{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 461,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.21691973969631237,
      "grad_norm": 0.26772719621658325,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 2.5114,
      "step": 100
    },
    {
      "epoch": 0.43383947939262474,
      "grad_norm": 0.47866562008857727,
      "learning_rate": 4.000000000000001e-06,
      "loss": 2.4846,
      "step": 200
    },
    {
      "epoch": 0.6507592190889371,
      "grad_norm": 0.3118322193622589,
      "learning_rate": 6e-06,
      "loss": 2.4356,
      "step": 300
    },
    {
      "epoch": 0.8676789587852495,
      "grad_norm": 0.2797354459762573,
      "learning_rate": 8.000000000000001e-06,
      "loss": 2.3119,
      "step": 400
    },
    {
      "epoch": 1.0,
      "step": 461,
      "total_flos": 8396998901760000.0,
      "train_loss": 2.4215627409630898,
      "train_runtime": 122.1636,
      "train_samples_per_second": 7.547,
      "train_steps_per_second": 3.774
    }
  ],
  "logging_steps": 100,
  "max_steps": 461,
  "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": 8396998901760000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}