{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0125786163522013,
  "eval_steps": 4,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.050314465408805034,
      "eval_loss": 4.6238532066345215,
      "eval_runtime": 7.3014,
      "eval_samples_per_second": 18.353,
      "eval_steps_per_second": 2.328,
      "step": 1
    },
    {
      "epoch": 0.20125786163522014,
      "eval_loss": 2.7055089473724365,
      "eval_runtime": 7.303,
      "eval_samples_per_second": 18.349,
      "eval_steps_per_second": 2.328,
      "step": 4
    },
    {
      "epoch": 0.4025157232704403,
      "eval_loss": 0.34124085307121277,
      "eval_runtime": 7.2623,
      "eval_samples_per_second": 18.451,
      "eval_steps_per_second": 2.341,
      "step": 8
    },
    {
      "epoch": 0.5031446540880503,
      "grad_norm": 2.018986225128174,
      "learning_rate": 5.868240888334653e-05,
      "loss": 2.1898,
      "step": 10
    },
    {
      "epoch": 0.6037735849056604,
      "eval_loss": 0.010044231079518795,
      "eval_runtime": 7.259,
      "eval_samples_per_second": 18.46,
      "eval_steps_per_second": 2.342,
      "step": 12
    },
    {
      "epoch": 0.8050314465408805,
      "eval_loss": 0.003949903883039951,
      "eval_runtime": 7.3201,
      "eval_samples_per_second": 18.306,
      "eval_steps_per_second": 2.322,
      "step": 16
    },
    {
      "epoch": 1.0125786163522013,
      "grad_norm": 0.1989864557981491,
      "learning_rate": 0.0,
      "loss": 0.0158,
      "step": 20
    },
    {
      "epoch": 1.0125786163522013,
      "eval_loss": 0.003575759707018733,
      "eval_runtime": 7.2525,
      "eval_samples_per_second": 18.476,
      "eval_steps_per_second": 2.344,
      "step": 20
    }
  ],
  "logging_steps": 10,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.918605594066944e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}