{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0019425696710083928,
  "eval_steps": 10,
  "global_step": 39,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.9809478743804945e-05,
      "eval_loss": 5.598320484161377,
      "eval_runtime": 366.3802,
      "eval_samples_per_second": 23.074,
      "eval_steps_per_second": 11.537,
      "step": 1
    },
    {
      "epoch": 0.00024904739371902474,
      "grad_norm": 1.6849825382232666,
      "learning_rate": 5e-05,
      "loss": 5.2579,
      "step": 5
    },
    {
      "epoch": 0.0004980947874380495,
      "grad_norm": 4.025472164154053,
      "learning_rate": 0.0001,
      "loss": 5.42,
      "step": 10
    },
    {
      "epoch": 0.0004980947874380495,
      "eval_loss": 5.418887138366699,
      "eval_runtime": 369.3174,
      "eval_samples_per_second": 22.891,
      "eval_steps_per_second": 11.445,
      "step": 10
    },
    {
      "epoch": 0.0007471421811570742,
      "grad_norm": 3.5612637996673584,
      "learning_rate": 9.619397662556435e-05,
      "loss": 4.6641,
      "step": 15
    },
    {
      "epoch": 0.000996189574876099,
      "grad_norm": 4.4747772216796875,
      "learning_rate": 8.535533905932738e-05,
      "loss": 4.7422,
      "step": 20
    },
    {
      "epoch": 0.000996189574876099,
      "eval_loss": 4.1750593185424805,
      "eval_runtime": 369.8356,
      "eval_samples_per_second": 22.859,
      "eval_steps_per_second": 11.429,
      "step": 20
    },
    {
      "epoch": 0.0012452369685951236,
      "grad_norm": 3.614565372467041,
      "learning_rate": 6.91341716182545e-05,
      "loss": 3.1483,
      "step": 25
    },
    {
      "epoch": 0.0014942843623141483,
      "grad_norm": 4.936511993408203,
      "learning_rate": 5e-05,
      "loss": 2.9863,
      "step": 30
    },
    {
      "epoch": 0.0014942843623141483,
      "eval_loss": 3.2937183380126953,
      "eval_runtime": 368.9107,
      "eval_samples_per_second": 22.916,
      "eval_steps_per_second": 11.458,
      "step": 30
    },
    {
      "epoch": 0.001743331756033173,
      "grad_norm": 8.728450775146484,
      "learning_rate": 3.086582838174551e-05,
      "loss": 2.8798,
      "step": 35
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2673865880764416.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}