{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0003696743784849512,
  "eval_steps": 3,
  "global_step": 3,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00012322479282831706,
      "grad_norm": 11.761505126953125,
      "learning_rate": 2e-05,
      "loss": 6.768,
      "step": 1
    },
    {
      "epoch": 0.00012322479282831706,
      "eval_loss": 1.7490488290786743,
      "eval_runtime": 166.2322,
      "eval_samples_per_second": 20.556,
      "eval_steps_per_second": 10.281,
      "step": 1
    },
    {
      "epoch": 0.0002464495856566341,
      "grad_norm": 11.395349502563477,
      "learning_rate": 4e-05,
      "loss": 7.1368,
      "step": 2
    },
    {
      "epoch": 0.0003696743784849512,
      "grad_norm": 10.02564811706543,
      "learning_rate": 6e-05,
      "loss": 6.9487,
      "step": 3
    },
    {
      "epoch": 0.0003696743784849512,
      "eval_loss": 1.7319248914718628,
      "eval_runtime": 165.0709,
      "eval_samples_per_second": 20.7,
      "eval_steps_per_second": 10.353,
      "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": 788702309646336.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}