{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9896907216494846,
  "eval_steps": 500,
  "global_step": 48,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.10309278350515463,
      "grad_norm": Infinity,
      "learning_rate": 0.0002,
      "loss": 3.403,
      "step": 5
    },
    {
      "epoch": 0.20618556701030927,
      "grad_norm": 13.370658874511719,
      "learning_rate": 0.0002,
      "loss": 2.9247,
      "step": 10
    },
    {
      "epoch": 0.30927835051546393,
      "grad_norm": 2.7434089183807373,
      "learning_rate": 0.0002,
      "loss": 1.678,
      "step": 15
    },
    {
      "epoch": 0.41237113402061853,
      "grad_norm": 3.8863208293914795,
      "learning_rate": 0.0002,
      "loss": 1.3139,
      "step": 20
    },
    {
      "epoch": 0.5154639175257731,
      "grad_norm": 3.474966049194336,
      "learning_rate": 0.0002,
      "loss": 1.146,
      "step": 25
    },
    {
      "epoch": 0.6185567010309279,
      "grad_norm": 0.8887417912483215,
      "learning_rate": 0.0002,
      "loss": 1.0428,
      "step": 30
    },
    {
      "epoch": 0.7216494845360825,
      "grad_norm": 0.9037402868270874,
      "learning_rate": 0.0002,
      "loss": 1.0127,
      "step": 35
    },
    {
      "epoch": 0.8247422680412371,
      "grad_norm": 0.8795015215873718,
      "learning_rate": 0.0002,
      "loss": 0.9857,
      "step": 40
    },
    {
      "epoch": 0.9278350515463918,
      "grad_norm": 2.827643394470215,
      "learning_rate": 0.0002,
      "loss": 0.9728,
      "step": 45
    },
    {
      "epoch": 0.9896907216494846,
      "step": 48,
      "total_flos": 3.80894385757225e+16,
      "train_loss": 1.5669735769430797,
      "train_runtime": 889.8109,
      "train_samples_per_second": 0.865,
      "train_steps_per_second": 0.054
    }
  ],
  "logging_steps": 5,
  "max_steps": 48,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 3.80894385757225e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}