{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.07111111111111111,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.014222222222222223,
      "grad_norm": 9.075620651245117,
      "learning_rate": 1e-05,
      "loss": 3.7461,
      "step": 1
    },
    {
      "epoch": 0.014222222222222223,
      "eval_loss": 3.7275147438049316,
      "eval_runtime": 78.3299,
      "eval_samples_per_second": 1.519,
      "eval_steps_per_second": 0.766,
      "step": 1
    },
    {
      "epoch": 0.028444444444444446,
      "grad_norm": 8.784140586853027,
      "learning_rate": 2e-05,
      "loss": 3.6371,
      "step": 2
    },
    {
      "epoch": 0.028444444444444446,
      "eval_loss": 3.5604934692382812,
      "eval_runtime": 3.0095,
      "eval_samples_per_second": 39.541,
      "eval_steps_per_second": 19.937,
      "step": 2
    },
    {
      "epoch": 0.042666666666666665,
      "grad_norm": 8.346254348754883,
      "learning_rate": 3e-05,
      "loss": 3.4886,
      "step": 3
    },
    {
      "epoch": 0.05688888888888889,
      "grad_norm": 7.41143798828125,
      "learning_rate": 4e-05,
      "loss": 3.2963,
      "step": 4
    },
    {
      "epoch": 0.05688888888888889,
      "eval_loss": 3.1900227069854736,
      "eval_runtime": 3.0162,
      "eval_samples_per_second": 39.454,
      "eval_steps_per_second": 19.893,
      "step": 4
    },
    {
      "epoch": 0.07111111111111111,
      "grad_norm": 7.675928115844727,
      "learning_rate": 5e-05,
      "loss": 3.2664,
      "step": 5
    }
  ],
  "logging_steps": 1,
  "max_steps": 5,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3822182832537600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}