{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.957345971563981,
  "eval_steps": 500,
  "global_step": 78,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.3791469194312796,
      "grad_norm": 0.2653672397136688,
      "learning_rate": 0.00029939614409928584,
      "loss": 0.8199,
      "step": 10
    },
    {
      "epoch": 0.7582938388625592,
      "grad_norm": 0.1669384390115738,
      "learning_rate": 0.0002787673190402799,
      "loss": 0.6913,
      "step": 20
    },
    {
      "epoch": 1.1374407582938388,
      "grad_norm": 0.13310174643993378,
      "learning_rate": 0.00023263454721781537,
      "loss": 0.6417,
      "step": 30
    },
    {
      "epoch": 1.5165876777251186,
      "grad_norm": 0.12457551062107086,
      "learning_rate": 0.00017013498987264832,
      "loss": 0.6113,
      "step": 40
    },
    {
      "epoch": 1.8957345971563981,
      "grad_norm": 0.13069939613342285,
      "learning_rate": 0.0001036474508437579,
      "loss": 0.5921,
      "step": 50
    },
    {
      "epoch": 2.2748815165876777,
      "grad_norm": 0.1313541829586029,
      "learning_rate": 4.63406026519703e-05,
      "loss": 0.5841,
      "step": 60
    },
    {
      "epoch": 2.654028436018957,
      "grad_norm": 0.12558336555957794,
      "learning_rate": 9.564769404039419e-06,
      "loss": 0.5766,
      "step": 70
    }
  ],
  "logging_steps": 10,
  "max_steps": 78,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 1.0702567157373338e+18,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}