Training in progress, step 400, checkpoint

last-checkpoint/optimizer_0/__0_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6939fa8cdf25c762650f2d3d3355a3af6563f0ff00721b627282f60908c3f59
+oid sha256:f921a800df9e1dffff8b5a8bcc1f2a0feb901fec73f9493bf23a26bbfd289dee
 size 13934748

last-checkpoint/optimizer_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c7b3f1a318e2cc496fca5a0e17c82951b82e48847a73776b67435515bd3b117
+oid sha256:43c35f0bba2dac2fc00c2513ab5c093e5cc1f901061ce7075f6a71be7f09406c
 size 13999412

last-checkpoint/optimizer_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c357e6d93334bf277b9c7d69bbecfbf0d574ee83594d4aefca9a358b7697dc63
+oid sha256:c4c98b1c8a54259e41cf12b723ef7c30e33cbf9738ce4dc4dac2c39b2adf6b3c
 size 13990904

last-checkpoint/optimizer_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3df6316f9b70a49fe93ecd1dcb217b8cf2b9f1d06201e9cd378d30cf1ac2444
+oid sha256:cac1f5d07c5e17d137b36140c387006437dfae82a07139fc1281af22eb735e14
 size 13990904

last-checkpoint/pytorch_model_fsdp_0/__0_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:735c4d9885bdc1f40b2e139d1c5be6fdf8fb80870faadee69ed0f5b65eb4bf69
+oid sha256:ef94e962df8e23fffbf048a91877fe4589fff476632626f5bafb7efd3b2acda7
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fa86e6ee20e276dd223620f5f73051d773a3cf00f532b08afcae9924c2b3c84
+oid sha256:234599af5e1a25d1045977c614c305932361fd4bcedb2322b0301336cf3f11ab
 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:a1545702147d9ee97bdd5dc7bbcde2426e2ae21146f2807dae5aded5896daaa7
+oid sha256:bc64ed046978893df84936deae86223a8c9cff25882d6836987351d5130abc8e
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07fbf2ec86fb6b1d0da0836072b0dca651e3c394204002f1ed426eecc30a569a
+oid sha256:070dd4c7d9c6778725480a26c2a2eddc5d8292ade48824aaac9156e774f03e88
 size 6966784

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b97d0b3b52285a9a23cb592a2b624fc30f4e8b1b49dee2093250a42185714fae
+oid sha256:6e58c3cfa1be4906eb2ebeeaad21e3dcfbf751786ea43c11178b57bba3ed86be
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14c4dc09b19022d70ab1e7f40c998143b4e686e79e0e83e59d15521c0f0652bd
+oid sha256:c54e94cba9de0aafa574d47115cd05dfd16183a274746e3174c3dcb17a6811cf
 size 14960

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed26153973e4964d16eab6644bf6fd88bae202c6e07155a00cad65a1de0f6bcf
+oid sha256:fb1096396058d8eeae102f1d20b279a916b115344006e88908ca3e87cdfd8e4d
 size 14960

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ddf99c805abb2056960209b3190c0de826effa11fd4c4b1fb50ceb4079b7f5b
+oid sha256:da8e5ce8dd34c6a1d036cd8fdb0cb302e7064cf817ace6812c11bd3ddad1f6d1
 size 14960

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36e32dd1a5ae7a273ff3b5c3ef07147f38ae674d07fd46f56c265e9de492bff2
+oid sha256:df6ff9c3246b4f09b8ee1c0ebc72d5335ca411ed855fde12555eeeb1d0837c70
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3712871287128713,
+  "epoch": 0.49504950495049505,
   "eval_steps": 20,
-  "global_step": 300,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2299,6 +2299,766 @@
       "eval_samples_per_second": 5.691,
       "eval_steps_per_second": 0.186,
       "step": 300
+    },
+    {
+      "epoch": 0.3725247524752475,
+      "grad_norm": 6.07203483581543,
+      "learning_rate": 1.5811230893694214e-05,
+      "loss": 0.2375,
+      "step": 301
+    },
+    {
+      "epoch": 0.37376237623762376,
+      "grad_norm": 5.992534160614014,
+      "learning_rate": 1.5776009243194158e-05,
+      "loss": 0.2989,
+      "step": 302
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 7.230125427246094,
+      "learning_rate": 1.574067973326248e-05,
+      "loss": 0.2541,
+      "step": 303
+    },
+    {
+      "epoch": 0.37623762376237624,
+      "grad_norm": 5.320266246795654,
+      "learning_rate": 1.570524302363165e-05,
+      "loss": 0.2273,
+      "step": 304
+    },
+    {
+      "epoch": 0.3774752475247525,
+      "grad_norm": 8.311070442199707,
+      "learning_rate": 1.5669699776035958e-05,
+      "loss": 0.1916,
+      "step": 305
+    },
+    {
+      "epoch": 0.3787128712871287,
+      "grad_norm": 7.01260232925415,
+      "learning_rate": 1.5634050654199147e-05,
+      "loss": 0.2083,
+      "step": 306
+    },
+    {
+      "epoch": 0.37995049504950495,
+      "grad_norm": 6.13078498840332,
+      "learning_rate": 1.5598296323822026e-05,
+      "loss": 0.1955,
+      "step": 307
+    },
+    {
+      "epoch": 0.3811881188118812,
+      "grad_norm": 5.786803722381592,
+      "learning_rate": 1.556243745257003e-05,
+      "loss": 0.2323,
+      "step": 308
+    },
+    {
+      "epoch": 0.38242574257425743,
+      "grad_norm": 8.768049240112305,
+      "learning_rate": 1.5526474710060767e-05,
+      "loss": 0.2716,
+      "step": 309
+    },
+    {
+      "epoch": 0.38366336633663367,
+      "grad_norm": 5.660022735595703,
+      "learning_rate": 1.5490408767851506e-05,
+      "loss": 0.2747,
+      "step": 310
+    },
+    {
+      "epoch": 0.3849009900990099,
+      "grad_norm": 3.7780046463012695,
+      "learning_rate": 1.5454240299426626e-05,
+      "loss": 0.1875,
+      "step": 311
+    },
+    {
+      "epoch": 0.38613861386138615,
+      "grad_norm": 3.4342143535614014,
+      "learning_rate": 1.5417969980185055e-05,
+      "loss": 0.1794,
+      "step": 312
+    },
+    {
+      "epoch": 0.3873762376237624,
+      "grad_norm": 5.58084774017334,
+      "learning_rate": 1.538159848742765e-05,
+      "loss": 0.2996,
+      "step": 313
+    },
+    {
+      "epoch": 0.3886138613861386,
+      "grad_norm": 4.530074119567871,
+      "learning_rate": 1.5345126500344555e-05,
+      "loss": 0.1944,
+      "step": 314
+    },
+    {
+      "epoch": 0.38985148514851486,
+      "grad_norm": 6.155841827392578,
+      "learning_rate": 1.530855470000251e-05,
+      "loss": 0.2508,
+      "step": 315
+    },
+    {
+      "epoch": 0.3910891089108911,
+      "grad_norm": 7.240228652954102,
+      "learning_rate": 1.5271883769332144e-05,
+      "loss": 0.2912,
+      "step": 316
+    },
+    {
+      "epoch": 0.39232673267326734,
+      "grad_norm": 4.011997699737549,
+      "learning_rate": 1.5235114393115202e-05,
+      "loss": 0.215,
+      "step": 317
+    },
+    {
+      "epoch": 0.3935643564356436,
+      "grad_norm": 2.886672258377075,
+      "learning_rate": 1.5198247257971788e-05,
+      "loss": 0.1769,
+      "step": 318
+    },
+    {
+      "epoch": 0.3948019801980198,
+      "grad_norm": 3.5629324913024902,
+      "learning_rate": 1.5161283052347516e-05,
+      "loss": 0.2009,
+      "step": 319
+    },
+    {
+      "epoch": 0.39603960396039606,
+      "grad_norm": 3.8855140209198,
+      "learning_rate": 1.5124222466500665e-05,
+      "loss": 0.2109,
+      "step": 320
+    },
+    {
+      "epoch": 0.39603960396039606,
+      "eval_accuracy": 0.8569844789356984,
+      "eval_f1": 0.7061503416856492,
+      "eval_loss": 0.3063695430755615,
+      "eval_precision": 0.8333333333333334,
+      "eval_recall": 0.6126482213438735,
+      "eval_runtime": 50.0323,
+      "eval_samples_per_second": 5.516,
+      "eval_steps_per_second": 0.18,
+      "step": 320
+    },
+    {
+      "epoch": 0.3972772277227723,
+      "grad_norm": 3.4308321475982666,
+      "learning_rate": 1.5087066192489288e-05,
+      "loss": 0.1939,
+      "step": 321
+    },
+    {
+      "epoch": 0.39851485148514854,
+      "grad_norm": 3.8520755767822266,
+      "learning_rate": 1.5049814924158298e-05,
+      "loss": 0.1707,
+      "step": 322
+    },
+    {
+      "epoch": 0.3997524752475248,
+      "grad_norm": 5.031585693359375,
+      "learning_rate": 1.5012469357126496e-05,
+      "loss": 0.2002,
+      "step": 323
+    },
+    {
+      "epoch": 0.400990099009901,
+      "grad_norm": 3.010558843612671,
+      "learning_rate": 1.4975030188773585e-05,
+      "loss": 0.1784,
+      "step": 324
+    },
+    {
+      "epoch": 0.40222772277227725,
+      "grad_norm": 6.272927761077881,
+      "learning_rate": 1.4937498118227156e-05,
+      "loss": 0.2514,
+      "step": 325
+    },
+    {
+      "epoch": 0.4034653465346535,
+      "grad_norm": 3.995131254196167,
+      "learning_rate": 1.4899873846349626e-05,
+      "loss": 0.1942,
+      "step": 326
+    },
+    {
+      "epoch": 0.40470297029702973,
+      "grad_norm": 4.409802436828613,
+      "learning_rate": 1.486215807572515e-05,
+      "loss": 0.1932,
+      "step": 327
+    },
+    {
+      "epoch": 0.40594059405940597,
+      "grad_norm": 3.927633285522461,
+      "learning_rate": 1.4824351510646508e-05,
+      "loss": 0.2129,
+      "step": 328
+    },
+    {
+      "epoch": 0.40717821782178215,
+      "grad_norm": 4.012439250946045,
+      "learning_rate": 1.478645485710194e-05,
+      "loss": 0.2854,
+      "step": 329
+    },
+    {
+      "epoch": 0.4084158415841584,
+      "grad_norm": 4.1401848793029785,
+      "learning_rate": 1.4748468822761974e-05,
+      "loss": 0.2454,
+      "step": 330
+    },
+    {
+      "epoch": 0.40965346534653463,
+      "grad_norm": 4.657931804656982,
+      "learning_rate": 1.4710394116966206e-05,
+      "loss": 0.2288,
+      "step": 331
+    },
+    {
+      "epoch": 0.41089108910891087,
+      "grad_norm": 6.472193717956543,
+      "learning_rate": 1.4672231450710066e-05,
+      "loss": 0.26,
+      "step": 332
+    },
+    {
+      "epoch": 0.4121287128712871,
+      "grad_norm": 4.930477142333984,
+      "learning_rate": 1.4633981536631514e-05,
+      "loss": 0.25,
+      "step": 333
+    },
+    {
+      "epoch": 0.41336633663366334,
+      "grad_norm": 6.003932476043701,
+      "learning_rate": 1.4595645088997758e-05,
+      "loss": 0.2209,
+      "step": 334
+    },
+    {
+      "epoch": 0.4146039603960396,
+      "grad_norm": 4.356766700744629,
+      "learning_rate": 1.4557222823691913e-05,
+      "loss": 0.2051,
+      "step": 335
+    },
+    {
+      "epoch": 0.4158415841584158,
+      "grad_norm": 4.463465213775635,
+      "learning_rate": 1.451871545819961e-05,
+      "loss": 0.206,
+      "step": 336
+    },
+    {
+      "epoch": 0.41707920792079206,
+      "grad_norm": 4.003593444824219,
+      "learning_rate": 1.4480123711595637e-05,
+      "loss": 0.232,
+      "step": 337
+    },
+    {
+      "epoch": 0.4183168316831683,
+      "grad_norm": 4.910566806793213,
+      "learning_rate": 1.4441448304530467e-05,
+      "loss": 0.2214,
+      "step": 338
+    },
+    {
+      "epoch": 0.41955445544554454,
+      "grad_norm": 5.432886123657227,
+      "learning_rate": 1.4402689959216845e-05,
+      "loss": 0.2621,
+      "step": 339
+    },
+    {
+      "epoch": 0.4207920792079208,
+      "grad_norm": 3.290602922439575,
+      "learning_rate": 1.4363849399416254e-05,
+      "loss": 0.1961,
+      "step": 340
+    },
+    {
+      "epoch": 0.4207920792079208,
+      "eval_accuracy": 0.8625277161862528,
+      "eval_f1": 0.7194570135746606,
+      "eval_loss": 0.30351048707962036,
+      "eval_precision": 0.8412698412698413,
+      "eval_recall": 0.6284584980237155,
+      "eval_runtime": 47.8239,
+      "eval_samples_per_second": 5.771,
+      "eval_steps_per_second": 0.188,
+      "step": 340
+    },
+    {
+      "epoch": 0.422029702970297,
+      "grad_norm": 4.072077751159668,
+      "learning_rate": 1.4324927350425451e-05,
+      "loss": 0.2061,
+      "step": 341
+    },
+    {
+      "epoch": 0.42326732673267325,
+      "grad_norm": 5.433284282684326,
+      "learning_rate": 1.4285924539062878e-05,
+      "loss": 0.2536,
+      "step": 342
+    },
+    {
+      "epoch": 0.4245049504950495,
+      "grad_norm": 4.794254779815674,
+      "learning_rate": 1.424684169365512e-05,
+      "loss": 0.2207,
+      "step": 343
+    },
+    {
+      "epoch": 0.42574257425742573,
+      "grad_norm": 4.268115043640137,
+      "learning_rate": 1.4207679544023289e-05,
+      "loss": 0.172,
+      "step": 344
+    },
+    {
+      "epoch": 0.42698019801980197,
+      "grad_norm": 3.946532964706421,
+      "learning_rate": 1.4168438821469402e-05,
+      "loss": 0.2167,
+      "step": 345
+    },
+    {
+      "epoch": 0.4282178217821782,
+      "grad_norm": 4.425963401794434,
+      "learning_rate": 1.4129120258762719e-05,
+      "loss": 0.1608,
+      "step": 346
+    },
+    {
+      "epoch": 0.42945544554455445,
+      "grad_norm": 3.5604379177093506,
+      "learning_rate": 1.4089724590126061e-05,
+      "loss": 0.1506,
+      "step": 347
+    },
+    {
+      "epoch": 0.4306930693069307,
+      "grad_norm": 3.63785719871521,
+      "learning_rate": 1.4050252551222115e-05,
+      "loss": 0.2117,
+      "step": 348
+    },
+    {
+      "epoch": 0.4319306930693069,
+      "grad_norm": 5.928184509277344,
+      "learning_rate": 1.4010704879139669e-05,
+      "loss": 0.2693,
+      "step": 349
+    },
+    {
+      "epoch": 0.43316831683168316,
+      "grad_norm": 6.965827941894531,
+      "learning_rate": 1.3971082312379864e-05,
+      "loss": 0.2764,
+      "step": 350
+    },
+    {
+      "epoch": 0.4344059405940594,
+      "grad_norm": 6.468440532684326,
+      "learning_rate": 1.3931385590842412e-05,
+      "loss": 0.256,
+      "step": 351
+    },
+    {
+      "epoch": 0.43564356435643564,
+      "grad_norm": 3.584207773208618,
+      "learning_rate": 1.3891615455811751e-05,
+      "loss": 0.2238,
+      "step": 352
+    },
+    {
+      "epoch": 0.4368811881188119,
+      "grad_norm": 5.467838764190674,
+      "learning_rate": 1.3851772649943238e-05,
+      "loss": 0.227,
+      "step": 353
+    },
+    {
+      "epoch": 0.4381188118811881,
+      "grad_norm": 3.78888201713562,
+      "learning_rate": 1.3811857917249254e-05,
+      "loss": 0.1581,
+      "step": 354
+    },
+    {
+      "epoch": 0.43935643564356436,
+      "grad_norm": 3.6381869316101074,
+      "learning_rate": 1.3771872003085315e-05,
+      "loss": 0.1825,
+      "step": 355
+    },
+    {
+      "epoch": 0.4405940594059406,
+      "grad_norm": 7.276025772094727,
+      "learning_rate": 1.373181565413617e-05,
+      "loss": 0.1976,
+      "step": 356
+    },
+    {
+      "epoch": 0.44183168316831684,
+      "grad_norm": 3.857329845428467,
+      "learning_rate": 1.3691689618401836e-05,
+      "loss": 0.2113,
+      "step": 357
+    },
+    {
+      "epoch": 0.4430693069306931,
+      "grad_norm": 7.177792072296143,
+      "learning_rate": 1.365149464518364e-05,
+      "loss": 0.216,
+      "step": 358
+    },
+    {
+      "epoch": 0.4443069306930693,
+      "grad_norm": 4.157836437225342,
+      "learning_rate": 1.3611231485070233e-05,
+      "loss": 0.2549,
+      "step": 359
+    },
+    {
+      "epoch": 0.44554455445544555,
+      "grad_norm": 4.768564701080322,
+      "learning_rate": 1.3570900889923566e-05,
+      "loss": 0.2369,
+      "step": 360
+    },
+    {
+      "epoch": 0.44554455445544555,
+      "eval_accuracy": 0.8747228381374723,
+      "eval_f1": 0.754880694143167,
+      "eval_loss": 0.2958848178386688,
+      "eval_precision": 0.8365384615384616,
+      "eval_recall": 0.6877470355731226,
+      "eval_runtime": 48.4168,
+      "eval_samples_per_second": 5.7,
+      "eval_steps_per_second": 0.186,
+      "step": 360
+    },
+    {
+      "epoch": 0.4467821782178218,
+      "grad_norm": 4.88621187210083,
+      "learning_rate": 1.3530503612864846e-05,
+      "loss": 0.2358,
+      "step": 361
+    },
+    {
+      "epoch": 0.44801980198019803,
+      "grad_norm": 6.0111188888549805,
+      "learning_rate": 1.3490040408260481e-05,
+      "loss": 0.2217,
+      "step": 362
+    },
+    {
+      "epoch": 0.44925742574257427,
+      "grad_norm": 4.757837295532227,
+      "learning_rate": 1.3449512031707987e-05,
+      "loss": 0.2563,
+      "step": 363
+    },
+    {
+      "epoch": 0.4504950495049505,
+      "grad_norm": 4.659700870513916,
+      "learning_rate": 1.340891924002189e-05,
+      "loss": 0.2332,
+      "step": 364
+    },
+    {
+      "epoch": 0.45173267326732675,
+      "grad_norm": 4.033824920654297,
+      "learning_rate": 1.3368262791219568e-05,
+      "loss": 0.1607,
+      "step": 365
+    },
+    {
+      "epoch": 0.452970297029703,
+      "grad_norm": 3.7575106620788574,
+      "learning_rate": 1.3327543444507134e-05,
+      "loss": 0.1768,
+      "step": 366
+    },
+    {
+      "epoch": 0.4542079207920792,
+      "grad_norm": 3.7037270069122314,
+      "learning_rate": 1.3286761960265216e-05,
+      "loss": 0.1891,
+      "step": 367
+    },
+    {
+      "epoch": 0.45544554455445546,
+      "grad_norm": 4.199578762054443,
+      "learning_rate": 1.3245919100034794e-05,
+      "loss": 0.2017,
+      "step": 368
+    },
+    {
+      "epoch": 0.4566831683168317,
+      "grad_norm": 5.948062419891357,
+      "learning_rate": 1.3205015626502957e-05,
+      "loss": 0.2974,
+      "step": 369
+    },
+    {
+      "epoch": 0.45792079207920794,
+      "grad_norm": 7.015734672546387,
+      "learning_rate": 1.3164052303488673e-05,
+      "loss": 0.2077,
+      "step": 370
+    },
+    {
+      "epoch": 0.4591584158415842,
+      "grad_norm": 4.3216657638549805,
+      "learning_rate": 1.3123029895928516e-05,
+      "loss": 0.1838,
+      "step": 371
+    },
+    {
+      "epoch": 0.4603960396039604,
+      "grad_norm": 3.7913501262664795,
+      "learning_rate": 1.3081949169862398e-05,
+      "loss": 0.2199,
+      "step": 372
+    },
+    {
+      "epoch": 0.46163366336633666,
+      "grad_norm": 4.902266979217529,
+      "learning_rate": 1.304081089241923e-05,
+      "loss": 0.166,
+      "step": 373
+    },
+    {
+      "epoch": 0.4628712871287129,
+      "grad_norm": 4.847469806671143,
+      "learning_rate": 1.2999615831802647e-05,
+      "loss": 0.2465,
+      "step": 374
+    },
+    {
+      "epoch": 0.46410891089108913,
+      "grad_norm": 5.700747013092041,
+      "learning_rate": 1.2958364757276616e-05,
+      "loss": 0.2151,
+      "step": 375
+    },
+    {
+      "epoch": 0.46534653465346537,
+      "grad_norm": 4.389228343963623,
+      "learning_rate": 1.2917058439151101e-05,
+      "loss": 0.206,
+      "step": 376
+    },
+    {
+      "epoch": 0.4665841584158416,
+      "grad_norm": 3.7354536056518555,
+      "learning_rate": 1.2875697648767664e-05,
+      "loss": 0.1675,
+      "step": 377
+    },
+    {
+      "epoch": 0.46782178217821785,
+      "grad_norm": 4.175409317016602,
+      "learning_rate": 1.2834283158485064e-05,
+      "loss": 0.1649,
+      "step": 378
+    },
+    {
+      "epoch": 0.46905940594059403,
+      "grad_norm": 4.25518274307251,
+      "learning_rate": 1.2792815741664839e-05,
+      "loss": 0.2133,
+      "step": 379
+    },
+    {
+      "epoch": 0.47029702970297027,
+      "grad_norm": 5.524796009063721,
+      "learning_rate": 1.2751296172656862e-05,
+      "loss": 0.2355,
+      "step": 380
+    },
+    {
+      "epoch": 0.47029702970297027,
+      "eval_accuracy": 0.8536585365853658,
+      "eval_f1": 0.6944444444444444,
+      "eval_loss": 0.3176264464855194,
+      "eval_precision": 0.8379888268156425,
+      "eval_recall": 0.5928853754940712,
+      "eval_runtime": 49.1355,
+      "eval_samples_per_second": 5.617,
+      "eval_steps_per_second": 0.183,
+      "step": 380
+    },
+    {
+      "epoch": 0.4715346534653465,
+      "grad_norm": 4.528620719909668,
+      "learning_rate": 1.2709725226784872e-05,
+      "loss": 0.2361,
+      "step": 381
+    },
+    {
+      "epoch": 0.47277227722772275,
+      "grad_norm": 4.263962745666504,
+      "learning_rate": 1.2668103680332011e-05,
+      "loss": 0.1655,
+      "step": 382
+    },
+    {
+      "epoch": 0.474009900990099,
+      "grad_norm": 4.377805709838867,
+      "learning_rate": 1.2626432310526321e-05,
+      "loss": 0.1856,
+      "step": 383
+    },
+    {
+      "epoch": 0.4752475247524752,
+      "grad_norm": 3.614685535430908,
+      "learning_rate": 1.2584711895526227e-05,
+      "loss": 0.1409,
+      "step": 384
+    },
+    {
+      "epoch": 0.47648514851485146,
+      "grad_norm": 4.1616644859313965,
+      "learning_rate": 1.2542943214406012e-05,
+      "loss": 0.2266,
+      "step": 385
+    },
+    {
+      "epoch": 0.4777227722772277,
+      "grad_norm": 3.9394242763519287,
+      "learning_rate": 1.250112704714126e-05,
+      "loss": 0.2002,
+      "step": 386
+    },
+    {
+      "epoch": 0.47896039603960394,
+      "grad_norm": 4.4327497482299805,
+      "learning_rate": 1.2459264174594303e-05,
+      "loss": 0.2154,
+      "step": 387
+    },
+    {
+      "epoch": 0.4801980198019802,
+      "grad_norm": 5.662235260009766,
+      "learning_rate": 1.2417355378499631e-05,
+      "loss": 0.1944,
+      "step": 388
+    },
+    {
+      "epoch": 0.4814356435643564,
+      "grad_norm": 5.926950454711914,
+      "learning_rate": 1.2375401441449296e-05,
+      "loss": 0.2783,
+      "step": 389
+    },
+    {
+      "epoch": 0.48267326732673266,
+      "grad_norm": 5.828728199005127,
+      "learning_rate": 1.23334031468783e-05,
+      "loss": 0.191,
+      "step": 390
+    },
+    {
+      "epoch": 0.4839108910891089,
+      "grad_norm": 4.729196071624756,
+      "learning_rate": 1.229136127904996e-05,
+      "loss": 0.2154,
+      "step": 391
+    },
+    {
+      "epoch": 0.48514851485148514,
+      "grad_norm": 6.837848663330078,
+      "learning_rate": 1.2249276623041268e-05,
+      "loss": 0.2192,
+      "step": 392
+    },
+    {
+      "epoch": 0.4863861386138614,
+      "grad_norm": 5.411125659942627,
+      "learning_rate": 1.2207149964728236e-05,
+      "loss": 0.196,
+      "step": 393
+    },
+    {
+      "epoch": 0.4876237623762376,
+      "grad_norm": 3.0349247455596924,
+      "learning_rate": 1.2164982090771202e-05,
+      "loss": 0.1437,
+      "step": 394
+    },
+    {
+      "epoch": 0.48886138613861385,
+      "grad_norm": 8.826495170593262,
+      "learning_rate": 1.2122773788600164e-05,
+      "loss": 0.2106,
+      "step": 395
+    },
+    {
+      "epoch": 0.4900990099009901,
+      "grad_norm": 4.7112555503845215,
+      "learning_rate": 1.2080525846400055e-05,
+      "loss": 0.2362,
+      "step": 396
+    },
+    {
+      "epoch": 0.49133663366336633,
+      "grad_norm": 4.847238063812256,
+      "learning_rate": 1.203823905309604e-05,
+      "loss": 0.2131,
+      "step": 397
+    },
+    {
+      "epoch": 0.49257425742574257,
+      "grad_norm": 4.841707229614258,
+      "learning_rate": 1.1995914198338777e-05,
+      "loss": 0.2312,
+      "step": 398
+    },
+    {
+      "epoch": 0.4938118811881188,
+      "grad_norm": 6.640840530395508,
+      "learning_rate": 1.1953552072489666e-05,
+      "loss": 0.272,
+      "step": 399
+    },
+    {
+      "epoch": 0.49504950495049505,
+      "grad_norm": 3.752530097961426,
+      "learning_rate": 1.1911153466606105e-05,
+      "loss": 0.1538,
+      "step": 400
+    },
+    {
+      "epoch": 0.49504950495049505,
+      "eval_accuracy": 0.8503325942350333,
+      "eval_f1": 0.6778042959427207,
+      "eval_loss": 0.3098345696926117,
+      "eval_precision": 0.8554216867469879,
+      "eval_recall": 0.5612648221343873,
+      "eval_runtime": 47.9792,
+      "eval_samples_per_second": 5.752,
+      "eval_steps_per_second": 0.188,
+      "step": 400
     }
   ],
   "logging_steps": 1,
@@ -2318,7 +3078,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.14412078544978e+16,
+  "total_flos": 1.2241982554374144e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null