{
  "best_metric": 0.00033540153526701033,
  "best_model_checkpoint": "./high_accuracy_model/checkpoints/checkpoint-486",
  "epoch": 9.0,
  "eval_steps": 500,
  "global_step": 486,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.18518518518518517,
      "grad_norm": 1.84208345413208,
      "learning_rate": 5.555555555555555e-06,
      "loss": 1.3842,
      "step": 10
    },
    {
      "epoch": 0.37037037037037035,
      "grad_norm": 1.194960594177246,
      "learning_rate": 1.111111111111111e-05,
      "loss": 1.3909,
      "step": 20
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 2.837631940841675,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 1.3735,
      "step": 30
    },
    {
      "epoch": 0.7407407407407407,
      "grad_norm": 6.684326171875,
      "learning_rate": 2.222222222222222e-05,
      "loss": 1.2219,
      "step": 40
    },
    {
      "epoch": 0.9259259259259259,
      "grad_norm": 8.828328132629395,
      "learning_rate": 2.777777777777778e-05,
      "loss": 0.607,
      "step": 50
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.14139007031917572,
      "eval_runtime": 5.3313,
      "eval_samples_per_second": 81.031,
      "eval_steps_per_second": 2.626,
      "step": 54
    },
    {
      "epoch": 1.1111111111111112,
      "grad_norm": 5.395774841308594,
      "learning_rate": 2.962962962962963e-05,
      "loss": 0.1888,
      "step": 60
    },
    {
      "epoch": 1.2962962962962963,
      "grad_norm": 0.4055171012878418,
      "learning_rate": 2.9012345679012347e-05,
      "loss": 0.0843,
      "step": 70
    },
    {
      "epoch": 1.4814814814814814,
      "grad_norm": 0.1396542340517044,
      "learning_rate": 2.839506172839506e-05,
      "loss": 0.0149,
      "step": 80
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 0.10366827249526978,
      "learning_rate": 2.777777777777778e-05,
      "loss": 0.0149,
      "step": 90
    },
    {
      "epoch": 1.8518518518518519,
      "grad_norm": 0.04384304955601692,
      "learning_rate": 2.7160493827160493e-05,
      "loss": 0.0068,
      "step": 100
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.0060031237080693245,
      "eval_runtime": 5.3271,
      "eval_samples_per_second": 81.094,
      "eval_steps_per_second": 2.628,
      "step": 108
    },
    {
      "epoch": 2.037037037037037,
      "grad_norm": 58.33610916137695,
      "learning_rate": 2.654320987654321e-05,
      "loss": 0.0282,
      "step": 110
    },
    {
      "epoch": 2.2222222222222223,
      "grad_norm": 0.025968477129936218,
      "learning_rate": 2.5925925925925925e-05,
      "loss": 0.0028,
      "step": 120
    },
    {
      "epoch": 2.4074074074074074,
      "grad_norm": 0.02779112197458744,
      "learning_rate": 2.5308641975308642e-05,
      "loss": 0.0023,
      "step": 130
    },
    {
      "epoch": 2.5925925925925926,
      "grad_norm": 0.02369321882724762,
      "learning_rate": 2.469135802469136e-05,
      "loss": 0.0021,
      "step": 140
    },
    {
      "epoch": 2.7777777777777777,
      "grad_norm": 0.019034041091799736,
      "learning_rate": 2.4074074074074074e-05,
      "loss": 0.0018,
      "step": 150
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 0.017112266272306442,
      "learning_rate": 2.345679012345679e-05,
      "loss": 0.0016,
      "step": 160
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.0009095199056901038,
      "eval_runtime": 5.3498,
      "eval_samples_per_second": 80.75,
      "eval_steps_per_second": 2.617,
      "step": 162
    },
    {
      "epoch": 3.148148148148148,
      "grad_norm": 0.0168638713657856,
      "learning_rate": 2.2839506172839506e-05,
      "loss": 0.0015,
      "step": 170
    },
    {
      "epoch": 3.3333333333333335,
      "grad_norm": 0.01457894779741764,
      "learning_rate": 2.222222222222222e-05,
      "loss": 0.0014,
      "step": 180
    },
    {
      "epoch": 3.5185185185185186,
      "grad_norm": 0.015107030980288982,
      "learning_rate": 2.160493827160494e-05,
      "loss": 0.0013,
      "step": 190
    },
    {
      "epoch": 3.7037037037037037,
      "grad_norm": 0.014471936039626598,
      "learning_rate": 2.0987654320987655e-05,
      "loss": 0.0012,
      "step": 200
    },
    {
      "epoch": 3.888888888888889,
      "grad_norm": 0.015352337621152401,
      "learning_rate": 2.0370370370370372e-05,
      "loss": 0.0011,
      "step": 210
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.000643909617792815,
      "eval_runtime": 5.3279,
      "eval_samples_per_second": 81.082,
      "eval_steps_per_second": 2.628,
      "step": 216
    },
    {
      "epoch": 4.074074074074074,
      "grad_norm": 0.012968766503036022,
      "learning_rate": 1.9753086419753087e-05,
      "loss": 0.0011,
      "step": 220
    },
    {
      "epoch": 4.2592592592592595,
      "grad_norm": 0.010898980312049389,
      "learning_rate": 1.9135802469135804e-05,
      "loss": 0.0011,
      "step": 230
    },
    {
      "epoch": 4.444444444444445,
      "grad_norm": 0.010916095227003098,
      "learning_rate": 1.8518518518518518e-05,
      "loss": 0.001,
      "step": 240
    },
    {
      "epoch": 4.62962962962963,
      "grad_norm": 0.0120779974386096,
      "learning_rate": 1.7901234567901232e-05,
      "loss": 0.001,
      "step": 250
    },
    {
      "epoch": 4.814814814814815,
      "grad_norm": 0.010523187927901745,
      "learning_rate": 1.7283950617283953e-05,
      "loss": 0.0009,
      "step": 260
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.011234262958168983,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.0009,
      "step": 270
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.0005087139434181154,
      "eval_runtime": 5.2996,
      "eval_samples_per_second": 81.516,
      "eval_steps_per_second": 2.642,
      "step": 270
    },
    {
      "epoch": 5.185185185185185,
      "grad_norm": 0.009681645780801773,
      "learning_rate": 1.6049382716049385e-05,
      "loss": 0.0009,
      "step": 280
    },
    {
      "epoch": 5.37037037037037,
      "grad_norm": 0.009395086206495762,
      "learning_rate": 1.54320987654321e-05,
      "loss": 0.0008,
      "step": 290
    },
    {
      "epoch": 5.555555555555555,
      "grad_norm": 0.009616800583899021,
      "learning_rate": 1.4814814814814815e-05,
      "loss": 0.0008,
      "step": 300
    },
    {
      "epoch": 5.7407407407407405,
      "grad_norm": 0.008898408152163029,
      "learning_rate": 1.419753086419753e-05,
      "loss": 0.0008,
      "step": 310
    },
    {
      "epoch": 5.925925925925926,
      "grad_norm": 0.008080519735813141,
      "learning_rate": 1.3580246913580247e-05,
      "loss": 0.0007,
      "step": 320
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.00043077277950942516,
      "eval_runtime": 5.3388,
      "eval_samples_per_second": 80.917,
      "eval_steps_per_second": 2.622,
      "step": 324
    },
    {
      "epoch": 6.111111111111111,
      "grad_norm": 0.008911211043596268,
      "learning_rate": 1.2962962962962962e-05,
      "loss": 0.0007,
      "step": 330
    },
    {
      "epoch": 6.296296296296296,
      "grad_norm": 0.00797555223107338,
      "learning_rate": 1.234567901234568e-05,
      "loss": 0.0007,
      "step": 340
    },
    {
      "epoch": 6.481481481481482,
      "grad_norm": 0.0076234182342886925,
      "learning_rate": 1.1728395061728396e-05,
      "loss": 0.0007,
      "step": 350
    },
    {
      "epoch": 6.666666666666667,
      "grad_norm": 0.007601814344525337,
      "learning_rate": 1.111111111111111e-05,
      "loss": 0.0007,
      "step": 360
    },
    {
      "epoch": 6.851851851851852,
      "grad_norm": 0.007262354716658592,
      "learning_rate": 1.0493827160493827e-05,
      "loss": 0.0006,
      "step": 370
    },
    {
      "epoch": 7.0,
      "eval_loss": 0.0003821477002929896,
      "eval_runtime": 5.3454,
      "eval_samples_per_second": 80.817,
      "eval_steps_per_second": 2.619,
      "step": 378
    },
    {
      "epoch": 7.037037037037037,
      "grad_norm": 0.007605003193020821,
      "learning_rate": 9.876543209876543e-06,
      "loss": 0.0006,
      "step": 380
    },
    {
      "epoch": 7.222222222222222,
      "grad_norm": 0.007823699153959751,
      "learning_rate": 9.259259259259259e-06,
      "loss": 0.0006,
      "step": 390
    },
    {
      "epoch": 7.407407407407407,
      "grad_norm": 0.006984628736972809,
      "learning_rate": 8.641975308641977e-06,
      "loss": 0.0006,
      "step": 400
    },
    {
      "epoch": 7.592592592592593,
      "grad_norm": 0.0069269961677491665,
      "learning_rate": 8.024691358024692e-06,
      "loss": 0.0006,
      "step": 410
    },
    {
      "epoch": 7.777777777777778,
      "grad_norm": 0.00705177616328001,
      "learning_rate": 7.4074074074074075e-06,
      "loss": 0.0006,
      "step": 420
    },
    {
      "epoch": 7.962962962962963,
      "grad_norm": 0.006812036037445068,
      "learning_rate": 6.790123456790123e-06,
      "loss": 0.0006,
      "step": 430
    },
    {
      "epoch": 8.0,
      "eval_loss": 0.00035223510349169374,
      "eval_runtime": 5.3231,
      "eval_samples_per_second": 81.156,
      "eval_steps_per_second": 2.63,
      "step": 432
    },
    {
      "epoch": 8.148148148148149,
      "grad_norm": 0.01267582643777132,
      "learning_rate": 6.17283950617284e-06,
      "loss": 0.0006,
      "step": 440
    },
    {
      "epoch": 8.333333333333334,
      "grad_norm": 0.0074326274916529655,
      "learning_rate": 5.555555555555555e-06,
      "loss": 0.0006,
      "step": 450
    },
    {
      "epoch": 8.518518518518519,
      "grad_norm": 0.006270403973758221,
      "learning_rate": 4.938271604938272e-06,
      "loss": 0.0006,
      "step": 460
    },
    {
      "epoch": 8.703703703703704,
      "grad_norm": 0.006308271083980799,
      "learning_rate": 4.320987654320988e-06,
      "loss": 0.0006,
      "step": 470
    },
    {
      "epoch": 8.88888888888889,
      "grad_norm": 0.006707304157316685,
      "learning_rate": 3.7037037037037037e-06,
      "loss": 0.0006,
      "step": 480
    },
    {
      "epoch": 9.0,
      "eval_loss": 0.00033540153526701033,
      "eval_runtime": 5.3591,
      "eval_samples_per_second": 80.611,
      "eval_steps_per_second": 2.612,
      "step": 486
    }
  ],
  "logging_steps": 10,
  "max_steps": 540,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "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": 2045988306026496.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}