{
  "best_metric": 0.07254856824874878,
  "best_model_checkpoint": "./teapotllm/checkpoint-1224",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 1224,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 0.07505040615797043,
      "learning_rate": 4.75e-05,
      "loss": 0.0953,
      "step": 408
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.07464946806430817,
      "eval_runtime": 4.9963,
      "eval_samples_per_second": 45.034,
      "eval_steps_per_second": 5.804,
      "step": 408
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.3880476951599121,
      "learning_rate": 4.5e-05,
      "loss": 0.0706,
      "step": 816
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.0732811763882637,
      "eval_runtime": 4.9711,
      "eval_samples_per_second": 45.262,
      "eval_steps_per_second": 5.834,
      "step": 816
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.514928936958313,
      "learning_rate": 4.25e-05,
      "loss": 0.0579,
      "step": 1224
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.07254856824874878,
      "eval_runtime": 4.9773,
      "eval_samples_per_second": 45.205,
      "eval_steps_per_second": 5.826,
      "step": 1224
    }
  ],
  "logging_steps": 500,
  "max_steps": 8160,
  "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": 1674231726735360.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}