{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.06855184233076264,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.013710368466152529,
      "grad_norm": 2.012660026550293,
      "learning_rate": 1e-05,
      "loss": 3.3235,
      "step": 1
    },
    {
      "epoch": 0.013710368466152529,
      "eval_loss": 3.620076894760132,
      "eval_runtime": 90.1841,
      "eval_samples_per_second": 1.364,
      "eval_steps_per_second": 0.687,
      "step": 1
    },
    {
      "epoch": 0.027420736932305057,
      "grad_norm": 2.247971773147583,
      "learning_rate": 2e-05,
      "loss": 3.7035,
      "step": 2
    },
    {
      "epoch": 0.027420736932305057,
      "eval_loss": 3.574040651321411,
      "eval_runtime": 6.2469,
      "eval_samples_per_second": 19.69,
      "eval_steps_per_second": 9.925,
      "step": 2
    },
    {
      "epoch": 0.04113110539845758,
      "grad_norm": 2.1602447032928467,
      "learning_rate": 3e-05,
      "loss": 3.1581,
      "step": 3
    },
    {
      "epoch": 0.054841473864610114,
      "grad_norm": 2.1010167598724365,
      "learning_rate": 4e-05,
      "loss": 3.1185,
      "step": 4
    },
    {
      "epoch": 0.054841473864610114,
      "eval_loss": 3.522392988204956,
      "eval_runtime": 6.2565,
      "eval_samples_per_second": 19.659,
      "eval_steps_per_second": 9.91,
      "step": 4
    },
    {
      "epoch": 0.06855184233076264,
      "grad_norm": 2.1184775829315186,
      "learning_rate": 5e-05,
      "loss": 3.2489,
      "step": 5
    }
  ],
  "logging_steps": 1,
  "max_steps": 5,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3699128496291840.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}