{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.018507451176958224,
  "eval_steps": 40,
  "global_step": 120,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001542287598079852,
      "eval_loss": NaN,
      "eval_runtime": 636.8668,
      "eval_samples_per_second": 17.148,
      "eval_steps_per_second": 8.575,
      "step": 1
    },
    {
      "epoch": 0.006169150392319408,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.006169150392319408,
      "eval_loss": NaN,
      "eval_runtime": 635.9746,
      "eval_samples_per_second": 17.172,
      "eval_steps_per_second": 8.587,
      "step": 40
    },
    {
      "epoch": 0.012338300784638816,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 80
    },
    {
      "epoch": 0.012338300784638816,
      "eval_loss": NaN,
      "eval_runtime": 635.916,
      "eval_samples_per_second": 17.174,
      "eval_steps_per_second": 8.588,
      "step": 80
    },
    {
      "epoch": 0.018507451176958224,
      "grad_norm": NaN,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 0.0,
      "step": 120
    },
    {
      "epoch": 0.018507451176958224,
      "eval_loss": NaN,
      "eval_runtime": 636.2214,
      "eval_samples_per_second": 17.165,
      "eval_steps_per_second": 8.583,
      "step": 120
    }
  ],
  "logging_steps": 40,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 40,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 8.364653021233152e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}