Upload 12 files

config.json

@@ -30,7 +30,7 @@
   "pad_token_id": 3,
   "pretraining_tp": 4,
   "problem_type": "single_label_classification",
-  "seq_length": 2048,
+  "seq_length": 512,
   "skip_bias_add": true,
   "skip_bias_add_qkv": false,
   "slow_but_exact": false,

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e25972de8180fc10cad9e151af9cf748eb5e70bce391ee42a5beee72d894aac
+oid sha256:5f4ed7acd97147ae137798f194176b95c29dac68ebf8a78b7e0695d99e91b3e3
 size 24020817451

pytorch_model-00001-of-00002.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9c8f97329473aa11ca607af7aadd2dde0f2e8670980f786a51cd176f2762840
+oid sha256:726bae473dd2a0db8d69761af142a4c6313d6bd5f0500e94f321636e66fd32d1
 size 9912311464

pytorch_model-00002-of-00002.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8d463e9eeaf58b97d6a48cb3dbcb3169370ab28f131ea12cc27655cd9c16021
+oid sha256:35d56a47e44ff12d3b362896dcd05b334a231089d157a044a2bac708d014ca56
 size 2098070557

tokenizer_config.json

@@ -2,7 +2,7 @@
   "add_prefix_space": false,
   "bos_token": "<s>",
   "eos_token": "</s>",
-  "model_max_length": 1000000000000000019884624838656,
+  "model_max_length": 512 ,#1000000000000000019884624838656
   "name_or_path": "bigscience/bloomz-3b",
   "pad_token": "<pad>",
   "special_tokens_map_file": null,

trainer_state.json

@@ -10,907 +10,907 @@
     {
       "epoch": 0.0,
       "learning_rate": 4.9971428571428576e-05,
-      "loss": 8.3826,
+      "loss": 18.0539,
       "step": 1
     },
     {
       "epoch": 0.02,
       "learning_rate": 4.9e-05,
-      "loss": 3.6284,
+      "loss": 4.1309,
       "step": 35
     },
     {
       "epoch": 0.02,
-      "eval_accuracy": 0.656,
-      "eval_f1": 0.47560975609756095,
-      "eval_loss": 1.8382066488265991,
-      "eval_precision": 1.0,
-      "eval_recall": 0.312,
-      "eval_runtime": 462.8972,
-      "eval_samples_per_second": 6.481,
-      "eval_steps_per_second": 0.81,
+      "eval_accuracy": 0.8826666666666667,
+      "eval_f1": 0.8778625954198473,
+      "eval_loss": 0.34147411584854126,
+      "eval_precision": 0.9153400868306801,
+      "eval_recall": 0.8433333333333334,
+      "eval_runtime": 463.3794,
+      "eval_samples_per_second": 6.474,
+      "eval_steps_per_second": 0.809,
       "step": 35
     },
     {
       "epoch": 0.04,
       "learning_rate": 4.8e-05,
-      "loss": 0.8755,
+      "loss": 0.6366,
       "step": 70
     },
     {
       "epoch": 0.04,
-      "eval_accuracy": 0.891,
-      "eval_f1": 0.8799118619170032,
-      "eval_loss": 0.9740824103355408,
-      "eval_precision": 0.9795584627964022,
-      "eval_recall": 0.7986666666666666,
-      "eval_runtime": 462.3762,
-      "eval_samples_per_second": 6.488,
-      "eval_steps_per_second": 0.811,
+      "eval_accuracy": 0.9403333333333334,
+      "eval_f1": 0.9423881557772771,
+      "eval_loss": 0.139574334025383,
+      "eval_precision": 0.911014312383323,
+      "eval_recall": 0.976,
+      "eval_runtime": 463.7246,
+      "eval_samples_per_second": 6.469,
+      "eval_steps_per_second": 0.809,
       "step": 70
     },
     {
       "epoch": 0.06,
       "learning_rate": 4.7e-05,
-      "loss": 0.5529,
+      "loss": 0.8166,
       "step": 105
     },
     {
       "epoch": 0.06,
-      "eval_accuracy": 0.85,
-      "eval_f1": 0.823943661971831,
-      "eval_loss": 0.8984822630882263,
-      "eval_precision": 0.9971590909090909,
-      "eval_recall": 0.702,
-      "eval_runtime": 463.7211,
-      "eval_samples_per_second": 6.469,
+      "eval_accuracy": 0.8373333333333334,
+      "eval_f1": 0.8576429404900816,
+      "eval_loss": 0.8452138900756836,
+      "eval_precision": 0.7624481327800829,
+      "eval_recall": 0.98,
+      "eval_runtime": 463.2546,
+      "eval_samples_per_second": 6.476,
       "eval_steps_per_second": 0.809,
       "step": 105
     },
     {
       "epoch": 0.08,
       "learning_rate": 4.600000000000001e-05,
-      "loss": 0.4281,
+      "loss": 1.8141,
       "step": 140
     },
     {
       "epoch": 0.08,
-      "eval_accuracy": 0.948,
-      "eval_f1": 0.948,
-      "eval_loss": 0.28269827365875244,
-      "eval_precision": 0.948,
-      "eval_recall": 0.948,
-      "eval_runtime": 462.5168,
-      "eval_samples_per_second": 6.486,
-      "eval_steps_per_second": 0.811,
+      "eval_accuracy": 0.8703333333333333,
+      "eval_f1": 0.8838459241564646,
+      "eval_loss": 2.6052372455596924,
+      "eval_precision": 0.8004326663061114,
+      "eval_recall": 0.9866666666666667,
+      "eval_runtime": 463.8217,
+      "eval_samples_per_second": 6.468,
+      "eval_steps_per_second": 0.809,
       "step": 140
     },
     {
       "epoch": 0.1,
       "learning_rate": 4.5e-05,
-      "loss": 0.4027,
+      "loss": 0.994,
       "step": 175
     },
     {
       "epoch": 0.1,
-      "eval_accuracy": 0.8686666666666667,
-      "eval_f1": 0.8490421455938698,
-      "eval_loss": 1.2850149869918823,
-      "eval_precision": 0.9981981981981982,
-      "eval_recall": 0.7386666666666667,
-      "eval_runtime": 462.9807,
-      "eval_samples_per_second": 6.48,
-      "eval_steps_per_second": 0.81,
+      "eval_accuracy": 0.8933333333333333,
+      "eval_f1": 0.9029714978775015,
+      "eval_loss": 0.5267955660820007,
+      "eval_precision": 0.8281423804226918,
+      "eval_recall": 0.9926666666666667,
+      "eval_runtime": 463.9594,
+      "eval_samples_per_second": 6.466,
+      "eval_steps_per_second": 0.808,
       "step": 175
     },
     {
       "epoch": 0.12,
       "learning_rate": 4.4000000000000006e-05,
-      "loss": 0.4487,
+      "loss": 0.3827,
       "step": 210
     },
     {
       "epoch": 0.12,
-      "eval_accuracy": 0.9423333333333334,
-      "eval_f1": 0.9391059486096445,
-      "eval_loss": 0.1546011120080948,
-      "eval_precision": 0.9947800149142431,
-      "eval_recall": 0.8893333333333333,
-      "eval_runtime": 462.5947,
-      "eval_samples_per_second": 6.485,
-      "eval_steps_per_second": 0.811,
+      "eval_accuracy": 0.9343333333333333,
+      "eval_f1": 0.9345297441010303,
+      "eval_loss": 0.296316534280777,
+      "eval_precision": 0.9317428760768721,
+      "eval_recall": 0.9373333333333334,
+      "eval_runtime": 463.5088,
+      "eval_samples_per_second": 6.472,
+      "eval_steps_per_second": 0.809,
       "step": 210
     },
     {
       "epoch": 0.14,
       "learning_rate": 4.3e-05,
-      "loss": 0.4095,
+      "loss": 0.5048,
       "step": 245
     },
     {
       "epoch": 0.14,
-      "eval_accuracy": 0.8943333333333333,
-      "eval_f1": 0.8818486768542676,
-      "eval_loss": 0.8063055276870728,
-      "eval_precision": 1.0,
-      "eval_recall": 0.7886666666666666,
-      "eval_runtime": 463.8636,
-      "eval_samples_per_second": 6.467,
-      "eval_steps_per_second": 0.808,
+      "eval_accuracy": 0.9526666666666667,
+      "eval_f1": 0.9523489932885906,
+      "eval_loss": 0.2187061905860901,
+      "eval_precision": 0.9587837837837838,
+      "eval_recall": 0.946,
+      "eval_runtime": 467.9247,
+      "eval_samples_per_second": 6.411,
+      "eval_steps_per_second": 0.801,
       "step": 245
     },
     {
       "epoch": 0.16,
       "learning_rate": 4.2e-05,
-      "loss": 0.2566,
+      "loss": 0.2841,
       "step": 280
     },
     {
       "epoch": 0.16,
-      "eval_accuracy": 0.9623333333333334,
-      "eval_f1": 0.9620932572962093,
-      "eval_loss": 0.37129560112953186,
-      "eval_precision": 0.9682646860229575,
-      "eval_recall": 0.956,
-      "eval_runtime": 462.5562,
-      "eval_samples_per_second": 6.486,
-      "eval_steps_per_second": 0.811,
+      "eval_accuracy": 0.8916666666666667,
+      "eval_f1": 0.8787765759045133,
+      "eval_loss": 1.027541160583496,
+      "eval_precision": 0.9974597798475868,
+      "eval_recall": 0.7853333333333333,
+      "eval_runtime": 463.3965,
+      "eval_samples_per_second": 6.474,
+      "eval_steps_per_second": 0.809,
       "step": 280
     },
     {
       "epoch": 0.18,
       "learning_rate": 4.1e-05,
-      "loss": 0.2851,
+      "loss": 0.3962,
       "step": 315
     },
     {
       "epoch": 0.18,
-      "eval_accuracy": 0.9386666666666666,
-      "eval_f1": 0.9357990230286113,
-      "eval_loss": 0.3722746670246124,
-      "eval_precision": 0.9816983894582724,
-      "eval_recall": 0.894,
-      "eval_runtime": 462.4018,
-      "eval_samples_per_second": 6.488,
-      "eval_steps_per_second": 0.811,
+      "eval_accuracy": 0.9496666666666667,
+      "eval_f1": 0.948656919415165,
+      "eval_loss": 0.3296962380409241,
+      "eval_precision": 0.9680777238029147,
+      "eval_recall": 0.93,
+      "eval_runtime": 463.326,
+      "eval_samples_per_second": 6.475,
+      "eval_steps_per_second": 0.809,
       "step": 315
     },
     {
       "epoch": 0.2,
       "learning_rate": 4e-05,
-      "loss": 0.4674,
+      "loss": 0.488,
       "step": 350
     },
     {
       "epoch": 0.2,
-      "eval_accuracy": 0.8966666666666666,
-      "eval_f1": 0.8849294729027467,
-      "eval_loss": 0.9987091422080994,
-      "eval_precision": 0.998324958123953,
-      "eval_recall": 0.7946666666666666,
-      "eval_runtime": 462.5055,
-      "eval_samples_per_second": 6.486,
-      "eval_steps_per_second": 0.811,
+      "eval_accuracy": 0.9443333333333334,
+      "eval_f1": 0.9429839535677706,
+      "eval_loss": 0.4798208773136139,
+      "eval_precision": 0.966410076976907,
+      "eval_recall": 0.9206666666666666,
+      "eval_runtime": 463.3936,
+      "eval_samples_per_second": 6.474,
+      "eval_steps_per_second": 0.809,
       "step": 350
     },
     {
       "epoch": 0.22,
       "learning_rate": 3.9000000000000006e-05,
-      "loss": 0.1749,
+      "loss": 0.4094,
       "step": 385
     },
     {
       "epoch": 0.22,
-      "eval_accuracy": 0.9473333333333334,
-      "eval_f1": 0.9446002805049089,
-      "eval_loss": 0.4473351240158081,
-      "eval_precision": 0.996301775147929,
-      "eval_recall": 0.898,
-      "eval_runtime": 462.5402,
-      "eval_samples_per_second": 6.486,
-      "eval_steps_per_second": 0.811,
+      "eval_accuracy": 0.9096666666666666,
+      "eval_f1": 0.9166922840454964,
+      "eval_loss": 0.5374864339828491,
+      "eval_precision": 0.8505419281232174,
+      "eval_recall": 0.994,
+      "eval_runtime": 463.4888,
+      "eval_samples_per_second": 6.473,
+      "eval_steps_per_second": 0.809,
       "step": 385
     },
     {
       "epoch": 0.24,
       "learning_rate": 3.8e-05,
-      "loss": 0.3134,
+      "loss": 0.2203,
       "step": 420
     },
     {
       "epoch": 0.24,
-      "eval_accuracy": 0.9313333333333333,
-      "eval_f1": 0.9263759828448893,
-      "eval_loss": 0.8257947564125061,
-      "eval_precision": 0.9984591679506933,
-      "eval_recall": 0.864,
-      "eval_runtime": 462.4771,
-      "eval_samples_per_second": 6.487,
-      "eval_steps_per_second": 0.811,
+      "eval_accuracy": 0.957,
+      "eval_f1": 0.958130477117819,
+      "eval_loss": 0.18050691485404968,
+      "eval_precision": 0.9335863377609108,
+      "eval_recall": 0.984,
+      "eval_runtime": 463.3488,
+      "eval_samples_per_second": 6.475,
+      "eval_steps_per_second": 0.809,
       "step": 420
     },
     {
       "epoch": 0.26,
       "learning_rate": 3.7e-05,
-      "loss": 0.4379,
+      "loss": 0.2526,
       "step": 455
     },
     {
       "epoch": 0.26,
-      "eval_accuracy": 0.9496666666666667,
-      "eval_f1": 0.9478050466643623,
-      "eval_loss": 0.34615999460220337,
-      "eval_precision": 0.9842067480258435,
-      "eval_recall": 0.914,
-      "eval_runtime": 462.467,
-      "eval_samples_per_second": 6.487,
-      "eval_steps_per_second": 0.811,
+      "eval_accuracy": 0.9566666666666667,
+      "eval_f1": 0.9579288025889968,
+      "eval_loss": 0.32805779576301575,
+      "eval_precision": 0.9308176100628931,
+      "eval_recall": 0.9866666666666667,
+      "eval_runtime": 464.3941,
+      "eval_samples_per_second": 6.46,
+      "eval_steps_per_second": 0.808,
       "step": 455
     },
     {
       "epoch": 0.28,
       "learning_rate": 3.6e-05,
-      "loss": 0.1028,
+      "loss": 0.1888,
       "step": 490
     },
     {
       "epoch": 0.28,
-      "eval_accuracy": 0.9523333333333334,
-      "eval_f1": 0.9523174391463821,
-      "eval_loss": 0.3040553629398346,
-      "eval_precision": 0.95263509006004,
-      "eval_recall": 0.952,
-      "eval_runtime": 462.402,
-      "eval_samples_per_second": 6.488,
-      "eval_steps_per_second": 0.811,
+      "eval_accuracy": 0.972,
+      "eval_f1": 0.9723502304147466,
+      "eval_loss": 0.15383633971214294,
+      "eval_precision": 0.9603381014304291,
+      "eval_recall": 0.9846666666666667,
+      "eval_runtime": 463.4989,
+      "eval_samples_per_second": 6.473,
+      "eval_steps_per_second": 0.809,
       "step": 490
     },
     {
       "epoch": 0.3,
       "learning_rate": 3.5e-05,
-      "loss": 0.1392,
+      "loss": 0.1859,
       "step": 525
     },
     {
       "epoch": 0.3,
-      "eval_accuracy": 0.9576666666666667,
-      "eval_f1": 0.9566996249573816,
-      "eval_loss": 0.3112805485725403,
-      "eval_precision": 0.9790648988136776,
-      "eval_recall": 0.9353333333333333,
-      "eval_runtime": 463.4665,
-      "eval_samples_per_second": 6.473,
+      "eval_accuracy": 0.9783333333333334,
+      "eval_f1": 0.9781659388646288,
+      "eval_loss": 0.11581222712993622,
+      "eval_precision": 0.985781990521327,
+      "eval_recall": 0.9706666666666667,
+      "eval_runtime": 463.5881,
+      "eval_samples_per_second": 6.471,
       "eval_steps_per_second": 0.809,
       "step": 525
     },
     {
       "epoch": 0.32,
       "learning_rate": 3.4000000000000007e-05,
-      "loss": 0.0944,
+      "loss": 0.1007,
       "step": 560
     },
     {
       "epoch": 0.32,
-      "eval_accuracy": 0.9196666666666666,
-      "eval_f1": 0.9127759681505611,
-      "eval_loss": 0.9487587213516235,
-      "eval_precision": 0.9984164687252574,
-      "eval_recall": 0.8406666666666667,
-      "eval_runtime": 463.9336,
-      "eval_samples_per_second": 6.466,
-      "eval_steps_per_second": 0.808,
+      "eval_accuracy": 0.9753333333333334,
+      "eval_f1": 0.9755129053606882,
+      "eval_loss": 0.14892521500587463,
+      "eval_precision": 0.9684625492772667,
+      "eval_recall": 0.9826666666666667,
+      "eval_runtime": 463.553,
+      "eval_samples_per_second": 6.472,
+      "eval_steps_per_second": 0.809,
       "step": 560
     },
     {
       "epoch": 0.34,
       "learning_rate": 3.3e-05,
-      "loss": 0.1758,
+      "loss": 0.1065,
       "step": 595
     },
     {
       "epoch": 0.34,
-      "eval_accuracy": 0.935,
-      "eval_f1": 0.9306296691568836,
-      "eval_loss": 0.4119901657104492,
-      "eval_precision": 0.9977116704805492,
-      "eval_recall": 0.872,
-      "eval_runtime": 462.719,
-      "eval_samples_per_second": 6.483,
-      "eval_steps_per_second": 0.81,
+      "eval_accuracy": 0.9726666666666667,
+      "eval_f1": 0.9720327421555252,
+      "eval_loss": 0.15965215861797333,
+      "eval_precision": 0.9951117318435754,
+      "eval_recall": 0.95,
+      "eval_runtime": 463.6429,
+      "eval_samples_per_second": 6.47,
+      "eval_steps_per_second": 0.809,
       "step": 595
     },
     {
       "epoch": 0.36,
       "learning_rate": 3.2000000000000005e-05,
-      "loss": 0.1123,
+      "loss": 0.2868,
       "step": 630
     },
     {
       "epoch": 0.36,
-      "eval_accuracy": 0.9673333333333334,
-      "eval_f1": 0.9671361502347419,
-      "eval_loss": 0.18079321086406708,
-      "eval_precision": 0.9730094466936572,
-      "eval_recall": 0.9613333333333334,
-      "eval_runtime": 462.4961,
-      "eval_samples_per_second": 6.487,
-      "eval_steps_per_second": 0.811,
+      "eval_accuracy": 0.9806666666666667,
+      "eval_f1": 0.9807180851063829,
+      "eval_loss": 0.08715511113405228,
+      "eval_precision": 0.9781167108753316,
+      "eval_recall": 0.9833333333333333,
+      "eval_runtime": 463.4149,
+      "eval_samples_per_second": 6.474,
+      "eval_steps_per_second": 0.809,
       "step": 630
     },
     {
       "epoch": 0.38,
       "learning_rate": 3.1e-05,
-      "loss": 0.187,
+      "loss": 0.1818,
       "step": 665
     },
     {
       "epoch": 0.38,
-      "eval_accuracy": 0.9563333333333334,
-      "eval_f1": 0.954936360509116,
-      "eval_loss": 0.3595654368400574,
-      "eval_precision": 0.9864960909737029,
-      "eval_recall": 0.9253333333333333,
-      "eval_runtime": 463.4737,
-      "eval_samples_per_second": 6.473,
-      "eval_steps_per_second": 0.809,
+      "eval_accuracy": 0.9796666666666667,
+      "eval_f1": 0.9795781720790091,
+      "eval_loss": 0.12202201038599014,
+      "eval_precision": 0.9838601210490922,
+      "eval_recall": 0.9753333333333334,
+      "eval_runtime": 464.4798,
+      "eval_samples_per_second": 6.459,
+      "eval_steps_per_second": 0.807,
       "step": 665
     },
     {
       "epoch": 0.4,
       "learning_rate": 3e-05,
-      "loss": 0.1876,
+      "loss": 0.3238,
       "step": 700
     },
     {
       "epoch": 0.4,
-      "eval_accuracy": 0.962,
-      "eval_f1": 0.9621262458471761,
-      "eval_loss": 0.26878979802131653,
-      "eval_precision": 0.9589403973509933,
-      "eval_recall": 0.9653333333333334,
-      "eval_runtime": 462.4658,
-      "eval_samples_per_second": 6.487,
-      "eval_steps_per_second": 0.811,
+      "eval_accuracy": 0.9786666666666667,
+      "eval_f1": 0.9784221173297369,
+      "eval_loss": 0.16317808628082275,
+      "eval_precision": 0.9897680763983628,
+      "eval_recall": 0.9673333333333334,
+      "eval_runtime": 463.2126,
+      "eval_samples_per_second": 6.477,
+      "eval_steps_per_second": 0.81,
       "step": 700
     },
     {
       "epoch": 0.42,
       "learning_rate": 2.9e-05,
-      "loss": 0.1762,
+      "loss": 0.125,
       "step": 735
     },
     {
       "epoch": 0.42,
-      "eval_accuracy": 0.9513333333333334,
-      "eval_f1": 0.949375866851595,
-      "eval_loss": 0.30938494205474854,
-      "eval_precision": 0.9891618497109826,
-      "eval_recall": 0.9126666666666666,
-      "eval_runtime": 462.6352,
-      "eval_samples_per_second": 6.485,
-      "eval_steps_per_second": 0.811,
+      "eval_accuracy": 0.9796666666666667,
+      "eval_f1": 0.9796054831160146,
+      "eval_loss": 0.1086646318435669,
+      "eval_precision": 0.9825620389000671,
+      "eval_recall": 0.9766666666666667,
+      "eval_runtime": 464.4048,
+      "eval_samples_per_second": 6.46,
+      "eval_steps_per_second": 0.807,
       "step": 735
     },
     {
       "epoch": 0.44,
       "learning_rate": 2.8000000000000003e-05,
-      "loss": 0.0164,
+      "loss": 0.1361,
       "step": 770
     },
     {
       "epoch": 0.44,
-      "eval_accuracy": 0.9543333333333334,
-      "eval_f1": 0.9526115530958146,
-      "eval_loss": 0.3230161964893341,
-      "eval_precision": 0.9899352983465133,
-      "eval_recall": 0.918,
-      "eval_runtime": 464.4305,
-      "eval_samples_per_second": 6.46,
-      "eval_steps_per_second": 0.807,
+      "eval_accuracy": 0.976,
+      "eval_f1": 0.9754935330156569,
+      "eval_loss": 0.15513776242733002,
+      "eval_precision": 0.9965229485396384,
+      "eval_recall": 0.9553333333333334,
+      "eval_runtime": 463.6268,
+      "eval_samples_per_second": 6.471,
+      "eval_steps_per_second": 0.809,
       "step": 770
     },
     {
       "epoch": 0.46,
       "learning_rate": 2.7000000000000002e-05,
-      "loss": 0.0903,
+      "loss": 0.1276,
       "step": 805
     },
     {
       "epoch": 0.46,
-      "eval_accuracy": 0.9593333333333334,
-      "eval_f1": 0.9585597826086957,
-      "eval_loss": 0.33148592710494995,
-      "eval_precision": 0.9771468144044322,
-      "eval_recall": 0.9406666666666667,
-      "eval_runtime": 462.7729,
-      "eval_samples_per_second": 6.483,
-      "eval_steps_per_second": 0.81,
+      "eval_accuracy": 0.9683333333333334,
+      "eval_f1": 0.9673875729488499,
+      "eval_loss": 0.20085427165031433,
+      "eval_precision": 0.997169143665959,
+      "eval_recall": 0.9393333333333334,
+      "eval_runtime": 463.7219,
+      "eval_samples_per_second": 6.469,
+      "eval_steps_per_second": 0.809,
       "step": 805
     },
     {
       "epoch": 0.48,
       "learning_rate": 2.6000000000000002e-05,
-      "loss": 0.2401,
+      "loss": 0.1618,
       "step": 840
     },
     {
       "epoch": 0.48,
-      "eval_accuracy": 0.9326666666666666,
-      "eval_f1": 0.9285208775654635,
-      "eval_loss": 0.5261781215667725,
-      "eval_precision": 0.9894419306184012,
-      "eval_recall": 0.8746666666666667,
-      "eval_runtime": 462.0723,
-      "eval_samples_per_second": 6.492,
-      "eval_steps_per_second": 0.812,
+      "eval_accuracy": 0.9766666666666667,
+      "eval_f1": 0.9762066621346024,
+      "eval_loss": 0.12355328351259232,
+      "eval_precision": 0.9958391123439667,
+      "eval_recall": 0.9573333333333334,
+      "eval_runtime": 464.5376,
+      "eval_samples_per_second": 6.458,
+      "eval_steps_per_second": 0.807,
       "step": 840
     },
     {
       "epoch": 0.5,
       "learning_rate": 2.5e-05,
-      "loss": 0.1308,
+      "loss": 0.2574,
       "step": 875
     },
     {
       "epoch": 0.5,
-      "eval_accuracy": 0.922,
-      "eval_f1": 0.9155844155844155,
-      "eval_loss": 0.5081947445869446,
-      "eval_precision": 0.9976415094339622,
-      "eval_recall": 0.846,
-      "eval_runtime": 462.3765,
-      "eval_samples_per_second": 6.488,
-      "eval_steps_per_second": 0.811,
+      "eval_accuracy": 0.9806666666666667,
+      "eval_f1": 0.9804054054054054,
+      "eval_loss": 0.126968115568161,
+      "eval_precision": 0.9938356164383562,
+      "eval_recall": 0.9673333333333334,
+      "eval_runtime": 465.883,
+      "eval_samples_per_second": 6.439,
+      "eval_steps_per_second": 0.805,
       "step": 875
     },
     {
       "epoch": 0.52,
       "learning_rate": 2.4e-05,
-      "loss": 0.1004,
+      "loss": 0.1482,
       "step": 910
     },
     {
       "epoch": 0.52,
-      "eval_accuracy": 0.9353333333333333,
-      "eval_f1": 0.9321203638908327,
-      "eval_loss": 0.6189997792243958,
-      "eval_precision": 0.9808541973490427,
-      "eval_recall": 0.888,
-      "eval_runtime": 462.3735,
-      "eval_samples_per_second": 6.488,
-      "eval_steps_per_second": 0.811,
+      "eval_accuracy": 0.9576666666666667,
+      "eval_f1": 0.9558874609239321,
+      "eval_loss": 0.2774529755115509,
+      "eval_precision": 0.9978245105148659,
+      "eval_recall": 0.9173333333333333,
+      "eval_runtime": 465.4264,
+      "eval_samples_per_second": 6.446,
+      "eval_steps_per_second": 0.806,
       "step": 910
     },
     {
       "epoch": 0.54,
       "learning_rate": 2.3000000000000003e-05,
-      "loss": 0.0982,
+      "loss": 0.1156,
       "step": 945
     },
     {
       "epoch": 0.54,
-      "eval_accuracy": 0.9496666666666667,
-      "eval_f1": 0.9480921278789962,
-      "eval_loss": 0.5868619680404663,
-      "eval_precision": 0.978708303761533,
-      "eval_recall": 0.9193333333333333,
-      "eval_runtime": 462.6069,
-      "eval_samples_per_second": 6.485,
-      "eval_steps_per_second": 0.811,
+      "eval_accuracy": 0.9856666666666667,
+      "eval_f1": 0.9855849815621857,
+      "eval_loss": 0.1439618021249771,
+      "eval_precision": 0.9912339851652057,
+      "eval_recall": 0.98,
+      "eval_runtime": 466.4591,
+      "eval_samples_per_second": 6.431,
+      "eval_steps_per_second": 0.804,
       "step": 945
     },
     {
       "epoch": 0.56,
       "learning_rate": 2.2000000000000003e-05,
-      "loss": 0.1627,
+      "loss": 0.2393,
       "step": 980
     },
     {
       "epoch": 0.56,
-      "eval_accuracy": 0.9503333333333334,
-      "eval_f1": 0.9483177245924385,
-      "eval_loss": 0.5452014803886414,
-      "eval_precision": 0.9884309472161966,
-      "eval_recall": 0.9113333333333333,
-      "eval_runtime": 462.2788,
-      "eval_samples_per_second": 6.49,
-      "eval_steps_per_second": 0.811,
+      "eval_accuracy": 0.9406666666666667,
+      "eval_f1": 0.9369688385269122,
+      "eval_loss": 0.37739551067352295,
+      "eval_precision": 0.9992447129909365,
+      "eval_recall": 0.882,
+      "eval_runtime": 465.7379,
+      "eval_samples_per_second": 6.441,
+      "eval_steps_per_second": 0.805,
       "step": 980
     },
     {
       "epoch": 0.58,
       "learning_rate": 2.1e-05,
-      "loss": 0.2264,
+      "loss": 0.2364,
       "step": 1015
     },
     {
       "epoch": 0.58,
-      "eval_accuracy": 0.962,
-      "eval_f1": 0.9608785175017158,
-      "eval_loss": 0.36828112602233887,
-      "eval_precision": 0.9900990099009901,
-      "eval_recall": 0.9333333333333333,
-      "eval_runtime": 462.546,
-      "eval_samples_per_second": 6.486,
-      "eval_steps_per_second": 0.811,
+      "eval_accuracy": 0.984,
+      "eval_f1": 0.9838601210490923,
+      "eval_loss": 0.0981753021478653,
+      "eval_precision": 0.9925373134328358,
+      "eval_recall": 0.9753333333333334,
+      "eval_runtime": 464.4225,
+      "eval_samples_per_second": 6.46,
+      "eval_steps_per_second": 0.807,
       "step": 1015
     },
     {
       "epoch": 0.6,
       "learning_rate": 2e-05,
-      "loss": 0.2683,
+      "loss": 0.1246,
       "step": 1050
     },
     {
       "epoch": 0.6,
-      "eval_accuracy": 0.959,
-      "eval_f1": 0.9577464788732394,
-      "eval_loss": 0.2027631402015686,
-      "eval_precision": 0.9879518072289156,
-      "eval_recall": 0.9293333333333333,
-      "eval_runtime": 462.4537,
-      "eval_samples_per_second": 6.487,
-      "eval_steps_per_second": 0.811,
+      "eval_accuracy": 0.985,
+      "eval_f1": 0.9848637739656912,
+      "eval_loss": 0.08204901963472366,
+      "eval_precision": 0.9938900203665988,
+      "eval_recall": 0.976,
+      "eval_runtime": 466.5569,
+      "eval_samples_per_second": 6.43,
+      "eval_steps_per_second": 0.804,
       "step": 1050
     },
     {
       "epoch": 0.62,
       "learning_rate": 1.9e-05,
-      "loss": 0.088,
+      "loss": 0.1411,
       "step": 1085
     },
     {
       "epoch": 0.62,
-      "eval_accuracy": 0.937,
-      "eval_f1": 0.9328596802841918,
-      "eval_loss": 0.5130247473716736,
-      "eval_precision": 0.9984790874524715,
-      "eval_recall": 0.8753333333333333,
-      "eval_runtime": 462.3506,
-      "eval_samples_per_second": 6.489,
-      "eval_steps_per_second": 0.811,
+      "eval_accuracy": 0.9873333333333333,
+      "eval_f1": 0.9872824631860776,
+      "eval_loss": 0.05377618223428726,
+      "eval_precision": 0.991263440860215,
+      "eval_recall": 0.9833333333333333,
+      "eval_runtime": 464.6089,
+      "eval_samples_per_second": 6.457,
+      "eval_steps_per_second": 0.807,
       "step": 1085
     },
     {
       "epoch": 0.64,
       "learning_rate": 1.8e-05,
-      "loss": 0.214,
+      "loss": 0.2055,
       "step": 1120
     },
     {
       "epoch": 0.64,
-      "eval_accuracy": 0.9443333333333334,
-      "eval_f1": 0.9413829413829414,
-      "eval_loss": 0.38535651564598083,
-      "eval_precision": 0.994069681245367,
-      "eval_recall": 0.894,
-      "eval_runtime": 462.2352,
-      "eval_samples_per_second": 6.49,
-      "eval_steps_per_second": 0.811,
+      "eval_accuracy": 0.9736666666666667,
+      "eval_f1": 0.9730099077553809,
+      "eval_loss": 0.15216030180454254,
+      "eval_precision": 0.9978976874562018,
+      "eval_recall": 0.9493333333333334,
+      "eval_runtime": 465.4747,
+      "eval_samples_per_second": 6.445,
+      "eval_steps_per_second": 0.806,
       "step": 1120
     },
     {
       "epoch": 0.66,
       "learning_rate": 1.7000000000000003e-05,
-      "loss": 0.0811,
+      "loss": 0.3018,
       "step": 1155
     },
     {
       "epoch": 0.66,
-      "eval_accuracy": 0.9563333333333334,
-      "eval_f1": 0.954936360509116,
-      "eval_loss": 0.2761794328689575,
-      "eval_precision": 0.9864960909737029,
-      "eval_recall": 0.9253333333333333,
-      "eval_runtime": 463.2198,
-      "eval_samples_per_second": 6.476,
-      "eval_steps_per_second": 0.81,
+      "eval_accuracy": 0.9813333333333333,
+      "eval_f1": 0.9815059445178336,
+      "eval_loss": 0.07627255469560623,
+      "eval_precision": 0.9725130890052356,
+      "eval_recall": 0.9906666666666667,
+      "eval_runtime": 464.4389,
+      "eval_samples_per_second": 6.459,
+      "eval_steps_per_second": 0.807,
       "step": 1155
     },
     {
       "epoch": 0.68,
       "learning_rate": 1.6000000000000003e-05,
-      "loss": 0.0716,
+      "loss": 0.1702,
       "step": 1190
     },
     {
       "epoch": 0.68,
-      "eval_accuracy": 0.9603333333333334,
-      "eval_f1": 0.9593717992488903,
-      "eval_loss": 0.3206270635128021,
-      "eval_precision": 0.9832050384884534,
-      "eval_recall": 0.9366666666666666,
-      "eval_runtime": 461.5741,
-      "eval_samples_per_second": 6.499,
-      "eval_steps_per_second": 0.812,
+      "eval_accuracy": 0.9873333333333333,
+      "eval_f1": 0.9873586161011311,
+      "eval_loss": 0.07290682196617126,
+      "eval_precision": 0.9853917662682603,
+      "eval_recall": 0.9893333333333333,
+      "eval_runtime": 464.5835,
+      "eval_samples_per_second": 6.457,
+      "eval_steps_per_second": 0.807,
       "step": 1190
     },
     {
       "epoch": 0.7,
       "learning_rate": 1.5e-05,
-      "loss": 0.0843,
+      "loss": 0.2085,
       "step": 1225
     },
     {
       "epoch": 0.7,
-      "eval_accuracy": 0.9546666666666667,
-      "eval_f1": 0.953103448275862,
-      "eval_loss": 0.38527336716651917,
-      "eval_precision": 0.9871428571428571,
-      "eval_recall": 0.9213333333333333,
-      "eval_runtime": 462.2164,
-      "eval_samples_per_second": 6.49,
-      "eval_steps_per_second": 0.811,
+      "eval_accuracy": 0.986,
+      "eval_f1": 0.9859060402684564,
+      "eval_loss": 0.08615541458129883,
+      "eval_precision": 0.9925675675675676,
+      "eval_recall": 0.9793333333333333,
+      "eval_runtime": 464.5251,
+      "eval_samples_per_second": 6.458,
+      "eval_steps_per_second": 0.807,
       "step": 1225
     },
     {
       "epoch": 0.72,
       "learning_rate": 1.4000000000000001e-05,
-      "loss": 0.0744,
+      "loss": 0.0899,
       "step": 1260
     },
     {
       "epoch": 0.72,
-      "eval_accuracy": 0.9556666666666667,
-      "eval_f1": 0.9542168674698795,
-      "eval_loss": 0.4054282307624817,
-      "eval_precision": 0.9864768683274021,
-      "eval_recall": 0.924,
-      "eval_runtime": 461.3748,
-      "eval_samples_per_second": 6.502,
-      "eval_steps_per_second": 0.813,
+      "eval_accuracy": 0.987,
+      "eval_f1": 0.9869782971619365,
+      "eval_loss": 0.07593820989131927,
+      "eval_precision": 0.988628762541806,
+      "eval_recall": 0.9853333333333333,
+      "eval_runtime": 464.4867,
+      "eval_samples_per_second": 6.459,
+      "eval_steps_per_second": 0.807,
       "step": 1260
     },
     {
       "epoch": 0.74,
       "learning_rate": 1.3000000000000001e-05,
-      "loss": 0.0748,
+      "loss": 0.212,
       "step": 1295
     },
     {
       "epoch": 0.74,
-      "eval_accuracy": 0.9476666666666667,
-      "eval_f1": 0.9450472523626182,
-      "eval_loss": 0.4932408928871155,
-      "eval_precision": 0.9948415622697127,
-      "eval_recall": 0.9,
-      "eval_runtime": 462.1327,
-      "eval_samples_per_second": 6.492,
-      "eval_steps_per_second": 0.811,
+      "eval_accuracy": 0.9846666666666667,
+      "eval_f1": 0.9847277556440903,
+      "eval_loss": 0.08726092427968979,
+      "eval_precision": 0.9808201058201058,
+      "eval_recall": 0.9886666666666667,
+      "eval_runtime": 463.8528,
+      "eval_samples_per_second": 6.468,
+      "eval_steps_per_second": 0.808,
       "step": 1295
     },
     {
       "epoch": 0.76,
       "learning_rate": 1.2e-05,
-      "loss": 0.0181,
+      "loss": 0.0459,
       "step": 1330
     },
     {
       "epoch": 0.76,
-      "eval_accuracy": 0.95,
-      "eval_f1": 0.9479889042995839,
-      "eval_loss": 0.4586262106895447,
-      "eval_precision": 0.9877167630057804,
-      "eval_recall": 0.9113333333333333,
-      "eval_runtime": 462.3672,
-      "eval_samples_per_second": 6.488,
-      "eval_steps_per_second": 0.811,
+      "eval_accuracy": 0.981,
+      "eval_f1": 0.9807237064592493,
+      "eval_loss": 0.11619190126657486,
+      "eval_precision": 0.9951956074124915,
+      "eval_recall": 0.9666666666666667,
+      "eval_runtime": 463.7918,
+      "eval_samples_per_second": 6.468,
+      "eval_steps_per_second": 0.809,
       "step": 1330
     },
     {
       "epoch": 0.78,
       "learning_rate": 1.1000000000000001e-05,
-      "loss": 0.098,
+      "loss": 0.2035,
       "step": 1365
     },
     {
       "epoch": 0.78,
-      "eval_accuracy": 0.9503333333333334,
-      "eval_f1": 0.9479566887879846,
-      "eval_loss": 0.4024898409843445,
-      "eval_precision": 0.9955979457079971,
-      "eval_recall": 0.9046666666666666,
-      "eval_runtime": 461.9999,
-      "eval_samples_per_second": 6.494,
-      "eval_steps_per_second": 0.812,
+      "eval_accuracy": 0.9876666666666667,
+      "eval_f1": 0.9875797247398456,
+      "eval_loss": 0.07956338673830032,
+      "eval_precision": 0.9945909398242055,
+      "eval_recall": 0.9806666666666667,
+      "eval_runtime": 464.4206,
+      "eval_samples_per_second": 6.46,
+      "eval_steps_per_second": 0.807,
       "step": 1365
     },
     {
       "epoch": 0.8,
       "learning_rate": 1e-05,
-      "loss": 0.0752,
+      "loss": 0.0942,
       "step": 1400
     },
     {
       "epoch": 0.8,
-      "eval_accuracy": 0.955,
-      "eval_f1": 0.9534322180062091,
-      "eval_loss": 0.2519637942314148,
-      "eval_precision": 0.9878484631879915,
-      "eval_recall": 0.9213333333333333,
-      "eval_runtime": 462.3269,
-      "eval_samples_per_second": 6.489,
-      "eval_steps_per_second": 0.811,
+      "eval_accuracy": 0.979,
+      "eval_f1": 0.979269496544916,
+      "eval_loss": 0.09173166751861572,
+      "eval_precision": 0.9668615984405458,
+      "eval_recall": 0.992,
+      "eval_runtime": 464.6027,
+      "eval_samples_per_second": 6.457,
+      "eval_steps_per_second": 0.807,
       "step": 1400
     },
     {
       "epoch": 0.82,
       "learning_rate": 9e-06,
-      "loss": 0.0575,
+      "loss": 0.161,
       "step": 1435
     },
     {
       "epoch": 0.82,
-      "eval_accuracy": 0.959,
-      "eval_f1": 0.958120531154239,
-      "eval_loss": 0.24917536973953247,
-      "eval_precision": 0.9791231732776617,
-      "eval_recall": 0.938,
-      "eval_runtime": 462.2475,
-      "eval_samples_per_second": 6.49,
-      "eval_steps_per_second": 0.811,
+      "eval_accuracy": 0.9873333333333333,
+      "eval_f1": 0.9872397582269979,
+      "eval_loss": 0.06276000291109085,
+      "eval_precision": 0.9945872801082544,
+      "eval_recall": 0.98,
+      "eval_runtime": 463.3979,
+      "eval_samples_per_second": 6.474,
+      "eval_steps_per_second": 0.809,
       "step": 1435
     },
     {
       "epoch": 0.84,
       "learning_rate": 8.000000000000001e-06,
-      "loss": 0.0691,
+      "loss": 0.0365,
       "step": 1470
     },
     {
       "epoch": 0.84,
-      "eval_accuracy": 0.9576666666666667,
-      "eval_f1": 0.9564322469982849,
-      "eval_loss": 0.3299550414085388,
-      "eval_precision": 0.9851590106007068,
-      "eval_recall": 0.9293333333333333,
-      "eval_runtime": 463.7914,
-      "eval_samples_per_second": 6.468,
+      "eval_accuracy": 0.9843333333333333,
+      "eval_f1": 0.9841162554917202,
+      "eval_loss": 0.08324441313743591,
+      "eval_precision": 0.997943797121316,
+      "eval_recall": 0.9706666666666667,
+      "eval_runtime": 463.6189,
+      "eval_samples_per_second": 6.471,
       "eval_steps_per_second": 0.809,
       "step": 1470
     },
     {
       "epoch": 0.86,
       "learning_rate": 7.000000000000001e-06,
-      "loss": 0.0617,
+      "loss": 0.0508,
       "step": 1505
     },
     {
       "epoch": 0.86,
-      "eval_accuracy": 0.957,
-      "eval_f1": 0.9556853315012023,
-      "eval_loss": 0.33974531292915344,
-      "eval_precision": 0.9858256555634302,
-      "eval_recall": 0.9273333333333333,
-      "eval_runtime": 462.1154,
-      "eval_samples_per_second": 6.492,
-      "eval_steps_per_second": 0.811,
+      "eval_accuracy": 0.9843333333333333,
+      "eval_f1": 0.9841162554917202,
+      "eval_loss": 0.09412873536348343,
+      "eval_precision": 0.997943797121316,
+      "eval_recall": 0.9706666666666667,
+      "eval_runtime": 466.9343,
+      "eval_samples_per_second": 6.425,
+      "eval_steps_per_second": 0.803,
       "step": 1505
     },
     {
       "epoch": 0.88,
       "learning_rate": 6e-06,
-      "loss": 0.0392,
+      "loss": 0.0597,
       "step": 1540
     },
     {
       "epoch": 0.88,
-      "eval_accuracy": 0.9573333333333334,
-      "eval_f1": 0.9561042524005487,
-      "eval_loss": 0.3205489218235016,
-      "eval_precision": 0.9844632768361582,
-      "eval_recall": 0.9293333333333333,
-      "eval_runtime": 463.3482,
-      "eval_samples_per_second": 6.475,
-      "eval_steps_per_second": 0.809,
+      "eval_accuracy": 0.9873333333333333,
+      "eval_f1": 0.9872994652406418,
+      "eval_loss": 0.05775593966245651,
+      "eval_precision": 0.989946380697051,
+      "eval_recall": 0.9846666666666667,
+      "eval_runtime": 464.2967,
+      "eval_samples_per_second": 6.461,
+      "eval_steps_per_second": 0.808,
       "step": 1540
     },
     {
       "epoch": 0.9,
       "learning_rate": 5e-06,
-      "loss": 0.0386,
+      "loss": 0.0055,
       "step": 1575
     },
     {
       "epoch": 0.9,
-      "eval_accuracy": 0.958,
-      "eval_f1": 0.9571428571428571,
-      "eval_loss": 0.27690985798835754,
-      "eval_precision": 0.9770833333333333,
-      "eval_recall": 0.938,
-      "eval_runtime": 462.2334,
-      "eval_samples_per_second": 6.49,
-      "eval_steps_per_second": 0.811,
+      "eval_accuracy": 0.9863333333333333,
+      "eval_f1": 0.9861813279406809,
+      "eval_loss": 0.07944045215845108,
+      "eval_precision": 0.9972733469665985,
+      "eval_recall": 0.9753333333333334,
+      "eval_runtime": 464.3973,
+      "eval_samples_per_second": 6.46,
+      "eval_steps_per_second": 0.807,
       "step": 1575
     },
     {
       "epoch": 0.92,
       "learning_rate": 4.000000000000001e-06,
-      "loss": 0.0334,
+      "loss": 0.0681,
       "step": 1610
     },
     {
       "epoch": 0.92,
-      "eval_accuracy": 0.9573333333333334,
-      "eval_f1": 0.9562243502051984,
-      "eval_loss": 0.30371883511543274,
-      "eval_precision": 0.9817415730337079,
-      "eval_recall": 0.932,
-      "eval_runtime": 462.4404,
-      "eval_samples_per_second": 6.487,
-      "eval_steps_per_second": 0.811,
+      "eval_accuracy": 0.9873333333333333,
+      "eval_f1": 0.9872139973082099,
+      "eval_loss": 0.07313308119773865,
+      "eval_precision": 0.9966032608695652,
+      "eval_recall": 0.978,
+      "eval_runtime": 464.8711,
+      "eval_samples_per_second": 6.453,
+      "eval_steps_per_second": 0.807,
       "step": 1610
     },
     {
       "epoch": 0.94,
       "learning_rate": 3e-06,
-      "loss": 0.1167,
+      "loss": 0.0978,
       "step": 1645
     },
     {
       "epoch": 0.94,
-      "eval_accuracy": 0.9593333333333334,
-      "eval_f1": 0.9583333333333333,
-      "eval_loss": 0.3056192100048065,
-      "eval_precision": 0.9824929971988795,
-      "eval_recall": 0.9353333333333333,
-      "eval_runtime": 461.9141,
-      "eval_samples_per_second": 6.495,
-      "eval_steps_per_second": 0.812,
+      "eval_accuracy": 0.9883333333333333,
+      "eval_f1": 0.9883138564273791,
+      "eval_loss": 0.058573223650455475,
+      "eval_precision": 0.9899665551839465,
+      "eval_recall": 0.9866666666666667,
+      "eval_runtime": 465.0949,
+      "eval_samples_per_second": 6.45,
+      "eval_steps_per_second": 0.806,
       "step": 1645
     },
     {
       "epoch": 0.96,
       "learning_rate": 2.0000000000000003e-06,
-      "loss": 0.0505,
+      "loss": 0.1392,
       "step": 1680
     },
     {
       "epoch": 0.96,
-      "eval_accuracy": 0.953,
-      "eval_f1": 0.9510586601874348,
-      "eval_loss": 0.42186784744262695,
-      "eval_precision": 0.9920347574221579,
-      "eval_recall": 0.9133333333333333,
-      "eval_runtime": 462.3061,
-      "eval_samples_per_second": 6.489,
-      "eval_steps_per_second": 0.811,
+      "eval_accuracy": 0.9883333333333333,
+      "eval_f1": 0.9883060474440362,
+      "eval_loss": 0.055864058434963226,
+      "eval_precision": 0.9906229068988613,
+      "eval_recall": 0.986,
+      "eval_runtime": 464.3364,
+      "eval_samples_per_second": 6.461,
+      "eval_steps_per_second": 0.808,
       "step": 1680
     },
     {
       "epoch": 0.98,
       "learning_rate": 1.0000000000000002e-06,
-      "loss": 0.0468,
+      "loss": 0.0432,
       "step": 1715
     },
     {
       "epoch": 0.98,
-      "eval_accuracy": 0.9576666666666667,
-      "eval_f1": 0.9562822719449227,
-      "eval_loss": 0.3499450385570526,
-      "eval_precision": 0.9886120996441281,
-      "eval_recall": 0.926,
-      "eval_runtime": 462.275,
-      "eval_samples_per_second": 6.49,
-      "eval_steps_per_second": 0.811,
+      "eval_accuracy": 0.9883333333333333,
+      "eval_f1": 0.9883060474440362,
+      "eval_loss": 0.055420782417058945,
+      "eval_precision": 0.9906229068988613,
+      "eval_recall": 0.986,
+      "eval_runtime": 464.6017,
+      "eval_samples_per_second": 6.457,
+      "eval_steps_per_second": 0.807,
       "step": 1715
     },
     {
       "epoch": 1.0,
       "learning_rate": 0.0,
-      "loss": 0.0429,
+      "loss": 0.0006,
       "step": 1750
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.9576666666666667,
-      "eval_f1": 0.9562822719449227,
-      "eval_loss": 0.34879612922668457,
-      "eval_precision": 0.9886120996441281,
-      "eval_recall": 0.926,
-      "eval_runtime": 462.1636,
-      "eval_samples_per_second": 6.491,
-      "eval_steps_per_second": 0.811,
+      "eval_accuracy": 0.988,
+      "eval_f1": 0.9879679144385026,
+      "eval_loss": 0.05567142367362976,
+      "eval_precision": 0.9906166219839142,
+      "eval_recall": 0.9853333333333333,
+      "eval_runtime": 464.5424,
+      "eval_samples_per_second": 6.458,
+      "eval_steps_per_second": 0.807,
       "step": 1750
     }
   ],