df631b50102c30cc698", "labels_vector_sha256": "4f90de870cfb4fe7a778e8c2db58cec388c73a303ad5f96b3fc025d1521c4fe8", "planned_active_tokens": 66740, "realized_active_tokens": 66740, "cumulative_start": 61934181, "cumulative_end": 62000921, "loss_sum": 26970.216278076172, "token_normalized_loss": 0.40410872457411107, "grad_norm_before_clip": 0.1623203456401825, "learning_rates_at_step": { "lora": 2.721624232619069e-07, "row_tokens": 2.721624232619069e-07 }, "learning_rates_after_step": { "lora": 2.540263484767491e-07, "row_tokens": 2.540263484767491e-07 } }, { "update_id": 946, "row_count": 9, "row_ids_sha256": "a07be2341d9fd6044302afc7f37cc1eb39be763720d512b3d33f928ae5ca9470", "input_ids_vector_sha256": "c1940be069330c5f37cf0510b76ab1d7b1dd0ebc790e9763dfae33b99940d112", "labels_vector_sha256": "8af61de455e9f17c63ffd3d893ffcd7b68ee4c2bc6c6b03523b3dcbd9451c800", "planned_active_tokens": 67808, "realized_active_tokens": 67808, "cumulative_start": 62000921, "cumulative_end": 62068729, "loss_sum": 26909.5029296875, "token_normalized_loss": 0.39684849766528285, "grad_norm_before_clip": 0.1522219032049179, "learning_rates_at_step": { "lora": 2.540263484767491e-07, "row_tokens": 2.540263484767491e-07 }, "learning_rates_after_step": { "lora": 2.3793920170839812e-07, "row_tokens": 2.3793920170839812e-07 } }, { "update_id": 947, "row_count": 12, "row_ids_sha256": "c9b8d9809630ce1cc9e1a6814cfd84edde32bc2ba262265fb5ea13258e438f58", "input_ids_vector_sha256": "cd3e4732f2a045ffa4f1d864ca7070ec6142516840004254424a80d3b692664a", "labels_vector_sha256": "e3d3f5d0d889bbce27ec66763ff5eeb74caef3852cb8310b7376136ce0702dbf", "planned_active_tokens": 62198, "realized_active_tokens": 62198, "cumulative_start": 62068729, "cumulative_end": 62130927, "loss_sum": 23295.659301757812, "token_normalized_loss": 0.37454032769153045, "grad_norm_before_clip": 0.1553712636232376, "learning_rates_at_step": { "lora": 2.3793920170839812e-07, "row_tokens": 2.3793920170839812e-07 }, "learning_rates_after_step": { "lora": 2.2210652898944084e-07, "row_tokens": 2.2210652898944084e-07 } }, { "update_id": 948, "row_count": 13, "row_ids_sha256": "086c4a76106542f4fe7b8189457b0c215995e9d940c917bb48385eebbebeda41", "input_ids_vector_sha256": "02fbb050af302cbf13bb968069a07e31c29a360f008cb08a39276237a892ccb6", "labels_vector_sha256": "c19f5f27c83d20e37c1557c255dd9274fbdaba4adeb98b0d17d5ee716c3b606c", "planned_active_tokens": 63298, "realized_active_tokens": 63298, "cumulative_start": 62130927, "cumulative_end": 62194225, "loss_sum": 25389.105926513672, "token_normalized_loss": 0.4011043939226148, "grad_norm_before_clip": 0.1656549870967865, "learning_rates_at_step": { "lora": 2.2210652898944084e-07, "row_tokens": 2.2210652898944084e-07 }, "learning_rates_after_step": { "lora": 2.0592880427316441e-07, "row_tokens": 2.0592880427316441e-07 } }, { "update_id": 949, "row_count": 14, "row_ids_sha256": "cee572f9e0ca183573d64d72317c2bc054247330f99c9c6632cb5a29affd658a", "input_ids_vector_sha256": "1be76904a8de6bf5d4303e303579e5418fc0b9ef2880a56cdf74e567c244c5da", "labels_vector_sha256": "e8553b38ebf91a4ffdf9b19b5d0913745f8bbdb50a4365c5627afa1fde2a3bfc", "planned_active_tokens": 67049, "realized_active_tokens": 67049, "cumulative_start": 62194225, "cumulative_end": 62261274, "loss_sum": 26852.02471923828, "token_normalized_loss": 0.40048359735772765, "grad_norm_before_clip": 0.1841222047805786, "learning_rates_at_step": { "lora": 2.0592880427316441e-07, "row_tokens": 2.0592880427316441e-07 }, "learning_rates_after_step": { "lora": 1.9090274547071686e-07, "row_tokens": 1.9090274547071686e-07 } }, { "update_id": 950, "row_count": 8, "row_ids_sha256": "6000de5c3231785a731d74c963ab45e537dae26702ce019ce2204369fa403d57", "input_ids_vector_sha256": "bd15e90f53ebb9d2397ee5067761b40cb5066d9731405b518367af35b4e50e3e", "labels_vector_sha256": "cf61bbaaebd91a528b4163d89e7834b74935c52fb7c6360a83751040816272c9", "planned_active_tokens": 64673, "realized_active_tokens": 64673, "cumulative_start": 62261274, "cumulative_end": 62325947, "loss_sum": 26704.065795898438, "token_normalized_loss": 0.4129090315262697, "grad_norm_before_clip": 0.189000204205513, "learning_rates_at_step": { "lora": 1.9090274547071686e-07, "row_tokens": 1.9090274547071686e-07 }, "learning_rates_after_step": { "lora": 1.7472726809691364e-07, "row_tokens": 1.7472726809691364e-07 } }, { "update_id": 951, "row_count": 15, "row_ids_sha256": "8fb1d4162027c86883bf20b3a0f8b76a5f72d23338c16bf33ef580955ccddbf0", "input_ids_vector_sha256": "10d57e9727f0e8109dcfe73ff154e5d97df45d5af88e542e2822de69d1142fbb", "labels_vector_sha256": "ed32c43d2d6b445e1e11375e93cce00a886659bb5eaa12285bcb0c4d725b3681", "planned_active_tokens": 72529, "realized_active_tokens": 72529, "cumulative_start": 62325947, "cumulative_end": 62398476, "loss_sum": 25686.28727722168, "token_normalized_loss": 0.3541519568341171, "grad_norm_before_clip": 0.14138659834861755, "learning_rates_at_step": { "lora": 1.7472726809691364e-07, "row_tokens": 1.7472726809691364e-07 }, "learning_rates_after_step": { "lora": 1.6236713459102936e-07, "row_tokens": 1.6236713459102936e-07 } }, { "update_id": 952, "row_count": 12, "row_ids_sha256": "755560d01f15b2c15063cb22d57a39b69eab33a681eeb04d6ccb8d6002b4304b", "input_ids_vector_sha256": "d1ea0533f915e9cee72b37aa786a95909f1ec225c652e3d9111e2312349af34c", "labels_vector_sha256": "28aed8cfb71de2720d56ea9d521ad4534c3af50acc1b1f8df14fb7d8cc1dc882", "planned_active_tokens": 57711, "realized_active_tokens": 57711, "cumulative_start": 62398476, "cumulative_end": 62456187, "loss_sum": 21738.71661376953, "token_normalized_loss": 0.37668237621544476, "grad_norm_before_clip": 0.16800370812416077, "learning_rates_at_step": { "lora": 1.6236713459102936e-07, "row_tokens": 1.6236713459102936e-07 }, "learning_rates_after_step": { "lora": 1.484552406207873e-07, "row_tokens": 1.484552406207873e-07 } }, { "update_id": 953, "row_count": 14, "row_ids_sha256": "fd61c96d2cf84cf239f84cbb7345e0debe61d440358cacf9539bdaff38d787e0", "input_ids_vector_sha256": "f036062a335cee165c61e2407fdf6028565bcd4e52d9bf1a65bd7324d5d134c2", "labels_vector_sha256": "e1df263511021a7dc6cc3ef904711f732a392980168b89308e91d1ad1a0b900f", "planned_active_tokens": 67647, "realized_active_tokens": 67647, "cumulative_start": 62456187, "cumulative_end": 62523834, "loss_sum": 24241.435180664062, "token_normalized_loss": 0.3583519621071749, "grad_norm_before_clip": 0.14543063938617706, "learning_rates_at_step": { "lora": 1.484552406207873e-07, "row_tokens": 1.484552406207873e-07 }, "learning_rates_after_step": { "lora": 1.3554866968846225e-07, "row_tokens": 1.3554866968846225e-07 } }, { "update_id": 954, "row_count": 13, "row_ids_sha256": "f72be1950066d03a1f3261ea2c903217be764861a7c2c1491cdf4e1c0c0c5f1e", "input_ids_vector_sha256": "695f69e10ccfe5dffee804597d394803dd75a1b0f8854b4186a82fc257b91345", "labels_vector_sha256": "26e8200449357772548bc0e73c67359a4de7a08c47038f6080ede4011541c58d", "planned_active_tokens": 65651, "realized_active_tokens": 65651, "cumulative_start": 62523834, "cumulative_end": 62589485, "loss_sum": 22239.576782226562, "token_normalized_loss": 0.3387545777250394, "grad_norm_before_clip": 0.1486036628484726, "learning_rates_at_step": { "lora": 1.3554866968846225e-07, "row_tokens": 1.3554866968846225e-07 }, "learning_rates_after_step": { "lora": 1.2329505990426593e-07, "row_tokens": 1.2329505990426593e-07 } }, { "update_id": 955, "row_count": 7, "row_ids_sha256": "3414ae075512f6b61303130cffb536e4d401bb775738135a65ab8cba0aa7e4e5", "input_ids_vector_sha256": "f4cce238ce340a9fba5411330714d9f57da5f587b9d1583a4a30d32e02bbdd50", "labels_vector_sha256": "918eac2b1317cf1b1b21abe4f80a58034147e6644972235d7521a519ac50b068", "planned_active_tokens": 65286, "realized_active_tokens": 65286, "cumulative_start": 62589485, "cumulative_end": 62654771, "loss_sum": 25215.0458984375, "token_normalized_loss": 0.3862243957117529, "grad_norm_before_clip": 0.3765133321285248, "learning_rates_at_step": { "lora": 1.2329505990426593e-07, "row_tokens": 1.2329505990426593e-07 }, "learning_rates_after_step": { "lora": 1.111044176991205e-07, "row_tokens": 1.111044176991205e-07 } }, { "update_id": 956, "row_count": 12, "row_ids_sha256": "cde67390c55f278de26eaaed567d14a808e7f10ff9a8f8062520fd21782bade5", "input_ids_vector_sha256": "2898f0d9ea4ce84c579edefc87871369a6f0460b5f8742bcd6789d9de83478c7", "labels_vector_sha256": "0a38e432d97136711ba4209ecf68580216e00bf289d705b551104d413bcaaafd", "planned_active_tokens": 68253, "realized_active_tokens": 68253, "cumulative_start": 62654771, "cumulative_end": 62723024, "loss_sum": 25340.872497558594, "token_normalized_loss": 0.3712785151943298, "grad_norm_before_clip": 0.14753606915473938, "learning_rates_at_step": { "lora": 1.111044176991205e-07, "row_tokens": 1.111044176991205e-07 }, "learning_rates_after_step": { "lora": 9.991974276468696e-08, "row_tokens": 9.991974276468696e-08 } }, { "update_id": 957, "row_count": 11, "row_ids_sha256": "f5f50d6cb77541cbefd62e777390e891ac6d86bb2ea15f81455d6ccfe57f2956", "input_ids_vector_sha256": "1e793a5968afc6f777e39520f834dced20d700467abf153d4dd4f39ba0f9ca87", "labels_vector_sha256": "16b998fc52f6c054d4f2c06d2f0e602f719dad953fa2a4f403a377e50ca588c3", "planned_active_tokens": 65995, "realized_active_tokens": 65995, "cumulative_start": 62723024, "cumulative_end": 62789019, "loss_sum": 20404.662109375, "token_normalized_loss": 0.30918497021554664, "grad_norm_before_clip": 0.14317916333675385, "learning_rates_at_step": { "lora": 9.991974276468696e-08, "row_tokens": 9.991974276468696e-08 }, "learning_rates_after_step": { "lora": 8.943369202883411e-08, "row_tokens": 8.943369202883411e-08 } }, { "update_id": 958, "row_count": 11, "row_ids_sha256": "a7f92b43a81f4044675912399d587d50eda9624eb15a434235f4c6d4f871611d", "input_ids_vector_sha256": "0264fcfbae062d3eddca7ba365adb5352de3796a8a2d25e9546ad1bf707c503c", "labels_vector_sha256": "0f024c1783da8dd3eb9588a201dda6cd90527c26edc35a67d1b1e433e193c349", "planned_active_tokens": 65316, "realized_active_tokens": 65316, "cumulative_start": 62789019, "cumulative_end": 62854335, "loss_sum": 22740.83056640625, "token_normalized_loss": 0.34816630789402675, "grad_norm_before_clip": 0.14984846115112305, "learning_rates_at_step": { "lora": 8.943369202883411e-08, "row_tokens": 8.943369202883411e-08 }, "learning_rates_after_step": { "lora": 7.880436110469513e-08, "row_tokens": 7.880436110469513e-08 } }, { "update_id": 959, "row_count": 11, "row_ids_sha256": "a8fdae7d1fa15e264cb70f924fa3d7c3ff4a8163a43115ec640c9c6d280391a5", "input_ids_vector_sha256": "38409a5d7b00678bedb7e2c5e7394eb3a6865592e8662f9da7a15f39bbfdd92a", "labels_vector_sha256": "acfe533bf5253ad18f32322ff4d8bd68c28143843243dc7152ed14bf44a545b2", "planned_active_tokens": 70245, "realized_active_tokens": 70245, "cumulative_start": 62854335, "cumulative_end": 62924580, "loss_sum": 27948.34878540039, "token_normalized_loss": 0.397869581968829, "grad_norm_before_clip": 0.15612605214118958, "learning_rates_at_step": { "lora": 7.880436110469513e-08, "row_tokens": 7.880436110469513e-08 }, "learning_rates_after_step": { "lora": 7.022649121665725e-08, "row_tokens": 7.022649121665725e-08 } }, { "update_id": 960, "row_count": 10, "row_ids_sha256": "b161071282ef733344acfd6ad2a96f1d16dd961024246170a00154434e123824", "input_ids_vector_sha256": "125c91db8961ad33aecebc45a047b09374734c406df31df6045f05b4f1ee1371", "labels_vector_sha256": "a2e662fc9bf53d7708e1d8af370be4ef3a68e3cb69b0c78bcb30debb2912da61", "planned_active_tokens": 60222, "realized_active_tokens": 60222, "cumulative_start": 62924580, "cumulative_end": 62984802, "loss_sum": 22750.359588623047, "token_normalized_loss": 0.37777489270736686, "grad_norm_before_clip": 0.16068950295448303, "learning_rates_at_step": { "lora": 7.022649121665725e-08, "row_tokens": 7.022649121665725e-08 }, "learning_rates_after_step": { "lora": 6.135086337509255e-08, "row_tokens": 6.135086337509255e-08 } }, { "update_id": 961, "row_count": 16, "row_ids_sha256": "e40342697750fc027eac382332ca2f55393d18c5b3bb685c3b99a932db238a9e", "input_ids_vector_sha256": "617a3f567d9ff7991db9655e6365c8a7cb759b6bcc14a890cd114cf189ac52d1", "labels_vector_sha256": "f3b673f2170162ed85f1e60bf189effc54411827caa124ce386b56fc5eb3fdde", "planned_active_tokens": 66324, "realized_active_tokens": 66324, "cumulative_start": 62984802, "cumulative_end": 63051126, "loss_sum": 23360.07632446289, "token_normalized_loss": 0.3522115120388229, "grad_norm_before_clip": 0.14887601137161255, "learning_rates_at_step": { "lora": 6.135086337509255e-08, "row_tokens": 6.135086337509255e-08 }, "learning_rates_after_step": { "lora": 5.290387575719313e-08, "row_tokens": 5.290387575719313e-08 } }, { "update_id": 962, "row_count": 11, "row_ids_sha256": "f41b783c52bd4ab667d7a016198d05b50148bc946682b4f5aae2091855b03310", "input_ids_vector_sha256": "c111ca903d04aa0ce5c50630d2d543d2b3e5d62381d44a98a0ef851b85e7413c", "labels_vector_sha256": "6e57536083ca9b8574537b3aca56cbdcb817da799d5c8299d10a9d977b103119", "planned_active_tokens": 67742, "realized_active_tokens": 67742, "cumulative_start": 63051126, "cumulative_end": 63118868, "loss_sum": 24716.200073242188, "token_normalized_loss": 0.3648578440737236, "grad_norm_before_clip": 0.14971105754375458, "learning_rates_at_step": { "lora": 5.290387575719313e-08, "row_tokens": 5.290387575719313e-08 }, "learning_rates_after_step": { "lora": 4.577418487543561e-08, "row_tokens": 4.577418487543561e-08 } }, { "update_id": 963, "row_count": 13, "row_ids_sha256": "abf1df7300c9e1902790aa9d98366c1d7ab78ce1c03c9634df0aa6d9ac670adc", "input_ids_vector_sha256": "0e093bc15b6f918f9032a22386e715166ad898a6606e70df103dc82ae9df4a67", "labels_vector_sha256": "a5d893ea0d88dcfd1fcdc42ab0866f745887017dfe146c4d98d3939ed08b1a2c", "planned_active_tokens": 61521, "realized_active_tokens": 61521, "cumulative_start": 63118868, "cumulative_end": 63180389, "loss_sum": 22781.760009765625, "token_normalized_loss": 0.37030867524529226, "grad_norm_before_clip": 0.1543746292591095, "learning_rates_at_step": { "lora": 4.577418487543561e-08, "row_tokens": 4.577418487543561e-08 }, "learning_rates_after_step": { "lora": 3.795691632513254e-08, "row_tokens": 3.795691632513254e-08 } }, { "update_id": 964, "row_count": 9, "row_ids_sha256": "3db916bb5a72a84220c5a415008819748bf5a8bde16443a7c7d412b2cda7da49", "input_ids_vector_sha256": "59b21f2029c816ab8303950a0d9850082b6f98e36da9b79070266fef174cc3cf", "labels_vector_sha256": "750c86f4e272ca5036b61fae0a2d2bb78df357767a0302e20ad4a424cd3fba1b", "planned_active_tokens": 73257, "realized_active_tokens": 73257, "cumulative_start": 63180389, "cumulative_end": 63253646, "loss_sum": 26655.72393798828, "token_normalized_loss": 0.3638658959278742, "grad_norm_before_clip": 0.14548158645629883, "learning_rates_at_step": { "lora": 3.795691632513254e-08, "row_tokens": 3.795691632513254e-08 }, "learning_rates_after_step": { "lora": 3.2341524304313474e-08, "row_tokens": 3.2341524304313474e-08 } }, { "update_id": 965, "row_count": 9, "row_ids_sha256": "81fbc11e25de5ec7e13d4618ffe437dafc6b51b1db421ce4568067333a575d34", "input_ids_vector_sha256": "da29634e4ad842b7bbf517ed0918c2b03975ac60a182f741ac9fa9ef4afac297", "labels_vector_sha256": "23f5a0206eefa0d9d02544c3cd70cb04c5980753c768c41efe66a4f78968ecbf", "planned_active_tokens": 57412, "realized_active_tokens": 57412, "cumulative_start": 63253646, "cumulative_end": 63311058, "loss_sum": 21709.44091796875, "token_normalized_loss": 0.3781342039637837, "grad_norm_before_clip": 0.15773670375347137, "learning_rates_at_step": { "lora": 3.2341524304313474e-08, "row_tokens": 3.2341524304313474e-08 }, "learning_rates_after_step": { "lora": 2.672662697261741e-08, "row_tokens": 2.672662697261741e-08 } }, { "update_id": 966, "row_count": 12, "row_ids_sha256": "7cd12b3490267804379565a0fdd94926fb6037bb126453d122b5d6a51e286e8a", "input_ids_vector_sha256": "0b8de4f3d26d555ffbabe136c131c9067cc5345c9eb5258f352bb2b286fcd9c1", "labels_vector_sha256": "191028a88885d337d09a6796424d8b9b3addf85152a0f67bcf62fed4ae63ae8b", "planned_active_tokens": 62646, "realized_active_tokens": 62646, "cumulative_start": 63311058, "cumulative_end": 63373704, "loss_sum": 24077.944427490234, "token_normalized_loss": 0.3843492709429211, "grad_norm_before_clip": 0.1591206192970276, "learning_rates_at_step": { "lora": 2.672662697261741e-08, "row_tokens": 2.672662697261741e-08 }, "learning_rates_after_step": { "lora": 2.1392863003866227e-08, "row_tokens": 2.1392863003866227e-08 } }, { "update_id": 967, "row_count": 12, "row_ids_sha256": "260dad841e6bc3e918b710ba4d63a1970ad00d0d69742e9fe384c0a8fb88ae5e", "input_ids_vector_sha256": "1cc28a9f283f22a4bdafabc918baa42e0162faa6f357a2bcafd0dc25fc95b9b7", "labels_vector_sha256": "a061f9508e4281bc4c71750a2230ec2a472328eb33e711308d17cfbebcaad3a4", "planned_active_tokens": 65958, "realized_active_tokens": 65958, "cumulative_start": 63373704, "cumulative_end": 63439662, "loss_sum": 25931.114685058594, "token_normalized_loss": 0.393145860775927, "grad_norm_before_clip": 0.1629813313484192, "learning_rates_at_step": { "lora": 2.1392863003866227e-08, "row_tokens": 2.1392863003866227e-08 }, "learning_rates_after_step": { "lora": 1.6536403479411324e-08, "row_tokens": 1.6536403479411324e-08 } }, { "update_id": 968, "row_count": 18, "row_ids_sha256": "28fffd9598823582292c09bd430558c9af34734d5de92b42ab789a248a55f518", "input_ids_vector_sha256": "6ca6996a7eecc28cc62e3ea66f949900fc4fc5abe866a22cf1abc2c5f2096218", "labels_vector_sha256": "4846ee0fd175601a137b2c21b91e86699e14228088ca9498a82c0fa2583f4d44", "planned_active_tokens": 67677, "realized_active_tokens": 67677, "cumulative_start": 63439662, "cumulative_end": 63507339, "loss_sum": 23217.050048828125, "token_normalized_loss": 0.34305672604914705, "grad_norm_before_clip": 0.1612449437379837, "learning_rates_at_step": { "lora": 1.6536403479411324e-08, "row_tokens": 1.6536403479411324e-08 }, "learning_rates_after_step": { "lora": 1.24075041510463e-08, "row_tokens": 1.24075041510463e-08 } }, { "update_id": 969, "row_count": 10, "row_ids_sha256": "23c4e236aa140a0fd28bab5d12754c914d2e9b18e6574d4d4d21bb8243a3d733", "input_ids_vector_sha256": "7fa61a5a16200aac6e1bf5234f1d939d971a10f37f9c7d3fe92358fa7edf8923", "labels_vector_sha256": "4376232b757a137558ea7aa4cff992112a0d19532754b9506c17933dbb6e033c", "planned_active_tokens": 65898, "realized_active_tokens": 65898, "cumulative_start": 63507339, "cumulative_end": 63573237, "loss_sum": 26387.504852294922, "token_normalized_loss": 0.4004295252100962, "grad_norm_before_clip": 0.16804347932338715, "learning_rates_at_step": { "lora": 1.24075041510463e-08, "row_tokens": 1.24075041510463e-08 }, "learning_rates_after_step": { "lora": 8.701408574496305e-09, "row_tokens": 8.701408574496305e-09 } }, { "update_id": 970, "row_count": 8, "row_ids_sha256": "c0cb856cadb4a8c9a5be5f00dc0871da5cef33d555a278c2d1294b31658736b7", "input_ids_vector_sha256": "0a422b8c1cafebab80277fa7ce7a37d241bc9af4ae8f95f31bec928a994bfc8b", "labels_vector_sha256": "2477346f57c6e76ffa8535d61d9ebee91585bd6a60cbac83a2c6420d6f2ff544", "planned_active_tokens": 69354, "realized_active_tokens": 69354, "cumulative_start": 63573237, "cumulative_end": 63642591, "loss_sum": 27443.371948242188, "token_normalized_loss": 0.3956999156247972, "grad_norm_before_clip": 0.14875589311122894, "learning_rates_at_step": { "lora": 8.701408574496305e-09, "row_tokens": 8.701408574496305e-09 }, "learning_rates_after_step": { "lora": 6.07305222164456e-09, "row_tokens": 6.07305222164456e-09 } }, { "update_id": 971, "row_count": 8, "row_ids_sha256": "e600b5c2be811f29f81370681d4e8bb64bb910b6c92d78870b07960d8ba0fca1", "input_ids_vector_sha256": "ab0eaa2a205c837669e8df4abb453d395a34575e23bbd4d935fe4303eb17e9ba", "labels_vector_sha256": "7b96740cba0d8f1339dea53d37cead2acef6aaeece01e059f5192cf17dda0b87", "planned_active_tokens": 58797, "realized_active_tokens": 58797, "cumulative_start": 63642591, "cumulative_end": 63701388, "loss_sum": 23238.96807861328, "token_normalized_loss": 0.3952407108970403, "grad_norm_before_clip": 0.1675461381673813, "learning_rates_at_step": { "lora": 6.07305222164456e-09, "row_tokens": 6.07305222164456e-09 }, "learning_rates_after_step": { "lora": 3.5419545492743065e-09, "row_tokens": 3.5419545492743065e-09 } }, { "update_id": 972, "row_count": 15, "row_ids_sha256": "ae0019df7f2a10f34142bdadf81810f9022df8c7cd5daebc0622fc4d04c108d8", "input_ids_vector_sha256": "39b2e0da1f8f4360943faec329231c112009b84271f585d72c8ee63fbcbf768c", "labels_vector_sha256": "92c86478e6a59134372f321a538bdc1e6d6ffd7539bfeb53a72ee3e366387dba", "planned_active_tokens": 70531, "realized_active_tokens": 70531, "cumulative_start": 63701388, "cumulative_end": 63771919, "loss_sum": 24893.72998046875, "token_normalized_loss": 0.35294735620462986, "grad_norm_before_clip": 0.1439007669687271, "learning_rates_at_step": { "lora": 3.5419545492743065e-09, "row_tokens": 3.5419545492743065e-09 }, "learning_rates_after_step": { "lora": 1.8197897977023647e-09, "row_tokens": 1.8197897977023647e-09 } }, { "update_id": 973, "row_count": 9, "row_ids_sha256": "05488b05d9f41d2c238c1c4d9b3373ae8e743f470dd914b2ebee95a81de686b3", "input_ids_vector_sha256": "09c6d534f73e93190f7a910c7d5bd087b0d89c4aed9061509f1075a8cf8fd60a", "labels_vector_sha256": "c798b5a1b2c0052af9353c833c8e91c6151c8ab7a525309265139e3753307057", "planned_active_tokens": 64555, "realized_active_tokens": 64555, "cumulative_start": 63771919, "cumulative_end": 63836474, "loss_sum": 26518.772827148438, "token_normalized_loss": 0.4107934757516604, "grad_norm_before_clip": 0.16435874998569489, "learning_rates_at_step": { "lora": 1.8197897977023647e-09, "row_tokens": 1.8197897977023647e-09 }, "learning_rates_after_step": { "lora": 5.621527687127426e-10, "row_tokens": 5.621527687127426e-10 } }, { "update_id": 974, "row_count": 15, "row_ids_sha256": "e7ff3b05757ddaf91e6c2598677002b3c59f8fc3b89f5d403d2ab055ccb7b679", "input_ids_vector_sha256": "2ea962ac45840573371fc7497e5d52439a3a963f4098ba9148e6a1b2c178736a", "labels_vector_sha256": "bac34bc497331dd32fc988ca39eb977fc50dc823867bdfd36afe15066df144d9", "planned_active_tokens": 72574, "realized_active_tokens": 72574, "cumulative_start": 63836474, "cumulative_end": 63909048, "loss_sum": 28707.311157226562, "token_normalized_loss": 0.39555916936129415, "grad_norm_before_clip": 0.14986871182918549, "learning_rates_at_step": { "lora": 5.621527687127426e-10, "row_tokens": 5.621527687127426e-10 }, "learning_rates_after_step": { "lora": 7.353348751015787e-11, "row_tokens": 7.353348751015787e-11 } }, { "update_id": 975, "row_count": 7, "row_ids_sha256": "e7e16246e203c89414439c06c1586a77d32ae2d2d73ed04ddaeb985b41fa86f8", "input_ids_vector_sha256": "c6252b4fd728e62641e884f10103a935488cfe21dcbf4a582fada3aff6c26365", "labels_vector_sha256": "333683e3fc30938675b25e5b59d0fbe698bc83ff40d09d8ad3fa9fe66b0c3a6d", "planned_active_tokens": 57964, "realized_active_tokens": 57964, "cumulative_start": 63909048, "cumulative_end": 63967012, "loss_sum": 22881.276580810547, "token_normalized_loss": 0.39474978574305686, "grad_norm_before_clip": 0.1675298511981964, "learning_rates_at_step": { "lora": 7.353348751015787e-11, "row_tokens": 7.353348751015787e-11 }, "learning_rates_after_step": { "lora": 0.0, "row_tokens": 0.0 } }, { "update_id": 976, "row_count": 5, "row_ids_sha256": "3cf83de80341a1d3ea3428a39254fdf0bd924bb487c3d57029f64ea8a30dd953", "input_ids_vector_sha256": "cb96bb58f472e92d9c90253c04cf64d25de3f52d71ba9efb442e084eec92e24a", "labels_vector_sha256": "db6852f1aab3dc3b8ab7211b9498b4f638be1e349a4bdfbc757fb4db45a1afe6", "planned_active_tokens": 32842, "realized_active_tokens": 32842, "cumulative_start": 63967012, "cumulative_end": 63999854, "loss_sum": 12566.921936035156, "token_normalized_loss": 0.3826478879494293, "grad_norm_before_clip": 0.21681900322437286, "learning_rates_at_step": { "lora": 0.0, "row_tokens": 0.0 }, "learning_rates_after_step": { "lora": 0.0, "row_tokens": 0.0 } } ], "frozen_base_digest_start": { "scope": "frozen_base", "sha256": "e6ad2d1626ce1bba946ed9a10f7560ba5a4e101d611421670d0549ead9ec9e77", "parameter_count": 399, "bytes": 8822848512, "names_sha256": "76f6fba21da1d275c17e0470efbad7fb1d99cdeef7b4ffac8a5ac71ef82fdfa8" }, "optimizer_membership": { "schema": "think-b-2ep-optimizer-membership/1", "token_bake_enabled": false, "groups": [ { "group": "lora", "param_count": 504, "params": [ { "name": "base_model.model.model.layers.0.self_attn.q_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.0.self_attn.q_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.0.self_attn.k_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.0.self_attn.k_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.0.self_attn.v_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.0.self_attn.v_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.0.self_attn.o_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.0.self_attn.o_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.0.mlp.gate_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.0.mlp.gate_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.0.mlp.up_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.0.mlp.up_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.0.mlp.down_proj.lora_A.default.weight", "shape": [ 64, 9728 ] }, { "name": "base_model.model.model.layers.0.mlp.down_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.1.self_attn.q_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.1.self_attn.q_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.1.self_attn.k_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.1.self_attn.k_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.1.self_attn.v_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.1.self_attn.v_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.1.self_attn.o_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.1.self_attn.o_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.1.mlp.gate_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.1.mlp.gate_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.1.mlp.up_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.1.mlp.up_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.1.mlp.down_proj.lora_A.default.weight", "shape": [ 64, 9728 ] }, { "name": "base_model.model.model.layers.1.mlp.down_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.2.self_attn.q_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.2.self_attn.q_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.2.self_attn.k_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.2.self_attn.k_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.2.self_attn.v_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.2.self_attn.v_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.2.self_attn.o_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.2.self_attn.o_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.2.mlp.gate_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.2.mlp.gate_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.2.mlp.up_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.2.mlp.up_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.2.mlp.down_proj.lora_A.default.weight", "shape": [ 64, 9728 ] }, { "name": "base_model.model.model.layers.2.mlp.down_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.3.self_attn.q_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.3.self_attn.q_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.3.self_attn.k_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.3.self_attn.k_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.3.self_attn.v_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.3.self_attn.v_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.3.self_attn.o_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.3.self_attn.o_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.3.mlp.gate_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.3.mlp.gate_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.3.mlp.up_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.3.mlp.up_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.3.mlp.down_proj.lora_A.default.weight", "shape": [ 64, 9728 ] }, { "name": "base_model.model.model.layers.3.mlp.down_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.4.self_attn.q_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.4.self_attn.q_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.4.self_attn.k_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.4.self_attn.k_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.4.self_attn.v_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.4.self_attn.v_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.4.self_attn.o_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.4.self_attn.o_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.4.mlp.gate_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.4.mlp.gate_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.4.mlp.up_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.4.mlp.up_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.4.mlp.down_proj.lora_A.default.weight", "shape": [ 64, 9728 ] }, { "name": "base_model.model.model.layers.4.mlp.down_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.5.self_attn.q_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.5.self_attn.q_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.5.self_attn.k_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.5.self_attn.k_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.5.self_attn.v_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.5.self_attn.v_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.5.self_attn.o_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.5.self_attn.o_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.5.mlp.gate_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.5.mlp.gate_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.5.mlp.up_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.5.mlp.up_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.5.mlp.down_proj.lora_A.default.weight", "shape": [ 64, 9728 ] }, { "name": "base_model.model.model.layers.5.mlp.down_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.6.self_attn.q_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.6.self_attn.q_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.6.self_attn.k_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.6.self_attn.k_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.6.self_attn.v_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.6.self_attn.v_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.6.self_attn.o_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.6.self_attn.o_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.6.mlp.gate_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.6.mlp.gate_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.6.mlp.up_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.6.mlp.up_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.6.mlp.down_proj.lora_A.default.weight", "shape": [ 64, 9728 ] }, { "name": "base_model.model.model.layers.6.mlp.down_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.7.self_attn.q_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.7.self_attn.q_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.7.self_attn.k_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.7.self_attn.k_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.7.self_attn.v_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.7.self_attn.v_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.7.self_attn.o_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.7.self_attn.o_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.7.mlp.gate_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.7.mlp.gate_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.7.mlp.up_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.7.mlp.up_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.7.mlp.down_proj.lora_A.default.weight", "shape": [ 64, 9728 ] }, { "name": "base_model.model.model.layers.7.mlp.down_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.8.self_attn.q_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.8.self_attn.q_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.8.self_attn.k_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.8.self_attn.k_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.8.self_attn.v_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.8.self_attn.v_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.8.self_attn.o_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.8.self_attn.o_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.8.mlp.gate_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.8.mlp.gate_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.8.mlp.up_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.8.mlp.up_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.8.mlp.down_proj.lora_A.default.weight", "shape": [ 64, 9728 ] }, { "name": "base_model.model.model.layers.8.mlp.down_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.9.self_attn.q_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.9.self_attn.q_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.9.self_attn.k_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.9.self_attn.k_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.9.self_attn.v_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.9.self_attn.v_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.9.self_attn.o_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.9.self_attn.o_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.9.mlp.gate_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.9.mlp.gate_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.9.mlp.up_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.9.mlp.up_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.9.mlp.down_proj.lora_A.default.weight", "shape": [ 64, 9728 ] }, { "name": "base_model.model.model.layers.9.mlp.down_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.10.self_attn.q_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.10.self_attn.q_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.10.self_attn.k_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.10.self_attn.k_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.10.self_attn.v_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.10.self_attn.v_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.10.self_attn.o_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.10.self_attn.o_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.10.mlp.gate_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.10.mlp.gate_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.10.mlp.up_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.10.mlp.up_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.10.mlp.down_proj.lora_A.default.weight", "shape": [ 64, 9728 ] }, { "name": "base_model.model.model.layers.10.mlp.down_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.11.self_attn.q_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.11.self_attn.q_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.11.self_attn.k_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.11.self_attn.k_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.11.self_attn.v_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.11.self_attn.v_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.11.self_attn.o_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.11.self_attn.o_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.11.mlp.gate_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.11.mlp.gate_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.11.mlp.up_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.11.mlp.up_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.11.mlp.down_proj.lora_A.default.weight", "shape": [ 64, 9728 ] }, { "name": "base_model.model.model.layers.11.mlp.down_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.12.self_attn.q_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.12.self_attn.q_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.12.self_attn.k_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.12.self_attn.k_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.12.self_attn.v_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.12.self_attn.v_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.12.self_attn.o_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.12.self_attn.o_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.12.mlp.gate_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.12.mlp.gate_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.12.mlp.up_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.12.mlp.up_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.12.mlp.down_proj.lora_A.default.weight", "shape": [ 64, 9728 ] }, { "name": "base_model.model.model.layers.12.mlp.down_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.13.self_attn.q_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.13.self_attn.q_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.13.self_attn.k_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.13.self_attn.k_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.13.self_attn.v_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.13.self_attn.v_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.13.self_attn.o_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.13.self_attn.o_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.13.mlp.gate_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.13.mlp.gate_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.13.mlp.up_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.13.mlp.up_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.13.mlp.down_proj.lora_A.default.weight", "shape": [ 64, 9728 ] }, { "name": "base_model.model.model.layers.13.mlp.down_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.14.self_attn.q_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.14.self_attn.q_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.14.self_attn.k_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.14.self_attn.k_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.14.self_attn.v_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.14.self_attn.v_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.14.self_attn.o_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.14.self_attn.o_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.14.mlp.gate_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.14.mlp.gate_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.14.mlp.up_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.14.mlp.up_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.14.mlp.down_proj.lora_A.default.weight", "shape": [ 64, 9728 ] }, { "name": "base_model.model.model.layers.14.mlp.down_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.15.self_attn.q_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.15.self_attn.q_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.15.self_attn.k_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.15.self_attn.k_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.15.self_attn.v_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.15.self_attn.v_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.15.self_attn.o_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.15.self_attn.o_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.15.mlp.gate_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.15.mlp.gate_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.15.mlp.up_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.15.mlp.up_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.15.mlp.down_proj.lora_A.default.weight", "shape": [ 64, 9728 ] }, { "name": "base_model.model.model.layers.15.mlp.down_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.16.self_attn.q_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.16.self_attn.q_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.16.self_attn.k_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.16.self_attn.k_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.16.self_attn.v_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.16.self_attn.v_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.16.self_attn.o_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.16.self_attn.o_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.16.mlp.gate_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.16.mlp.gate_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.16.mlp.up_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.16.mlp.up_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.16.mlp.down_proj.lora_A.default.weight", "shape": [ 64, 9728 ] }, { "name": "base_model.model.model.layers.16.mlp.down_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.17.self_attn.q_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.17.self_attn.q_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.17.self_attn.k_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.17.self_attn.k_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.17.self_attn.v_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.17.self_attn.v_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.17.self_attn.o_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.17.self_attn.o_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.17.mlp.gate_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.17.mlp.gate_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.17.mlp.up_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.17.mlp.up_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.17.mlp.down_proj.lora_A.default.weight", "shape": [ 64, 9728 ] }, { "name": "base_model.model.model.layers.17.mlp.down_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.18.self_attn.q_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.18.self_attn.q_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.18.self_attn.k_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.18.self_attn.k_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.18.self_attn.v_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.18.self_attn.v_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.18.self_attn.o_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.18.self_attn.o_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.18.mlp.gate_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.18.mlp.gate_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.18.mlp.up_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.18.mlp.up_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.18.mlp.down_proj.lora_A.default.weight", "shape": [ 64, 9728 ] }, { "name": "base_model.model.model.layers.18.mlp.down_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.19.self_attn.q_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.19.self_attn.q_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.19.self_attn.k_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.19.self_attn.k_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.19.self_attn.v_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.19.self_attn.v_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.19.self_attn.o_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.19.self_attn.o_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.19.mlp.gate_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.19.mlp.gate_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.19.mlp.up_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.19.mlp.up_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.19.mlp.down_proj.lora_A.default.weight", "shape": [ 64, 9728 ] }, { "name": "base_model.model.model.layers.19.mlp.down_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.20.self_attn.q_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.20.self_attn.q_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.20.self_attn.k_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.20.self_attn.k_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.20.self_attn.v_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.20.self_attn.v_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.20.self_attn.o_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.20.self_attn.o_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.20.mlp.gate_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.20.mlp.gate_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.20.mlp.up_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.20.mlp.up_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.20.mlp.down_proj.lora_A.default.weight", "shape": [ 64, 9728 ] }, { "name": "base_model.model.model.layers.20.mlp.down_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.21.self_attn.q_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.21.self_attn.q_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.21.self_attn.k_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.21.self_attn.k_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.21.self_attn.v_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.21.self_attn.v_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.21.self_attn.o_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.21.self_attn.o_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.21.mlp.gate_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.21.mlp.gate_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.21.mlp.up_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.21.mlp.up_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.21.mlp.down_proj.lora_A.default.weight", "shape": [ 64, 9728 ] }, { "name": "base_model.model.model.layers.21.mlp.down_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.22.self_attn.q_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.22.self_attn.q_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.22.self_attn.k_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.22.self_attn.k_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.22.self_attn.v_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.22.self_attn.v_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.22.self_attn.o_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.22.self_attn.o_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.22.mlp.gate_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.22.mlp.gate_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.22.mlp.up_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.22.mlp.up_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.22.mlp.down_proj.lora_A.default.weight", "shape": [ 64, 9728 ] }, { "name": "base_model.model.model.layers.22.mlp.down_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.23.self_attn.q_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.23.self_attn.q_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.23.self_attn.k_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.23.self_attn.k_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.23.self_attn.v_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.23.self_attn.v_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.23.self_attn.o_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.23.self_attn.o_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.23.mlp.gate_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.23.mlp.gate_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.23.mlp.up_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.23.mlp.up_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.23.mlp.down_proj.lora_A.default.weight", "shape": [ 64, 9728 ] }, { "name": "base_model.model.model.layers.23.mlp.down_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.24.self_attn.q_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.24.self_attn.q_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.24.self_attn.k_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.24.self_attn.k_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.24.self_attn.v_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.24.self_attn.v_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.24.self_attn.o_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.24.self_attn.o_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.24.mlp.gate_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.24.mlp.gate_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.24.mlp.up_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.24.mlp.up_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.24.mlp.down_proj.lora_A.default.weight", "shape": [ 64, 9728 ] }, { "name": "base_model.model.model.layers.24.mlp.down_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.25.self_attn.q_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.25.self_attn.q_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.25.self_attn.k_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.25.self_attn.k_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.25.self_attn.v_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.25.self_attn.v_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.25.self_attn.o_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.25.self_attn.o_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.25.mlp.gate_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.25.mlp.gate_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.25.mlp.up_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.25.mlp.up_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.25.mlp.down_proj.lora_A.default.weight", "shape": [ 64, 9728 ] }, { "name": "base_model.model.model.layers.25.mlp.down_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.26.self_attn.q_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.26.self_attn.q_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.26.self_attn.k_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.26.self_attn.k_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.26.self_attn.v_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.26.self_attn.v_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.26.self_attn.o_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.26.self_attn.o_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.26.mlp.gate_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.26.mlp.gate_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.26.mlp.up_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.26.mlp.up_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.26.mlp.down_proj.lora_A.default.weight", "shape": [ 64, 9728 ] }, { "name": "base_model.model.model.layers.26.mlp.down_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.27.self_attn.q_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.27.self_attn.q_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.27.self_attn.k_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.27.self_attn.k_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.27.self_attn.v_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.27.self_attn.v_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.27.self_attn.o_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.27.self_attn.o_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.27.mlp.gate_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.27.mlp.gate_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.27.mlp.up_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.27.mlp.up_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.27.mlp.down_proj.lora_A.default.weight", "shape": [ 64, 9728 ] }, { "name": "base_model.model.model.layers.27.mlp.down_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.28.self_attn.q_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.28.self_attn.q_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.28.self_attn.k_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.28.self_attn.k_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.28.self_attn.v_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.28.self_attn.v_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.28.self_attn.o_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.28.self_attn.o_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.28.mlp.gate_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.28.mlp.gate_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.28.mlp.up_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.28.mlp.up_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.28.mlp.down_proj.lora_A.default.weight", "shape": [ 64, 9728 ] }, { "name": "base_model.model.model.layers.28.mlp.down_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.29.self_attn.q_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.29.self_attn.q_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.29.self_attn.k_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.29.self_attn.k_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.29.self_attn.v_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.29.self_attn.v_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.29.self_attn.o_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.29.self_attn.o_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.29.mlp.gate_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.29.mlp.gate_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.29.mlp.up_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.29.mlp.up_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.29.mlp.down_proj.lora_A.default.weight", "shape": [ 64, 9728 ] }, { "name": "base_model.model.model.layers.29.mlp.down_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.30.self_attn.q_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.30.self_attn.q_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.30.self_attn.k_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.30.self_attn.k_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.30.self_attn.v_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.30.self_attn.v_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.30.self_attn.o_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.30.self_attn.o_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.30.mlp.gate_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.30.mlp.gate_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.30.mlp.up_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.30.mlp.up_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.30.mlp.down_proj.lora_A.default.weight", "shape": [ 64, 9728 ] }, { "name": "base_model.model.model.layers.30.mlp.down_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.31.self_attn.q_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.31.self_attn.q_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.31.self_attn.k_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.31.self_attn.k_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.31.self_attn.v_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.31.self_attn.v_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.31.self_attn.o_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.31.self_attn.o_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.31.mlp.gate_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.31.mlp.gate_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.31.mlp.up_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.31.mlp.up_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.31.mlp.down_proj.lora_A.default.weight", "shape": [ 64, 9728 ] }, { "name": "base_model.model.model.layers.31.mlp.down_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.32.self_attn.q_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.32.self_attn.q_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.32.self_attn.k_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.32.self_attn.k_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.32.self_attn.v_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.32.self_attn.v_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.32.self_attn.o_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.32.self_attn.o_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.32.mlp.gate_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.32.mlp.gate_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.32.mlp.up_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.32.mlp.up_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.32.mlp.down_proj.lora_A.default.weight", "shape": [ 64, 9728 ] }, { "name": "base_model.model.model.layers.32.mlp.down_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.33.self_attn.q_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.33.self_attn.q_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.33.self_attn.k_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.33.self_attn.k_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.33.self_attn.v_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.33.self_attn.v_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.33.self_attn.o_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.33.self_attn.o_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.33.mlp.gate_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.33.mlp.gate_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.33.mlp.up_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.33.mlp.up_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.33.mlp.down_proj.lora_A.default.weight", "shape": [ 64, 9728 ] }, { "name": "base_model.model.model.layers.33.mlp.down_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.34.self_attn.q_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.34.self_attn.q_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.34.self_attn.k_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.34.self_attn.k_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.34.self_attn.v_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.34.self_attn.v_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.34.self_attn.o_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.34.self_attn.o_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.34.mlp.gate_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.34.mlp.gate_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.34.mlp.up_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.34.mlp.up_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.34.mlp.down_proj.lora_A.default.weight", "shape": [ 64, 9728 ] }, { "name": "base_model.model.model.layers.34.mlp.down_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.35.self_attn.q_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.35.self_attn.q_proj.lora_B.default.weight", "shape": [ 4096, 64 ] }, { "name": "base_model.model.model.layers.35.self_attn.k_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.35.self_attn.k_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.35.self_attn.v_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.35.self_attn.v_proj.lora_B.default.weight", "shape": [ 1024, 64 ] }, { "name": "base_model.model.model.layers.35.self_attn.o_proj.lora_A.default.weight", "shape": [ 64, 4096 ] }, { "name": "base_model.model.model.layers.35.self_attn.o_proj.lora_B.default.weight", "shape": [ 2560, 64 ] }, { "name": "base_model.model.model.layers.35.mlp.gate_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.35.mlp.gate_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.35.mlp.up_proj.lora_A.default.weight", "shape": [ 64, 2560 ] }, { "name": "base_model.model.model.layers.35.mlp.up_proj.lora_B.default.weight", "shape": [ 9728, 64 ] }, { "name": "base_model.model.model.layers.35.mlp.down_proj.lora_A.default.weight", "shape": [ 64, 9728 ] }, { "name": "base_model.model.model.layers.35.mlp.down_proj.lora_B.default.weight", "shape": [ 2560, 64 ] } ] }, { "group": "row_tokens", "param_count": 2, "params": [ { "name": "base_model.model.model.embed_tokens.token_adapter.trainable_tokens_delta.default", "shape": [ 3, 2560 ] }, { "name": "base_model.model.lm_head.token_adapter.trainable_tokens_delta.default", "shape": [ 3, 2560 ] } ] } ] }, "tied_token_canary": null, "continuation": null, "lora_digest_start": { "scope": "lora", "sha256": "b5c8857a053d3f25970801e14e08483872c0503ca38d876902da21ea70841297", "parameter_count": 506, "bytes": 528543744, "names_sha256": "bb45cbfe1a7fcc7231a004dc60e90e0ddc33dcbcb776306b4f372164f4989122" } }