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 sha256:6c6cd9bbf69ca7d063802c57c85eae4c8a4594c67d7465d15bea57713fe47513
+oid sha256:e2685cd63188a12b6e51a5f87202565fae64cf192dedbad3017d3d9a00011716
 size 13934748

last-checkpoint/optimizer_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ccc731a20bfee6a4b55db5e68d3cde38d8ac7d2f719abd77539294a3e34b2ec
+oid sha256:a564ea22e8120a98d07382ac39eaaeaf5ddb197a900e74e310ad7f4d8286fb1e
 size 13999412

last-checkpoint/optimizer_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2785839db765cda31082ddf8a82d30deab7dd42debaf778105e6f1e72628bf0b
+oid sha256:fc676c0cbe36a418bebb6a770754ec6e6b4550ec6cc2173fee8f8473cfd8acb2
 size 13990904

last-checkpoint/optimizer_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6543635366541dceae1dd968c306b2f0f2b4ecbd81d3aea258b1607da46815a7
+oid sha256:1e0189f4aacb249403224b0e30e9c8aa2b90c60a248a90d9f5fdee546b7c9452
 size 13990904

last-checkpoint/pytorch_model_fsdp_0/__0_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b475c353783d4026335e7030c57ba069d3d2acec25effee2905e6c973933656
+oid sha256:edae67eb4587445733f88b71e1245cfb3f5164c085e6d89fa55d75c346a20afb
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:722e06e8226ee81e6a1d319d49c78ac25f3e3038d6458b00cb35e8a42e093c2b
+oid sha256:ee7eeca1e6b6ba7221886609291f76f4c0ee14fdab353839097d8c6fbf7ee572
 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:c2282b29b361aca76f71e45f53ef426769df72fecd3cfe3e9040dd5f970c053c
+oid sha256:daabfcc6e1a3483f4db21790ddb98974904e8bc9e77135d80c25a77935fcb7db
 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:cd6c20f9a7c898a644f42332beb081e2ffc36926b9b070c86a030d2234848a7f
+oid sha256:9c434609d68ad98f7889ff98e8f1dc2f6ac56615be0728c4c1a08a0e95e8e983
 size 6966784

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9417da51974d70b68528d0d38ed2aa065576da18992311f443f57eb70377b35a
+oid sha256:672bc765d367d7d4ffae64a9a7720cba4580c54ee7b0c79f366c5fcfec50f7ae
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29eb939b26d6f551db8d7074c3cce05769523646edbde94bdcfcf35d61bc8110
+oid sha256:6a9b6f6648a3802b1d7df894c5bbd13bfaaff3cdef6fb263aaa54636226f2ff6
 size 14960

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:584643f2a79df1538d3f949cf4a835bec142b64a553256df7939bcbd22be0239
+oid sha256:742fcffc6aba3ef3530cc33f6ad6b89ccb93cdf34124275e474711f05d532257
 size 14960

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7cf12f3a30d07de0068e40183f8060da3680a455554f62dd104c0e905fb0bf5
+oid sha256:56b41b47676e62b604b32ae1968e1fffa4fc215a0c59a21338a7a142638b146f
 size 14960

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcc4feba00073f29deb4ad23d7b496e19059f229ff63aac62d469be206d14266
+oid sha256:1e3dd1bae2a933732e2e6fffe805496ee2173debbdafb8e9682fed9cdf6cd22a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2782931354359926,
+  "epoch": 0.37105751391465674,
   "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": 5.751,
       "eval_steps_per_second": 0.188,
       "step": 300
+    },
+    {
+      "epoch": 0.2792207792207792,
+      "grad_norm": 4.416810512542725,
+      "learning_rate": 1.810916440552835e-05,
+      "loss": 0.2122,
+      "step": 301
+    },
+    {
+      "epoch": 0.28014842300556586,
+      "grad_norm": 4.608455657958984,
+      "learning_rate": 1.8090169943749477e-05,
+      "loss": 0.1634,
+      "step": 302
+    },
+    {
+      "epoch": 0.2810760667903525,
+      "grad_norm": 2.9112977981567383,
+      "learning_rate": 1.8071090619916095e-05,
+      "loss": 0.1863,
+      "step": 303
+    },
+    {
+      "epoch": 0.2820037105751391,
+      "grad_norm": 4.165685176849365,
+      "learning_rate": 1.8051926634161282e-05,
+      "loss": 0.1607,
+      "step": 304
+    },
+    {
+      "epoch": 0.2829313543599258,
+      "grad_norm": 3.188124895095825,
+      "learning_rate": 1.8032678187506187e-05,
+      "loss": 0.1379,
+      "step": 305
+    },
+    {
+      "epoch": 0.28385899814471244,
+      "grad_norm": 4.277055740356445,
+      "learning_rate": 1.8013345481857903e-05,
+      "loss": 0.1945,
+      "step": 306
+    },
+    {
+      "epoch": 0.2847866419294991,
+      "grad_norm": 4.259377956390381,
+      "learning_rate": 1.799392872000736e-05,
+      "loss": 0.2123,
+      "step": 307
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 4.486137390136719,
+      "learning_rate": 1.797442810562721e-05,
+      "loss": 0.2004,
+      "step": 308
+    },
+    {
+      "epoch": 0.28664192949907236,
+      "grad_norm": 6.125461578369141,
+      "learning_rate": 1.7954843843269665e-05,
+      "loss": 0.2124,
+      "step": 309
+    },
+    {
+      "epoch": 0.287569573283859,
+      "grad_norm": 4.838400363922119,
+      "learning_rate": 1.793517613836437e-05,
+      "loss": 0.2112,
+      "step": 310
+    },
+    {
+      "epoch": 0.2884972170686456,
+      "grad_norm": 3.1725666522979736,
+      "learning_rate": 1.7915425197216246e-05,
+      "loss": 0.1658,
+      "step": 311
+    },
+    {
+      "epoch": 0.2894248608534323,
+      "grad_norm": 3.154855489730835,
+      "learning_rate": 1.7895591227003316e-05,
+      "loss": 0.2081,
+      "step": 312
+    },
+    {
+      "epoch": 0.29035250463821893,
+      "grad_norm": 3.7664122581481934,
+      "learning_rate": 1.7875674435774546e-05,
+      "loss": 0.1628,
+      "step": 313
+    },
+    {
+      "epoch": 0.2912801484230056,
+      "grad_norm": 5.876150131225586,
+      "learning_rate": 1.7855675032447648e-05,
+      "loss": 0.1882,
+      "step": 314
+    },
+    {
+      "epoch": 0.2922077922077922,
+      "grad_norm": 2.4536941051483154,
+      "learning_rate": 1.7835593226806902e-05,
+      "loss": 0.1287,
+      "step": 315
+    },
+    {
+      "epoch": 0.29313543599257885,
+      "grad_norm": 4.552228927612305,
+      "learning_rate": 1.7815429229500946e-05,
+      "loss": 0.2509,
+      "step": 316
+    },
+    {
+      "epoch": 0.2940630797773655,
+      "grad_norm": 3.861381769180298,
+      "learning_rate": 1.7795183252040568e-05,
+      "loss": 0.1827,
+      "step": 317
+    },
+    {
+      "epoch": 0.2949907235621521,
+      "grad_norm": 3.6626925468444824,
+      "learning_rate": 1.7774855506796497e-05,
+      "loss": 0.154,
+      "step": 318
+    },
+    {
+      "epoch": 0.29591836734693877,
+      "grad_norm": 6.695428848266602,
+      "learning_rate": 1.7754446206997152e-05,
+      "loss": 0.2334,
+      "step": 319
+    },
+    {
+      "epoch": 0.29684601113172543,
+      "grad_norm": 3.2786192893981934,
+      "learning_rate": 1.7733955566726438e-05,
+      "loss": 0.1671,
+      "step": 320
+    },
+    {
+      "epoch": 0.29684601113172543,
+      "eval_accuracy": 0.8337028824833703,
+      "eval_f1": 0.625,
+      "eval_loss": 0.3371331989765167,
+      "eval_precision": 0.8503401360544217,
+      "eval_recall": 0.49407114624505927,
+      "eval_runtime": 47.664,
+      "eval_samples_per_second": 5.791,
+      "eval_steps_per_second": 0.189,
+      "step": 320
+    },
+    {
+      "epoch": 0.29777365491651203,
+      "grad_norm": 4.181811809539795,
+      "learning_rate": 1.771338380092148e-05,
+      "loss": 0.2198,
+      "step": 321
+    },
+    {
+      "epoch": 0.2987012987012987,
+      "grad_norm": 4.808495998382568,
+      "learning_rate": 1.7692731125370355e-05,
+      "loss": 0.171,
+      "step": 322
+    },
+    {
+      "epoch": 0.29962894248608535,
+      "grad_norm": 5.946144104003906,
+      "learning_rate": 1.767199775670986e-05,
+      "loss": 0.2176,
+      "step": 323
+    },
+    {
+      "epoch": 0.300556586270872,
+      "grad_norm": 4.010025978088379,
+      "learning_rate": 1.7651183912423228e-05,
+      "loss": 0.2003,
+      "step": 324
+    },
+    {
+      "epoch": 0.3014842300556586,
+      "grad_norm": 4.795968055725098,
+      "learning_rate": 1.7630289810837836e-05,
+      "loss": 0.165,
+      "step": 325
+    },
+    {
+      "epoch": 0.30241187384044527,
+      "grad_norm": 2.9344944953918457,
+      "learning_rate": 1.7609315671122912e-05,
+      "loss": 0.1603,
+      "step": 326
+    },
+    {
+      "epoch": 0.3033395176252319,
+      "grad_norm": 5.812965393066406,
+      "learning_rate": 1.758826171328727e-05,
+      "loss": 0.1458,
+      "step": 327
+    },
+    {
+      "epoch": 0.3042671614100185,
+      "grad_norm": 4.66487979888916,
+      "learning_rate": 1.7567128158176955e-05,
+      "loss": 0.2155,
+      "step": 328
+    },
+    {
+      "epoch": 0.3051948051948052,
+      "grad_norm": 3.436579942703247,
+      "learning_rate": 1.7545915227472967e-05,
+      "loss": 0.1699,
+      "step": 329
+    },
+    {
+      "epoch": 0.30612244897959184,
+      "grad_norm": 4.022927284240723,
+      "learning_rate": 1.7524623143688905e-05,
+      "loss": 0.2037,
+      "step": 330
+    },
+    {
+      "epoch": 0.3070500927643785,
+      "grad_norm": 3.154623031616211,
+      "learning_rate": 1.7503252130168657e-05,
+      "loss": 0.1627,
+      "step": 331
+    },
+    {
+      "epoch": 0.3079777365491651,
+      "grad_norm": 2.7966222763061523,
+      "learning_rate": 1.748180241108404e-05,
+      "loss": 0.1439,
+      "step": 332
+    },
+    {
+      "epoch": 0.30890538033395176,
+      "grad_norm": 3.8477606773376465,
+      "learning_rate": 1.7460274211432463e-05,
+      "loss": 0.135,
+      "step": 333
+    },
+    {
+      "epoch": 0.3098330241187384,
+      "grad_norm": 3.51237416267395,
+      "learning_rate": 1.7438667757034547e-05,
+      "loss": 0.213,
+      "step": 334
+    },
+    {
+      "epoch": 0.310760667903525,
+      "grad_norm": 4.482552528381348,
+      "learning_rate": 1.7416983274531777e-05,
+      "loss": 0.2018,
+      "step": 335
+    },
+    {
+      "epoch": 0.3116883116883117,
+      "grad_norm": 3.7399659156799316,
+      "learning_rate": 1.739522099138411e-05,
+      "loss": 0.2196,
+      "step": 336
+    },
+    {
+      "epoch": 0.31261595547309834,
+      "grad_norm": 3.4632811546325684,
+      "learning_rate": 1.7373381135867605e-05,
+      "loss": 0.1588,
+      "step": 337
+    },
+    {
+      "epoch": 0.313543599257885,
+      "grad_norm": 5.400178909301758,
+      "learning_rate": 1.7351463937072008e-05,
+      "loss": 0.2455,
+      "step": 338
+    },
+    {
+      "epoch": 0.3144712430426716,
+      "grad_norm": 4.754225730895996,
+      "learning_rate": 1.732946962489836e-05,
+      "loss": 0.2067,
+      "step": 339
+    },
+    {
+      "epoch": 0.31539888682745826,
+      "grad_norm": 3.6749982833862305,
+      "learning_rate": 1.7307398430056595e-05,
+      "loss": 0.1809,
+      "step": 340
+    },
+    {
+      "epoch": 0.31539888682745826,
+      "eval_accuracy": 0.8514412416851441,
+      "eval_f1": 0.6912442396313364,
+      "eval_loss": 0.34059056639671326,
+      "eval_precision": 0.8287292817679558,
+      "eval_recall": 0.5928853754940712,
+      "eval_runtime": 47.764,
+      "eval_samples_per_second": 5.778,
+      "eval_steps_per_second": 0.188,
+      "step": 340
+    },
+    {
+      "epoch": 0.3163265306122449,
+      "grad_norm": 5.549361705780029,
+      "learning_rate": 1.72852505840631e-05,
+      "loss": 0.1656,
+      "step": 341
+    },
+    {
+      "epoch": 0.3172541743970315,
+      "grad_norm": 7.491882801055908,
+      "learning_rate": 1.72630263192383e-05,
+      "loss": 0.2493,
+      "step": 342
+    },
+    {
+      "epoch": 0.3181818181818182,
+      "grad_norm": 5.225057125091553,
+      "learning_rate": 1.7240725868704218e-05,
+      "loss": 0.2031,
+      "step": 343
+    },
+    {
+      "epoch": 0.31910946196660483,
+      "grad_norm": 7.436551094055176,
+      "learning_rate": 1.7218349466382024e-05,
+      "loss": 0.2245,
+      "step": 344
+    },
+    {
+      "epoch": 0.3200371057513915,
+      "grad_norm": 4.4297871589660645,
+      "learning_rate": 1.719589734698959e-05,
+      "loss": 0.2226,
+      "step": 345
+    },
+    {
+      "epoch": 0.3209647495361781,
+      "grad_norm": 6.560292720794678,
+      "learning_rate": 1.7173369746039026e-05,
+      "loss": 0.2331,
+      "step": 346
+    },
+    {
+      "epoch": 0.32189239332096475,
+      "grad_norm": 5.045467376708984,
+      "learning_rate": 1.7150766899834205e-05,
+      "loss": 0.2321,
+      "step": 347
+    },
+    {
+      "epoch": 0.3228200371057514,
+      "grad_norm": 6.464671611785889,
+      "learning_rate": 1.7128089045468294e-05,
+      "loss": 0.19,
+      "step": 348
+    },
+    {
+      "epoch": 0.323747680890538,
+      "grad_norm": 2.7538771629333496,
+      "learning_rate": 1.7105336420821247e-05,
+      "loss": 0.1642,
+      "step": 349
+    },
+    {
+      "epoch": 0.3246753246753247,
+      "grad_norm": 4.287221431732178,
+      "learning_rate": 1.7082509264557333e-05,
+      "loss": 0.1556,
+      "step": 350
+    },
+    {
+      "epoch": 0.32560296846011133,
+      "grad_norm": 3.1308867931365967,
+      "learning_rate": 1.705960781612262e-05,
+      "loss": 0.1583,
+      "step": 351
+    },
+    {
+      "epoch": 0.32653061224489793,
+      "grad_norm": 3.598468542098999,
+      "learning_rate": 1.7036632315742464e-05,
+      "loss": 0.1571,
+      "step": 352
+    },
+    {
+      "epoch": 0.3274582560296846,
+      "grad_norm": 2.93074369430542,
+      "learning_rate": 1.7013583004418994e-05,
+      "loss": 0.1463,
+      "step": 353
+    },
+    {
+      "epoch": 0.32838589981447125,
+      "grad_norm": 3.5115561485290527,
+      "learning_rate": 1.6990460123928577e-05,
+      "loss": 0.1522,
+      "step": 354
+    },
+    {
+      "epoch": 0.3293135435992579,
+      "grad_norm": 2.3975048065185547,
+      "learning_rate": 1.696726391681929e-05,
+      "loss": 0.136,
+      "step": 355
+    },
+    {
+      "epoch": 0.3302411873840445,
+      "grad_norm": 3.01874041557312,
+      "learning_rate": 1.6943994626408365e-05,
+      "loss": 0.1928,
+      "step": 356
+    },
+    {
+      "epoch": 0.33116883116883117,
+      "grad_norm": 3.620572805404663,
+      "learning_rate": 1.692065249677965e-05,
+      "loss": 0.1964,
+      "step": 357
+    },
+    {
+      "epoch": 0.3320964749536178,
+      "grad_norm": 3.1630985736846924,
+      "learning_rate": 1.6897237772781046e-05,
+      "loss": 0.1757,
+      "step": 358
+    },
+    {
+      "epoch": 0.33302411873840443,
+      "grad_norm": 2.7404632568359375,
+      "learning_rate": 1.6873750700021917e-05,
+      "loss": 0.1391,
+      "step": 359
+    },
+    {
+      "epoch": 0.3339517625231911,
+      "grad_norm": 3.915576696395874,
+      "learning_rate": 1.6850191524870548e-05,
+      "loss": 0.1672,
+      "step": 360
+    },
+    {
+      "epoch": 0.3339517625231911,
+      "eval_accuracy": 0.8392461197339246,
+      "eval_f1": 0.6365914786967418,
+      "eval_loss": 0.3519636392593384,
+      "eval_precision": 0.8698630136986302,
+      "eval_recall": 0.5019762845849802,
+      "eval_runtime": 48.8319,
+      "eval_samples_per_second": 5.652,
+      "eval_steps_per_second": 0.184,
+      "step": 360
+    },
+    {
+      "epoch": 0.33487940630797774,
+      "grad_norm": 4.442441940307617,
+      "learning_rate": 1.682656049445154e-05,
+      "loss": 0.1695,
+      "step": 361
+    },
+    {
+      "epoch": 0.3358070500927644,
+      "grad_norm": 3.9514217376708984,
+      "learning_rate": 1.6802857856643214e-05,
+      "loss": 0.1744,
+      "step": 362
+    },
+    {
+      "epoch": 0.336734693877551,
+      "grad_norm": 5.170446395874023,
+      "learning_rate": 1.6779083860075032e-05,
+      "loss": 0.1198,
+      "step": 363
+    },
+    {
+      "epoch": 0.33766233766233766,
+      "grad_norm": 7.009990215301514,
+      "learning_rate": 1.6755238754124965e-05,
+      "loss": 0.1708,
+      "step": 364
+    },
+    {
+      "epoch": 0.3385899814471243,
+      "grad_norm": 7.845787048339844,
+      "learning_rate": 1.6731322788916892e-05,
+      "loss": 0.1723,
+      "step": 365
+    },
+    {
+      "epoch": 0.3395176252319109,
+      "grad_norm": 3.684112071990967,
+      "learning_rate": 1.6707336215317968e-05,
+      "loss": 0.1136,
+      "step": 366
+    },
+    {
+      "epoch": 0.3404452690166976,
+      "grad_norm": 6.165255069732666,
+      "learning_rate": 1.6683279284936004e-05,
+      "loss": 0.2895,
+      "step": 367
+    },
+    {
+      "epoch": 0.34137291280148424,
+      "grad_norm": 5.1027326583862305,
+      "learning_rate": 1.665915225011681e-05,
+      "loss": 0.1915,
+      "step": 368
+    },
+    {
+      "epoch": 0.3423005565862709,
+      "grad_norm": 4.702267646789551,
+      "learning_rate": 1.6634955363941573e-05,
+      "loss": 0.135,
+      "step": 369
+    },
+    {
+      "epoch": 0.3432282003710575,
+      "grad_norm": 3.623323678970337,
+      "learning_rate": 1.6610688880224178e-05,
+      "loss": 0.1364,
+      "step": 370
+    },
+    {
+      "epoch": 0.34415584415584416,
+      "grad_norm": 4.77068567276001,
+      "learning_rate": 1.6586353053508548e-05,
+      "loss": 0.2082,
+      "step": 371
+    },
+    {
+      "epoch": 0.3450834879406308,
+      "grad_norm": 6.354672908782959,
+      "learning_rate": 1.6561948139065997e-05,
+      "loss": 0.2037,
+      "step": 372
+    },
+    {
+      "epoch": 0.3460111317254174,
+      "grad_norm": 3.074613094329834,
+      "learning_rate": 1.6537474392892527e-05,
+      "loss": 0.1123,
+      "step": 373
+    },
+    {
+      "epoch": 0.3469387755102041,
+      "grad_norm": 5.388340473175049,
+      "learning_rate": 1.6512932071706153e-05,
+      "loss": 0.2308,
+      "step": 374
+    },
+    {
+      "epoch": 0.34786641929499074,
+      "grad_norm": 3.377591609954834,
+      "learning_rate": 1.6488321432944218e-05,
+      "loss": 0.1607,
+      "step": 375
+    },
+    {
+      "epoch": 0.34879406307977734,
+      "grad_norm": 3.697253465652466,
+      "learning_rate": 1.646364273476067e-05,
+      "loss": 0.2064,
+      "step": 376
+    },
+    {
+      "epoch": 0.349721706864564,
+      "grad_norm": 2.825587272644043,
+      "learning_rate": 1.6438896236023374e-05,
+      "loss": 0.1405,
+      "step": 377
+    },
+    {
+      "epoch": 0.35064935064935066,
+      "grad_norm": 5.332752227783203,
+      "learning_rate": 1.6414082196311402e-05,
+      "loss": 0.1838,
+      "step": 378
+    },
+    {
+      "epoch": 0.3515769944341373,
+      "grad_norm": 3.3014256954193115,
+      "learning_rate": 1.638920087591228e-05,
+      "loss": 0.1516,
+      "step": 379
+    },
+    {
+      "epoch": 0.3525046382189239,
+      "grad_norm": 2.9438254833221436,
+      "learning_rate": 1.6364252535819284e-05,
+      "loss": 0.153,
+      "step": 380
+    },
+    {
+      "epoch": 0.3525046382189239,
+      "eval_accuracy": 0.8458980044345898,
+      "eval_f1": 0.6634382566585957,
+      "eval_loss": 0.32734009623527527,
+      "eval_precision": 0.85625,
+      "eval_recall": 0.541501976284585,
+      "eval_runtime": 47.3489,
+      "eval_samples_per_second": 5.829,
+      "eval_steps_per_second": 0.19,
+      "step": 380
+    },
+    {
+      "epoch": 0.3534322820037106,
+      "grad_norm": 4.24219274520874,
+      "learning_rate": 1.63392374377287e-05,
+      "loss": 0.1265,
+      "step": 381
+    },
+    {
+      "epoch": 0.35435992578849723,
+      "grad_norm": 3.8825278282165527,
+      "learning_rate": 1.6314155844037074e-05,
+      "loss": 0.173,
+      "step": 382
+    },
+    {
+      "epoch": 0.35528756957328383,
+      "grad_norm": 4.059886455535889,
+      "learning_rate": 1.6289008017838447e-05,
+      "loss": 0.1639,
+      "step": 383
+    },
+    {
+      "epoch": 0.3562152133580705,
+      "grad_norm": 5.13779878616333,
+      "learning_rate": 1.626379422292162e-05,
+      "loss": 0.1006,
+      "step": 384
+    },
+    {
+      "epoch": 0.35714285714285715,
+      "grad_norm": 5.269052028656006,
+      "learning_rate": 1.6238514723767372e-05,
+      "loss": 0.2033,
+      "step": 385
+    },
+    {
+      "epoch": 0.3580705009276438,
+      "grad_norm": 4.739077091217041,
+      "learning_rate": 1.6213169785545688e-05,
+      "loss": 0.2673,
+      "step": 386
+    },
+    {
+      "epoch": 0.3589981447124304,
+      "grad_norm": 5.1900634765625,
+      "learning_rate": 1.6187759674112972e-05,
+      "loss": 0.2156,
+      "step": 387
+    },
+    {
+      "epoch": 0.35992578849721707,
+      "grad_norm": 2.844031810760498,
+      "learning_rate": 1.6162284656009276e-05,
+      "loss": 0.0855,
+      "step": 388
+    },
+    {
+      "epoch": 0.3608534322820037,
+      "grad_norm": 5.831792831420898,
+      "learning_rate": 1.6136744998455477e-05,
+      "loss": 0.2278,
+      "step": 389
+    },
+    {
+      "epoch": 0.36178107606679033,
+      "grad_norm": 3.952970504760742,
+      "learning_rate": 1.6111140969350504e-05,
+      "loss": 0.1348,
+      "step": 390
+    },
+    {
+      "epoch": 0.362708719851577,
+      "grad_norm": 3.9323179721832275,
+      "learning_rate": 1.6085472837268504e-05,
+      "loss": 0.1731,
+      "step": 391
+    },
+    {
+      "epoch": 0.36363636363636365,
+      "grad_norm": 4.621875286102295,
+      "learning_rate": 1.6059740871456035e-05,
+      "loss": 0.2011,
+      "step": 392
+    },
+    {
+      "epoch": 0.3645640074211503,
+      "grad_norm": 6.936546325683594,
+      "learning_rate": 1.603394534182925e-05,
+      "loss": 0.1766,
+      "step": 393
+    },
+    {
+      "epoch": 0.3654916512059369,
+      "grad_norm": 4.287359237670898,
+      "learning_rate": 1.6008086518971037e-05,
+      "loss": 0.1939,
+      "step": 394
+    },
+    {
+      "epoch": 0.36641929499072357,
+      "grad_norm": 3.0315101146698,
+      "learning_rate": 1.598216467412822e-05,
+      "loss": 0.1091,
+      "step": 395
+    },
+    {
+      "epoch": 0.3673469387755102,
+      "grad_norm": 6.599478721618652,
+      "learning_rate": 1.5956180079208684e-05,
+      "loss": 0.232,
+      "step": 396
+    },
+    {
+      "epoch": 0.3682745825602968,
+      "grad_norm": 4.763383388519287,
+      "learning_rate": 1.593013300677853e-05,
+      "loss": 0.1877,
+      "step": 397
+    },
+    {
+      "epoch": 0.3692022263450835,
+      "grad_norm": 4.326437950134277,
+      "learning_rate": 1.5904023730059227e-05,
+      "loss": 0.1924,
+      "step": 398
+    },
+    {
+      "epoch": 0.37012987012987014,
+      "grad_norm": 4.332076072692871,
+      "learning_rate": 1.5877852522924733e-05,
+      "loss": 0.201,
+      "step": 399
+    },
+    {
+      "epoch": 0.37105751391465674,
+      "grad_norm": 4.557116985321045,
+      "learning_rate": 1.5851619659898623e-05,
+      "loss": 0.2,
+      "step": 400
+    },
+    {
+      "epoch": 0.37105751391465674,
+      "eval_accuracy": 0.844789356984479,
+      "eval_f1": 0.6585365853658537,
+      "eval_loss": 0.33066147565841675,
+      "eval_precision": 0.8598726114649682,
+      "eval_recall": 0.5335968379446641,
+      "eval_runtime": 47.9063,
+      "eval_samples_per_second": 5.761,
+      "eval_steps_per_second": 0.188,
+      "step": 400
     }
   ],
   "logging_steps": 1,
@@ -2318,7 +3078,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.58457253545902e+16,
+  "total_flos": 1.2786427319078093e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null