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 sha256:64ce02d94b7d924c632a2067f73c82bb18c67f7a726992c6269ace98bdc6f056
+oid sha256:61e0583ec5819bd9d218cb7cbb3d96a13e38ffa7c04c77bed86909e60e2d8d43
 size 13934748

last-checkpoint/optimizer_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3fe0457fac8b753b7310b82e2980163e79f3ec63eda7fc5078528d806ac9366
+oid sha256:bc9ceb414aa18285c6e881640d933d01fb0146850bfc8ecd06ab1f6bb1bed056
 size 13999412

last-checkpoint/optimizer_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cdb0f1caf04a6ef7c87c522ede00a27f1e96ab25cd3d03dc1218ed3d6bf20b8
+oid sha256:1366fd8d18df6071e3e46f037affd2fa48cd8fbddf1de76bfad3a682252957dc
 size 13990904

last-checkpoint/optimizer_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bc82b46510200e245a640ac75a1015933d3bfdd29a9f14f7e6e3cf00746cc9f
+oid sha256:d27689e09f171d3bfac23f02586872ccd9295635653d605d59ab909896aef34d
 size 13990904

last-checkpoint/pytorch_model_fsdp_0/__0_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f062cfd6da4a5849543ad9f156b79c7cb80350250de63ee7e3ea29c94d29be4
+oid sha256:ba710043ec7c5e37f0cc9912a7fc1e35ee1c93b7c28149447a9da2468e8d2738
 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:b9629d3c55606b00e24d749b100b32fb20097550ff7d500801506540c686e621
+oid sha256:34df0713f48ac78099ac04b6aa827e0b9450f86e65d38e6f95738f425b9fe3cb
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:102dc9d8e967de85cf93dfd57a3dcb2e8948d2b8aec650c2929692368e17358b
+oid sha256:22216db04e5f7b4575fd49e958bbf8d52502bd3d4c610f1ee1ac28962fb2221f
 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:a95ccc72a79fe5e1e19337f8b060654731a9cc11cc1a00aca76960a6644d8396
+oid sha256:ad4699d37b4a4fd828dc85d7a4afb8b7233d8ff3f31f19da2eb15b5020878277
 size 6966784

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5cb7c663bda618877a07c8634119b894f845c6c1f48ffc773fae5fc7587910b
+oid sha256:770f70341965762eba950e78530dac18548c5ffc01747f586966a93dd2aaecc5
 size 15088

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f5facd7e65af3371a0f80215db840e12650b3c5facc3bc8e9c313b25307f1c5
+oid sha256:e6a5808c82049f750089c2b8c24ef7ed5c78e67dc53d231bb7066cc5400ea6c0
 size 15088

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1b0b8e0d8818ddd524ea79ea80b4c68befffe51c42d62588c2d5ea88da10a4b
+oid sha256:26584d4d2b2c938da795ee83cefc212ad7531e84dccb612e0d827ed54c445ba7
 size 15088

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a7feadabf89d4316a6005d255da1c51ac5f256268f862f7e85e39e78d9a3025
+oid sha256:ce4ce133b799ebf855812e6c0a1492b8b6983f401e5b15fef49b386da6c07a2e
 size 15088

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdc582f335d9f0cb32903e57fe4f3123895d2a8b97f7e3cac7005c8f96d98b1d
+oid sha256:e72f0c2b42252f9bf5b1a5e2d7757bd051d85eef3fb930f6dcbfeb449c5c3e1a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2542372881355932,
+  "epoch": 0.3389830508474576,
   "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": 5.566,
       "eval_steps_per_second": 0.191,
       "step": 300
+    },
+    {
+      "epoch": 0.25508474576271184,
+      "grad_norm": 0.9495724439620972,
+      "learning_rate": 1.8570149053999154e-05,
+      "loss": 0.0102,
+      "step": 301
+    },
+    {
+      "epoch": 0.2559322033898305,
+      "grad_norm": 1.3956694602966309,
+      "learning_rate": 1.8554868297922728e-05,
+      "loss": 0.0094,
+      "step": 302
+    },
+    {
+      "epoch": 0.25677966101694916,
+      "grad_norm": 2.1316022872924805,
+      "learning_rate": 1.853951267945023e-05,
+      "loss": 0.0169,
+      "step": 303
+    },
+    {
+      "epoch": 0.2576271186440678,
+      "grad_norm": 1.0728296041488647,
+      "learning_rate": 1.852408233295643e-05,
+      "loss": 0.0131,
+      "step": 304
+    },
+    {
+      "epoch": 0.2584745762711864,
+      "grad_norm": 1.8492826223373413,
+      "learning_rate": 1.8508577393470014e-05,
+      "loss": 0.0292,
+      "step": 305
+    },
+    {
+      "epoch": 0.2593220338983051,
+      "grad_norm": 1.082140564918518,
+      "learning_rate": 1.8492997996672436e-05,
+      "loss": 0.0094,
+      "step": 306
+    },
+    {
+      "epoch": 0.26016949152542374,
+      "grad_norm": 2.817040205001831,
+      "learning_rate": 1.8477344278896708e-05,
+      "loss": 0.0222,
+      "step": 307
+    },
+    {
+      "epoch": 0.26101694915254237,
+      "grad_norm": 1.3377786874771118,
+      "learning_rate": 1.846161637712622e-05,
+      "loss": 0.0183,
+      "step": 308
+    },
+    {
+      "epoch": 0.261864406779661,
+      "grad_norm": 2.062629222869873,
+      "learning_rate": 1.8445814428993528e-05,
+      "loss": 0.028,
+      "step": 309
+    },
+    {
+      "epoch": 0.2627118644067797,
+      "grad_norm": 2.208967447280884,
+      "learning_rate": 1.8429938572779154e-05,
+      "loss": 0.0267,
+      "step": 310
+    },
+    {
+      "epoch": 0.2635593220338983,
+      "grad_norm": 1.015850305557251,
+      "learning_rate": 1.8413988947410388e-05,
+      "loss": 0.0112,
+      "step": 311
+    },
+    {
+      "epoch": 0.26440677966101694,
+      "grad_norm": 1.2069474458694458,
+      "learning_rate": 1.839796569246006e-05,
+      "loss": 0.0122,
+      "step": 312
+    },
+    {
+      "epoch": 0.2652542372881356,
+      "grad_norm": 1.5780760049819946,
+      "learning_rate": 1.8381868948145317e-05,
+      "loss": 0.0197,
+      "step": 313
+    },
+    {
+      "epoch": 0.26610169491525426,
+      "grad_norm": 0.7285755276679993,
+      "learning_rate": 1.836569885532641e-05,
+      "loss": 0.0064,
+      "step": 314
+    },
+    {
+      "epoch": 0.2669491525423729,
+      "grad_norm": 2.682543992996216,
+      "learning_rate": 1.8349455555505445e-05,
+      "loss": 0.0285,
+      "step": 315
+    },
+    {
+      "epoch": 0.2677966101694915,
+      "grad_norm": 1.949136734008789,
+      "learning_rate": 1.833313919082515e-05,
+      "loss": 0.0232,
+      "step": 316
+    },
+    {
+      "epoch": 0.26864406779661015,
+      "grad_norm": 3.491502285003662,
+      "learning_rate": 1.8316749904067637e-05,
+      "loss": 0.0264,
+      "step": 317
+    },
+    {
+      "epoch": 0.26949152542372884,
+      "grad_norm": 0.8317990303039551,
+      "learning_rate": 1.8300287838653155e-05,
+      "loss": 0.0048,
+      "step": 318
+    },
+    {
+      "epoch": 0.27033898305084747,
+      "grad_norm": 1.39896821975708,
+      "learning_rate": 1.828375313863881e-05,
+      "loss": 0.0149,
+      "step": 319
+    },
+    {
+      "epoch": 0.2711864406779661,
+      "grad_norm": 1.3299435377120972,
+      "learning_rate": 1.8267145948717338e-05,
+      "loss": 0.0053,
+      "step": 320
+    },
+    {
+      "epoch": 0.2711864406779661,
+      "eval_accuracy": 1.0,
+      "eval_f1": 1.0,
+      "eval_loss": 0.0007786459173075855,
+      "eval_precision": 1.0,
+      "eval_recall": 1.0,
+      "eval_runtime": 52.8212,
+      "eval_samples_per_second": 5.528,
+      "eval_steps_per_second": 0.189,
+      "step": 320
+    },
+    {
+      "epoch": 0.27203389830508473,
+      "grad_norm": 0.4707522392272949,
+      "learning_rate": 1.8250466414215816e-05,
+      "loss": 0.0044,
+      "step": 321
+    },
+    {
+      "epoch": 0.27288135593220336,
+      "grad_norm": 2.0582358837127686,
+      "learning_rate": 1.8233714681094405e-05,
+      "loss": 0.0194,
+      "step": 322
+    },
+    {
+      "epoch": 0.27372881355932205,
+      "grad_norm": 2.306215286254883,
+      "learning_rate": 1.8216890895945062e-05,
+      "loss": 0.0157,
+      "step": 323
+    },
+    {
+      "epoch": 0.2745762711864407,
+      "grad_norm": 0.5328612923622131,
+      "learning_rate": 1.8199995205990256e-05,
+      "loss": 0.0025,
+      "step": 324
+    },
+    {
+      "epoch": 0.2754237288135593,
+      "grad_norm": 1.3948057889938354,
+      "learning_rate": 1.818302775908169e-05,
+      "loss": 0.0114,
+      "step": 325
+    },
+    {
+      "epoch": 0.27627118644067794,
+      "grad_norm": 0.7532712817192078,
+      "learning_rate": 1.8165988703699003e-05,
+      "loss": 0.0047,
+      "step": 326
+    },
+    {
+      "epoch": 0.2771186440677966,
+      "grad_norm": 1.3939229249954224,
+      "learning_rate": 1.814887818894846e-05,
+      "loss": 0.0169,
+      "step": 327
+    },
+    {
+      "epoch": 0.27796610169491526,
+      "grad_norm": 1.9840660095214844,
+      "learning_rate": 1.813169636456167e-05,
+      "loss": 0.0139,
+      "step": 328
+    },
+    {
+      "epoch": 0.2788135593220339,
+      "grad_norm": 3.3618903160095215,
+      "learning_rate": 1.8114443380894248e-05,
+      "loss": 0.0212,
+      "step": 329
+    },
+    {
+      "epoch": 0.2796610169491525,
+      "grad_norm": 1.521863579750061,
+      "learning_rate": 1.8097119388924524e-05,
+      "loss": 0.0063,
+      "step": 330
+    },
+    {
+      "epoch": 0.2805084745762712,
+      "grad_norm": 2.661334991455078,
+      "learning_rate": 1.8079724540252204e-05,
+      "loss": 0.0212,
+      "step": 331
+    },
+    {
+      "epoch": 0.28135593220338984,
+      "grad_norm": 0.9505246877670288,
+      "learning_rate": 1.8062258987097062e-05,
+      "loss": 0.0044,
+      "step": 332
+    },
+    {
+      "epoch": 0.28220338983050847,
+      "grad_norm": 2.677922010421753,
+      "learning_rate": 1.8044722882297582e-05,
+      "loss": 0.0323,
+      "step": 333
+    },
+    {
+      "epoch": 0.2830508474576271,
+      "grad_norm": 2.3942182064056396,
+      "learning_rate": 1.8027116379309637e-05,
+      "loss": 0.0173,
+      "step": 334
+    },
+    {
+      "epoch": 0.2838983050847458,
+      "grad_norm": 5.396221160888672,
+      "learning_rate": 1.8009439632205162e-05,
+      "loss": 0.0445,
+      "step": 335
+    },
+    {
+      "epoch": 0.2847457627118644,
+      "grad_norm": 3.2957260608673096,
+      "learning_rate": 1.7991692795670764e-05,
+      "loss": 0.0344,
+      "step": 336
+    },
+    {
+      "epoch": 0.28559322033898304,
+      "grad_norm": 2.7046103477478027,
+      "learning_rate": 1.7973876025006407e-05,
+      "loss": 0.0119,
+      "step": 337
+    },
+    {
+      "epoch": 0.2864406779661017,
+      "grad_norm": 2.09260630607605,
+      "learning_rate": 1.7955989476124035e-05,
+      "loss": 0.0191,
+      "step": 338
+    },
+    {
+      "epoch": 0.28728813559322036,
+      "grad_norm": 1.4881995916366577,
+      "learning_rate": 1.7938033305546208e-05,
+      "loss": 0.0198,
+      "step": 339
+    },
+    {
+      "epoch": 0.288135593220339,
+      "grad_norm": 0.29988396167755127,
+      "learning_rate": 1.7920007670404738e-05,
+      "loss": 0.0028,
+      "step": 340
+    },
+    {
+      "epoch": 0.288135593220339,
+      "eval_accuracy": 1.0,
+      "eval_f1": 1.0,
+      "eval_loss": 0.0003622370131779462,
+      "eval_precision": 1.0,
+      "eval_recall": 1.0,
+      "eval_runtime": 51.8576,
+      "eval_samples_per_second": 5.631,
+      "eval_steps_per_second": 0.193,
+      "step": 340
+    },
+    {
+      "epoch": 0.2889830508474576,
+      "grad_norm": 1.238132357597351,
+      "learning_rate": 1.7901912728439317e-05,
+      "loss": 0.0105,
+      "step": 341
+    },
+    {
+      "epoch": 0.28983050847457625,
+      "grad_norm": 5.88295316696167,
+      "learning_rate": 1.7883748637996113e-05,
+      "loss": 0.0363,
+      "step": 342
+    },
+    {
+      "epoch": 0.29067796610169494,
+      "grad_norm": 1.8744484186172485,
+      "learning_rate": 1.786551555802643e-05,
+      "loss": 0.014,
+      "step": 343
+    },
+    {
+      "epoch": 0.29152542372881357,
+      "grad_norm": 0.7737008333206177,
+      "learning_rate": 1.7847213648085257e-05,
+      "loss": 0.0071,
+      "step": 344
+    },
+    {
+      "epoch": 0.2923728813559322,
+      "grad_norm": 1.2532923221588135,
+      "learning_rate": 1.7828843068329923e-05,
+      "loss": 0.015,
+      "step": 345
+    },
+    {
+      "epoch": 0.29322033898305083,
+      "grad_norm": 1.273977279663086,
+      "learning_rate": 1.781040397951868e-05,
+      "loss": 0.0071,
+      "step": 346
+    },
+    {
+      "epoch": 0.2940677966101695,
+      "grad_norm": 1.9330259561538696,
+      "learning_rate": 1.7791896543009282e-05,
+      "loss": 0.0245,
+      "step": 347
+    },
+    {
+      "epoch": 0.29491525423728815,
+      "grad_norm": 1.0898295640945435,
+      "learning_rate": 1.7773320920757597e-05,
+      "loss": 0.0099,
+      "step": 348
+    },
+    {
+      "epoch": 0.2957627118644068,
+      "grad_norm": 2.295070171356201,
+      "learning_rate": 1.775467727531615e-05,
+      "loss": 0.0212,
+      "step": 349
+    },
+    {
+      "epoch": 0.2966101694915254,
+      "grad_norm": 2.575789213180542,
+      "learning_rate": 1.7735965769832754e-05,
+      "loss": 0.0204,
+      "step": 350
+    },
+    {
+      "epoch": 0.29745762711864404,
+      "grad_norm": 0.6911354660987854,
+      "learning_rate": 1.7717186568049048e-05,
+      "loss": 0.0045,
+      "step": 351
+    },
+    {
+      "epoch": 0.2983050847457627,
+      "grad_norm": 2.2805356979370117,
+      "learning_rate": 1.7698339834299064e-05,
+      "loss": 0.0148,
+      "step": 352
+    },
+    {
+      "epoch": 0.29915254237288136,
+      "grad_norm": 2.1223855018615723,
+      "learning_rate": 1.7679425733507802e-05,
+      "loss": 0.0291,
+      "step": 353
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.93767911195755,
+      "learning_rate": 1.766044443118978e-05,
+      "loss": 0.0048,
+      "step": 354
+    },
+    {
+      "epoch": 0.3008474576271186,
+      "grad_norm": 1.8879729509353638,
+      "learning_rate": 1.764139609344759e-05,
+      "loss": 0.0196,
+      "step": 355
+    },
+    {
+      "epoch": 0.3016949152542373,
+      "grad_norm": 1.6808807849884033,
+      "learning_rate": 1.7622280886970436e-05,
+      "loss": 0.0116,
+      "step": 356
+    },
+    {
+      "epoch": 0.30254237288135594,
+      "grad_norm": 2.692596912384033,
+      "learning_rate": 1.7603098979032683e-05,
+      "loss": 0.0215,
+      "step": 357
+    },
+    {
+      "epoch": 0.30338983050847457,
+      "grad_norm": 0.6760978698730469,
+      "learning_rate": 1.7583850537492386e-05,
+      "loss": 0.0053,
+      "step": 358
+    },
+    {
+      "epoch": 0.3042372881355932,
+      "grad_norm": 0.8519519567489624,
+      "learning_rate": 1.7564535730789835e-05,
+      "loss": 0.0057,
+      "step": 359
+    },
+    {
+      "epoch": 0.3050847457627119,
+      "grad_norm": 2.1830923557281494,
+      "learning_rate": 1.7545154727946065e-05,
+      "loss": 0.015,
+      "step": 360
+    },
+    {
+      "epoch": 0.3050847457627119,
+      "eval_accuracy": 1.0,
+      "eval_f1": 1.0,
+      "eval_loss": 0.00035791730624623597,
+      "eval_precision": 1.0,
+      "eval_recall": 1.0,
+      "eval_runtime": 51.4513,
+      "eval_samples_per_second": 5.675,
+      "eval_steps_per_second": 0.194,
+      "step": 360
+    },
+    {
+      "epoch": 0.3059322033898305,
+      "grad_norm": 1.3546723127365112,
+      "learning_rate": 1.7525707698561383e-05,
+      "loss": 0.0152,
+      "step": 361
+    },
+    {
+      "epoch": 0.30677966101694915,
+      "grad_norm": 2.3119301795959473,
+      "learning_rate": 1.7506194812813896e-05,
+      "loss": 0.031,
+      "step": 362
+    },
+    {
+      "epoch": 0.3076271186440678,
+      "grad_norm": 2.6761271953582764,
+      "learning_rate": 1.7486616241457994e-05,
+      "loss": 0.0133,
+      "step": 363
+    },
+    {
+      "epoch": 0.30847457627118646,
+      "grad_norm": 1.6576277017593384,
+      "learning_rate": 1.746697215582288e-05,
+      "loss": 0.0095,
+      "step": 364
+    },
+    {
+      "epoch": 0.3093220338983051,
+      "grad_norm": 2.716494083404541,
+      "learning_rate": 1.7447262727811062e-05,
+      "loss": 0.0229,
+      "step": 365
+    },
+    {
+      "epoch": 0.3101694915254237,
+      "grad_norm": 2.4295156002044678,
+      "learning_rate": 1.7427488129896852e-05,
+      "loss": 0.0245,
+      "step": 366
+    },
+    {
+      "epoch": 0.31101694915254235,
+      "grad_norm": 1.3123137950897217,
+      "learning_rate": 1.740764853512485e-05,
+      "loss": 0.0066,
+      "step": 367
+    },
+    {
+      "epoch": 0.31186440677966104,
+      "grad_norm": 1.4011317491531372,
+      "learning_rate": 1.738774411710844e-05,
+      "loss": 0.0215,
+      "step": 368
+    },
+    {
+      "epoch": 0.31271186440677967,
+      "grad_norm": 1.852777361869812,
+      "learning_rate": 1.7367775050028254e-05,
+      "loss": 0.0119,
+      "step": 369
+    },
+    {
+      "epoch": 0.3135593220338983,
+      "grad_norm": 1.4631356000900269,
+      "learning_rate": 1.7347741508630673e-05,
+      "loss": 0.0142,
+      "step": 370
+    },
+    {
+      "epoch": 0.31440677966101693,
+      "grad_norm": 2.603271961212158,
+      "learning_rate": 1.732764366822627e-05,
+      "loss": 0.0218,
+      "step": 371
+    },
+    {
+      "epoch": 0.3152542372881356,
+      "grad_norm": 1.0737484693527222,
+      "learning_rate": 1.73074817046883e-05,
+      "loss": 0.0087,
+      "step": 372
+    },
+    {
+      "epoch": 0.31610169491525425,
+      "grad_norm": 3.7462353706359863,
+      "learning_rate": 1.728725579445114e-05,
+      "loss": 0.0573,
+      "step": 373
+    },
+    {
+      "epoch": 0.3169491525423729,
+      "grad_norm": 1.9481991529464722,
+      "learning_rate": 1.7266966114508764e-05,
+      "loss": 0.011,
+      "step": 374
+    },
+    {
+      "epoch": 0.3177966101694915,
+      "grad_norm": 0.9563993811607361,
+      "learning_rate": 1.7246612842413177e-05,
+      "loss": 0.0073,
+      "step": 375
+    },
+    {
+      "epoch": 0.31864406779661014,
+      "grad_norm": 4.024267196655273,
+      "learning_rate": 1.7226196156272873e-05,
+      "loss": 0.0278,
+      "step": 376
+    },
+    {
+      "epoch": 0.31949152542372883,
+      "grad_norm": 2.5183022022247314,
+      "learning_rate": 1.720571623475128e-05,
+      "loss": 0.0349,
+      "step": 377
+    },
+    {
+      "epoch": 0.32033898305084746,
+      "grad_norm": 1.7995777130126953,
+      "learning_rate": 1.7185173257065178e-05,
+      "loss": 0.0097,
+      "step": 378
+    },
+    {
+      "epoch": 0.3211864406779661,
+      "grad_norm": 1.5496909618377686,
+      "learning_rate": 1.7164567402983153e-05,
+      "loss": 0.0133,
+      "step": 379
+    },
+    {
+      "epoch": 0.3220338983050847,
+      "grad_norm": 2.2646713256835938,
+      "learning_rate": 1.7143898852824005e-05,
+      "loss": 0.0446,
+      "step": 380
+    },
+    {
+      "epoch": 0.3220338983050847,
+      "eval_accuracy": 1.0,
+      "eval_f1": 1.0,
+      "eval_loss": 0.0006280901725403965,
+      "eval_precision": 1.0,
+      "eval_recall": 1.0,
+      "eval_runtime": 51.0586,
+      "eval_samples_per_second": 5.719,
+      "eval_steps_per_second": 0.196,
+      "step": 380
+    },
+    {
+      "epoch": 0.3228813559322034,
+      "grad_norm": 2.7952117919921875,
+      "learning_rate": 1.7123167787455176e-05,
+      "loss": 0.021,
+      "step": 381
+    },
+    {
+      "epoch": 0.32372881355932204,
+      "grad_norm": 1.8368139266967773,
+      "learning_rate": 1.7102374388291182e-05,
+      "loss": 0.0117,
+      "step": 382
+    },
+    {
+      "epoch": 0.32457627118644067,
+      "grad_norm": 1.9440964460372925,
+      "learning_rate": 1.7081518837292006e-05,
+      "loss": 0.0113,
+      "step": 383
+    },
+    {
+      "epoch": 0.3254237288135593,
+      "grad_norm": 1.4448236227035522,
+      "learning_rate": 1.7060601316961504e-05,
+      "loss": 0.0097,
+      "step": 384
+    },
+    {
+      "epoch": 0.326271186440678,
+      "grad_norm": 1.075166940689087,
+      "learning_rate": 1.7039622010345832e-05,
+      "loss": 0.0087,
+      "step": 385
+    },
+    {
+      "epoch": 0.3271186440677966,
+      "grad_norm": 1.9080896377563477,
+      "learning_rate": 1.7018581101031814e-05,
+      "loss": 0.014,
+      "step": 386
+    },
+    {
+      "epoch": 0.32796610169491525,
+      "grad_norm": 0.934737503528595,
+      "learning_rate": 1.6997478773145363e-05,
+      "loss": 0.0074,
+      "step": 387
+    },
+    {
+      "epoch": 0.3288135593220339,
+      "grad_norm": 1.9116491079330444,
+      "learning_rate": 1.6976315211349848e-05,
+      "loss": 0.024,
+      "step": 388
+    },
+    {
+      "epoch": 0.32966101694915256,
+      "grad_norm": 0.9697662591934204,
+      "learning_rate": 1.6955090600844494e-05,
+      "loss": 0.0058,
+      "step": 389
+    },
+    {
+      "epoch": 0.3305084745762712,
+      "grad_norm": 2.447063446044922,
+      "learning_rate": 1.6933805127362744e-05,
+      "loss": 0.0205,
+      "step": 390
+    },
+    {
+      "epoch": 0.3313559322033898,
+      "grad_norm": 1.4310107231140137,
+      "learning_rate": 1.6912458977170655e-05,
+      "loss": 0.0289,
+      "step": 391
+    },
+    {
+      "epoch": 0.33220338983050846,
+      "grad_norm": 1.9119633436203003,
+      "learning_rate": 1.6891052337065256e-05,
+      "loss": 0.0095,
+      "step": 392
+    },
+    {
+      "epoch": 0.33305084745762714,
+      "grad_norm": 1.6527955532073975,
+      "learning_rate": 1.68695853943729e-05,
+      "loss": 0.0147,
+      "step": 393
+    },
+    {
+      "epoch": 0.3338983050847458,
+      "grad_norm": 0.6647539138793945,
+      "learning_rate": 1.6848058336947657e-05,
+      "loss": 0.0045,
+      "step": 394
+    },
+    {
+      "epoch": 0.3347457627118644,
+      "grad_norm": 2.0844597816467285,
+      "learning_rate": 1.682647135316965e-05,
+      "loss": 0.0057,
+      "step": 395
+    },
+    {
+      "epoch": 0.33559322033898303,
+      "grad_norm": 1.3205703496932983,
+      "learning_rate": 1.6804824631943385e-05,
+      "loss": 0.0074,
+      "step": 396
+    },
+    {
+      "epoch": 0.3364406779661017,
+      "grad_norm": 1.966313362121582,
+      "learning_rate": 1.6783118362696162e-05,
+      "loss": 0.0199,
+      "step": 397
+    },
+    {
+      "epoch": 0.33728813559322035,
+      "grad_norm": 1.4938113689422607,
+      "learning_rate": 1.6761352735376343e-05,
+      "loss": 0.0098,
+      "step": 398
+    },
+    {
+      "epoch": 0.338135593220339,
+      "grad_norm": 1.2858011722564697,
+      "learning_rate": 1.6739527940451742e-05,
+      "loss": 0.0055,
+      "step": 399
+    },
+    {
+      "epoch": 0.3389830508474576,
+      "grad_norm": 2.423365592956543,
+      "learning_rate": 1.671764416890793e-05,
+      "loss": 0.0261,
+      "step": 400
+    },
+    {
+      "epoch": 0.3389830508474576,
+      "eval_accuracy": 1.0,
+      "eval_f1": 1.0,
+      "eval_loss": 0.00033162630279548466,
+      "eval_precision": 1.0,
+      "eval_recall": 1.0,
+      "eval_runtime": 51.2242,
+      "eval_samples_per_second": 5.7,
+      "eval_steps_per_second": 0.195,
+      "step": 400
     }
   ],
   "logging_steps": 1,
@@ -2318,7 +3078,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.289113333137408e+16,
+  "total_flos": 1.2357669100716032e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null