Training in progress, step 500, checkpoint

last-checkpoint/optimizer_0/__0_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61e0583ec5819bd9d218cb7cbb3d96a13e38ffa7c04c77bed86909e60e2d8d43
+oid sha256:e2b93ad52642a85b05dfeb12298d5fc96031e28deca183e4c2c08dee55390519
 size 13934748

last-checkpoint/optimizer_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc9ceb414aa18285c6e881640d933d01fb0146850bfc8ecd06ab1f6bb1bed056
+oid sha256:2efb917810cc2f95e9f9ce9dbedd055ab564155034f3abefbe6e2c2aba3ca26d
 size 13999412

last-checkpoint/optimizer_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1366fd8d18df6071e3e46f037affd2fa48cd8fbddf1de76bfad3a682252957dc
+oid sha256:a1074fb3e5da840427a8c2bea51f33775455c187a3952a36a214f784d7d2276f
 size 13990904

last-checkpoint/optimizer_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d27689e09f171d3bfac23f02586872ccd9295635653d605d59ab909896aef34d
+oid sha256:125e0693505ee7832ee7ccc24457433cbae25876a3094529f034b3e75b927697
 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:ba710043ec7c5e37f0cc9912a7fc1e35ee1c93b7c28149447a9da2468e8d2738
+oid sha256:a160bd7b9e08e738f42a7a457989e3c22a3b5edc1387393e647818565d70087c
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34df0713f48ac78099ac04b6aa827e0b9450f86e65d38e6f95738f425b9fe3cb
+oid sha256:ecc75e35548f117f565dab4461f84d0eafe694b50abee164ab9bef5eab3b4ee4
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22216db04e5f7b4575fd49e958bbf8d52502bd3d4c610f1ee1ac28962fb2221f
+oid sha256:3ae5b867cd013595180bd2ccabeca150c9cfa9878165ccfecdfd9293bc574562
 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:ad4699d37b4a4fd828dc85d7a4afb8b7233d8ff3f31f19da2eb15b5020878277
+oid sha256:3a70ec7443f662da848c4b8210fe462d74b2d7a68b35699dc79e5bd86cb1eae2
 size 6966784

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:770f70341965762eba950e78530dac18548c5ffc01747f586966a93dd2aaecc5
+oid sha256:c76de5da5afcc5abc533d34acaa4a5f75726ae0dddef8d03dce20b4b0bb16b26
 size 15088

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6a5808c82049f750089c2b8c24ef7ed5c78e67dc53d231bb7066cc5400ea6c0
+oid sha256:fe6768c650c318d7513b359980365700ed7262b73426a2846102802665f07202
 size 15088

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26584d4d2b2c938da795ee83cefc212ad7531e84dccb612e0d827ed54c445ba7
+oid sha256:984877f9215c7cb40eee3a9c80335cc677560aa6c451b66bba02e1f3bd6a640f
 size 15088

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce4ce133b799ebf855812e6c0a1492b8b6983f401e5b15fef49b386da6c07a2e
+oid sha256:61f55f74596ac7956ac8ae93c9417eb4717b8e1452599a0c994329e13b642c3c
 size 15088

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e72f0c2b42252f9bf5b1a5e2d7757bd051d85eef3fb930f6dcbfeb449c5c3e1a
+oid sha256:976dc23b255118d6686ca07b5635c96d50eb321a91532eac8dd124ba2740fad5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3389830508474576,
+  "epoch": 0.423728813559322,
   "eval_steps": 20,
-  "global_step": 400,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3059,6 +3059,766 @@
       "eval_samples_per_second": 5.7,
       "eval_steps_per_second": 0.195,
       "step": 400
+    },
+    {
+      "epoch": 0.3398305084745763,
+      "grad_norm": 1.8987358808517456,
+      "learning_rate": 1.6695701612246578e-05,
+      "loss": 0.0087,
+      "step": 401
+    },
+    {
+      "epoch": 0.34067796610169493,
+      "grad_norm": 2.600064277648926,
+      "learning_rate": 1.6673700462483776e-05,
+      "loss": 0.0215,
+      "step": 402
+    },
+    {
+      "epoch": 0.34152542372881356,
+      "grad_norm": 0.21410588920116425,
+      "learning_rate": 1.6651640912148362e-05,
+      "loss": 0.0013,
+      "step": 403
+    },
+    {
+      "epoch": 0.3423728813559322,
+      "grad_norm": 2.80786395072937,
+      "learning_rate": 1.662952315428021e-05,
+      "loss": 0.0257,
+      "step": 404
+    },
+    {
+      "epoch": 0.3432203389830508,
+      "grad_norm": 2.0962929725646973,
+      "learning_rate": 1.6607347382428577e-05,
+      "loss": 0.0106,
+      "step": 405
+    },
+    {
+      "epoch": 0.3440677966101695,
+      "grad_norm": 1.8939802646636963,
+      "learning_rate": 1.658511379065039e-05,
+      "loss": 0.0211,
+      "step": 406
+    },
+    {
+      "epoch": 0.34491525423728814,
+      "grad_norm": 1.2169216871261597,
+      "learning_rate": 1.6562822573508533e-05,
+      "loss": 0.0056,
+      "step": 407
+    },
+    {
+      "epoch": 0.34576271186440677,
+      "grad_norm": 1.3260303735733032,
+      "learning_rate": 1.6540473926070183e-05,
+      "loss": 0.0137,
+      "step": 408
+    },
+    {
+      "epoch": 0.3466101694915254,
+      "grad_norm": 2.0518648624420166,
+      "learning_rate": 1.6518068043905075e-05,
+      "loss": 0.0104,
+      "step": 409
+    },
+    {
+      "epoch": 0.3474576271186441,
+      "grad_norm": 0.49681225419044495,
+      "learning_rate": 1.649560512308378e-05,
+      "loss": 0.0037,
+      "step": 410
+    },
+    {
+      "epoch": 0.3483050847457627,
+      "grad_norm": 1.43990957736969,
+      "learning_rate": 1.647308536017603e-05,
+      "loss": 0.0086,
+      "step": 411
+    },
+    {
+      "epoch": 0.34915254237288135,
+      "grad_norm": 1.290264368057251,
+      "learning_rate": 1.6450508952248957e-05,
+      "loss": 0.0159,
+      "step": 412
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.9707666039466858,
+      "learning_rate": 1.6427876096865394e-05,
+      "loss": 0.0074,
+      "step": 413
+    },
+    {
+      "epoch": 0.35084745762711866,
+      "grad_norm": 2.03999924659729,
+      "learning_rate": 1.6405186992082134e-05,
+      "loss": 0.0144,
+      "step": 414
+    },
+    {
+      "epoch": 0.3516949152542373,
+      "grad_norm": 0.5716383457183838,
+      "learning_rate": 1.6382441836448203e-05,
+      "loss": 0.0053,
+      "step": 415
+    },
+    {
+      "epoch": 0.3525423728813559,
+      "grad_norm": 0.6597254276275635,
+      "learning_rate": 1.635964082900311e-05,
+      "loss": 0.0033,
+      "step": 416
+    },
+    {
+      "epoch": 0.35338983050847456,
+      "grad_norm": 0.7216088175773621,
+      "learning_rate": 1.6336784169275132e-05,
+      "loss": 0.0039,
+      "step": 417
+    },
+    {
+      "epoch": 0.35423728813559324,
+      "grad_norm": 2.028721570968628,
+      "learning_rate": 1.6313872057279536e-05,
+      "loss": 0.0229,
+      "step": 418
+    },
+    {
+      "epoch": 0.3550847457627119,
+      "grad_norm": 3.6218316555023193,
+      "learning_rate": 1.6290904693516853e-05,
+      "loss": 0.0318,
+      "step": 419
+    },
+    {
+      "epoch": 0.3559322033898305,
+      "grad_norm": 0.5219744443893433,
+      "learning_rate": 1.6267882278971102e-05,
+      "loss": 0.0032,
+      "step": 420
+    },
+    {
+      "epoch": 0.3559322033898305,
+      "eval_accuracy": 1.0,
+      "eval_f1": 1.0,
+      "eval_loss": 0.00023322339984588325,
+      "eval_precision": 1.0,
+      "eval_recall": 1.0,
+      "eval_runtime": 51.4367,
+      "eval_samples_per_second": 5.677,
+      "eval_steps_per_second": 0.194,
+      "step": 420
+    },
+    {
+      "epoch": 0.35677966101694913,
+      "grad_norm": 1.2915095090866089,
+      "learning_rate": 1.624480501510806e-05,
+      "loss": 0.0086,
+      "step": 421
+    },
+    {
+      "epoch": 0.3576271186440678,
+      "grad_norm": 1.938812255859375,
+      "learning_rate": 1.6221673103873474e-05,
+      "loss": 0.0181,
+      "step": 422
+    },
+    {
+      "epoch": 0.35847457627118645,
+      "grad_norm": 2.0729336738586426,
+      "learning_rate": 1.6198486747691293e-05,
+      "loss": 0.0119,
+      "step": 423
+    },
+    {
+      "epoch": 0.3593220338983051,
+      "grad_norm": 1.3602229356765747,
+      "learning_rate": 1.617524614946192e-05,
+      "loss": 0.0121,
+      "step": 424
+    },
+    {
+      "epoch": 0.3601694915254237,
+      "grad_norm": 0.6615320444107056,
+      "learning_rate": 1.615195151256042e-05,
+      "loss": 0.0051,
+      "step": 425
+    },
+    {
+      "epoch": 0.3610169491525424,
+      "grad_norm": 1.0828938484191895,
+      "learning_rate": 1.6128603040834735e-05,
+      "loss": 0.0136,
+      "step": 426
+    },
+    {
+      "epoch": 0.36186440677966103,
+      "grad_norm": 1.0993672609329224,
+      "learning_rate": 1.6105200938603917e-05,
+      "loss": 0.0071,
+      "step": 427
+    },
+    {
+      "epoch": 0.36271186440677966,
+      "grad_norm": 1.2687034606933594,
+      "learning_rate": 1.608174541065632e-05,
+      "loss": 0.0124,
+      "step": 428
+    },
+    {
+      "epoch": 0.3635593220338983,
+      "grad_norm": 0.7331047654151917,
+      "learning_rate": 1.6058236662247827e-05,
+      "loss": 0.0042,
+      "step": 429
+    },
+    {
+      "epoch": 0.3644067796610169,
+      "grad_norm": 0.8685011863708496,
+      "learning_rate": 1.603467489910004e-05,
+      "loss": 0.0065,
+      "step": 430
+    },
+    {
+      "epoch": 0.3652542372881356,
+      "grad_norm": 0.4545860290527344,
+      "learning_rate": 1.6011060327398492e-05,
+      "loss": 0.0035,
+      "step": 431
+    },
+    {
+      "epoch": 0.36610169491525424,
+      "grad_norm": 1.2493585348129272,
+      "learning_rate": 1.5987393153790832e-05,
+      "loss": 0.0104,
+      "step": 432
+    },
+    {
+      "epoch": 0.36694915254237287,
+      "grad_norm": 0.7078704237937927,
+      "learning_rate": 1.5963673585385016e-05,
+      "loss": 0.0061,
+      "step": 433
+    },
+    {
+      "epoch": 0.3677966101694915,
+      "grad_norm": 1.4348129034042358,
+      "learning_rate": 1.5939901829747508e-05,
+      "loss": 0.0082,
+      "step": 434
+    },
+    {
+      "epoch": 0.3686440677966102,
+      "grad_norm": 1.2969249486923218,
+      "learning_rate": 1.5916078094901448e-05,
+      "loss": 0.0049,
+      "step": 435
+    },
+    {
+      "epoch": 0.3694915254237288,
+      "grad_norm": 0.5477801561355591,
+      "learning_rate": 1.5892202589324835e-05,
+      "loss": 0.0043,
+      "step": 436
+    },
+    {
+      "epoch": 0.37033898305084745,
+      "grad_norm": 1.7194287776947021,
+      "learning_rate": 1.5868275521948726e-05,
+      "loss": 0.0148,
+      "step": 437
+    },
+    {
+      "epoch": 0.3711864406779661,
+      "grad_norm": 1.6770473718643188,
+      "learning_rate": 1.5844297102155364e-05,
+      "loss": 0.0198,
+      "step": 438
+    },
+    {
+      "epoch": 0.37203389830508476,
+      "grad_norm": 2.6121509075164795,
+      "learning_rate": 1.582026753977638e-05,
+      "loss": 0.0135,
+      "step": 439
+    },
+    {
+      "epoch": 0.3728813559322034,
+      "grad_norm": 2.6553170680999756,
+      "learning_rate": 1.5796187045090943e-05,
+      "loss": 0.0413,
+      "step": 440
+    },
+    {
+      "epoch": 0.3728813559322034,
+      "eval_accuracy": 1.0,
+      "eval_f1": 1.0,
+      "eval_loss": 0.00017413182649761438,
+      "eval_precision": 1.0,
+      "eval_recall": 1.0,
+      "eval_runtime": 51.5352,
+      "eval_samples_per_second": 5.666,
+      "eval_steps_per_second": 0.194,
+      "step": 440
+    },
+    {
+      "epoch": 0.373728813559322,
+      "grad_norm": 1.9083479642868042,
+      "learning_rate": 1.577205582882393e-05,
+      "loss": 0.0052,
+      "step": 441
+    },
+    {
+      "epoch": 0.37457627118644066,
+      "grad_norm": 1.9797714948654175,
+      "learning_rate": 1.5747874102144073e-05,
+      "loss": 0.0103,
+      "step": 442
+    },
+    {
+      "epoch": 0.37542372881355934,
+      "grad_norm": 3.449254035949707,
+      "learning_rate": 1.57236420766621e-05,
+      "loss": 0.0396,
+      "step": 443
+    },
+    {
+      "epoch": 0.376271186440678,
+      "grad_norm": 1.179081916809082,
+      "learning_rate": 1.5699359964428917e-05,
+      "loss": 0.0054,
+      "step": 444
+    },
+    {
+      "epoch": 0.3771186440677966,
+      "grad_norm": 2.9331607818603516,
+      "learning_rate": 1.567502797793372e-05,
+      "loss": 0.0207,
+      "step": 445
+    },
+    {
+      "epoch": 0.37796610169491524,
+      "grad_norm": 2.226416826248169,
+      "learning_rate": 1.5650646330102144e-05,
+      "loss": 0.0225,
+      "step": 446
+    },
+    {
+      "epoch": 0.3788135593220339,
+      "grad_norm": 1.9515255689620972,
+      "learning_rate": 1.5626215234294416e-05,
+      "loss": 0.0122,
+      "step": 447
+    },
+    {
+      "epoch": 0.37966101694915255,
+      "grad_norm": 2.8020267486572266,
+      "learning_rate": 1.560173490430346e-05,
+      "loss": 0.0113,
+      "step": 448
+    },
+    {
+      "epoch": 0.3805084745762712,
+      "grad_norm": 2.073023557662964,
+      "learning_rate": 1.5577205554353056e-05,
+      "loss": 0.0083,
+      "step": 449
+    },
+    {
+      "epoch": 0.3813559322033898,
+      "grad_norm": 1.7509485483169556,
+      "learning_rate": 1.5552627399095943e-05,
+      "loss": 0.0146,
+      "step": 450
+    },
+    {
+      "epoch": 0.3822033898305085,
+      "grad_norm": 1.0263633728027344,
+      "learning_rate": 1.5528000653611935e-05,
+      "loss": 0.0048,
+      "step": 451
+    },
+    {
+      "epoch": 0.38305084745762713,
+      "grad_norm": 0.847665011882782,
+      "learning_rate": 1.5503325533406076e-05,
+      "loss": 0.0096,
+      "step": 452
+    },
+    {
+      "epoch": 0.38389830508474576,
+      "grad_norm": 1.1132762432098389,
+      "learning_rate": 1.5478602254406722e-05,
+      "loss": 0.0046,
+      "step": 453
+    },
+    {
+      "epoch": 0.3847457627118644,
+      "grad_norm": 0.4251544177532196,
+      "learning_rate": 1.5453831032963648e-05,
+      "loss": 0.0034,
+      "step": 454
+    },
+    {
+      "epoch": 0.3855932203389831,
+      "grad_norm": 1.9715460538864136,
+      "learning_rate": 1.5429012085846183e-05,
+      "loss": 0.0159,
+      "step": 455
+    },
+    {
+      "epoch": 0.3864406779661017,
+      "grad_norm": 2.9356298446655273,
+      "learning_rate": 1.5404145630241275e-05,
+      "loss": 0.0379,
+      "step": 456
+    },
+    {
+      "epoch": 0.38728813559322034,
+      "grad_norm": 0.7249993085861206,
+      "learning_rate": 1.537923188375164e-05,
+      "loss": 0.0025,
+      "step": 457
+    },
+    {
+      "epoch": 0.38813559322033897,
+      "grad_norm": 1.8938612937927246,
+      "learning_rate": 1.535427106439381e-05,
+      "loss": 0.0096,
+      "step": 458
+    },
+    {
+      "epoch": 0.3889830508474576,
+      "grad_norm": 3.1911001205444336,
+      "learning_rate": 1.5329263390596245e-05,
+      "loss": 0.0448,
+      "step": 459
+    },
+    {
+      "epoch": 0.3898305084745763,
+      "grad_norm": 2.0256171226501465,
+      "learning_rate": 1.5304209081197425e-05,
+      "loss": 0.0189,
+      "step": 460
+    },
+    {
+      "epoch": 0.3898305084745763,
+      "eval_accuracy": 1.0,
+      "eval_f1": 1.0,
+      "eval_loss": 0.0003800760896410793,
+      "eval_precision": 1.0,
+      "eval_recall": 1.0,
+      "eval_runtime": 51.2193,
+      "eval_samples_per_second": 5.701,
+      "eval_steps_per_second": 0.195,
+      "step": 460
+    },
+    {
+      "epoch": 0.3906779661016949,
+      "grad_norm": 1.5554085969924927,
+      "learning_rate": 1.5279108355443942e-05,
+      "loss": 0.0094,
+      "step": 461
+    },
+    {
+      "epoch": 0.39152542372881355,
+      "grad_norm": 1.625154972076416,
+      "learning_rate": 1.5253961432988548e-05,
+      "loss": 0.0218,
+      "step": 462
+    },
+    {
+      "epoch": 0.3923728813559322,
+      "grad_norm": 1.304267406463623,
+      "learning_rate": 1.5228768533888278e-05,
+      "loss": 0.0065,
+      "step": 463
+    },
+    {
+      "epoch": 0.39322033898305087,
+      "grad_norm": 2.61993408203125,
+      "learning_rate": 1.5203529878602484e-05,
+      "loss": 0.0283,
+      "step": 464
+    },
+    {
+      "epoch": 0.3940677966101695,
+      "grad_norm": 0.5497863292694092,
+      "learning_rate": 1.5178245687990937e-05,
+      "loss": 0.0034,
+      "step": 465
+    },
+    {
+      "epoch": 0.3949152542372881,
+      "grad_norm": 0.8741781711578369,
+      "learning_rate": 1.5152916183311881e-05,
+      "loss": 0.0034,
+      "step": 466
+    },
+    {
+      "epoch": 0.39576271186440676,
+      "grad_norm": 2.4400858879089355,
+      "learning_rate": 1.5127541586220077e-05,
+      "loss": 0.0174,
+      "step": 467
+    },
+    {
+      "epoch": 0.39661016949152544,
+      "grad_norm": 2.425032138824463,
+      "learning_rate": 1.510212211876491e-05,
+      "loss": 0.014,
+      "step": 468
+    },
+    {
+      "epoch": 0.3974576271186441,
+      "grad_norm": 1.969048261642456,
+      "learning_rate": 1.50766580033884e-05,
+      "loss": 0.0231,
+      "step": 469
+    },
+    {
+      "epoch": 0.3983050847457627,
+      "grad_norm": 3.7651619911193848,
+      "learning_rate": 1.5051149462923285e-05,
+      "loss": 0.036,
+      "step": 470
+    },
+    {
+      "epoch": 0.39915254237288134,
+      "grad_norm": 1.2159584760665894,
+      "learning_rate": 1.5025596720591052e-05,
+      "loss": 0.0068,
+      "step": 471
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.8400602340698242,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.0111,
+      "step": 472
+    },
+    {
+      "epoch": 0.40084745762711865,
+      "grad_norm": 0.26205798983573914,
+      "learning_rate": 1.4974359525143275e-05,
+      "loss": 0.0017,
+      "step": 473
+    },
+    {
+      "epoch": 0.4016949152542373,
+      "grad_norm": 1.555829405784607,
+      "learning_rate": 1.4948675520396893e-05,
+      "loss": 0.0209,
+      "step": 474
+    },
+    {
+      "epoch": 0.4025423728813559,
+      "grad_norm": 0.8700111508369446,
+      "learning_rate": 1.4922948210517822e-05,
+      "loss": 0.0037,
+      "step": 475
+    },
+    {
+      "epoch": 0.4033898305084746,
+      "grad_norm": 2.0976297855377197,
+      "learning_rate": 1.4897177820641966e-05,
+      "loss": 0.0134,
+      "step": 476
+    },
+    {
+      "epoch": 0.40423728813559323,
+      "grad_norm": 1.7627066373825073,
+      "learning_rate": 1.4871364576282223e-05,
+      "loss": 0.008,
+      "step": 477
+    },
+    {
+      "epoch": 0.40508474576271186,
+      "grad_norm": 0.7504107356071472,
+      "learning_rate": 1.4845508703326504e-05,
+      "loss": 0.0102,
+      "step": 478
+    },
+    {
+      "epoch": 0.4059322033898305,
+      "grad_norm": 1.8525331020355225,
+      "learning_rate": 1.4819610428035754e-05,
+      "loss": 0.019,
+      "step": 479
+    },
+    {
+      "epoch": 0.4067796610169492,
+      "grad_norm": 0.5475234985351562,
+      "learning_rate": 1.4793669977041978e-05,
+      "loss": 0.003,
+      "step": 480
+    },
+    {
+      "epoch": 0.4067796610169492,
+      "eval_accuracy": 1.0,
+      "eval_f1": 1.0,
+      "eval_loss": 0.0002279380423715338,
+      "eval_precision": 1.0,
+      "eval_recall": 1.0,
+      "eval_runtime": 51.1012,
+      "eval_samples_per_second": 5.714,
+      "eval_steps_per_second": 0.196,
+      "step": 480
+    },
+    {
+      "epoch": 0.4076271186440678,
+      "grad_norm": 0.4113156199455261,
+      "learning_rate": 1.4767687577346253e-05,
+      "loss": 0.0031,
+      "step": 481
+    },
+    {
+      "epoch": 0.40847457627118644,
+      "grad_norm": 1.466239094734192,
+      "learning_rate": 1.4741663456316742e-05,
+      "loss": 0.0096,
+      "step": 482
+    },
+    {
+      "epoch": 0.40932203389830507,
+      "grad_norm": 1.421286702156067,
+      "learning_rate": 1.4715597841686708e-05,
+      "loss": 0.0119,
+      "step": 483
+    },
+    {
+      "epoch": 0.4101694915254237,
+      "grad_norm": 1.6936863660812378,
+      "learning_rate": 1.4689490961552513e-05,
+      "loss": 0.0191,
+      "step": 484
+    },
+    {
+      "epoch": 0.4110169491525424,
+      "grad_norm": 2.2526814937591553,
+      "learning_rate": 1.4663343044371635e-05,
+      "loss": 0.018,
+      "step": 485
+    },
+    {
+      "epoch": 0.411864406779661,
+      "grad_norm": 0.3923169672489166,
+      "learning_rate": 1.4637154318960653e-05,
+      "loss": 0.002,
+      "step": 486
+    },
+    {
+      "epoch": 0.41271186440677965,
+      "grad_norm": 1.785679578781128,
+      "learning_rate": 1.461092501449326e-05,
+      "loss": 0.0066,
+      "step": 487
+    },
+    {
+      "epoch": 0.4135593220338983,
+      "grad_norm": 4.866019248962402,
+      "learning_rate": 1.4584655360498245e-05,
+      "loss": 0.0307,
+      "step": 488
+    },
+    {
+      "epoch": 0.41440677966101697,
+      "grad_norm": 3.334535598754883,
+      "learning_rate": 1.4558345586857496e-05,
+      "loss": 0.0293,
+      "step": 489
+    },
+    {
+      "epoch": 0.4152542372881356,
+      "grad_norm": 1.5165126323699951,
+      "learning_rate": 1.4531995923803974e-05,
+      "loss": 0.0156,
+      "step": 490
+    },
+    {
+      "epoch": 0.4161016949152542,
+      "grad_norm": 0.1444772481918335,
+      "learning_rate": 1.450560660191971e-05,
+      "loss": 0.001,
+      "step": 491
+    },
+    {
+      "epoch": 0.41694915254237286,
+      "grad_norm": 1.8422871828079224,
+      "learning_rate": 1.4479177852133787e-05,
+      "loss": 0.0237,
+      "step": 492
+    },
+    {
+      "epoch": 0.41779661016949154,
+      "grad_norm": 0.7579980492591858,
+      "learning_rate": 1.4452709905720314e-05,
+      "loss": 0.0036,
+      "step": 493
+    },
+    {
+      "epoch": 0.4186440677966102,
+      "grad_norm": 0.8799729943275452,
+      "learning_rate": 1.4426202994296401e-05,
+      "loss": 0.0069,
+      "step": 494
+    },
+    {
+      "epoch": 0.4194915254237288,
+      "grad_norm": 0.6293562054634094,
+      "learning_rate": 1.4399657349820136e-05,
+      "loss": 0.0038,
+      "step": 495
+    },
+    {
+      "epoch": 0.42033898305084744,
+      "grad_norm": 0.24156221747398376,
+      "learning_rate": 1.4373073204588556e-05,
+      "loss": 0.0017,
+      "step": 496
+    },
+    {
+      "epoch": 0.4211864406779661,
+      "grad_norm": 0.5691763758659363,
+      "learning_rate": 1.4346450791235611e-05,
+      "loss": 0.0037,
+      "step": 497
+    },
+    {
+      "epoch": 0.42203389830508475,
+      "grad_norm": 1.91914963722229,
+      "learning_rate": 1.4319790342730131e-05,
+      "loss": 0.0214,
+      "step": 498
+    },
+    {
+      "epoch": 0.4228813559322034,
+      "grad_norm": 3.101850748062134,
+      "learning_rate": 1.4293092092373786e-05,
+      "loss": 0.0217,
+      "step": 499
+    },
+    {
+      "epoch": 0.423728813559322,
+      "grad_norm": 1.2713143825531006,
+      "learning_rate": 1.4266356273799044e-05,
+      "loss": 0.0071,
+      "step": 500
+    },
+    {
+      "epoch": 0.423728813559322,
+      "eval_accuracy": 1.0,
+      "eval_f1": 1.0,
+      "eval_loss": 0.0003793275391217321,
+      "eval_precision": 1.0,
+      "eval_recall": 1.0,
+      "eval_runtime": 52.145,
+      "eval_samples_per_second": 5.6,
+      "eval_steps_per_second": 0.192,
+      "step": 500
     }
   ],
   "logging_steps": 1,
@@ -3078,7 +3838,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2357669100716032e+17,
+  "total_flos": 1.5414191977188557e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null