{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.015308075009567547,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0015308075009567547,
      "grad_norm": 0.029453441500663757,
      "learning_rate": 2e-05,
      "loss": 11.9389,
      "step": 1
    },
    {
      "epoch": 0.0030616150019135095,
      "grad_norm": 0.03346884995698929,
      "learning_rate": 4e-05,
      "loss": 11.9343,
      "step": 2
    },
    {
      "epoch": 0.004592422502870264,
      "grad_norm": 0.04336082935333252,
      "learning_rate": 6e-05,
      "loss": 11.9331,
      "step": 3
    },
    {
      "epoch": 0.004592422502870264,
      "eval_loss": 11.931778907775879,
      "eval_runtime": 6.9248,
      "eval_samples_per_second": 39.712,
      "eval_steps_per_second": 19.928,
      "step": 3
    },
    {
      "epoch": 0.006123230003827019,
      "grad_norm": 0.026239335536956787,
      "learning_rate": 8e-05,
      "loss": 11.9339,
      "step": 4
    },
    {
      "epoch": 0.007654037504783774,
      "grad_norm": 0.0368715301156044,
      "learning_rate": 0.0001,
      "loss": 11.9279,
      "step": 5
    },
    {
      "epoch": 0.009184845005740528,
      "grad_norm": 0.01770518533885479,
      "learning_rate": 0.00012,
      "loss": 11.9245,
      "step": 6
    },
    {
      "epoch": 0.009184845005740528,
      "eval_loss": 11.931729316711426,
      "eval_runtime": 7.8517,
      "eval_samples_per_second": 35.024,
      "eval_steps_per_second": 17.576,
      "step": 6
    },
    {
      "epoch": 0.010715652506697282,
      "grad_norm": 0.03689175471663475,
      "learning_rate": 0.00014,
      "loss": 11.9285,
      "step": 7
    },
    {
      "epoch": 0.012246460007654038,
      "grad_norm": 0.026708826422691345,
      "learning_rate": 0.00016,
      "loss": 11.9387,
      "step": 8
    },
    {
      "epoch": 0.013777267508610792,
      "grad_norm": 0.037856075912714005,
      "learning_rate": 0.00018,
      "loss": 11.9364,
      "step": 9
    },
    {
      "epoch": 0.013777267508610792,
      "eval_loss": 11.931624412536621,
      "eval_runtime": 8.4647,
      "eval_samples_per_second": 32.488,
      "eval_steps_per_second": 16.303,
      "step": 9
    },
    {
      "epoch": 0.015308075009567547,
      "grad_norm": 0.035534102469682693,
      "learning_rate": 0.0002,
      "loss": 11.9413,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1181614080.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}