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 sha256:497072355118f1678db7e5784e7d1e39546df8ff271f75f8c2187714c798f11e
+oid sha256:f0cdbad22026ef4570d69713ed36e9988e2d20ec1cc7872124c5cd8892b08e27
 size 13934748

last-checkpoint/optimizer_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5105f5cd224fd8c379436b63e7162eedb2642aa53d8f246e932003d0ff5bc78f
+oid sha256:3923f926094736f42eced54f19266b2bc2158d72fd9a0cd3c02b1fb8807d7f1a
 size 13999412

last-checkpoint/optimizer_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7eb609cebee906e97182dea7e0a548a24c93d8092c43b8769a13ac88ac30ca0b
+oid sha256:bf0b73f9e9c8a4f8582ff355de6d6d8a04a08766f7d07123d3184b4c761286e2
 size 13990904

last-checkpoint/optimizer_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86468afda6bbd409ae2802dc2168525968b1d04bc743d181938c5ea2835477cc
+oid sha256:405af69a03f0e3476450c607bb594ac182fec0cf1d886a9e839d148129be6f31
 size 13990904

last-checkpoint/pytorch_model_fsdp_0/__0_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63bedfd4b2ad0cda05109e50ae3b1e823ca8f370ea9bb2d787b8827531ba7fd1
+oid sha256:82f32ad9bc0b6e58cba7fbf99be1674a985aad888a5ff065293f47e660b96bab
 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:b1a0fec7711b1ada2501d686dae8a50aa87d00dd44b9f5e5841470fc00641044
+oid sha256:8de22ccd545a7c600de6661157194a8a1a602733e0e6257f75c693e2bdd31fdf
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:015f8ce7d1bce7cd13209586e24131790d6d4a3fc25fbecb01046bc158ab4bb9
+oid sha256:a13a44bba25ffaaf6f9f497c587a3626beec7a2d03275687f89e831910cd63f8
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65db59a453e5457db6c0a8e0a01fd2cd3a86d790e0382792da26ea2594a5dbb7
+oid sha256:108637bc0fb9efb13fc1b5168cfdd235eb84cd7e8cc51719953cd335a4c70f2e
 size 6966784

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c950c55a9d7f3f12cbea28994c56b76445a58ef1dc62941170045fc38602218
+oid sha256:89edf824a18aba9b3c02d829e9b5232f92be1587619439bb211a6f4c04f526e5
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5873717f8eba94ca2999c5e7faeb009fd70c6f5b058c0d4fa2de788fb4bc7147
+oid sha256:3c3586ec42dd7bf5113592e99bbd2a0db8d631b39e7118703fa3e4072757685b
 size 14960

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0ce3159bfbe08feafa005853a657da4d7626ac386bd152698eb37a03133432e
+oid sha256:71c8890fbab61f886e9d2c523858857c2c4744a1ded684b6faba27b61ef4cbc7
 size 14960

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e71856f4f14e84adc644fe75a9ff3c147b4f15948423de559ca90c2793460338
+oid sha256:9c2e1960a6de0eee1b69c7926b9a00fc7289af04f8d26a91220cf98719a57911
 size 14960

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2b0c16f74251cf23cb78b806076d6dd5e392623f6764fb5e3b3de0ffd4e1772
+oid sha256:9124382ef287402f7469543fd1aa06f5e61de79f60c9587d58340fa81df5700f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.15308075009567546,
+  "epoch": 0.2296211251435132,
   "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": 6.88,
       "eval_steps_per_second": 0.229,
       "step": 200
+    },
+    {
+      "epoch": 0.15384615384615385,
+      "grad_norm": 5.135117053985596,
+      "learning_rate": 1.982536873224748e-05,
+      "loss": 0.3718,
+      "step": 201
+    },
+    {
+      "epoch": 0.15461155759663223,
+      "grad_norm": 9.245200157165527,
+      "learning_rate": 1.982035872726042e-05,
+      "loss": 0.4988,
+      "step": 202
+    },
+    {
+      "epoch": 0.1553769613471106,
+      "grad_norm": 5.376220703125,
+      "learning_rate": 1.9815278520011364e-05,
+      "loss": 0.3518,
+      "step": 203
+    },
+    {
+      "epoch": 0.15614236509758897,
+      "grad_norm": 5.195625305175781,
+      "learning_rate": 1.98101281468169e-05,
+      "loss": 0.3542,
+      "step": 204
+    },
+    {
+      "epoch": 0.15690776884806737,
+      "grad_norm": 3.9978110790252686,
+      "learning_rate": 1.980490764449523e-05,
+      "loss": 0.332,
+      "step": 205
+    },
+    {
+      "epoch": 0.15767317259854574,
+      "grad_norm": 6.721541881561279,
+      "learning_rate": 1.979961705036587e-05,
+      "loss": 0.4359,
+      "step": 206
+    },
+    {
+      "epoch": 0.1584385763490241,
+      "grad_norm": 6.835299968719482,
+      "learning_rate": 1.9794256402249398e-05,
+      "loss": 0.4853,
+      "step": 207
+    },
+    {
+      "epoch": 0.15920398009950248,
+      "grad_norm": 7.488376617431641,
+      "learning_rate": 1.9788825738467194e-05,
+      "loss": 0.4803,
+      "step": 208
+    },
+    {
+      "epoch": 0.15996938384998086,
+      "grad_norm": 7.519308567047119,
+      "learning_rate": 1.978332509784114e-05,
+      "loss": 0.3915,
+      "step": 209
+    },
+    {
+      "epoch": 0.16073478760045926,
+      "grad_norm": 4.765905380249023,
+      "learning_rate": 1.977775451969337e-05,
+      "loss": 0.4286,
+      "step": 210
+    },
+    {
+      "epoch": 0.16150019135093763,
+      "grad_norm": 5.47350549697876,
+      "learning_rate": 1.9772114043845968e-05,
+      "loss": 0.4142,
+      "step": 211
+    },
+    {
+      "epoch": 0.162265595101416,
+      "grad_norm": 6.0178375244140625,
+      "learning_rate": 1.97664037106207e-05,
+      "loss": 0.5002,
+      "step": 212
+    },
+    {
+      "epoch": 0.16303099885189437,
+      "grad_norm": 5.823141098022461,
+      "learning_rate": 1.9760623560838707e-05,
+      "loss": 0.4094,
+      "step": 213
+    },
+    {
+      "epoch": 0.16379640260237274,
+      "grad_norm": 6.595653057098389,
+      "learning_rate": 1.9754773635820236e-05,
+      "loss": 0.4408,
+      "step": 214
+    },
+    {
+      "epoch": 0.16456180635285114,
+      "grad_norm": 6.631775379180908,
+      "learning_rate": 1.9748853977384326e-05,
+      "loss": 0.3829,
+      "step": 215
+    },
+    {
+      "epoch": 0.1653272101033295,
+      "grad_norm": 8.617928504943848,
+      "learning_rate": 1.974286462784851e-05,
+      "loss": 0.4709,
+      "step": 216
+    },
+    {
+      "epoch": 0.16609261385380789,
+      "grad_norm": 5.043487548828125,
+      "learning_rate": 1.973680563002853e-05,
+      "loss": 0.3764,
+      "step": 217
+    },
+    {
+      "epoch": 0.16685801760428626,
+      "grad_norm": 5.085770606994629,
+      "learning_rate": 1.973067702723801e-05,
+      "loss": 0.3281,
+      "step": 218
+    },
+    {
+      "epoch": 0.16762342135476463,
+      "grad_norm": 6.6135029792785645,
+      "learning_rate": 1.972447886328816e-05,
+      "loss": 0.4335,
+      "step": 219
+    },
+    {
+      "epoch": 0.16838882510524303,
+      "grad_norm": 8.10050106048584,
+      "learning_rate": 1.9718211182487455e-05,
+      "loss": 0.427,
+      "step": 220
+    },
+    {
+      "epoch": 0.16838882510524303,
+      "eval_accuracy": 0.8429602888086642,
+      "eval_f1": 0.7563025210084033,
+      "eval_loss": 0.4065958261489868,
+      "eval_precision": 0.8653846153846154,
+      "eval_recall": 0.6716417910447762,
+      "eval_runtime": 42.5974,
+      "eval_samples_per_second": 7.066,
+      "eval_steps_per_second": 0.235,
+      "step": 220
+    },
+    {
+      "epoch": 0.1691542288557214,
+      "grad_norm": 5.3172526359558105,
+      "learning_rate": 1.971187402964132e-05,
+      "loss": 0.4483,
+      "step": 221
+    },
+    {
+      "epoch": 0.16991963260619977,
+      "grad_norm": 5.775417804718018,
+      "learning_rate": 1.970546745005182e-05,
+      "loss": 0.3196,
+      "step": 222
+    },
+    {
+      "epoch": 0.17068503635667814,
+      "grad_norm": 5.696174621582031,
+      "learning_rate": 1.969899148951731e-05,
+      "loss": 0.3721,
+      "step": 223
+    },
+    {
+      "epoch": 0.17145044010715652,
+      "grad_norm": 4.350657939910889,
+      "learning_rate": 1.9692446194332144e-05,
+      "loss": 0.3112,
+      "step": 224
+    },
+    {
+      "epoch": 0.17221584385763491,
+      "grad_norm": 6.253859996795654,
+      "learning_rate": 1.9685831611286312e-05,
+      "loss": 0.3454,
+      "step": 225
+    },
+    {
+      "epoch": 0.1729812476081133,
+      "grad_norm": 5.843462944030762,
+      "learning_rate": 1.9679147787665128e-05,
+      "loss": 0.321,
+      "step": 226
+    },
+    {
+      "epoch": 0.17374665135859166,
+      "grad_norm": 9.418475151062012,
+      "learning_rate": 1.9672394771248867e-05,
+      "loss": 0.3685,
+      "step": 227
+    },
+    {
+      "epoch": 0.17451205510907003,
+      "grad_norm": 5.893159866333008,
+      "learning_rate": 1.966557261031246e-05,
+      "loss": 0.3446,
+      "step": 228
+    },
+    {
+      "epoch": 0.1752774588595484,
+      "grad_norm": 6.786052703857422,
+      "learning_rate": 1.9658681353625105e-05,
+      "loss": 0.4436,
+      "step": 229
+    },
+    {
+      "epoch": 0.1760428626100268,
+      "grad_norm": 5.613348007202148,
+      "learning_rate": 1.9651721050449964e-05,
+      "loss": 0.3582,
+      "step": 230
+    },
+    {
+      "epoch": 0.17680826636050517,
+      "grad_norm": 7.1399827003479,
+      "learning_rate": 1.964469175054377e-05,
+      "loss": 0.3733,
+      "step": 231
+    },
+    {
+      "epoch": 0.17757367011098354,
+      "grad_norm": 5.748831748962402,
+      "learning_rate": 1.963759350415649e-05,
+      "loss": 0.3765,
+      "step": 232
+    },
+    {
+      "epoch": 0.17833907386146192,
+      "grad_norm": 7.2922539710998535,
+      "learning_rate": 1.9630426362030978e-05,
+      "loss": 0.4476,
+      "step": 233
+    },
+    {
+      "epoch": 0.1791044776119403,
+      "grad_norm": 10.018366813659668,
+      "learning_rate": 1.962319037540259e-05,
+      "loss": 0.5118,
+      "step": 234
+    },
+    {
+      "epoch": 0.1798698813624187,
+      "grad_norm": 6.774781703948975,
+      "learning_rate": 1.9615885595998825e-05,
+      "loss": 0.3561,
+      "step": 235
+    },
+    {
+      "epoch": 0.18063528511289706,
+      "grad_norm": 9.361811637878418,
+      "learning_rate": 1.9608512076038964e-05,
+      "loss": 0.4204,
+      "step": 236
+    },
+    {
+      "epoch": 0.18140068886337543,
+      "grad_norm": 4.652408123016357,
+      "learning_rate": 1.9601069868233687e-05,
+      "loss": 0.3521,
+      "step": 237
+    },
+    {
+      "epoch": 0.1821660926138538,
+      "grad_norm": 6.97662353515625,
+      "learning_rate": 1.9593559025784692e-05,
+      "loss": 0.464,
+      "step": 238
+    },
+    {
+      "epoch": 0.18293149636433217,
+      "grad_norm": 5.046630382537842,
+      "learning_rate": 1.9585979602384334e-05,
+      "loss": 0.4245,
+      "step": 239
+    },
+    {
+      "epoch": 0.18369690011481057,
+      "grad_norm": 6.48331356048584,
+      "learning_rate": 1.9578331652215224e-05,
+      "loss": 0.346,
+      "step": 240
+    },
+    {
+      "epoch": 0.18369690011481057,
+      "eval_accuracy": 0.8339350180505415,
+      "eval_f1": 0.7722772277227723,
+      "eval_loss": 0.4155955910682678,
+      "eval_precision": 0.7684729064039408,
+      "eval_recall": 0.7761194029850746,
+      "eval_runtime": 44.3642,
+      "eval_samples_per_second": 6.785,
+      "eval_steps_per_second": 0.225,
+      "step": 240
+    },
+    {
+      "epoch": 0.18446230386528895,
+      "grad_norm": 5.903677940368652,
+      "learning_rate": 1.9570615229949844e-05,
+      "loss": 0.3271,
+      "step": 241
+    },
+    {
+      "epoch": 0.18522770761576732,
+      "grad_norm": 8.325933456420898,
+      "learning_rate": 1.9562830390750157e-05,
+      "loss": 0.3309,
+      "step": 242
+    },
+    {
+      "epoch": 0.1859931113662457,
+      "grad_norm": 4.691112518310547,
+      "learning_rate": 1.955497719026722e-05,
+      "loss": 0.4265,
+      "step": 243
+    },
+    {
+      "epoch": 0.18675851511672406,
+      "grad_norm": 5.79347562789917,
+      "learning_rate": 1.954705568464078e-05,
+      "loss": 0.3228,
+      "step": 244
+    },
+    {
+      "epoch": 0.18752391886720246,
+      "grad_norm": 6.642929553985596,
+      "learning_rate": 1.953906593049887e-05,
+      "loss": 0.3625,
+      "step": 245
+    },
+    {
+      "epoch": 0.18828932261768083,
+      "grad_norm": 6.772623538970947,
+      "learning_rate": 1.9531007984957408e-05,
+      "loss": 0.3105,
+      "step": 246
+    },
+    {
+      "epoch": 0.1890547263681592,
+      "grad_norm": 6.067032337188721,
+      "learning_rate": 1.9522881905619794e-05,
+      "loss": 0.3793,
+      "step": 247
+    },
+    {
+      "epoch": 0.18982013011863758,
+      "grad_norm": 6.046145439147949,
+      "learning_rate": 1.9514687750576483e-05,
+      "loss": 0.439,
+      "step": 248
+    },
+    {
+      "epoch": 0.19058553386911595,
+      "grad_norm": 5.100595951080322,
+      "learning_rate": 1.950642557840458e-05,
+      "loss": 0.3456,
+      "step": 249
+    },
+    {
+      "epoch": 0.19135093761959435,
+      "grad_norm": 9.742971420288086,
+      "learning_rate": 1.9498095448167435e-05,
+      "loss": 0.5016,
+      "step": 250
+    },
+    {
+      "epoch": 0.19211634137007272,
+      "grad_norm": 5.769988536834717,
+      "learning_rate": 1.948969741941418e-05,
+      "loss": 0.4057,
+      "step": 251
+    },
+    {
+      "epoch": 0.1928817451205511,
+      "grad_norm": 6.542685031890869,
+      "learning_rate": 1.948123155217936e-05,
+      "loss": 0.3563,
+      "step": 252
+    },
+    {
+      "epoch": 0.19364714887102946,
+      "grad_norm": 6.277159690856934,
+      "learning_rate": 1.947269790698245e-05,
+      "loss": 0.3911,
+      "step": 253
+    },
+    {
+      "epoch": 0.19441255262150783,
+      "grad_norm": 5.547085285186768,
+      "learning_rate": 1.946409654482745e-05,
+      "loss": 0.3616,
+      "step": 254
+    },
+    {
+      "epoch": 0.19517795637198623,
+      "grad_norm": 5.570236682891846,
+      "learning_rate": 1.945542752720245e-05,
+      "loss": 0.2538,
+      "step": 255
+    },
+    {
+      "epoch": 0.1959433601224646,
+      "grad_norm": 9.954462051391602,
+      "learning_rate": 1.944669091607919e-05,
+      "loss": 0.4541,
+      "step": 256
+    },
+    {
+      "epoch": 0.19670876387294298,
+      "grad_norm": 5.784120082855225,
+      "learning_rate": 1.9437886773912595e-05,
+      "loss": 0.3479,
+      "step": 257
+    },
+    {
+      "epoch": 0.19747416762342135,
+      "grad_norm": 4.724707126617432,
+      "learning_rate": 1.9429015163640363e-05,
+      "loss": 0.2393,
+      "step": 258
+    },
+    {
+      "epoch": 0.19823957137389972,
+      "grad_norm": 5.0216064453125,
+      "learning_rate": 1.942007614868248e-05,
+      "loss": 0.3678,
+      "step": 259
+    },
+    {
+      "epoch": 0.19900497512437812,
+      "grad_norm": 6.818700790405273,
+      "learning_rate": 1.9411069792940803e-05,
+      "loss": 0.3623,
+      "step": 260
+    },
+    {
+      "epoch": 0.19900497512437812,
+      "eval_accuracy": 0.8501805054151624,
+      "eval_f1": 0.7688022284122563,
+      "eval_loss": 0.40000924468040466,
+      "eval_precision": 0.8734177215189873,
+      "eval_recall": 0.6865671641791045,
+      "eval_runtime": 43.8991,
+      "eval_samples_per_second": 6.857,
+      "eval_steps_per_second": 0.228,
+      "step": 260
+    },
+    {
+      "epoch": 0.1997703788748565,
+      "grad_norm": 5.862509727478027,
+      "learning_rate": 1.9401996160798574e-05,
+      "loss": 0.3671,
+      "step": 261
+    },
+    {
+      "epoch": 0.20053578262533486,
+      "grad_norm": 4.842383861541748,
+      "learning_rate": 1.9392855317119966e-05,
+      "loss": 0.3314,
+      "step": 262
+    },
+    {
+      "epoch": 0.20130118637581323,
+      "grad_norm": 5.581681728363037,
+      "learning_rate": 1.9383647327249635e-05,
+      "loss": 0.4105,
+      "step": 263
+    },
+    {
+      "epoch": 0.2020665901262916,
+      "grad_norm": 5.401704788208008,
+      "learning_rate": 1.937437225701223e-05,
+      "loss": 0.3592,
+      "step": 264
+    },
+    {
+      "epoch": 0.20283199387677,
+      "grad_norm": 4.608808517456055,
+      "learning_rate": 1.9365030172711946e-05,
+      "loss": 0.3495,
+      "step": 265
+    },
+    {
+      "epoch": 0.20359739762724838,
+      "grad_norm": 4.868807792663574,
+      "learning_rate": 1.9355621141132022e-05,
+      "loss": 0.3881,
+      "step": 266
+    },
+    {
+      "epoch": 0.20436280137772675,
+      "grad_norm": 7.819051742553711,
+      "learning_rate": 1.9346145229534295e-05,
+      "loss": 0.4057,
+      "step": 267
+    },
+    {
+      "epoch": 0.20512820512820512,
+      "grad_norm": 7.824717044830322,
+      "learning_rate": 1.933660250565869e-05,
+      "loss": 0.3441,
+      "step": 268
+    },
+    {
+      "epoch": 0.2058936088786835,
+      "grad_norm": 7.23281192779541,
+      "learning_rate": 1.9326993037722762e-05,
+      "loss": 0.487,
+      "step": 269
+    },
+    {
+      "epoch": 0.2066590126291619,
+      "grad_norm": 4.351503849029541,
+      "learning_rate": 1.931731689442119e-05,
+      "loss": 0.3626,
+      "step": 270
+    },
+    {
+      "epoch": 0.20742441637964026,
+      "grad_norm": 9.379828453063965,
+      "learning_rate": 1.9307574144925288e-05,
+      "loss": 0.3386,
+      "step": 271
+    },
+    {
+      "epoch": 0.20818982013011864,
+      "grad_norm": 5.923501491546631,
+      "learning_rate": 1.9297764858882516e-05,
+      "loss": 0.3378,
+      "step": 272
+    },
+    {
+      "epoch": 0.208955223880597,
+      "grad_norm": 6.346581935882568,
+      "learning_rate": 1.9287889106415983e-05,
+      "loss": 0.3057,
+      "step": 273
+    },
+    {
+      "epoch": 0.20972062763107538,
+      "grad_norm": 5.1364593505859375,
+      "learning_rate": 1.927794695812394e-05,
+      "loss": 0.2919,
+      "step": 274
+    },
+    {
+      "epoch": 0.21048603138155378,
+      "grad_norm": 5.439457893371582,
+      "learning_rate": 1.9267938485079285e-05,
+      "loss": 0.4108,
+      "step": 275
+    },
+    {
+      "epoch": 0.21125143513203215,
+      "grad_norm": 4.554882526397705,
+      "learning_rate": 1.9257863758829038e-05,
+      "loss": 0.3876,
+      "step": 276
+    },
+    {
+      "epoch": 0.21201683888251052,
+      "grad_norm": 7.16301965713501,
+      "learning_rate": 1.9247722851393838e-05,
+      "loss": 0.399,
+      "step": 277
+    },
+    {
+      "epoch": 0.2127822426329889,
+      "grad_norm": 7.004945755004883,
+      "learning_rate": 1.9237515835267447e-05,
+      "loss": 0.3675,
+      "step": 278
+    },
+    {
+      "epoch": 0.21354764638346727,
+      "grad_norm": 5.764822959899902,
+      "learning_rate": 1.92272427834162e-05,
+      "loss": 0.3255,
+      "step": 279
+    },
+    {
+      "epoch": 0.21431305013394567,
+      "grad_norm": 7.27835750579834,
+      "learning_rate": 1.9216903769278498e-05,
+      "loss": 0.3446,
+      "step": 280
+    },
+    {
+      "epoch": 0.21431305013394567,
+      "eval_accuracy": 0.851985559566787,
+      "eval_f1": 0.7747252747252747,
+      "eval_loss": 0.39411845803260803,
+      "eval_precision": 0.8650306748466258,
+      "eval_recall": 0.7014925373134329,
+      "eval_runtime": 42.6819,
+      "eval_samples_per_second": 7.052,
+      "eval_steps_per_second": 0.234,
+      "step": 280
+    },
+    {
+      "epoch": 0.21507845388442404,
+      "grad_norm": 9.400500297546387,
+      "learning_rate": 1.920649886676429e-05,
+      "loss": 0.4279,
+      "step": 281
+    },
+    {
+      "epoch": 0.2158438576349024,
+      "grad_norm": 6.810932159423828,
+      "learning_rate": 1.9196028150254535e-05,
+      "loss": 0.4324,
+      "step": 282
+    },
+    {
+      "epoch": 0.21660926138538078,
+      "grad_norm": 5.471708297729492,
+      "learning_rate": 1.9185491694600668e-05,
+      "loss": 0.333,
+      "step": 283
+    },
+    {
+      "epoch": 0.21737466513585915,
+      "grad_norm": 5.115065097808838,
+      "learning_rate": 1.9174889575124077e-05,
+      "loss": 0.3169,
+      "step": 284
+    },
+    {
+      "epoch": 0.21814006888633755,
+      "grad_norm": 6.514889717102051,
+      "learning_rate": 1.9164221867615556e-05,
+      "loss": 0.319,
+      "step": 285
+    },
+    {
+      "epoch": 0.21890547263681592,
+      "grad_norm": 5.090853214263916,
+      "learning_rate": 1.915348864833476e-05,
+      "loss": 0.4063,
+      "step": 286
+    },
+    {
+      "epoch": 0.2196708763872943,
+      "grad_norm": 8.121560096740723,
+      "learning_rate": 1.9142689994009666e-05,
+      "loss": 0.3493,
+      "step": 287
+    },
+    {
+      "epoch": 0.22043628013777267,
+      "grad_norm": 8.17483139038086,
+      "learning_rate": 1.913182598183603e-05,
+      "loss": 0.3528,
+      "step": 288
+    },
+    {
+      "epoch": 0.22120168388825107,
+      "grad_norm": 6.741644382476807,
+      "learning_rate": 1.9120896689476817e-05,
+      "loss": 0.4365,
+      "step": 289
+    },
+    {
+      "epoch": 0.22196708763872944,
+      "grad_norm": 7.430425643920898,
+      "learning_rate": 1.9109902195061666e-05,
+      "loss": 0.3639,
+      "step": 290
+    },
+    {
+      "epoch": 0.2227324913892078,
+      "grad_norm": 6.185513496398926,
+      "learning_rate": 1.9098842577186315e-05,
+      "loss": 0.4335,
+      "step": 291
+    },
+    {
+      "epoch": 0.22349789513968618,
+      "grad_norm": 9.91633129119873,
+      "learning_rate": 1.9087717914912054e-05,
+      "loss": 0.4059,
+      "step": 292
+    },
+    {
+      "epoch": 0.22426329889016455,
+      "grad_norm": 5.951688289642334,
+      "learning_rate": 1.9076528287765145e-05,
+      "loss": 0.2802,
+      "step": 293
+    },
+    {
+      "epoch": 0.22502870264064295,
+      "grad_norm": 5.823990821838379,
+      "learning_rate": 1.9065273775736264e-05,
+      "loss": 0.4503,
+      "step": 294
+    },
+    {
+      "epoch": 0.22579410639112132,
+      "grad_norm": 9.704663276672363,
+      "learning_rate": 1.9053954459279934e-05,
+      "loss": 0.3731,
+      "step": 295
+    },
+    {
+      "epoch": 0.2265595101415997,
+      "grad_norm": 8.522269248962402,
+      "learning_rate": 1.9042570419313927e-05,
+      "loss": 0.4185,
+      "step": 296
+    },
+    {
+      "epoch": 0.22732491389207807,
+      "grad_norm": 7.043125152587891,
+      "learning_rate": 1.9031121737218706e-05,
+      "loss": 0.3138,
+      "step": 297
+    },
+    {
+      "epoch": 0.22809031764255644,
+      "grad_norm": 6.579213619232178,
+      "learning_rate": 1.9019608494836843e-05,
+      "loss": 0.4797,
+      "step": 298
+    },
+    {
+      "epoch": 0.22885572139303484,
+      "grad_norm": 4.732334613800049,
+      "learning_rate": 1.900803077447243e-05,
+      "loss": 0.2618,
+      "step": 299
+    },
+    {
+      "epoch": 0.2296211251435132,
+      "grad_norm": 6.821180820465088,
+      "learning_rate": 1.899638865889047e-05,
+      "loss": 0.2533,
+      "step": 300
+    },
+    {
+      "epoch": 0.2296211251435132,
+      "eval_accuracy": 0.855595667870036,
+      "eval_f1": 0.7740112994350282,
+      "eval_loss": 0.3807988166809082,
+      "eval_precision": 0.8954248366013072,
+      "eval_recall": 0.681592039800995,
+      "eval_runtime": 43.4459,
+      "eval_samples_per_second": 6.928,
+      "eval_steps_per_second": 0.23,
+      "step": 300
     }
   ],
   "logging_steps": 1,
@@ -1558,7 +2318,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.0850494259789824e+16,
+  "total_flos": 4.588769900914278e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null