{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00022468123349997192,
  "eval_steps": 8,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.246812334999719e-05,
      "eval_loss": 2.708707571029663,
      "eval_runtime": 2271.309,
      "eval_samples_per_second": 8.251,
      "eval_steps_per_second": 4.125,
      "step": 1
    },
    {
      "epoch": 6.740437004999158e-05,
      "grad_norm": 1.9373347759246826,
      "learning_rate": 6e-05,
      "loss": 2.5699,
      "step": 3
    },
    {
      "epoch": 0.00013480874009998316,
      "grad_norm": 1.7457520961761475,
      "learning_rate": 0.00012,
      "loss": 2.4162,
      "step": 6
    },
    {
      "epoch": 0.00017974498679997753,
      "eval_loss": 2.27852725982666,
      "eval_runtime": 2282.078,
      "eval_samples_per_second": 8.212,
      "eval_steps_per_second": 4.106,
      "step": 8
    },
    {
      "epoch": 0.00020221311014997472,
      "grad_norm": 1.6379685401916504,
      "learning_rate": 0.00018,
      "loss": 2.1973,
      "step": 9
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3305470584422400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}