{
  "best_metric": 0.9985358711566618,
  "best_model_checkpoint": "./cbt_classifier/checkpoint-400",
  "epoch": 1.9949748743718594,
  "eval_steps": 200,
  "global_step": 596,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.16750418760469013,
      "grad_norm": 0.858985424041748,
      "learning_rate": 2.5e-05,
      "loss": 0.5097,
      "step": 50
    },
    {
      "epoch": 0.33500837520938026,
      "grad_norm": 2.54575777053833,
      "learning_rate": 5e-05,
      "loss": 0.0863,
      "step": 100
    },
    {
      "epoch": 0.5025125628140703,
      "grad_norm": 38.31464767456055,
      "learning_rate": 4.495967741935484e-05,
      "loss": 0.0248,
      "step": 150
    },
    {
      "epoch": 0.6700167504187605,
      "grad_norm": 0.0192014928907156,
      "learning_rate": 3.991935483870968e-05,
      "loss": 0.0322,
      "step": 200
    },
    {
      "epoch": 0.6700167504187605,
      "eval_accuracy": 0.9941434846266471,
      "eval_loss": 0.023075200617313385,
      "eval_runtime": 7.8942,
      "eval_samples_per_second": 86.519,
      "eval_steps_per_second": 10.894,
      "step": 200
    },
    {
      "epoch": 0.8375209380234506,
      "grad_norm": 0.010706444270908833,
      "learning_rate": 3.487903225806452e-05,
      "loss": 0.0155,
      "step": 250
    },
    {
      "epoch": 1.003350083752094,
      "grad_norm": 0.030784547328948975,
      "learning_rate": 2.9838709677419357e-05,
      "loss": 0.0134,
      "step": 300
    },
    {
      "epoch": 1.170854271356784,
      "grad_norm": 0.012720568105578423,
      "learning_rate": 2.4798387096774196e-05,
      "loss": 0.015,
      "step": 350
    },
    {
      "epoch": 1.338358458961474,
      "grad_norm": 0.0057291556149721146,
      "learning_rate": 1.975806451612903e-05,
      "loss": 0.0028,
      "step": 400
    },
    {
      "epoch": 1.338358458961474,
      "eval_accuracy": 0.9985358711566618,
      "eval_loss": 0.003182810265570879,
      "eval_runtime": 7.8968,
      "eval_samples_per_second": 86.491,
      "eval_steps_per_second": 10.891,
      "step": 400
    },
    {
      "epoch": 1.5058626465661642,
      "grad_norm": 0.009387499652802944,
      "learning_rate": 1.4717741935483872e-05,
      "loss": 0.0003,
      "step": 450
    },
    {
      "epoch": 1.6733668341708543,
      "grad_norm": 0.0058885738253593445,
      "learning_rate": 9.67741935483871e-06,
      "loss": 0.01,
      "step": 500
    },
    {
      "epoch": 1.8408710217755444,
      "grad_norm": 0.0037801910657435656,
      "learning_rate": 4.637096774193548e-06,
      "loss": 0.0002,
      "step": 550
    }
  ],
  "logging_steps": 50,
  "max_steps": 596,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 315537343598592.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}