{
  "best_metric": 0.07522870600223541,
  "best_model_checkpoint": "./teapotllm/checkpoint-1640",
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 1640,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 5.528669357299805,
      "learning_rate": 4.75e-05,
      "loss": 6.5278,
      "step": 410
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.08746226876974106,
      "eval_runtime": 4.8581,
      "eval_samples_per_second": 45.285,
      "eval_steps_per_second": 5.764,
      "step": 410
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.16966140270233154,
      "learning_rate": 4.5e-05,
      "loss": 0.0895,
      "step": 820
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.0768546611070633,
      "eval_runtime": 4.8636,
      "eval_samples_per_second": 45.234,
      "eval_steps_per_second": 5.757,
      "step": 820
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.40588390827178955,
      "learning_rate": 4.25e-05,
      "loss": 0.1199,
      "step": 1230
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.07700426131486893,
      "eval_runtime": 4.8598,
      "eval_samples_per_second": 45.269,
      "eval_steps_per_second": 5.762,
      "step": 1230
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.0932304635643959,
      "learning_rate": 4e-05,
      "loss": 0.0639,
      "step": 1640
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.07522870600223541,
      "eval_runtime": 4.8695,
      "eval_samples_per_second": 45.179,
      "eval_steps_per_second": 5.75,
      "step": 1640
    }
  ],
  "logging_steps": 500,
  "max_steps": 8200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2246004116029440.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}