{
  "best_metric": 0.9857142857142858,
  "best_model_checkpoint": "document-spoof-clip/checkpoint-57",
  "epoch": 12.631578947368421,
  "eval_steps": 500,
  "global_step": 60,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.8421052631578947,
      "eval_accuracy": 0.8285714285714286,
      "eval_loss": 0.5341095328330994,
      "eval_runtime": 6.1365,
      "eval_samples_per_second": 11.407,
      "eval_steps_per_second": 0.815,
      "step": 4
    },
    {
      "epoch": 1.8947368421052633,
      "eval_accuracy": 0.8857142857142857,
      "eval_loss": 0.2827140986919403,
      "eval_runtime": 5.2456,
      "eval_samples_per_second": 13.345,
      "eval_steps_per_second": 0.953,
      "step": 9
    },
    {
      "epoch": 2.1052631578947367,
      "grad_norm": 14.946775436401367,
      "learning_rate": 4.62962962962963e-05,
      "loss": 0.6045,
      "step": 10
    },
    {
      "epoch": 2.9473684210526314,
      "eval_accuracy": 0.7857142857142857,
      "eval_loss": 0.4043836295604706,
      "eval_runtime": 5.2087,
      "eval_samples_per_second": 13.439,
      "eval_steps_per_second": 0.96,
      "step": 14
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9142857142857143,
      "eval_loss": 0.22778411209583282,
      "eval_runtime": 5.214,
      "eval_samples_per_second": 13.425,
      "eval_steps_per_second": 0.959,
      "step": 19
    },
    {
      "epoch": 4.2105263157894735,
      "grad_norm": 11.259857177734375,
      "learning_rate": 3.7037037037037037e-05,
      "loss": 0.7684,
      "step": 20
    },
    {
      "epoch": 4.842105263157895,
      "eval_accuracy": 0.9571428571428572,
      "eval_loss": 0.1032894104719162,
      "eval_runtime": 5.2447,
      "eval_samples_per_second": 13.347,
      "eval_steps_per_second": 0.953,
      "step": 23
    },
    {
      "epoch": 5.894736842105263,
      "eval_accuracy": 0.9714285714285714,
      "eval_loss": 0.1465865820646286,
      "eval_runtime": 5.2649,
      "eval_samples_per_second": 13.295,
      "eval_steps_per_second": 0.95,
      "step": 28
    },
    {
      "epoch": 6.315789473684211,
      "grad_norm": 8.416402816772461,
      "learning_rate": 2.777777777777778e-05,
      "loss": 0.2323,
      "step": 30
    },
    {
      "epoch": 6.947368421052632,
      "eval_accuracy": 0.9142857142857143,
      "eval_loss": 0.22525207698345184,
      "eval_runtime": 5.3071,
      "eval_samples_per_second": 13.19,
      "eval_steps_per_second": 0.942,
      "step": 33
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9714285714285714,
      "eval_loss": 0.12320270389318466,
      "eval_runtime": 5.3285,
      "eval_samples_per_second": 13.137,
      "eval_steps_per_second": 0.938,
      "step": 38
    },
    {
      "epoch": 8.421052631578947,
      "grad_norm": 32.6998176574707,
      "learning_rate": 1.8518518518518518e-05,
      "loss": 0.0933,
      "step": 40
    },
    {
      "epoch": 8.842105263157894,
      "eval_accuracy": 0.9714285714285714,
      "eval_loss": 0.05824749916791916,
      "eval_runtime": 5.376,
      "eval_samples_per_second": 13.021,
      "eval_steps_per_second": 0.93,
      "step": 42
    },
    {
      "epoch": 9.894736842105264,
      "eval_accuracy": 0.9714285714285714,
      "eval_loss": 0.06094963848590851,
      "eval_runtime": 5.3183,
      "eval_samples_per_second": 13.162,
      "eval_steps_per_second": 0.94,
      "step": 47
    },
    {
      "epoch": 10.526315789473685,
      "grad_norm": 7.5993194580078125,
      "learning_rate": 9.259259259259259e-06,
      "loss": 0.067,
      "step": 50
    },
    {
      "epoch": 10.947368421052632,
      "eval_accuracy": 0.9714285714285714,
      "eval_loss": 0.04527128115296364,
      "eval_runtime": 5.3452,
      "eval_samples_per_second": 13.096,
      "eval_steps_per_second": 0.935,
      "step": 52
    },
    {
      "epoch": 12.0,
      "eval_accuracy": 0.9857142857142858,
      "eval_loss": 0.04218948259949684,
      "eval_runtime": 5.3043,
      "eval_samples_per_second": 13.197,
      "eval_steps_per_second": 0.943,
      "step": 57
    },
    {
      "epoch": 12.631578947368421,
      "grad_norm": 6.4861040115356445,
      "learning_rate": 0.0,
      "loss": 0.0835,
      "step": 60
    },
    {
      "epoch": 12.631578947368421,
      "eval_accuracy": 0.9857142857142858,
      "eval_loss": 0.028362158685922623,
      "eval_runtime": 5.2306,
      "eval_samples_per_second": 13.383,
      "eval_steps_per_second": 0.956,
      "step": 60
    },
    {
      "epoch": 12.631578947368421,
      "step": 60,
      "total_flos": 2.993942051666657e+17,
      "train_loss": 0.30815972487131754,
      "train_runtime": 414.0498,
      "train_samples_per_second": 10.868,
      "train_steps_per_second": 0.145
    }
  ],
  "logging_steps": 10,
  "max_steps": 60,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 15,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.993942051666657e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}