{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.6623376623376624,
  "eval_steps": 500,
  "global_step": 40,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2077922077922078,
      "grad_norm": 0.1982421875,
      "learning_rate": 0.0001,
      "loss": 0.5391,
      "step": 5
    },
    {
      "epoch": 0.4155844155844156,
      "grad_norm": 0.080078125,
      "learning_rate": 0.0001,
      "loss": 0.3701,
      "step": 10
    },
    {
      "epoch": 0.6233766233766234,
      "grad_norm": 0.04345703125,
      "learning_rate": 0.0001,
      "loss": 0.3009,
      "step": 15
    },
    {
      "epoch": 0.8311688311688312,
      "grad_norm": 0.037353515625,
      "learning_rate": 0.0001,
      "loss": 0.2393,
      "step": 20
    },
    {
      "epoch": 1.0389610389610389,
      "grad_norm": 0.036865234375,
      "learning_rate": 0.0001,
      "loss": 0.1959,
      "step": 25
    },
    {
      "epoch": 1.2467532467532467,
      "grad_norm": 0.0986328125,
      "learning_rate": 0.0001,
      "loss": 0.1705,
      "step": 30
    },
    {
      "epoch": 1.4545454545454546,
      "grad_norm": 0.06884765625,
      "learning_rate": 0.0001,
      "loss": 0.1305,
      "step": 35
    },
    {
      "epoch": 1.6623376623376624,
      "grad_norm": 0.06591796875,
      "learning_rate": 0.0001,
      "loss": 0.1285,
      "step": 40
    }
  ],
  "logging_steps": 5,
  "max_steps": 40,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 90,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8.20631894326272e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}