Training in progress, step 300, checkpoint

last-checkpoint/optimizer_0/__0_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0ba6fb33cfa34a3a19c1c859523ba5b8ee34e4ce14cd7ee85604eeb2a478122
+oid sha256:3720c9d7c3d147e3c6a4c31b748a401804a80a6f28683e7c9983f2e8c8a0f20a
 size 13934748

last-checkpoint/optimizer_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af5a9ded1ac1ad15369c22168c9bdc24120369b807b0236304fc238cd01770cd
+oid sha256:3638a66f29f136c13174bee0dd43e693f5fc102e10bee4ca9b5d7060756ced7c
 size 13999412

last-checkpoint/optimizer_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aac30f6108157475f0f5a525a5d713d9caa83e68412d6e9feee34fa1c788d678
+oid sha256:59454dac3aeba9c46e0b8ed50eb871c1d98271ecbabd9754c8618cdc65584ad9
 size 13990904

last-checkpoint/optimizer_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39a8a076cc77e594caeb9e94a5de64b7a427c01ec5dd10b1dbe76fa77717e2cd
+oid sha256:93ca40f1a301b546ff3c8e51d511eb49571367df816e5ac6c43d69b073ba1e35
 size 13990904

last-checkpoint/pytorch_model_fsdp_0/__0_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28d745959ce06db61825f40fb63ea63b9e62f268815aaab31b17f3705247564b
+oid sha256:7e305eb64bbd004a3712d4d0f3b65560d9c0d8b3920c2789be35be33fef333cd
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c5600d73cdd63622761d1592bb37fa01c39c9bcc957af85fe4bd2e4cd01fabc
+oid sha256:16b6721393030c99c98218e1bcc44fa93cc347e7c920295cebba18bf69ebf311
 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:be56560930f7a89d468b530340537eec5b918174080267a8cc6186d4978acf89
+oid sha256:f9c2af98820448e537c2aa09618f8c2299b2ed8c9040abdad7cc23d455398738
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:851b0a400aa71d9fc3d83e0e2570f4bbeaf98efc2e51c1f18c4d64aa51f39304
+oid sha256:fa8dfa614952af057b305d24646b204cdfa9b2fbf5610aa112de72f4d1903dd4
 size 6966784

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:805afa176b455b67a891f7c63c255879dd3a372d6c9fa2140f3c0a2149d52710
+oid sha256:6185843c50764de20922699c89193c33e1e13037719a5d55479aa190e715e4fc
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:656385b8033d1cc9de4c8239cf888e2d83a5db8f95016de71e971858eab1c195
+oid sha256:35e51ecf57078c2d652964726d8abc8157e10e9fdddf8cacb5700305b465147a
 size 14960

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a4775b283f1cbab74e1bfc47bfbe045632e0a9c46d8f354762f3216e862bf61
+oid sha256:ebe10fe55b3a58ae13fa7a58fca8f2486fa82c4aa360522ee9cde43cc43ba473
 size 14960

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ecbc04b6bcc44f7032a40edb9b3c06e3acf5ba0f1fb508b9a44802995aad5b9
+oid sha256:fcda73faaa8d5a9ab0a72d2fef1c1af0341c8e7f8ec0eede744acae39dd22f43
 size 14960

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88d5a351fddcb4718730dd82c69354176cd179de4c82fa6d41e0282fb5e2ab11
+oid sha256:a3e47edb1b664bc04c493b0996774157c1ffdb9f0b12df515a0b32829d748704
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5747126436781609,
+  "epoch": 0.8620689655172413,
   "eval_steps": 20,
-  "global_step": 200,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1539,6 +1539,766 @@
       "eval_samples_per_second": 6.49,
       "eval_steps_per_second": 0.245,
       "step": 200
+    },
+    {
+      "epoch": 0.5775862068965517,
+      "grad_norm": 3.761861801147461,
+      "learning_rate": 9.047925700872552e-06,
+      "loss": 0.3089,
+      "step": 201
+    },
+    {
+      "epoch": 0.5804597701149425,
+      "grad_norm": 2.631603240966797,
+      "learning_rate": 8.948060899634846e-06,
+      "loss": 0.2943,
+      "step": 202
+    },
+    {
+      "epoch": 0.5833333333333334,
+      "grad_norm": 2.613485336303711,
+      "learning_rate": 8.848302072078762e-06,
+      "loss": 0.2866,
+      "step": 203
+    },
+    {
+      "epoch": 0.5862068965517241,
+      "grad_norm": 2.1991889476776123,
+      "learning_rate": 8.748659268035339e-06,
+      "loss": 0.2749,
+      "step": 204
+    },
+    {
+      "epoch": 0.5890804597701149,
+      "grad_norm": 2.7884528636932373,
+      "learning_rate": 8.649142525647271e-06,
+      "loss": 0.3378,
+      "step": 205
+    },
+    {
+      "epoch": 0.5919540229885057,
+      "grad_norm": 4.045213222503662,
+      "learning_rate": 8.549761870357633e-06,
+      "loss": 0.3398,
+      "step": 206
+    },
+    {
+      "epoch": 0.5948275862068966,
+      "grad_norm": 2.83146595954895,
+      "learning_rate": 8.450527313899923e-06,
+      "loss": 0.2951,
+      "step": 207
+    },
+    {
+      "epoch": 0.5977011494252874,
+      "grad_norm": 2.664379358291626,
+      "learning_rate": 8.351448853289448e-06,
+      "loss": 0.3452,
+      "step": 208
+    },
+    {
+      "epoch": 0.6005747126436781,
+      "grad_norm": 2.2802395820617676,
+      "learning_rate": 8.25253646981622e-06,
+      "loss": 0.2993,
+      "step": 209
+    },
+    {
+      "epoch": 0.603448275862069,
+      "grad_norm": 2.1689095497131348,
+      "learning_rate": 8.153800128039441e-06,
+      "loss": 0.2847,
+      "step": 210
+    },
+    {
+      "epoch": 0.6063218390804598,
+      "grad_norm": 3.4026296138763428,
+      "learning_rate": 8.05524977478364e-06,
+      "loss": 0.3192,
+      "step": 211
+    },
+    {
+      "epoch": 0.6091954022988506,
+      "grad_norm": 3.272836923599243,
+      "learning_rate": 7.956895338136618e-06,
+      "loss": 0.3129,
+      "step": 212
+    },
+    {
+      "epoch": 0.6120689655172413,
+      "grad_norm": 4.036294460296631,
+      "learning_rate": 7.858746726449309e-06,
+      "loss": 0.3199,
+      "step": 213
+    },
+    {
+      "epoch": 0.6149425287356322,
+      "grad_norm": 2.3944919109344482,
+      "learning_rate": 7.760813827337555e-06,
+      "loss": 0.2513,
+      "step": 214
+    },
+    {
+      "epoch": 0.617816091954023,
+      "grad_norm": 4.011943340301514,
+      "learning_rate": 7.663106506686057e-06,
+      "loss": 0.3026,
+      "step": 215
+    },
+    {
+      "epoch": 0.6206896551724138,
+      "grad_norm": 2.424299716949463,
+      "learning_rate": 7.565634607654453e-06,
+      "loss": 0.3029,
+      "step": 216
+    },
+    {
+      "epoch": 0.6235632183908046,
+      "grad_norm": 5.497297286987305,
+      "learning_rate": 7.468407949685695e-06,
+      "loss": 0.3601,
+      "step": 217
+    },
+    {
+      "epoch": 0.6264367816091954,
+      "grad_norm": 2.9515810012817383,
+      "learning_rate": 7.371436327516854e-06,
+      "loss": 0.328,
+      "step": 218
+    },
+    {
+      "epoch": 0.6293103448275862,
+      "grad_norm": 3.359109878540039,
+      "learning_rate": 7.274729510192367e-06,
+      "loss": 0.3104,
+      "step": 219
+    },
+    {
+      "epoch": 0.632183908045977,
+      "grad_norm": 3.1870110034942627,
+      "learning_rate": 7.1782972400798825e-06,
+      "loss": 0.34,
+      "step": 220
+    },
+    {
+      "epoch": 0.632183908045977,
+      "eval_accuracy": 0.8688118811881188,
+      "eval_f1": 0.7464114832535885,
+      "eval_loss": 0.31775230169296265,
+      "eval_precision": 0.7572815533980582,
+      "eval_recall": 0.7358490566037735,
+      "eval_runtime": 17.2507,
+      "eval_samples_per_second": 6.145,
+      "eval_steps_per_second": 0.232,
+      "step": 220
+    },
+    {
+      "epoch": 0.6350574712643678,
+      "grad_norm": 2.9183595180511475,
+      "learning_rate": 7.082149231888833e-06,
+      "loss": 0.2827,
+      "step": 221
+    },
+    {
+      "epoch": 0.6379310344827587,
+      "grad_norm": 4.59254789352417,
+      "learning_rate": 6.986295171691727e-06,
+      "loss": 0.3284,
+      "step": 222
+    },
+    {
+      "epoch": 0.6408045977011494,
+      "grad_norm": 2.9099929332733154,
+      "learning_rate": 6.890744715948388e-06,
+      "loss": 0.2972,
+      "step": 223
+    },
+    {
+      "epoch": 0.6436781609195402,
+      "grad_norm": 2.407136917114258,
+      "learning_rate": 6.795507490533142e-06,
+      "loss": 0.2973,
+      "step": 224
+    },
+    {
+      "epoch": 0.646551724137931,
+      "grad_norm": 2.786597728729248,
+      "learning_rate": 6.700593089765086e-06,
+      "loss": 0.3426,
+      "step": 225
+    },
+    {
+      "epoch": 0.6494252873563219,
+      "grad_norm": 2.642282485961914,
+      "learning_rate": 6.606011075441556e-06,
+      "loss": 0.3201,
+      "step": 226
+    },
+    {
+      "epoch": 0.6522988505747126,
+      "grad_norm": 2.1382575035095215,
+      "learning_rate": 6.511770975874862e-06,
+      "loss": 0.2767,
+      "step": 227
+    },
+    {
+      "epoch": 0.6551724137931034,
+      "grad_norm": 4.03010892868042,
+      "learning_rate": 6.417882284932373e-06,
+      "loss": 0.2742,
+      "step": 228
+    },
+    {
+      "epoch": 0.6580459770114943,
+      "grad_norm": 2.754526138305664,
+      "learning_rate": 6.324354461080121e-06,
+      "loss": 0.2672,
+      "step": 229
+    },
+    {
+      "epoch": 0.6609195402298851,
+      "grad_norm": 2.4932737350463867,
+      "learning_rate": 6.231196926429913e-06,
+      "loss": 0.2835,
+      "step": 230
+    },
+    {
+      "epoch": 0.6637931034482759,
+      "grad_norm": 4.364743232727051,
+      "learning_rate": 6.138419065790169e-06,
+      "loss": 0.3079,
+      "step": 231
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 2.9517085552215576,
+      "learning_rate": 6.046030225720456e-06,
+      "loss": 0.2422,
+      "step": 232
+    },
+    {
+      "epoch": 0.6695402298850575,
+      "grad_norm": 2.8469698429107666,
+      "learning_rate": 5.95403971358991e-06,
+      "loss": 0.2641,
+      "step": 233
+    },
+    {
+      "epoch": 0.6724137931034483,
+      "grad_norm": 3.698885440826416,
+      "learning_rate": 5.86245679663962e-06,
+      "loss": 0.3572,
+      "step": 234
+    },
+    {
+      "epoch": 0.6752873563218391,
+      "grad_norm": 2.205653667449951,
+      "learning_rate": 5.7712907010490036e-06,
+      "loss": 0.252,
+      "step": 235
+    },
+    {
+      "epoch": 0.6781609195402298,
+      "grad_norm": 3.1082050800323486,
+      "learning_rate": 5.680550611006372e-06,
+      "loss": 0.3062,
+      "step": 236
+    },
+    {
+      "epoch": 0.6810344827586207,
+      "grad_norm": 4.51684045791626,
+      "learning_rate": 5.590245667783701e-06,
+      "loss": 0.281,
+      "step": 237
+    },
+    {
+      "epoch": 0.6839080459770115,
+      "grad_norm": 2.53916335105896,
+      "learning_rate": 5.5003849688157075e-06,
+      "loss": 0.3273,
+      "step": 238
+    },
+    {
+      "epoch": 0.6867816091954023,
+      "grad_norm": 3.1908535957336426,
+      "learning_rate": 5.4109775667833866e-06,
+      "loss": 0.3091,
+      "step": 239
+    },
+    {
+      "epoch": 0.6896551724137931,
+      "grad_norm": 2.92702579498291,
+      "learning_rate": 5.322032468702037e-06,
+      "loss": 0.2969,
+      "step": 240
+    },
+    {
+      "epoch": 0.6896551724137931,
+      "eval_accuracy": 0.8564356435643564,
+      "eval_f1": 0.7289719626168224,
+      "eval_loss": 0.3177642822265625,
+      "eval_precision": 0.7222222222222222,
+      "eval_recall": 0.7358490566037735,
+      "eval_runtime": 16.3833,
+      "eval_samples_per_second": 6.47,
+      "eval_steps_per_second": 0.244,
+      "step": 240
+    },
+    {
+      "epoch": 0.6925287356321839,
+      "grad_norm": 2.631377696990967,
+      "learning_rate": 5.233558635013842e-06,
+      "loss": 0.3108,
+      "step": 241
+    },
+    {
+      "epoch": 0.6954022988505747,
+      "grad_norm": 2.5703439712524414,
+      "learning_rate": 5.145564978685234e-06,
+      "loss": 0.2965,
+      "step": 242
+    },
+    {
+      "epoch": 0.6982758620689655,
+      "grad_norm": 5.4829254150390625,
+      "learning_rate": 5.058060364308965e-06,
+      "loss": 0.3302,
+      "step": 243
+    },
+    {
+      "epoch": 0.7011494252873564,
+      "grad_norm": 4.077176570892334,
+      "learning_rate": 4.971053607211069e-06,
+      "loss": 0.3833,
+      "step": 244
+    },
+    {
+      "epoch": 0.7040229885057471,
+      "grad_norm": 3.5669100284576416,
+      "learning_rate": 4.884553472562809e-06,
+      "loss": 0.3203,
+      "step": 245
+    },
+    {
+      "epoch": 0.7068965517241379,
+      "grad_norm": 2.850348472595215,
+      "learning_rate": 4.7985686744976714e-06,
+      "loss": 0.2846,
+      "step": 246
+    },
+    {
+      "epoch": 0.7097701149425287,
+      "grad_norm": 3.9147164821624756,
+      "learning_rate": 4.713107875233459e-06,
+      "loss": 0.3315,
+      "step": 247
+    },
+    {
+      "epoch": 0.7126436781609196,
+      "grad_norm": 3.5606236457824707,
+      "learning_rate": 4.628179684199685e-06,
+      "loss": 0.3101,
+      "step": 248
+    },
+    {
+      "epoch": 0.7155172413793104,
+      "grad_norm": 2.9054181575775146,
+      "learning_rate": 4.543792657170228e-06,
+      "loss": 0.3086,
+      "step": 249
+    },
+    {
+      "epoch": 0.7183908045977011,
+      "grad_norm": 2.9038889408111572,
+      "learning_rate": 4.459955295401415e-06,
+      "loss": 0.2979,
+      "step": 250
+    },
+    {
+      "epoch": 0.7212643678160919,
+      "grad_norm": 2.952456474304199,
+      "learning_rate": 4.376676044775601e-06,
+      "loss": 0.3221,
+      "step": 251
+    },
+    {
+      "epoch": 0.7241379310344828,
+      "grad_norm": 2.3187882900238037,
+      "learning_rate": 4.293963294950313e-06,
+      "loss": 0.296,
+      "step": 252
+    },
+    {
+      "epoch": 0.7270114942528736,
+      "grad_norm": 4.975540637969971,
+      "learning_rate": 4.211825378513066e-06,
+      "loss": 0.3873,
+      "step": 253
+    },
+    {
+      "epoch": 0.7298850574712644,
+      "grad_norm": 2.431337833404541,
+      "learning_rate": 4.130270570141931e-06,
+      "loss": 0.3386,
+      "step": 254
+    },
+    {
+      "epoch": 0.7327586206896551,
+      "grad_norm": 3.258333921432495,
+      "learning_rate": 4.0493070857719305e-06,
+      "loss": 0.3402,
+      "step": 255
+    },
+    {
+      "epoch": 0.735632183908046,
+      "grad_norm": 2.442279577255249,
+      "learning_rate": 3.968943081767358e-06,
+      "loss": 0.2268,
+      "step": 256
+    },
+    {
+      "epoch": 0.7385057471264368,
+      "grad_norm": 3.3889667987823486,
+      "learning_rate": 3.889186654100089e-06,
+      "loss": 0.3008,
+      "step": 257
+    },
+    {
+      "epoch": 0.7413793103448276,
+      "grad_norm": 2.3388214111328125,
+      "learning_rate": 3.81004583753399e-06,
+      "loss": 0.3399,
+      "step": 258
+    },
+    {
+      "epoch": 0.7442528735632183,
+      "grad_norm": 2.363194704055786,
+      "learning_rate": 3.7315286048154862e-06,
+      "loss": 0.2797,
+      "step": 259
+    },
+    {
+      "epoch": 0.7471264367816092,
+      "grad_norm": 3.6801648139953613,
+      "learning_rate": 3.6536428658703594e-06,
+      "loss": 0.3179,
+      "step": 260
+    },
+    {
+      "epoch": 0.7471264367816092,
+      "eval_accuracy": 0.8663366336633663,
+      "eval_f1": 0.7452830188679245,
+      "eval_loss": 0.3128357529640198,
+      "eval_precision": 0.7452830188679245,
+      "eval_recall": 0.7452830188679245,
+      "eval_runtime": 16.9937,
+      "eval_samples_per_second": 6.238,
+      "eval_steps_per_second": 0.235,
+      "step": 260
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 3.5845208168029785,
+      "learning_rate": 3.576396467006925e-06,
+      "loss": 0.3121,
+      "step": 261
+    },
+    {
+      "epoch": 0.7528735632183908,
+      "grad_norm": 2.5115549564361572,
+      "learning_rate": 3.4997971901255588e-06,
+      "loss": 0.2695,
+      "step": 262
+    },
+    {
+      "epoch": 0.7557471264367817,
+      "grad_norm": 3.1949312686920166,
+      "learning_rate": 3.4238527519347353e-06,
+      "loss": 0.29,
+      "step": 263
+    },
+    {
+      "epoch": 0.7586206896551724,
+      "grad_norm": 3.134657859802246,
+      "learning_rate": 3.3485708031736698e-06,
+      "loss": 0.2959,
+      "step": 264
+    },
+    {
+      "epoch": 0.7614942528735632,
+      "grad_norm": 2.359828472137451,
+      "learning_rate": 3.2739589278415252e-06,
+      "loss": 0.299,
+      "step": 265
+    },
+    {
+      "epoch": 0.764367816091954,
+      "grad_norm": 2.662598133087158,
+      "learning_rate": 3.2000246424334315e-06,
+      "loss": 0.2887,
+      "step": 266
+    },
+    {
+      "epoch": 0.7672413793103449,
+      "grad_norm": 2.822681188583374,
+      "learning_rate": 3.1267753951832523e-06,
+      "loss": 0.3337,
+      "step": 267
+    },
+    {
+      "epoch": 0.7701149425287356,
+      "grad_norm": 3.435675859451294,
+      "learning_rate": 3.0542185653132216e-06,
+      "loss": 0.2431,
+      "step": 268
+    },
+    {
+      "epoch": 0.7729885057471264,
+      "grad_norm": 3.8508052825927734,
+      "learning_rate": 2.982361462290575e-06,
+      "loss": 0.3625,
+      "step": 269
+    },
+    {
+      "epoch": 0.7758620689655172,
+      "grad_norm": 3.24882435798645,
+      "learning_rate": 2.9112113250911844e-06,
+      "loss": 0.3255,
+      "step": 270
+    },
+    {
+      "epoch": 0.7787356321839081,
+      "grad_norm": 3.215721368789673,
+      "learning_rate": 2.8407753214702694e-06,
+      "loss": 0.3055,
+      "step": 271
+    },
+    {
+      "epoch": 0.7816091954022989,
+      "grad_norm": 3.5768065452575684,
+      "learning_rate": 2.7710605472403373e-06,
+      "loss": 0.2593,
+      "step": 272
+    },
+    {
+      "epoch": 0.7844827586206896,
+      "grad_norm": 3.4842770099639893,
+      "learning_rate": 2.702074025556327e-06,
+      "loss": 0.3183,
+      "step": 273
+    },
+    {
+      "epoch": 0.7873563218390804,
+      "grad_norm": 2.8685038089752197,
+      "learning_rate": 2.6338227062080924e-06,
+      "loss": 0.2674,
+      "step": 274
+    },
+    {
+      "epoch": 0.7902298850574713,
+      "grad_norm": 3.008521318435669,
+      "learning_rate": 2.566313464920265e-06,
+      "loss": 0.2944,
+      "step": 275
+    },
+    {
+      "epoch": 0.7931034482758621,
+      "grad_norm": 2.9339377880096436,
+      "learning_rate": 2.4995531026595952e-06,
+      "loss": 0.295,
+      "step": 276
+    },
+    {
+      "epoch": 0.7959770114942529,
+      "grad_norm": 4.123067378997803,
+      "learning_rate": 2.4335483449498053e-06,
+      "loss": 0.2295,
+      "step": 277
+    },
+    {
+      "epoch": 0.7988505747126436,
+      "grad_norm": 2.862365245819092,
+      "learning_rate": 2.3683058411940563e-06,
+      "loss": 0.2967,
+      "step": 278
+    },
+    {
+      "epoch": 0.8017241379310345,
+      "grad_norm": 4.078983783721924,
+      "learning_rate": 2.3038321640050763e-06,
+      "loss": 0.3005,
+      "step": 279
+    },
+    {
+      "epoch": 0.8045977011494253,
+      "grad_norm": 4.147453308105469,
+      "learning_rate": 2.2401338085430326e-06,
+      "loss": 0.2901,
+      "step": 280
+    },
+    {
+      "epoch": 0.8045977011494253,
+      "eval_accuracy": 0.8638613861386139,
+      "eval_f1": 0.7417840375586855,
+      "eval_loss": 0.3146108090877533,
+      "eval_precision": 0.7383177570093458,
+      "eval_recall": 0.7452830188679245,
+      "eval_runtime": 16.7331,
+      "eval_samples_per_second": 6.335,
+      "eval_steps_per_second": 0.239,
+      "step": 280
+    },
+    {
+      "epoch": 0.8074712643678161,
+      "grad_norm": 2.4641005992889404,
+      "learning_rate": 2.177217191861183e-06,
+      "loss": 0.2452,
+      "step": 281
+    },
+    {
+      "epoch": 0.8103448275862069,
+      "grad_norm": 3.1481075286865234,
+      "learning_rate": 2.115088652259446e-06,
+      "loss": 0.3355,
+      "step": 282
+    },
+    {
+      "epoch": 0.8132183908045977,
+      "grad_norm": 2.2011497020721436,
+      "learning_rate": 2.053754448645846e-06,
+      "loss": 0.2256,
+      "step": 283
+    },
+    {
+      "epoch": 0.8160919540229885,
+      "grad_norm": 3.1297502517700195,
+      "learning_rate": 1.9932207599059782e-06,
+      "loss": 0.2899,
+      "step": 284
+    },
+    {
+      "epoch": 0.8189655172413793,
+      "grad_norm": 2.566171646118164,
+      "learning_rate": 1.933493684280574e-06,
+      "loss": 0.2527,
+      "step": 285
+    },
+    {
+      "epoch": 0.8218390804597702,
+      "grad_norm": 3.0499560832977295,
+      "learning_rate": 1.8745792387511241e-06,
+      "loss": 0.2979,
+      "step": 286
+    },
+    {
+      "epoch": 0.8247126436781609,
+      "grad_norm": 3.5081562995910645,
+      "learning_rate": 1.8164833584337216e-06,
+      "loss": 0.2766,
+      "step": 287
+    },
+    {
+      "epoch": 0.8275862068965517,
+      "grad_norm": 3.2664620876312256,
+      "learning_rate": 1.75921189598118e-06,
+      "loss": 0.3008,
+      "step": 288
+    },
+    {
+      "epoch": 0.8304597701149425,
+      "grad_norm": 3.314521551132202,
+      "learning_rate": 1.7027706209933903e-06,
+      "loss": 0.3387,
+      "step": 289
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 2.5149619579315186,
+      "learning_rate": 1.6471652194361131e-06,
+      "loss": 0.3032,
+      "step": 290
+    },
+    {
+      "epoch": 0.8362068965517241,
+      "grad_norm": 3.847849130630493,
+      "learning_rate": 1.5924012930681643e-06,
+      "loss": 0.3218,
+      "step": 291
+    },
+    {
+      "epoch": 0.8390804597701149,
+      "grad_norm": 6.620360374450684,
+      "learning_rate": 1.5384843588770626e-06,
+      "loss": 0.3464,
+      "step": 292
+    },
+    {
+      "epoch": 0.8419540229885057,
+      "grad_norm": 3.233356475830078,
+      "learning_rate": 1.4854198485232696e-06,
+      "loss": 0.2475,
+      "step": 293
+    },
+    {
+      "epoch": 0.8448275862068966,
+      "grad_norm": 4.268490314483643,
+      "learning_rate": 1.433213107792991e-06,
+      "loss": 0.3646,
+      "step": 294
+    },
+    {
+      "epoch": 0.8477011494252874,
+      "grad_norm": 3.641005754470825,
+      "learning_rate": 1.3818693960596186e-06,
+      "loss": 0.3347,
+      "step": 295
+    },
+    {
+      "epoch": 0.8505747126436781,
+      "grad_norm": 2.945902109146118,
+      "learning_rate": 1.3313938857539133e-06,
+      "loss": 0.2806,
+      "step": 296
+    },
+    {
+      "epoch": 0.853448275862069,
+      "grad_norm": 3.552212715148926,
+      "learning_rate": 1.2817916618429194e-06,
+      "loss": 0.2993,
+      "step": 297
+    },
+    {
+      "epoch": 0.8563218390804598,
+      "grad_norm": 3.9987523555755615,
+      "learning_rate": 1.2330677213177034e-06,
+      "loss": 0.2611,
+      "step": 298
+    },
+    {
+      "epoch": 0.8591954022988506,
+      "grad_norm": 4.93873405456543,
+      "learning_rate": 1.1852269726899423e-06,
+      "loss": 0.3131,
+      "step": 299
+    },
+    {
+      "epoch": 0.8620689655172413,
+      "grad_norm": 2.6833460330963135,
+      "learning_rate": 1.138274235497443e-06,
+      "loss": 0.2587,
+      "step": 300
+    },
+    {
+      "epoch": 0.8620689655172413,
+      "eval_accuracy": 0.8638613861386139,
+      "eval_f1": 0.7417840375586855,
+      "eval_loss": 0.3137795925140381,
+      "eval_precision": 0.7383177570093458,
+      "eval_recall": 0.7452830188679245,
+      "eval_runtime": 16.8912,
+      "eval_samples_per_second": 6.275,
+      "eval_steps_per_second": 0.237,
+      "step": 300
     }
   ],
   "logging_steps": 1,
@@ -1558,7 +2318,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.331748017661542e+16,
+  "total_flos": 9.46781682579538e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null