{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00473186119873817,
  "eval_steps": 3,
  "global_step": 3,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0015772870662460567,
      "grad_norm": 0.05421409383416176,
      "learning_rate": 2e-05,
      "loss": 10.3729,
      "step": 1
    },
    {
      "epoch": 0.0015772870662460567,
      "eval_loss": 10.378344535827637,
      "eval_runtime": 0.957,
      "eval_samples_per_second": 278.992,
      "eval_steps_per_second": 140.018,
      "step": 1
    },
    {
      "epoch": 0.0031545741324921135,
      "grad_norm": 0.06451243162155151,
      "learning_rate": 4e-05,
      "loss": 10.378,
      "step": 2
    },
    {
      "epoch": 0.00473186119873817,
      "grad_norm": 0.053572166711091995,
      "learning_rate": 6e-05,
      "loss": 10.3766,
      "step": 3
    },
    {
      "epoch": 0.00473186119873817,
      "eval_loss": 10.37829875946045,
      "eval_runtime": 0.9721,
      "eval_samples_per_second": 274.671,
      "eval_steps_per_second": 137.85,
      "step": 3
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 77585448960.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}