{
  "best_metric": 0.646373450756073,
  "best_model_checkpoint": "knowledge-Distillation/checkpoint-500",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.048,
      "grad_norm": 4.009671688079834,
      "learning_rate": 4.800000000000001e-06,
      "loss": 1.1378,
      "step": 12
    },
    {
      "epoch": 0.096,
      "grad_norm": 1.55279541015625,
      "learning_rate": 9.600000000000001e-06,
      "loss": 1.1198,
      "step": 24
    },
    {
      "epoch": 0.144,
      "grad_norm": 2.4240620136260986,
      "learning_rate": 1.44e-05,
      "loss": 1.0868,
      "step": 36
    },
    {
      "epoch": 0.192,
      "grad_norm": 4.712751388549805,
      "learning_rate": 1.9200000000000003e-05,
      "loss": 1.0798,
      "step": 48
    },
    {
      "epoch": 0.24,
      "grad_norm": 12.531917572021484,
      "learning_rate": 2.4e-05,
      "loss": 1.0255,
      "step": 60
    },
    {
      "epoch": 0.288,
      "grad_norm": 7.460992336273193,
      "learning_rate": 2.88e-05,
      "loss": 1.0152,
      "step": 72
    },
    {
      "epoch": 0.336,
      "grad_norm": 12.766624450683594,
      "learning_rate": 3.3600000000000004e-05,
      "loss": 0.8645,
      "step": 84
    },
    {
      "epoch": 0.384,
      "grad_norm": 8.186197280883789,
      "learning_rate": 3.8400000000000005e-05,
      "loss": 0.8678,
      "step": 96
    },
    {
      "epoch": 0.432,
      "grad_norm": 16.78915786743164,
      "learning_rate": 4.32e-05,
      "loss": 0.7689,
      "step": 108
    },
    {
      "epoch": 0.48,
      "grad_norm": 22.758197784423828,
      "learning_rate": 4.8e-05,
      "loss": 0.7054,
      "step": 120
    },
    {
      "epoch": 0.528,
      "grad_norm": 10.546210289001465,
      "learning_rate": 4.968888888888889e-05,
      "loss": 0.8524,
      "step": 132
    },
    {
      "epoch": 0.576,
      "grad_norm": 9.998793601989746,
      "learning_rate": 4.915555555555556e-05,
      "loss": 0.7466,
      "step": 144
    },
    {
      "epoch": 0.624,
      "grad_norm": 16.722980499267578,
      "learning_rate": 4.862222222222222e-05,
      "loss": 0.8522,
      "step": 156
    },
    {
      "epoch": 0.672,
      "grad_norm": 9.654285430908203,
      "learning_rate": 4.808888888888889e-05,
      "loss": 0.748,
      "step": 168
    },
    {
      "epoch": 0.72,
      "grad_norm": 23.497644424438477,
      "learning_rate": 4.755555555555556e-05,
      "loss": 0.8113,
      "step": 180
    },
    {
      "epoch": 0.768,
      "grad_norm": 29.93133544921875,
      "learning_rate": 4.702222222222222e-05,
      "loss": 0.7375,
      "step": 192
    },
    {
      "epoch": 0.816,
      "grad_norm": 21.097806930541992,
      "learning_rate": 4.648888888888889e-05,
      "loss": 0.6061,
      "step": 204
    },
    {
      "epoch": 0.864,
      "grad_norm": 11.148388862609863,
      "learning_rate": 4.5955555555555555e-05,
      "loss": 0.8176,
      "step": 216
    },
    {
      "epoch": 0.912,
      "grad_norm": 41.14344787597656,
      "learning_rate": 4.5422222222222225e-05,
      "loss": 0.7304,
      "step": 228
    },
    {
      "epoch": 0.96,
      "grad_norm": 11.007186889648438,
      "learning_rate": 4.4888888888888894e-05,
      "loss": 0.8662,
      "step": 240
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7207207207207207,
      "eval_f1_macro": 0.6400173200358859,
      "eval_f1_micro": 0.7207207207207207,
      "eval_f1_weighted": 0.6863741252230461,
      "eval_loss": 0.8032302260398865,
      "eval_precision_macro": 0.7771056423671171,
      "eval_precision_micro": 0.7207207207207207,
      "eval_precision_weighted": 0.754485589161179,
      "eval_recall_macro": 0.64472593537768,
      "eval_recall_micro": 0.7207207207207207,
      "eval_recall_weighted": 0.7207207207207207,
      "eval_runtime": 162.5414,
      "eval_samples_per_second": 6.146,
      "eval_steps_per_second": 0.197,
      "step": 250
    },
    {
      "epoch": 1.008,
      "grad_norm": 8.793386459350586,
      "learning_rate": 4.435555555555556e-05,
      "loss": 0.6726,
      "step": 252
    },
    {
      "epoch": 1.056,
      "grad_norm": 8.431066513061523,
      "learning_rate": 4.3822222222222227e-05,
      "loss": 0.728,
      "step": 264
    },
    {
      "epoch": 1.104,
      "grad_norm": 13.071714401245117,
      "learning_rate": 4.328888888888889e-05,
      "loss": 0.5935,
      "step": 276
    },
    {
      "epoch": 1.152,
      "grad_norm": 11.652353286743164,
      "learning_rate": 4.275555555555556e-05,
      "loss": 0.5623,
      "step": 288
    },
    {
      "epoch": 1.2,
      "grad_norm": 15.519989013671875,
      "learning_rate": 4.222222222222222e-05,
      "loss": 0.5258,
      "step": 300
    },
    {
      "epoch": 1.248,
      "grad_norm": 12.270814895629883,
      "learning_rate": 4.168888888888889e-05,
      "loss": 0.5467,
      "step": 312
    },
    {
      "epoch": 1.296,
      "grad_norm": 45.41197967529297,
      "learning_rate": 4.115555555555556e-05,
      "loss": 0.687,
      "step": 324
    },
    {
      "epoch": 1.3439999999999999,
      "grad_norm": 18.447298049926758,
      "learning_rate": 4.062222222222222e-05,
      "loss": 0.7523,
      "step": 336
    },
    {
      "epoch": 1.392,
      "grad_norm": 16.430402755737305,
      "learning_rate": 4.008888888888889e-05,
      "loss": 0.5786,
      "step": 348
    },
    {
      "epoch": 1.44,
      "grad_norm": 13.083454132080078,
      "learning_rate": 3.9555555555555556e-05,
      "loss": 0.4946,
      "step": 360
    },
    {
      "epoch": 1.488,
      "grad_norm": 17.238567352294922,
      "learning_rate": 3.9022222222222225e-05,
      "loss": 0.6058,
      "step": 372
    },
    {
      "epoch": 1.536,
      "grad_norm": 18.45892906188965,
      "learning_rate": 3.848888888888889e-05,
      "loss": 0.5246,
      "step": 384
    },
    {
      "epoch": 1.584,
      "grad_norm": 23.937816619873047,
      "learning_rate": 3.795555555555556e-05,
      "loss": 0.6662,
      "step": 396
    },
    {
      "epoch": 1.6320000000000001,
      "grad_norm": 17.260282516479492,
      "learning_rate": 3.742222222222223e-05,
      "loss": 0.6118,
      "step": 408
    },
    {
      "epoch": 1.6800000000000002,
      "grad_norm": 15.230131149291992,
      "learning_rate": 3.688888888888889e-05,
      "loss": 0.6536,
      "step": 420
    },
    {
      "epoch": 1.728,
      "grad_norm": 12.828449249267578,
      "learning_rate": 3.635555555555556e-05,
      "loss": 0.6201,
      "step": 432
    },
    {
      "epoch": 1.776,
      "grad_norm": 20.50193214416504,
      "learning_rate": 3.582222222222222e-05,
      "loss": 0.5495,
      "step": 444
    },
    {
      "epoch": 1.8239999999999998,
      "grad_norm": 15.018689155578613,
      "learning_rate": 3.528888888888889e-05,
      "loss": 0.4981,
      "step": 456
    },
    {
      "epoch": 1.8719999999999999,
      "grad_norm": 20.459606170654297,
      "learning_rate": 3.475555555555556e-05,
      "loss": 0.5907,
      "step": 468
    },
    {
      "epoch": 1.92,
      "grad_norm": 14.490087509155273,
      "learning_rate": 3.4222222222222224e-05,
      "loss": 0.519,
      "step": 480
    },
    {
      "epoch": 1.968,
      "grad_norm": 23.004623413085938,
      "learning_rate": 3.368888888888889e-05,
      "loss": 0.5737,
      "step": 492
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7447447447447447,
      "eval_f1_macro": 0.7298437618326189,
      "eval_f1_micro": 0.7447447447447447,
      "eval_f1_weighted": 0.7467396946425192,
      "eval_loss": 0.646373450756073,
      "eval_precision_macro": 0.7348636077090247,
      "eval_precision_micro": 0.7447447447447447,
      "eval_precision_weighted": 0.7644157119297172,
      "eval_recall_macro": 0.7382166799546654,
      "eval_recall_micro": 0.7447447447447447,
      "eval_recall_weighted": 0.7447447447447447,
      "eval_runtime": 163.7809,
      "eval_samples_per_second": 6.1,
      "eval_steps_per_second": 0.195,
      "step": 500
    }
  ],
  "logging_steps": 12,
  "max_steps": 1250,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 525305938493952.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}