{
  "best_metric": 1.0832968950271606,
  "best_model_checkpoint": "Tether2/checkpoint-774",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 774,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.046511627906976744,
      "grad_norm": 3.96823787689209,
      "learning_rate": 7.692307692307694e-06,
      "loss": 3.2522,
      "step": 12
    },
    {
      "epoch": 0.09302325581395349,
      "grad_norm": 5.03609561920166,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 3.2157,
      "step": 24
    },
    {
      "epoch": 0.13953488372093023,
      "grad_norm": 6.75431489944458,
      "learning_rate": 2.307692307692308e-05,
      "loss": 3.1114,
      "step": 36
    },
    {
      "epoch": 0.18604651162790697,
      "grad_norm": 22.154630661010742,
      "learning_rate": 3.0769230769230774e-05,
      "loss": 2.9807,
      "step": 48
    },
    {
      "epoch": 0.23255813953488372,
      "grad_norm": 9.958882331848145,
      "learning_rate": 3.846153846153846e-05,
      "loss": 2.8858,
      "step": 60
    },
    {
      "epoch": 0.27906976744186046,
      "grad_norm": 8.20565128326416,
      "learning_rate": 4.615384615384616e-05,
      "loss": 2.7925,
      "step": 72
    },
    {
      "epoch": 0.32558139534883723,
      "grad_norm": 9.204078674316406,
      "learning_rate": 4.9568965517241384e-05,
      "loss": 2.8233,
      "step": 84
    },
    {
      "epoch": 0.37209302325581395,
      "grad_norm": 10.973845481872559,
      "learning_rate": 4.870689655172414e-05,
      "loss": 2.8384,
      "step": 96
    },
    {
      "epoch": 0.4186046511627907,
      "grad_norm": 9.10534381866455,
      "learning_rate": 4.78448275862069e-05,
      "loss": 2.6588,
      "step": 108
    },
    {
      "epoch": 0.46511627906976744,
      "grad_norm": 7.395918846130371,
      "learning_rate": 4.698275862068966e-05,
      "loss": 2.5407,
      "step": 120
    },
    {
      "epoch": 0.5116279069767442,
      "grad_norm": 12.590022087097168,
      "learning_rate": 4.612068965517242e-05,
      "loss": 2.4686,
      "step": 132
    },
    {
      "epoch": 0.5581395348837209,
      "grad_norm": 8.628605842590332,
      "learning_rate": 4.5258620689655176e-05,
      "loss": 2.3784,
      "step": 144
    },
    {
      "epoch": 0.6046511627906976,
      "grad_norm": 12.470245361328125,
      "learning_rate": 4.4396551724137933e-05,
      "loss": 2.2395,
      "step": 156
    },
    {
      "epoch": 0.6511627906976745,
      "grad_norm": 10.687325477600098,
      "learning_rate": 4.353448275862069e-05,
      "loss": 2.3603,
      "step": 168
    },
    {
      "epoch": 0.6976744186046512,
      "grad_norm": 12.147785186767578,
      "learning_rate": 4.267241379310345e-05,
      "loss": 2.3779,
      "step": 180
    },
    {
      "epoch": 0.7441860465116279,
      "grad_norm": 8.938596725463867,
      "learning_rate": 4.1810344827586205e-05,
      "loss": 2.0315,
      "step": 192
    },
    {
      "epoch": 0.7906976744186046,
      "grad_norm": 16.89861488342285,
      "learning_rate": 4.094827586206897e-05,
      "loss": 1.8416,
      "step": 204
    },
    {
      "epoch": 0.8372093023255814,
      "grad_norm": 25.249252319335938,
      "learning_rate": 4.0086206896551726e-05,
      "loss": 2.2595,
      "step": 216
    },
    {
      "epoch": 0.8837209302325582,
      "grad_norm": 19.04043960571289,
      "learning_rate": 3.922413793103448e-05,
      "loss": 2.0284,
      "step": 228
    },
    {
      "epoch": 0.9302325581395349,
      "grad_norm": 19.253995895385742,
      "learning_rate": 3.8362068965517246e-05,
      "loss": 1.9197,
      "step": 240
    },
    {
      "epoch": 0.9767441860465116,
      "grad_norm": 11.264032363891602,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 1.9238,
      "step": 252
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5155038759689923,
      "eval_f1_macro": 0.25891991433400224,
      "eval_f1_micro": 0.5155038759689923,
      "eval_f1_weighted": 0.46535411334465737,
      "eval_loss": 1.7225582599639893,
      "eval_precision_macro": 0.2992259890948827,
      "eval_precision_micro": 0.5155038759689923,
      "eval_precision_weighted": 0.4992061498287774,
      "eval_recall_macro": 0.27495621077215004,
      "eval_recall_micro": 0.5155038759689923,
      "eval_recall_weighted": 0.5155038759689923,
      "eval_runtime": 69.7638,
      "eval_samples_per_second": 7.396,
      "eval_steps_per_second": 0.473,
      "step": 258
    },
    {
      "epoch": 1.0232558139534884,
      "grad_norm": 11.877735137939453,
      "learning_rate": 3.663793103448276e-05,
      "loss": 1.6197,
      "step": 264
    },
    {
      "epoch": 1.069767441860465,
      "grad_norm": 15.443757057189941,
      "learning_rate": 3.5775862068965524e-05,
      "loss": 1.7034,
      "step": 276
    },
    {
      "epoch": 1.1162790697674418,
      "grad_norm": 20.39283561706543,
      "learning_rate": 3.4913793103448275e-05,
      "loss": 1.4275,
      "step": 288
    },
    {
      "epoch": 1.1627906976744187,
      "grad_norm": 21.803442001342773,
      "learning_rate": 3.405172413793103e-05,
      "loss": 1.4556,
      "step": 300
    },
    {
      "epoch": 1.2093023255813953,
      "grad_norm": 28.840351104736328,
      "learning_rate": 3.3189655172413796e-05,
      "loss": 1.6046,
      "step": 312
    },
    {
      "epoch": 1.255813953488372,
      "grad_norm": 12.907221794128418,
      "learning_rate": 3.232758620689655e-05,
      "loss": 1.579,
      "step": 324
    },
    {
      "epoch": 1.302325581395349,
      "grad_norm": 14.40406322479248,
      "learning_rate": 3.146551724137931e-05,
      "loss": 1.385,
      "step": 336
    },
    {
      "epoch": 1.3488372093023255,
      "grad_norm": 18.017547607421875,
      "learning_rate": 3.060344827586207e-05,
      "loss": 1.4536,
      "step": 348
    },
    {
      "epoch": 1.3953488372093024,
      "grad_norm": 39.87833023071289,
      "learning_rate": 2.974137931034483e-05,
      "loss": 1.5883,
      "step": 360
    },
    {
      "epoch": 1.441860465116279,
      "grad_norm": 19.605663299560547,
      "learning_rate": 2.8879310344827588e-05,
      "loss": 1.5453,
      "step": 372
    },
    {
      "epoch": 1.4883720930232558,
      "grad_norm": 12.39608383178711,
      "learning_rate": 2.8017241379310345e-05,
      "loss": 1.3432,
      "step": 384
    },
    {
      "epoch": 1.5348837209302326,
      "grad_norm": 20.467025756835938,
      "learning_rate": 2.7155172413793105e-05,
      "loss": 1.4855,
      "step": 396
    },
    {
      "epoch": 1.5813953488372094,
      "grad_norm": 12.10073184967041,
      "learning_rate": 2.6293103448275862e-05,
      "loss": 1.1955,
      "step": 408
    },
    {
      "epoch": 1.627906976744186,
      "grad_norm": 21.128217697143555,
      "learning_rate": 2.543103448275862e-05,
      "loss": 1.3656,
      "step": 420
    },
    {
      "epoch": 1.6744186046511627,
      "grad_norm": 27.748998641967773,
      "learning_rate": 2.456896551724138e-05,
      "loss": 1.403,
      "step": 432
    },
    {
      "epoch": 1.7209302325581395,
      "grad_norm": 33.165916442871094,
      "learning_rate": 2.370689655172414e-05,
      "loss": 1.2075,
      "step": 444
    },
    {
      "epoch": 1.7674418604651163,
      "grad_norm": 23.034250259399414,
      "learning_rate": 2.2844827586206897e-05,
      "loss": 1.3793,
      "step": 456
    },
    {
      "epoch": 1.8139534883720931,
      "grad_norm": 26.05168342590332,
      "learning_rate": 2.1982758620689654e-05,
      "loss": 1.1603,
      "step": 468
    },
    {
      "epoch": 1.8604651162790697,
      "grad_norm": 30.397899627685547,
      "learning_rate": 2.1120689655172415e-05,
      "loss": 1.246,
      "step": 480
    },
    {
      "epoch": 1.9069767441860463,
      "grad_norm": 26.444442749023438,
      "learning_rate": 2.0258620689655172e-05,
      "loss": 1.5224,
      "step": 492
    },
    {
      "epoch": 1.9534883720930232,
      "grad_norm": 12.157238006591797,
      "learning_rate": 1.9396551724137932e-05,
      "loss": 1.2578,
      "step": 504
    },
    {
      "epoch": 2.0,
      "grad_norm": 7.6723833084106445,
      "learning_rate": 1.8534482758620693e-05,
      "loss": 1.0881,
      "step": 516
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.6337209302325582,
      "eval_f1_macro": 0.38147868610651525,
      "eval_f1_micro": 0.6337209302325582,
      "eval_f1_weighted": 0.606852249582538,
      "eval_loss": 1.1795549392700195,
      "eval_precision_macro": 0.4036122122616632,
      "eval_precision_micro": 0.6337209302325582,
      "eval_precision_weighted": 0.6131562523466949,
      "eval_recall_macro": 0.39422572999423094,
      "eval_recall_micro": 0.6337209302325582,
      "eval_recall_weighted": 0.6337209302325582,
      "eval_runtime": 71.7188,
      "eval_samples_per_second": 7.195,
      "eval_steps_per_second": 0.46,
      "step": 516
    },
    {
      "epoch": 2.046511627906977,
      "grad_norm": 24.36311149597168,
      "learning_rate": 1.767241379310345e-05,
      "loss": 0.9298,
      "step": 528
    },
    {
      "epoch": 2.0930232558139537,
      "grad_norm": 16.763669967651367,
      "learning_rate": 1.6810344827586207e-05,
      "loss": 0.9922,
      "step": 540
    },
    {
      "epoch": 2.13953488372093,
      "grad_norm": 26.640941619873047,
      "learning_rate": 1.5948275862068967e-05,
      "loss": 0.9947,
      "step": 552
    },
    {
      "epoch": 2.186046511627907,
      "grad_norm": 34.96234893798828,
      "learning_rate": 1.5086206896551724e-05,
      "loss": 0.8946,
      "step": 564
    },
    {
      "epoch": 2.2325581395348837,
      "grad_norm": 24.793346405029297,
      "learning_rate": 1.4224137931034485e-05,
      "loss": 0.9729,
      "step": 576
    },
    {
      "epoch": 2.2790697674418605,
      "grad_norm": 8.405088424682617,
      "learning_rate": 1.336206896551724e-05,
      "loss": 0.8749,
      "step": 588
    },
    {
      "epoch": 2.3255813953488373,
      "grad_norm": 25.962703704833984,
      "learning_rate": 1.25e-05,
      "loss": 0.9156,
      "step": 600
    },
    {
      "epoch": 2.3720930232558137,
      "grad_norm": 5.019805431365967,
      "learning_rate": 1.163793103448276e-05,
      "loss": 0.7937,
      "step": 612
    },
    {
      "epoch": 2.4186046511627906,
      "grad_norm": 28.168231964111328,
      "learning_rate": 1.0775862068965516e-05,
      "loss": 0.9856,
      "step": 624
    },
    {
      "epoch": 2.4651162790697674,
      "grad_norm": 21.698854446411133,
      "learning_rate": 9.913793103448277e-06,
      "loss": 0.7219,
      "step": 636
    },
    {
      "epoch": 2.511627906976744,
      "grad_norm": 18.83635139465332,
      "learning_rate": 9.051724137931036e-06,
      "loss": 0.9052,
      "step": 648
    },
    {
      "epoch": 2.558139534883721,
      "grad_norm": 14.555943489074707,
      "learning_rate": 8.189655172413793e-06,
      "loss": 0.8442,
      "step": 660
    },
    {
      "epoch": 2.604651162790698,
      "grad_norm": 28.036245346069336,
      "learning_rate": 7.3275862068965514e-06,
      "loss": 0.8283,
      "step": 672
    },
    {
      "epoch": 2.6511627906976747,
      "grad_norm": 17.01114845275879,
      "learning_rate": 6.465517241379311e-06,
      "loss": 0.8232,
      "step": 684
    },
    {
      "epoch": 2.697674418604651,
      "grad_norm": 19.991779327392578,
      "learning_rate": 5.603448275862069e-06,
      "loss": 0.7628,
      "step": 696
    },
    {
      "epoch": 2.744186046511628,
      "grad_norm": 26.620668411254883,
      "learning_rate": 4.741379310344828e-06,
      "loss": 0.7945,
      "step": 708
    },
    {
      "epoch": 2.7906976744186047,
      "grad_norm": 16.948158264160156,
      "learning_rate": 3.8793103448275865e-06,
      "loss": 0.7642,
      "step": 720
    },
    {
      "epoch": 2.8372093023255816,
      "grad_norm": 5.877094745635986,
      "learning_rate": 3.017241379310345e-06,
      "loss": 0.6525,
      "step": 732
    },
    {
      "epoch": 2.883720930232558,
      "grad_norm": 9.920417785644531,
      "learning_rate": 2.1551724137931035e-06,
      "loss": 0.7873,
      "step": 744
    },
    {
      "epoch": 2.9302325581395348,
      "grad_norm": 25.48910140991211,
      "learning_rate": 1.293103448275862e-06,
      "loss": 0.689,
      "step": 756
    },
    {
      "epoch": 2.9767441860465116,
      "grad_norm": 11.988759994506836,
      "learning_rate": 4.3103448275862073e-07,
      "loss": 0.7837,
      "step": 768
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.6531007751937985,
      "eval_f1_macro": 0.41533378210893174,
      "eval_f1_micro": 0.6531007751937985,
      "eval_f1_weighted": 0.6340857128792562,
      "eval_loss": 1.0832968950271606,
      "eval_precision_macro": 0.43774810378738616,
      "eval_precision_micro": 0.6531007751937985,
      "eval_precision_weighted": 0.6386639752005375,
      "eval_recall_macro": 0.4299005706500963,
      "eval_recall_micro": 0.6531007751937985,
      "eval_recall_weighted": 0.6531007751937985,
      "eval_runtime": 74.0841,
      "eval_samples_per_second": 6.965,
      "eval_steps_per_second": 0.445,
      "step": 774
    }
  ],
  "logging_steps": 12,
  "max_steps": 774,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.01
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 406791552950784.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}