Download checkpoint-1000/trainer_state.json from dawity/groot_dagger_it1: direct link, hf CLI and curl.
- Browser
- Download file 14.6 kB
-
https://huggingface.co/dawity/groot_dagger_it1/resolve/main/checkpoint-1000/trainer_state.json
- Command line
-
hf download hf://dawity/groot_dagger_it1/checkpoint-1000/trainer_state.json
-
curl -L -o trainer_state.json https://huggingface.co/dawity/groot_dagger_it1/resolve/main/checkpoint-1000/trainer_state.json
14.6 kB
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.16666666666666666, | |
| "eval_steps": 500, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "grad_norm": 1.1998956203460693, | |
| "learning_rate": 1.5e-06, | |
| "loss": 0.0948, | |
| "step": 10 | |
| }, | |
| { | |
| "grad_norm": 1.149483561515808, | |
| "learning_rate": 3.1666666666666667e-06, | |
| "loss": 0.1133, | |
| "step": 20 | |
| }, | |
| { | |
| "grad_norm": 0.5785359144210815, | |
| "learning_rate": 4.833333333333333e-06, | |
| "loss": 0.0921, | |
| "step": 30 | |
| }, | |
| { | |
| "grad_norm": 0.5978452563285828, | |
| "learning_rate": 6.5000000000000004e-06, | |
| "loss": 0.0424, | |
| "step": 40 | |
| }, | |
| { | |
| "grad_norm": 0.5148229598999023, | |
| "learning_rate": 8.166666666666666e-06, | |
| "loss": 0.0314, | |
| "step": 50 | |
| }, | |
| { | |
| "grad_norm": 0.456398606300354, | |
| "learning_rate": 9.833333333333333e-06, | |
| "loss": 0.0311, | |
| "step": 60 | |
| }, | |
| { | |
| "grad_norm": 0.2702748775482178, | |
| "learning_rate": 1.1500000000000002e-05, | |
| "loss": 0.0249, | |
| "step": 70 | |
| }, | |
| { | |
| "grad_norm": 0.2341022789478302, | |
| "learning_rate": 1.3166666666666667e-05, | |
| "loss": 0.0208, | |
| "step": 80 | |
| }, | |
| { | |
| "grad_norm": 0.24386702477931976, | |
| "learning_rate": 1.4833333333333334e-05, | |
| "loss": 0.0168, | |
| "step": 90 | |
| }, | |
| { | |
| "grad_norm": 0.15167136490345, | |
| "learning_rate": 1.65e-05, | |
| "loss": 0.0114, | |
| "step": 100 | |
| }, | |
| { | |
| "grad_norm": 0.12867538630962372, | |
| "learning_rate": 1.8166666666666667e-05, | |
| "loss": 0.015, | |
| "step": 110 | |
| }, | |
| { | |
| "grad_norm": 0.11734911054372787, | |
| "learning_rate": 1.9833333333333332e-05, | |
| "loss": 0.0108, | |
| "step": 120 | |
| }, | |
| { | |
| "grad_norm": 0.10739504545927048, | |
| "learning_rate": 2.15e-05, | |
| "loss": 0.0085, | |
| "step": 130 | |
| }, | |
| { | |
| "grad_norm": 0.11796178668737411, | |
| "learning_rate": 2.316666666666667e-05, | |
| "loss": 0.0108, | |
| "step": 140 | |
| }, | |
| { | |
| "grad_norm": 0.1394447386264801, | |
| "learning_rate": 2.483333333333333e-05, | |
| "loss": 0.0111, | |
| "step": 150 | |
| }, | |
| { | |
| "grad_norm": 0.1239742562174797, | |
| "learning_rate": 2.65e-05, | |
| "loss": 0.01, | |
| "step": 160 | |
| }, | |
| { | |
| "grad_norm": 0.15108101069927216, | |
| "learning_rate": 2.8166666666666666e-05, | |
| "loss": 0.0088, | |
| "step": 170 | |
| }, | |
| { | |
| "grad_norm": 0.10625599324703217, | |
| "learning_rate": 2.9833333333333335e-05, | |
| "loss": 0.0073, | |
| "step": 180 | |
| }, | |
| { | |
| "grad_norm": 0.18963077664375305, | |
| "learning_rate": 2.9999822989428527e-05, | |
| "loss": 0.0086, | |
| "step": 190 | |
| }, | |
| { | |
| "grad_norm": 0.13748835027217865, | |
| "learning_rate": 2.9999211106396838e-05, | |
| "loss": 0.008, | |
| "step": 200 | |
| }, | |
| { | |
| "grad_norm": 0.11299511790275574, | |
| "learning_rate": 2.9998162183413746e-05, | |
| "loss": 0.0084, | |
| "step": 210 | |
| }, | |
| { | |
| "grad_norm": 0.09556759148836136, | |
| "learning_rate": 2.9996676251042288e-05, | |
| "loss": 0.0075, | |
| "step": 220 | |
| }, | |
| { | |
| "grad_norm": 0.13729563355445862, | |
| "learning_rate": 2.9994753352578854e-05, | |
| "loss": 0.0078, | |
| "step": 230 | |
| }, | |
| { | |
| "grad_norm": 0.13592101633548737, | |
| "learning_rate": 2.999239354405195e-05, | |
| "loss": 0.0087, | |
| "step": 240 | |
| }, | |
| { | |
| "grad_norm": 0.13999280333518982, | |
| "learning_rate": 2.9989596894220574e-05, | |
| "loss": 0.0072, | |
| "step": 250 | |
| }, | |
| { | |
| "grad_norm": 0.20841121673583984, | |
| "learning_rate": 2.998636348457219e-05, | |
| "loss": 0.0078, | |
| "step": 260 | |
| }, | |
| { | |
| "grad_norm": 0.1364365965127945, | |
| "learning_rate": 2.998269340932036e-05, | |
| "loss": 0.0086, | |
| "step": 270 | |
| }, | |
| { | |
| "grad_norm": 0.1565951108932495, | |
| "learning_rate": 2.9978586775402017e-05, | |
| "loss": 0.0066, | |
| "step": 280 | |
| }, | |
| { | |
| "grad_norm": 0.1358197182416916, | |
| "learning_rate": 2.9974043702474322e-05, | |
| "loss": 0.0057, | |
| "step": 290 | |
| }, | |
| { | |
| "grad_norm": 0.11862654238939285, | |
| "learning_rate": 2.9969064322911198e-05, | |
| "loss": 0.0074, | |
| "step": 300 | |
| }, | |
| { | |
| "grad_norm": 0.13869383931159973, | |
| "learning_rate": 2.9963648781799457e-05, | |
| "loss": 0.0073, | |
| "step": 310 | |
| }, | |
| { | |
| "grad_norm": 0.10812313109636307, | |
| "learning_rate": 2.9957797236934595e-05, | |
| "loss": 0.0055, | |
| "step": 320 | |
| }, | |
| { | |
| "grad_norm": 0.10657292604446411, | |
| "learning_rate": 2.995150985881616e-05, | |
| "loss": 0.0066, | |
| "step": 330 | |
| }, | |
| { | |
| "grad_norm": 0.1428467333316803, | |
| "learning_rate": 2.9944786830642822e-05, | |
| "loss": 0.0075, | |
| "step": 340 | |
| }, | |
| { | |
| "grad_norm": 0.2037973701953888, | |
| "learning_rate": 2.9937628348307015e-05, | |
| "loss": 0.0068, | |
| "step": 350 | |
| }, | |
| { | |
| "grad_norm": 0.17431488633155823, | |
| "learning_rate": 2.9930034620389217e-05, | |
| "loss": 0.0085, | |
| "step": 360 | |
| }, | |
| { | |
| "grad_norm": 0.11183494329452515, | |
| "learning_rate": 2.9922005868151907e-05, | |
| "loss": 0.0075, | |
| "step": 370 | |
| }, | |
| { | |
| "grad_norm": 0.15082184970378876, | |
| "learning_rate": 2.991354232553308e-05, | |
| "loss": 0.0062, | |
| "step": 380 | |
| }, | |
| { | |
| "grad_norm": 0.18662261962890625, | |
| "learning_rate": 2.9904644239139453e-05, | |
| "loss": 0.0065, | |
| "step": 390 | |
| }, | |
| { | |
| "grad_norm": 0.08828644454479218, | |
| "learning_rate": 2.9895311868239293e-05, | |
| "loss": 0.0063, | |
| "step": 400 | |
| }, | |
| { | |
| "grad_norm": 0.09585582464933395, | |
| "learning_rate": 2.988554548475481e-05, | |
| "loss": 0.0085, | |
| "step": 410 | |
| }, | |
| { | |
| "grad_norm": 0.1154177337884903, | |
| "learning_rate": 2.9875345373254302e-05, | |
| "loss": 0.0062, | |
| "step": 420 | |
| }, | |
| { | |
| "grad_norm": 0.13848039507865906, | |
| "learning_rate": 2.986471183094382e-05, | |
| "loss": 0.0072, | |
| "step": 430 | |
| }, | |
| { | |
| "grad_norm": 0.11135748773813248, | |
| "learning_rate": 2.9853645167658494e-05, | |
| "loss": 0.0052, | |
| "step": 440 | |
| }, | |
| { | |
| "grad_norm": 0.15800616145133972, | |
| "learning_rate": 2.9842145705853565e-05, | |
| "loss": 0.0057, | |
| "step": 450 | |
| }, | |
| { | |
| "grad_norm": 0.11519774794578552, | |
| "learning_rate": 2.9830213780594925e-05, | |
| "loss": 0.0041, | |
| "step": 460 | |
| }, | |
| { | |
| "grad_norm": 0.06121053546667099, | |
| "learning_rate": 2.9817849739549408e-05, | |
| "loss": 0.0045, | |
| "step": 470 | |
| }, | |
| { | |
| "grad_norm": 0.11012984067201614, | |
| "learning_rate": 2.980505394297461e-05, | |
| "loss": 0.0047, | |
| "step": 480 | |
| }, | |
| { | |
| "grad_norm": 0.12504155933856964, | |
| "learning_rate": 2.9791826763708432e-05, | |
| "loss": 0.0043, | |
| "step": 490 | |
| }, | |
| { | |
| "grad_norm": 0.10626716166734695, | |
| "learning_rate": 2.9778168587158196e-05, | |
| "loss": 0.005, | |
| "step": 500 | |
| }, | |
| { | |
| "grad_norm": 0.100404754281044, | |
| "learning_rate": 2.976407981128942e-05, | |
| "loss": 0.0037, | |
| "step": 510 | |
| }, | |
| { | |
| "grad_norm": 0.11580510437488556, | |
| "learning_rate": 2.9749560846614216e-05, | |
| "loss": 0.0042, | |
| "step": 520 | |
| }, | |
| { | |
| "grad_norm": 0.1404998004436493, | |
| "learning_rate": 2.973461211617935e-05, | |
| "loss": 0.0055, | |
| "step": 530 | |
| }, | |
| { | |
| "grad_norm": 0.1066383644938469, | |
| "learning_rate": 2.9719234055553884e-05, | |
| "loss": 0.0055, | |
| "step": 540 | |
| }, | |
| { | |
| "grad_norm": 0.16468606889247894, | |
| "learning_rate": 2.970342711281651e-05, | |
| "loss": 0.0038, | |
| "step": 550 | |
| }, | |
| { | |
| "grad_norm": 0.1270781308412552, | |
| "learning_rate": 2.9687191748542485e-05, | |
| "loss": 0.0056, | |
| "step": 560 | |
| }, | |
| { | |
| "grad_norm": 0.13871441781520844, | |
| "learning_rate": 2.967052843579021e-05, | |
| "loss": 0.0079, | |
| "step": 570 | |
| }, | |
| { | |
| "grad_norm": 0.13760028779506683, | |
| "learning_rate": 2.965343766008745e-05, | |
| "loss": 0.0047, | |
| "step": 580 | |
| }, | |
| { | |
| "grad_norm": 0.23738646507263184, | |
| "learning_rate": 2.9635919919417175e-05, | |
| "loss": 0.0058, | |
| "step": 590 | |
| }, | |
| { | |
| "grad_norm": 0.12334813177585602, | |
| "learning_rate": 2.9617975724203065e-05, | |
| "loss": 0.006, | |
| "step": 600 | |
| }, | |
| { | |
| "grad_norm": 0.11787013709545135, | |
| "learning_rate": 2.9599605597294635e-05, | |
| "loss": 0.0042, | |
| "step": 610 | |
| }, | |
| { | |
| "grad_norm": 0.10075175762176514, | |
| "learning_rate": 2.958081007395199e-05, | |
| "loss": 0.0051, | |
| "step": 620 | |
| }, | |
| { | |
| "grad_norm": 0.12161751091480255, | |
| "learning_rate": 2.956158970183024e-05, | |
| "loss": 0.006, | |
| "step": 630 | |
| }, | |
| { | |
| "grad_norm": 0.1339486688375473, | |
| "learning_rate": 2.954194504096355e-05, | |
| "loss": 0.0053, | |
| "step": 640 | |
| }, | |
| { | |
| "grad_norm": 0.09474559128284454, | |
| "learning_rate": 2.9521876663748787e-05, | |
| "loss": 0.0069, | |
| "step": 650 | |
| }, | |
| { | |
| "grad_norm": 0.10630160570144653, | |
| "learning_rate": 2.950138515492888e-05, | |
| "loss": 0.0053, | |
| "step": 660 | |
| }, | |
| { | |
| "grad_norm": 0.1059340387582779, | |
| "learning_rate": 2.9480471111575768e-05, | |
| "loss": 0.0047, | |
| "step": 670 | |
| }, | |
| { | |
| "grad_norm": 0.13061285018920898, | |
| "learning_rate": 2.9459135143073e-05, | |
| "loss": 0.0044, | |
| "step": 680 | |
| }, | |
| { | |
| "grad_norm": 0.11301890015602112, | |
| "learning_rate": 2.9437377871097974e-05, | |
| "loss": 0.004, | |
| "step": 690 | |
| }, | |
| { | |
| "grad_norm": 0.11071354895830154, | |
| "learning_rate": 2.9415199929603843e-05, | |
| "loss": 0.0048, | |
| "step": 700 | |
| }, | |
| { | |
| "grad_norm": 0.10549204051494598, | |
| "learning_rate": 2.939260196480103e-05, | |
| "loss": 0.0053, | |
| "step": 710 | |
| }, | |
| { | |
| "grad_norm": 0.13164091110229492, | |
| "learning_rate": 2.9369584635138386e-05, | |
| "loss": 0.0051, | |
| "step": 720 | |
| }, | |
| { | |
| "grad_norm": 0.1299622356891632, | |
| "learning_rate": 2.9346148611284025e-05, | |
| "loss": 0.0057, | |
| "step": 730 | |
| }, | |
| { | |
| "grad_norm": 0.12443673610687256, | |
| "learning_rate": 2.9322294576105785e-05, | |
| "loss": 0.0054, | |
| "step": 740 | |
| }, | |
| { | |
| "grad_norm": 0.2119351178407669, | |
| "learning_rate": 2.92980232246513e-05, | |
| "loss": 0.006, | |
| "step": 750 | |
| }, | |
| { | |
| "grad_norm": 0.17323265969753265, | |
| "learning_rate": 2.927333526412779e-05, | |
| "loss": 0.0051, | |
| "step": 760 | |
| }, | |
| { | |
| "grad_norm": 0.14540384709835052, | |
| "learning_rate": 2.9248231413881423e-05, | |
| "loss": 0.0051, | |
| "step": 770 | |
| }, | |
| { | |
| "grad_norm": 0.1042582094669342, | |
| "learning_rate": 2.9222712405376372e-05, | |
| "loss": 0.0058, | |
| "step": 780 | |
| }, | |
| { | |
| "grad_norm": 0.10313008725643158, | |
| "learning_rate": 2.919677898217348e-05, | |
| "loss": 0.0047, | |
| "step": 790 | |
| }, | |
| { | |
| "grad_norm": 0.09979265928268433, | |
| "learning_rate": 2.917043189990864e-05, | |
| "loss": 0.0046, | |
| "step": 800 | |
| }, | |
| { | |
| "grad_norm": 0.08516388386487961, | |
| "learning_rate": 2.914367192627072e-05, | |
| "loss": 0.0041, | |
| "step": 810 | |
| }, | |
| { | |
| "grad_norm": 0.12445282191038132, | |
| "learning_rate": 2.9116499840979232e-05, | |
| "loss": 0.0042, | |
| "step": 820 | |
| }, | |
| { | |
| "grad_norm": 0.07022149115800858, | |
| "learning_rate": 2.9088916435761604e-05, | |
| "loss": 0.0043, | |
| "step": 830 | |
| }, | |
| { | |
| "grad_norm": 0.12865330278873444, | |
| "learning_rate": 2.9060922514330117e-05, | |
| "loss": 0.0049, | |
| "step": 840 | |
| }, | |
| { | |
| "grad_norm": 0.16881509125232697, | |
| "learning_rate": 2.903251889235847e-05, | |
| "loss": 0.0054, | |
| "step": 850 | |
| }, | |
| { | |
| "grad_norm": 0.12935705482959747, | |
| "learning_rate": 2.9003706397458025e-05, | |
| "loss": 0.0053, | |
| "step": 860 | |
| }, | |
| { | |
| "grad_norm": 0.11892224848270416, | |
| "learning_rate": 2.8974485869153698e-05, | |
| "loss": 0.0039, | |
| "step": 870 | |
| }, | |
| { | |
| "grad_norm": 0.12481220811605453, | |
| "learning_rate": 2.8944858158859484e-05, | |
| "loss": 0.0059, | |
| "step": 880 | |
| }, | |
| { | |
| "grad_norm": 0.09241459518671036, | |
| "learning_rate": 2.8914824129853653e-05, | |
| "loss": 0.0051, | |
| "step": 890 | |
| }, | |
| { | |
| "grad_norm": 0.08305121958255768, | |
| "learning_rate": 2.8884384657253603e-05, | |
| "loss": 0.0057, | |
| "step": 900 | |
| }, | |
| { | |
| "grad_norm": 0.12699495255947113, | |
| "learning_rate": 2.8853540627990356e-05, | |
| "loss": 0.005, | |
| "step": 910 | |
| }, | |
| { | |
| "grad_norm": 0.11409413814544678, | |
| "learning_rate": 2.8822292940782718e-05, | |
| "loss": 0.0042, | |
| "step": 920 | |
| }, | |
| { | |
| "grad_norm": 0.1391240954399109, | |
| "learning_rate": 2.8790642506111083e-05, | |
| "loss": 0.0042, | |
| "step": 930 | |
| }, | |
| { | |
| "grad_norm": 0.12300487607717514, | |
| "learning_rate": 2.8758590246190914e-05, | |
| "loss": 0.005, | |
| "step": 940 | |
| }, | |
| { | |
| "grad_norm": 0.1318342536687851, | |
| "learning_rate": 2.8726137094945875e-05, | |
| "loss": 0.0058, | |
| "step": 950 | |
| }, | |
| { | |
| "grad_norm": 0.1381806582212448, | |
| "learning_rate": 2.8693283997980604e-05, | |
| "loss": 0.0049, | |
| "step": 960 | |
| }, | |
| { | |
| "grad_norm": 0.11659003049135208, | |
| "learning_rate": 2.8660031912553177e-05, | |
| "loss": 0.0059, | |
| "step": 970 | |
| }, | |
| { | |
| "grad_norm": 0.09772439301013947, | |
| "learning_rate": 2.8626381807547197e-05, | |
| "loss": 0.004, | |
| "step": 980 | |
| }, | |
| { | |
| "grad_norm": 0.11248010396957397, | |
| "learning_rate": 2.859233466344358e-05, | |
| "loss": 0.0062, | |
| "step": 990 | |
| }, | |
| { | |
| "grad_norm": 0.08497095108032227, | |
| "learning_rate": 2.8557891472291994e-05, | |
| "loss": 0.0051, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 6000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 9223372036854775807, | |
| "save_steps": 250, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |