{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0006444544692917445,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001288908938583489,
      "grad_norm": 8.74660587310791,
      "learning_rate": 1e-05,
      "loss": 11.6995,
      "step": 1
    },
    {
      "epoch": 0.0001288908938583489,
      "eval_loss": 10.968485832214355,
      "eval_runtime": 513.525,
      "eval_samples_per_second": 25.446,
      "eval_steps_per_second": 12.724,
      "step": 1
    },
    {
      "epoch": 0.0002577817877166978,
      "grad_norm": 8.534417152404785,
      "learning_rate": 2e-05,
      "loss": 11.1466,
      "step": 2
    },
    {
      "epoch": 0.0002577817877166978,
      "eval_loss": 10.751652717590332,
      "eval_runtime": 419.4229,
      "eval_samples_per_second": 31.155,
      "eval_steps_per_second": 15.579,
      "step": 2
    },
    {
      "epoch": 0.00038667268157504674,
      "grad_norm": 8.822925567626953,
      "learning_rate": 3e-05,
      "loss": 10.2727,
      "step": 3
    },
    {
      "epoch": 0.0005155635754333956,
      "grad_norm": 8.826478958129883,
      "learning_rate": 4e-05,
      "loss": 10.2251,
      "step": 4
    },
    {
      "epoch": 0.0005155635754333956,
      "eval_loss": 10.3470458984375,
      "eval_runtime": 396.3492,
      "eval_samples_per_second": 32.968,
      "eval_steps_per_second": 16.485,
      "step": 4
    },
    {
      "epoch": 0.0006444544692917445,
      "grad_norm": 8.90781021118164,
      "learning_rate": 5e-05,
      "loss": 10.2026,
      "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": 4115280452124672.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}