{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0020816203332674156,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.1632406665348305e-05,
      "eval_loss": 1.0742429494857788,
      "eval_runtime": 1203.9404,
      "eval_samples_per_second": 8.401,
      "eval_steps_per_second": 4.2,
      "step": 1
    },
    {
      "epoch": 0.00020816203332674153,
      "grad_norm": 0.5345484614372253,
      "learning_rate": 5e-05,
      "loss": 1.0408,
      "step": 5
    },
    {
      "epoch": 0.00041632406665348306,
      "grad_norm": 0.9220341444015503,
      "learning_rate": 0.0001,
      "loss": 0.8023,
      "step": 10
    },
    {
      "epoch": 0.00041632406665348306,
      "eval_loss": 0.909618616104126,
      "eval_runtime": 1211.9326,
      "eval_samples_per_second": 8.345,
      "eval_steps_per_second": 4.173,
      "step": 10
    },
    {
      "epoch": 0.0006244860999802246,
      "grad_norm": 1.2763328552246094,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.9267,
      "step": 15
    },
    {
      "epoch": 0.0008326481333069661,
      "grad_norm": 0.7904359698295593,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.7437,
      "step": 20
    },
    {
      "epoch": 0.0008326481333069661,
      "eval_loss": 0.6500961184501648,
      "eval_runtime": 1206.4363,
      "eval_samples_per_second": 8.383,
      "eval_steps_per_second": 4.192,
      "step": 20
    },
    {
      "epoch": 0.0010408101666337078,
      "grad_norm": 1.231951117515564,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.8784,
      "step": 25
    },
    {
      "epoch": 0.0012489721999604491,
      "grad_norm": 0.7472520470619202,
      "learning_rate": 5e-05,
      "loss": 0.7321,
      "step": 30
    },
    {
      "epoch": 0.0012489721999604491,
      "eval_loss": 0.606766939163208,
      "eval_runtime": 1206.6524,
      "eval_samples_per_second": 8.382,
      "eval_steps_per_second": 4.191,
      "step": 30
    },
    {
      "epoch": 0.0014571342332871907,
      "grad_norm": 0.9603462815284729,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.6446,
      "step": 35
    },
    {
      "epoch": 0.0016652962666139322,
      "grad_norm": 1.3737820386886597,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.576,
      "step": 40
    },
    {
      "epoch": 0.0016652962666139322,
      "eval_loss": 0.5835541486740112,
      "eval_runtime": 1207.1343,
      "eval_samples_per_second": 8.379,
      "eval_steps_per_second": 4.189,
      "step": 40
    },
    {
      "epoch": 0.0018734582999406738,
      "grad_norm": 0.8879534602165222,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.7198,
      "step": 45
    },
    {
      "epoch": 0.0020816203332674156,
      "grad_norm": 1.4516291618347168,
      "learning_rate": 0.0,
      "loss": 0.8384,
      "step": 50
    },
    {
      "epoch": 0.0020816203332674156,
      "eval_loss": 0.5801019668579102,
      "eval_runtime": 1207.2168,
      "eval_samples_per_second": 8.378,
      "eval_steps_per_second": 4.189,
      "step": 50
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.826444695044096e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}