{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0454545454545454,
  "eval_steps": 1,
  "global_step": 8,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.36363636363636365,
      "eval_loss": 9.707796096801758,
      "eval_runtime": 0.6353,
      "eval_samples_per_second": 7.87,
      "eval_steps_per_second": 3.148,
      "step": 1
    },
    {
      "epoch": 0.7272727272727273,
      "eval_loss": 8.552785873413086,
      "eval_runtime": 0.6367,
      "eval_samples_per_second": 7.853,
      "eval_steps_per_second": 3.141,
      "step": 2
    },
    {
      "epoch": 1.1363636363636362,
      "grad_norm": 68.7672348022461,
      "learning_rate": 3e-05,
      "loss": 10.3937,
      "step": 3
    },
    {
      "epoch": 1.1363636363636362,
      "eval_loss": 5.960778713226318,
      "eval_runtime": 0.6411,
      "eval_samples_per_second": 7.799,
      "eval_steps_per_second": 3.12,
      "step": 3
    },
    {
      "epoch": 1.5,
      "eval_loss": 3.21411395072937,
      "eval_runtime": 0.64,
      "eval_samples_per_second": 7.813,
      "eval_steps_per_second": 3.125,
      "step": 4
    },
    {
      "epoch": 1.8636363636363638,
      "eval_loss": 0.5463393926620483,
      "eval_runtime": 0.6385,
      "eval_samples_per_second": 7.831,
      "eval_steps_per_second": 3.132,
      "step": 5
    },
    {
      "epoch": 2.2727272727272725,
      "grad_norm": 15.696877479553223,
      "learning_rate": 6e-05,
      "loss": 3.3022,
      "step": 6
    },
    {
      "epoch": 2.2727272727272725,
      "eval_loss": 0.0035927104763686657,
      "eval_runtime": 0.6438,
      "eval_samples_per_second": 7.766,
      "eval_steps_per_second": 3.107,
      "step": 6
    },
    {
      "epoch": 2.6363636363636362,
      "eval_loss": 0.0004186338628642261,
      "eval_runtime": 0.6418,
      "eval_samples_per_second": 7.791,
      "eval_steps_per_second": 3.116,
      "step": 7
    },
    {
      "epoch": 3.0454545454545454,
      "eval_loss": 0.00037194820470176637,
      "eval_runtime": 0.6402,
      "eval_samples_per_second": 7.811,
      "eval_steps_per_second": 3.124,
      "step": 8
    }
  ],
  "logging_steps": 3,
  "max_steps": 8,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 1,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.3432689801560064e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}