{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.937728937728938,
  "eval_steps": 500,
  "global_step": 102,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.29304029304029305,
      "grad_norm": 0.6432506442070007,
      "learning_rate": 9.090909090909092e-05,
      "loss": 1.2624,
      "step": 10
    },
    {
      "epoch": 0.5860805860805861,
      "grad_norm": 0.3166349530220032,
      "learning_rate": 9.760588329553571e-05,
      "loss": 1.1353,
      "step": 20
    },
    {
      "epoch": 0.8791208791208791,
      "grad_norm": 0.32692158222198486,
      "learning_rate": 8.962384209755452e-05,
      "loss": 1.0604,
      "step": 30
    },
    {
      "epoch": 1.1465201465201464,
      "grad_norm": 0.2800314426422119,
      "learning_rate": 7.696600172495997e-05,
      "loss": 1.0072,
      "step": 40
    },
    {
      "epoch": 1.4395604395604396,
      "grad_norm": 0.4036503732204437,
      "learning_rate": 6.112604669781572e-05,
      "loss": 1.0499,
      "step": 50
    },
    {
      "epoch": 1.7326007326007327,
      "grad_norm": 0.2690628170967102,
      "learning_rate": 4.397316598723385e-05,
      "loss": 0.9917,
      "step": 60
    },
    {
      "epoch": 2.0,
      "grad_norm": 6.335123062133789,
      "learning_rate": 2.7531479951641924e-05,
      "loss": 1.0404,
      "step": 70
    },
    {
      "epoch": 2.293040293040293,
      "grad_norm": 0.38795047998428345,
      "learning_rate": 1.3741184642831189e-05,
      "loss": 1.0057,
      "step": 80
    },
    {
      "epoch": 2.586080586080586,
      "grad_norm": 0.3348829746246338,
      "learning_rate": 4.229599573731685e-06,
      "loss": 0.9651,
      "step": 90
    },
    {
      "epoch": 2.879120879120879,
      "grad_norm": 0.3123050630092621,
      "learning_rate": 1.191363849376237e-07,
      "loss": 0.9705,
      "step": 100
    },
    {
      "epoch": 2.937728937728938,
      "step": 102,
      "total_flos": 2.405589486193869e+16,
      "train_loss": 1.0459267169821496,
      "train_runtime": 1269.1774,
      "train_samples_per_second": 2.579,
      "train_steps_per_second": 0.08
    }
  ],
  "logging_steps": 10,
  "max_steps": 102,
  "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": 2.405589486193869e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}