Training in progress, step 2300, checkpoint

last-checkpoint/optimizer_0/__0_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7750d855d924ceddc42b25d22102dca161947437c25b8419a6816d7b96741aeb
+oid sha256:24312d61fce7e299202c695b1044a4796f624960d1404b905c54d6abb222cb8c
 size 13934748

last-checkpoint/optimizer_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe99c75ae54f8e353ca6b14a2263f36030ed5f3401ce134e4635385755a900b7
+oid sha256:175580163ae0def91026c5949833e86bc785d770db0b7757db53ef22072ca767
 size 13999412

last-checkpoint/optimizer_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d05e150230f6c9e3e975cd33a3210ca9291eb2e64c2ecdbf0603dafea8eea91
+oid sha256:ad31dbc2f54266d2c8e70ecf0aff447c10d4f855b87fe47ea62bb570e0d0da60
 size 13990904

last-checkpoint/optimizer_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8db5587c2ec1c9e3f57bc569cd655e9a5f4ffd08bc65175e481ebe68e67f7635
+oid sha256:ed8fb729039a78ead4b30a81f2aa16e8676ad408bc1552e8a482246f196e5cd6
 size 13990904

last-checkpoint/pytorch_model_fsdp_0/__0_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93bb3e67ee6ceedf8551709955d00de6d38ab5803dccee94006f2d5c386ec341
+oid sha256:adc3191d4cd665294dae5d0b36dbd57fee0d46d4c50f53249cdc0fd7e20b544f
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a83f77a5fe6ac8a4884389cb8ed767cc29a586c30e61019c17e47cadd3f5525
+oid sha256:8f6d689ceda9e9207e60fc38cd63eb39402b23c7d72b220cb0090e249e3e16b9
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3332e607aef586ed304912c7552b3516178a31f86acd384c43600315294afcd
+oid sha256:e1fc9f3b557eb444ea344ecab856d01b57a7c4ce5e5f21b392509cf9b23a08f9
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7f13e6b4d3e3cab59a425ff7c039652ef325d0fdbb428bc8660095468057bd1
+oid sha256:26e3dfe37061cd49d4cf48ef43c81018d73e05d1fa8c28a8822941449ee16073
 size 6966784

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a4586a2997b0b408d270738eb8db1b3f9fa8a1af8d3e8e24278c513ee508542
+oid sha256:6156d87a3edede0bd5fd215821a85320c517eca74046d12541e75ed03a44b648
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:411997a661a7b55a5c8ced9a28b09cc84c038cb5ccecb6043e26e62fd0dd502d
+oid sha256:f955a45267863f61f92f070f53d94052173924ff6923f8feaf17591492da3f8b
 size 14960

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1e8ad9fcb9ebe7d67655466925d5d831d7f2cfce33712846d8b9653de23bd8e
+oid sha256:affd28df85e029ed8ca9bcf5517998774ba1dc8d60a95c2935db00fe19d3e9cc
 size 14960

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:415a0bb82a0f7a72dd88fb835daa9883d9328dba7cb35db534eff4f51e188465
+oid sha256:681f001f5104f634663b499f6e9d4e2abb34e750656370cc2aa7892a48040504
 size 14960

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99ebe1c7d19cd6162f873b3b499cafe7fbbaa105c5efc40272cb3d608ff4b0e4
+oid sha256:71036ba3d5162c1e85b3994e14213b578278c107fdc908a31152acd41e824990
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3246034673552195,
+  "epoch": 0.33935817041682037,
   "eval_steps": 20,
-  "global_step": 2200,
+  "global_step": 2300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -16739,6 +16739,766 @@
       "eval_samples_per_second": 5.819,
       "eval_steps_per_second": 0.2,
       "step": 2200
+    },
+    {
+      "epoch": 0.3247510143858355,
+      "grad_norm": 2.656367301940918,
+      "learning_rate": 1.70774389708928e-05,
+      "loss": 0.0927,
+      "step": 2201
+    },
+    {
+      "epoch": 0.3248985614164515,
+      "grad_norm": 2.6321423053741455,
+      "learning_rate": 1.7073799012449524e-05,
+      "loss": 0.1059,
+      "step": 2202
+    },
+    {
+      "epoch": 0.3250461084470675,
+      "grad_norm": 2.040905475616455,
+      "learning_rate": 1.7070157177131954e-05,
+      "loss": 0.0781,
+      "step": 2203
+    },
+    {
+      "epoch": 0.32519365547768353,
+      "grad_norm": 1.4005239009857178,
+      "learning_rate": 1.7066513465906375e-05,
+      "loss": 0.0528,
+      "step": 2204
+    },
+    {
+      "epoch": 0.3253412025082995,
+      "grad_norm": 2.356604814529419,
+      "learning_rate": 1.7062867879739568e-05,
+      "loss": 0.0751,
+      "step": 2205
+    },
+    {
+      "epoch": 0.32548874953891554,
+      "grad_norm": 1.1565563678741455,
+      "learning_rate": 1.70592204195988e-05,
+      "loss": 0.0347,
+      "step": 2206
+    },
+    {
+      "epoch": 0.3256362965695315,
+      "grad_norm": 1.0566600561141968,
+      "learning_rate": 1.7055571086451842e-05,
+      "loss": 0.0169,
+      "step": 2207
+    },
+    {
+      "epoch": 0.32578384360014756,
+      "grad_norm": 1.6565196514129639,
+      "learning_rate": 1.705191988126697e-05,
+      "loss": 0.0689,
+      "step": 2208
+    },
+    {
+      "epoch": 0.32593139063076354,
+      "grad_norm": 4.447436332702637,
+      "learning_rate": 1.7048266805012948e-05,
+      "loss": 0.0736,
+      "step": 2209
+    },
+    {
+      "epoch": 0.3260789376613796,
+      "grad_norm": 2.0285775661468506,
+      "learning_rate": 1.7044611858659036e-05,
+      "loss": 0.0734,
+      "step": 2210
+    },
+    {
+      "epoch": 0.32622648469199556,
+      "grad_norm": 2.754542350769043,
+      "learning_rate": 1.7040955043174992e-05,
+      "loss": 0.0771,
+      "step": 2211
+    },
+    {
+      "epoch": 0.3263740317226116,
+      "grad_norm": 2.8806169033050537,
+      "learning_rate": 1.703729635953107e-05,
+      "loss": 0.0402,
+      "step": 2212
+    },
+    {
+      "epoch": 0.32652157875322757,
+      "grad_norm": 2.1255829334259033,
+      "learning_rate": 1.703363580869802e-05,
+      "loss": 0.0644,
+      "step": 2213
+    },
+    {
+      "epoch": 0.3266691257838436,
+      "grad_norm": 1.6564240455627441,
+      "learning_rate": 1.702997339164709e-05,
+      "loss": 0.0927,
+      "step": 2214
+    },
+    {
+      "epoch": 0.3268166728144596,
+      "grad_norm": 1.8921287059783936,
+      "learning_rate": 1.702630910935002e-05,
+      "loss": 0.0788,
+      "step": 2215
+    },
+    {
+      "epoch": 0.3269642198450756,
+      "grad_norm": 4.465273857116699,
+      "learning_rate": 1.7022642962779037e-05,
+      "loss": 0.0737,
+      "step": 2216
+    },
+    {
+      "epoch": 0.3271117668756916,
+      "grad_norm": 2.584212303161621,
+      "learning_rate": 1.7018974952906885e-05,
+      "loss": 0.0978,
+      "step": 2217
+    },
+    {
+      "epoch": 0.32725931390630764,
+      "grad_norm": 2.30361008644104,
+      "learning_rate": 1.7015305080706776e-05,
+      "loss": 0.0308,
+      "step": 2218
+    },
+    {
+      "epoch": 0.32740686093692367,
+      "grad_norm": 2.4971728324890137,
+      "learning_rate": 1.7011633347152437e-05,
+      "loss": 0.0478,
+      "step": 2219
+    },
+    {
+      "epoch": 0.32755440796753965,
+      "grad_norm": 1.7847650051116943,
+      "learning_rate": 1.7007959753218073e-05,
+      "loss": 0.0755,
+      "step": 2220
+    },
+    {
+      "epoch": 0.32755440796753965,
+      "eval_accuracy": 0.9782923299565847,
+      "eval_f1": 0.9627791563275434,
+      "eval_loss": 0.06917760521173477,
+      "eval_precision": 0.9847715736040609,
+      "eval_recall": 0.941747572815534,
+      "eval_runtime": 49.8729,
+      "eval_samples_per_second": 5.835,
+      "eval_steps_per_second": 0.201,
+      "step": 2220
+    },
+    {
+      "epoch": 0.3277019549981557,
+      "grad_norm": 1.4912227392196655,
+      "learning_rate": 1.7004284299878397e-05,
+      "loss": 0.0567,
+      "step": 2221
+    },
+    {
+      "epoch": 0.32784950202877167,
+      "grad_norm": 0.9491235613822937,
+      "learning_rate": 1.7000606988108606e-05,
+      "loss": 0.0369,
+      "step": 2222
+    },
+    {
+      "epoch": 0.3279970490593877,
+      "grad_norm": 0.8188719749450684,
+      "learning_rate": 1.699692781888439e-05,
+      "loss": 0.0276,
+      "step": 2223
+    },
+    {
+      "epoch": 0.3281445960900037,
+      "grad_norm": 1.8164491653442383,
+      "learning_rate": 1.6993246793181934e-05,
+      "loss": 0.0535,
+      "step": 2224
+    },
+    {
+      "epoch": 0.3282921431206197,
+      "grad_norm": 1.3040269613265991,
+      "learning_rate": 1.698956391197792e-05,
+      "loss": 0.0151,
+      "step": 2225
+    },
+    {
+      "epoch": 0.3284396901512357,
+      "grad_norm": 4.568538188934326,
+      "learning_rate": 1.6985879176249513e-05,
+      "loss": 0.044,
+      "step": 2226
+    },
+    {
+      "epoch": 0.32858723718185173,
+      "grad_norm": 3.484936237335205,
+      "learning_rate": 1.698219258697438e-05,
+      "loss": 0.1221,
+      "step": 2227
+    },
+    {
+      "epoch": 0.3287347842124677,
+      "grad_norm": 3.1631078720092773,
+      "learning_rate": 1.6978504145130674e-05,
+      "loss": 0.0445,
+      "step": 2228
+    },
+    {
+      "epoch": 0.32888233124308375,
+      "grad_norm": 3.169933557510376,
+      "learning_rate": 1.6974813851697037e-05,
+      "loss": 0.0632,
+      "step": 2229
+    },
+    {
+      "epoch": 0.3290298782736997,
+      "grad_norm": 2.9364147186279297,
+      "learning_rate": 1.697112170765261e-05,
+      "loss": 0.1092,
+      "step": 2230
+    },
+    {
+      "epoch": 0.32917742530431576,
+      "grad_norm": 1.1063787937164307,
+      "learning_rate": 1.6967427713977017e-05,
+      "loss": 0.0304,
+      "step": 2231
+    },
+    {
+      "epoch": 0.32932497233493174,
+      "grad_norm": 1.1559252738952637,
+      "learning_rate": 1.6963731871650377e-05,
+      "loss": 0.0158,
+      "step": 2232
+    },
+    {
+      "epoch": 0.3294725193655478,
+      "grad_norm": 1.299078345298767,
+      "learning_rate": 1.6960034181653303e-05,
+      "loss": 0.0284,
+      "step": 2233
+    },
+    {
+      "epoch": 0.32962006639616376,
+      "grad_norm": 2.1277706623077393,
+      "learning_rate": 1.695633464496689e-05,
+      "loss": 0.0631,
+      "step": 2234
+    },
+    {
+      "epoch": 0.3297676134267798,
+      "grad_norm": 4.438483238220215,
+      "learning_rate": 1.6952633262572734e-05,
+      "loss": 0.1384,
+      "step": 2235
+    },
+    {
+      "epoch": 0.3299151604573958,
+      "grad_norm": 1.8104290962219238,
+      "learning_rate": 1.6948930035452905e-05,
+      "loss": 0.0919,
+      "step": 2236
+    },
+    {
+      "epoch": 0.3300627074880118,
+      "grad_norm": 3.712137222290039,
+      "learning_rate": 1.6945224964589974e-05,
+      "loss": 0.0628,
+      "step": 2237
+    },
+    {
+      "epoch": 0.3302102545186278,
+      "grad_norm": 3.4406650066375732,
+      "learning_rate": 1.6941518050967002e-05,
+      "loss": 0.076,
+      "step": 2238
+    },
+    {
+      "epoch": 0.3303578015492438,
+      "grad_norm": 3.186852216720581,
+      "learning_rate": 1.6937809295567536e-05,
+      "loss": 0.0632,
+      "step": 2239
+    },
+    {
+      "epoch": 0.3305053485798598,
+      "grad_norm": 1.3787213563919067,
+      "learning_rate": 1.6934098699375608e-05,
+      "loss": 0.0122,
+      "step": 2240
+    },
+    {
+      "epoch": 0.3305053485798598,
+      "eval_accuracy": 0.9725036179450073,
+      "eval_f1": 0.9533169533169533,
+      "eval_loss": 0.07235416024923325,
+      "eval_precision": 0.9651741293532339,
+      "eval_recall": 0.941747572815534,
+      "eval_runtime": 49.7738,
+      "eval_samples_per_second": 5.846,
+      "eval_steps_per_second": 0.201,
+      "step": 2240
+    },
+    {
+      "epoch": 0.33065289561047584,
+      "grad_norm": 2.335592031478882,
+      "learning_rate": 1.6930386263375738e-05,
+      "loss": 0.0762,
+      "step": 2241
+    },
+    {
+      "epoch": 0.3308004426410919,
+      "grad_norm": 3.2321720123291016,
+      "learning_rate": 1.692667198855295e-05,
+      "loss": 0.0311,
+      "step": 2242
+    },
+    {
+      "epoch": 0.33094798967170785,
+      "grad_norm": 5.0269775390625,
+      "learning_rate": 1.6922955875892736e-05,
+      "loss": 0.1519,
+      "step": 2243
+    },
+    {
+      "epoch": 0.3310955367023239,
+      "grad_norm": 1.4114075899124146,
+      "learning_rate": 1.691923792638108e-05,
+      "loss": 0.0312,
+      "step": 2244
+    },
+    {
+      "epoch": 0.33124308373293987,
+      "grad_norm": 2.941546678543091,
+      "learning_rate": 1.691551814100446e-05,
+      "loss": 0.0618,
+      "step": 2245
+    },
+    {
+      "epoch": 0.3313906307635559,
+      "grad_norm": 1.8612760305404663,
+      "learning_rate": 1.691179652074984e-05,
+      "loss": 0.0432,
+      "step": 2246
+    },
+    {
+      "epoch": 0.3315381777941719,
+      "grad_norm": 7.949804306030273,
+      "learning_rate": 1.6908073066604665e-05,
+      "loss": 0.094,
+      "step": 2247
+    },
+    {
+      "epoch": 0.3316857248247879,
+      "grad_norm": 4.214132308959961,
+      "learning_rate": 1.6904347779556875e-05,
+      "loss": 0.0619,
+      "step": 2248
+    },
+    {
+      "epoch": 0.3318332718554039,
+      "grad_norm": 3.301882743835449,
+      "learning_rate": 1.6900620660594884e-05,
+      "loss": 0.0829,
+      "step": 2249
+    },
+    {
+      "epoch": 0.33198081888601993,
+      "grad_norm": 1.0096971988677979,
+      "learning_rate": 1.689689171070761e-05,
+      "loss": 0.0447,
+      "step": 2250
+    },
+    {
+      "epoch": 0.3321283659166359,
+      "grad_norm": 4.101325511932373,
+      "learning_rate": 1.6893160930884435e-05,
+      "loss": 0.0691,
+      "step": 2251
+    },
+    {
+      "epoch": 0.33227591294725195,
+      "grad_norm": 1.1518974304199219,
+      "learning_rate": 1.6889428322115247e-05,
+      "loss": 0.0306,
+      "step": 2252
+    },
+    {
+      "epoch": 0.33242345997786793,
+      "grad_norm": 6.926194190979004,
+      "learning_rate": 1.6885693885390405e-05,
+      "loss": 0.0677,
+      "step": 2253
+    },
+    {
+      "epoch": 0.33257100700848397,
+      "grad_norm": 3.5227413177490234,
+      "learning_rate": 1.688195762170076e-05,
+      "loss": 0.0887,
+      "step": 2254
+    },
+    {
+      "epoch": 0.33271855403909995,
+      "grad_norm": 1.2965720891952515,
+      "learning_rate": 1.687821953203765e-05,
+      "loss": 0.0249,
+      "step": 2255
+    },
+    {
+      "epoch": 0.332866101069716,
+      "grad_norm": 2.641340494155884,
+      "learning_rate": 1.6874479617392884e-05,
+      "loss": 0.0984,
+      "step": 2256
+    },
+    {
+      "epoch": 0.33301364810033196,
+      "grad_norm": 2.2977609634399414,
+      "learning_rate": 1.6870737878758775e-05,
+      "loss": 0.0543,
+      "step": 2257
+    },
+    {
+      "epoch": 0.333161195130948,
+      "grad_norm": 1.1189682483673096,
+      "learning_rate": 1.6866994317128105e-05,
+      "loss": 0.0566,
+      "step": 2258
+    },
+    {
+      "epoch": 0.333308742161564,
+      "grad_norm": 2.5354154109954834,
+      "learning_rate": 1.686324893349414e-05,
+      "loss": 0.0822,
+      "step": 2259
+    },
+    {
+      "epoch": 0.33345628919218,
+      "grad_norm": 1.2568128108978271,
+      "learning_rate": 1.685950172885064e-05,
+      "loss": 0.0472,
+      "step": 2260
+    },
+    {
+      "epoch": 0.33345628919218,
+      "eval_accuracy": 0.9710564399421129,
+      "eval_f1": 0.949238578680203,
+      "eval_loss": 0.07537344843149185,
+      "eval_precision": 0.9946808510638298,
+      "eval_recall": 0.9077669902912622,
+      "eval_runtime": 49.8557,
+      "eval_samples_per_second": 5.837,
+      "eval_steps_per_second": 0.201,
+      "step": 2260
+    },
+    {
+      "epoch": 0.333603836222796,
+      "grad_norm": 4.083811283111572,
+      "learning_rate": 1.6855752704191843e-05,
+      "loss": 0.1204,
+      "step": 2261
+    },
+    {
+      "epoch": 0.333751383253412,
+      "grad_norm": 4.4965338706970215,
+      "learning_rate": 1.685200186051246e-05,
+      "loss": 0.078,
+      "step": 2262
+    },
+    {
+      "epoch": 0.33389893028402806,
+      "grad_norm": 0.9255520105361938,
+      "learning_rate": 1.68482491988077e-05,
+      "loss": 0.0119,
+      "step": 2263
+    },
+    {
+      "epoch": 0.33404647731464404,
+      "grad_norm": 1.2964768409729004,
+      "learning_rate": 1.6844494720073247e-05,
+      "loss": 0.0356,
+      "step": 2264
+    },
+    {
+      "epoch": 0.3341940243452601,
+      "grad_norm": 2.200490713119507,
+      "learning_rate": 1.684073842530527e-05,
+      "loss": 0.1243,
+      "step": 2265
+    },
+    {
+      "epoch": 0.33434157137587606,
+      "grad_norm": 1.4421501159667969,
+      "learning_rate": 1.6836980315500417e-05,
+      "loss": 0.0449,
+      "step": 2266
+    },
+    {
+      "epoch": 0.3344891184064921,
+      "grad_norm": 3.5278217792510986,
+      "learning_rate": 1.6833220391655812e-05,
+      "loss": 0.0539,
+      "step": 2267
+    },
+    {
+      "epoch": 0.33463666543710807,
+      "grad_norm": 1.55814528465271,
+      "learning_rate": 1.6829458654769073e-05,
+      "loss": 0.0481,
+      "step": 2268
+    },
+    {
+      "epoch": 0.3347842124677241,
+      "grad_norm": 2.162083864212036,
+      "learning_rate": 1.682569510583829e-05,
+      "loss": 0.0087,
+      "step": 2269
+    },
+    {
+      "epoch": 0.3349317594983401,
+      "grad_norm": 1.685699224472046,
+      "learning_rate": 1.682192974586204e-05,
+      "loss": 0.0269,
+      "step": 2270
+    },
+    {
+      "epoch": 0.3350793065289561,
+      "grad_norm": 2.480480194091797,
+      "learning_rate": 1.6818162575839375e-05,
+      "loss": 0.0476,
+      "step": 2271
+    },
+    {
+      "epoch": 0.3352268535595721,
+      "grad_norm": 4.631017684936523,
+      "learning_rate": 1.6814393596769826e-05,
+      "loss": 0.1842,
+      "step": 2272
+    },
+    {
+      "epoch": 0.33537440059018814,
+      "grad_norm": 2.340878486633301,
+      "learning_rate": 1.6810622809653415e-05,
+      "loss": 0.0569,
+      "step": 2273
+    },
+    {
+      "epoch": 0.3355219476208041,
+      "grad_norm": 1.0919411182403564,
+      "learning_rate": 1.680685021549063e-05,
+      "loss": 0.0343,
+      "step": 2274
+    },
+    {
+      "epoch": 0.33566949465142015,
+      "grad_norm": 2.9381957054138184,
+      "learning_rate": 1.6803075815282442e-05,
+      "loss": 0.071,
+      "step": 2275
+    },
+    {
+      "epoch": 0.33581704168203613,
+      "grad_norm": 3.323485851287842,
+      "learning_rate": 1.6799299610030314e-05,
+      "loss": 0.117,
+      "step": 2276
+    },
+    {
+      "epoch": 0.33596458871265217,
+      "grad_norm": 1.3506728410720825,
+      "learning_rate": 1.6795521600736166e-05,
+      "loss": 0.055,
+      "step": 2277
+    },
+    {
+      "epoch": 0.33611213574326815,
+      "grad_norm": 3.0928151607513428,
+      "learning_rate": 1.6791741788402414e-05,
+      "loss": 0.0299,
+      "step": 2278
+    },
+    {
+      "epoch": 0.3362596827738842,
+      "grad_norm": 2.393380641937256,
+      "learning_rate": 1.6787960174031945e-05,
+      "loss": 0.1111,
+      "step": 2279
+    },
+    {
+      "epoch": 0.33640722980450016,
+      "grad_norm": 2.1875338554382324,
+      "learning_rate": 1.6784176758628127e-05,
+      "loss": 0.0404,
+      "step": 2280
+    },
+    {
+      "epoch": 0.33640722980450016,
+      "eval_accuracy": 0.9768451519536903,
+      "eval_f1": 0.9603960396039604,
+      "eval_loss": 0.06640757620334625,
+      "eval_precision": 0.9797979797979798,
+      "eval_recall": 0.941747572815534,
+      "eval_runtime": 49.5572,
+      "eval_samples_per_second": 5.872,
+      "eval_steps_per_second": 0.202,
+      "step": 2280
+    },
+    {
+      "epoch": 0.3365547768351162,
+      "grad_norm": 3.1600427627563477,
+      "learning_rate": 1.6780391543194804e-05,
+      "loss": 0.106,
+      "step": 2281
+    },
+    {
+      "epoch": 0.3367023238657322,
+      "grad_norm": 5.332502841949463,
+      "learning_rate": 1.67766045287363e-05,
+      "loss": 0.1328,
+      "step": 2282
+    },
+    {
+      "epoch": 0.3368498708963482,
+      "grad_norm": 12.91946792602539,
+      "learning_rate": 1.6772815716257414e-05,
+      "loss": 0.0924,
+      "step": 2283
+    },
+    {
+      "epoch": 0.3369974179269642,
+      "grad_norm": 2.88958477973938,
+      "learning_rate": 1.6769025106763417e-05,
+      "loss": 0.0885,
+      "step": 2284
+    },
+    {
+      "epoch": 0.33714496495758023,
+      "grad_norm": 1.5320292711257935,
+      "learning_rate": 1.676523270126007e-05,
+      "loss": 0.0241,
+      "step": 2285
+    },
+    {
+      "epoch": 0.33729251198819626,
+      "grad_norm": 4.352901458740234,
+      "learning_rate": 1.67614385007536e-05,
+      "loss": 0.0684,
+      "step": 2286
+    },
+    {
+      "epoch": 0.33744005901881224,
+      "grad_norm": 1.6219866275787354,
+      "learning_rate": 1.6757642506250713e-05,
+      "loss": 0.0619,
+      "step": 2287
+    },
+    {
+      "epoch": 0.3375876060494283,
+      "grad_norm": 2.50010085105896,
+      "learning_rate": 1.6753844718758592e-05,
+      "loss": 0.0624,
+      "step": 2288
+    },
+    {
+      "epoch": 0.33773515308004426,
+      "grad_norm": 1.923895239830017,
+      "learning_rate": 1.6750045139284892e-05,
+      "loss": 0.0436,
+      "step": 2289
+    },
+    {
+      "epoch": 0.3378827001106603,
+      "grad_norm": 1.3771748542785645,
+      "learning_rate": 1.6746243768837752e-05,
+      "loss": 0.0488,
+      "step": 2290
+    },
+    {
+      "epoch": 0.3380302471412763,
+      "grad_norm": 1.6006910800933838,
+      "learning_rate": 1.6742440608425772e-05,
+      "loss": 0.0466,
+      "step": 2291
+    },
+    {
+      "epoch": 0.3381777941718923,
+      "grad_norm": 0.9986759424209595,
+      "learning_rate": 1.6738635659058045e-05,
+      "loss": 0.0322,
+      "step": 2292
+    },
+    {
+      "epoch": 0.3383253412025083,
+      "grad_norm": 2.151573419570923,
+      "learning_rate": 1.6734828921744127e-05,
+      "loss": 0.0706,
+      "step": 2293
+    },
+    {
+      "epoch": 0.3384728882331243,
+      "grad_norm": 1.4651777744293213,
+      "learning_rate": 1.6731020397494044e-05,
+      "loss": 0.084,
+      "step": 2294
+    },
+    {
+      "epoch": 0.3386204352637403,
+      "grad_norm": 3.3459606170654297,
+      "learning_rate": 1.6727210087318308e-05,
+      "loss": 0.021,
+      "step": 2295
+    },
+    {
+      "epoch": 0.33876798229435634,
+      "grad_norm": 1.4047874212265015,
+      "learning_rate": 1.6723397992227898e-05,
+      "loss": 0.0156,
+      "step": 2296
+    },
+    {
+      "epoch": 0.3389155293249723,
+      "grad_norm": 2.0876870155334473,
+      "learning_rate": 1.671958411323427e-05,
+      "loss": 0.032,
+      "step": 2297
+    },
+    {
+      "epoch": 0.33906307635558836,
+      "grad_norm": 2.436588764190674,
+      "learning_rate": 1.671576845134935e-05,
+      "loss": 0.0934,
+      "step": 2298
+    },
+    {
+      "epoch": 0.33921062338620434,
+      "grad_norm": 2.535916566848755,
+      "learning_rate": 1.671195100758554e-05,
+      "loss": 0.0255,
+      "step": 2299
+    },
+    {
+      "epoch": 0.33935817041682037,
+      "grad_norm": 3.2804372310638428,
+      "learning_rate": 1.6708131782955713e-05,
+      "loss": 0.0952,
+      "step": 2300
+    },
+    {
+      "epoch": 0.33935817041682037,
+      "eval_accuracy": 0.9696092619392185,
+      "eval_f1": 0.9465648854961832,
+      "eval_loss": 0.08067480474710464,
+      "eval_precision": 0.9946524064171123,
+      "eval_recall": 0.9029126213592233,
+      "eval_runtime": 49.5636,
+      "eval_samples_per_second": 5.871,
+      "eval_steps_per_second": 0.202,
+      "step": 2300
     }
   ],
   "logging_steps": 1,
@@ -16758,7 +17518,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.775547294038098e+17,
+  "total_flos": 7.084455024457155e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null