{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00831255195344971,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008312551953449709,
      "grad_norm": 3.210545063018799,
      "learning_rate": 2e-05,
      "loss": 10.8636,
      "step": 1
    },
    {
      "epoch": 0.0008312551953449709,
      "eval_loss": 2.586120128631592,
      "eval_runtime": 31.3102,
      "eval_samples_per_second": 16.193,
      "eval_steps_per_second": 8.112,
      "step": 1
    },
    {
      "epoch": 0.0016625103906899418,
      "grad_norm": 1.1623685359954834,
      "learning_rate": 4e-05,
      "loss": 9.5429,
      "step": 2
    },
    {
      "epoch": 0.0024937655860349127,
      "grad_norm": 1.2950330972671509,
      "learning_rate": 6e-05,
      "loss": 8.0154,
      "step": 3
    },
    {
      "epoch": 0.0024937655860349127,
      "eval_loss": 2.584691047668457,
      "eval_runtime": 31.2532,
      "eval_samples_per_second": 16.222,
      "eval_steps_per_second": 8.127,
      "step": 3
    },
    {
      "epoch": 0.0033250207813798837,
      "grad_norm": 0.9268551468849182,
      "learning_rate": 8e-05,
      "loss": 7.8673,
      "step": 4
    },
    {
      "epoch": 0.004156275976724855,
      "grad_norm": 1.3835371732711792,
      "learning_rate": 0.0001,
      "loss": 7.6594,
      "step": 5
    },
    {
      "epoch": 0.004987531172069825,
      "grad_norm": 1.0690666437149048,
      "learning_rate": 0.00012,
      "loss": 6.5273,
      "step": 6
    },
    {
      "epoch": 0.004987531172069825,
      "eval_loss": 2.560739755630493,
      "eval_runtime": 31.2713,
      "eval_samples_per_second": 16.213,
      "eval_steps_per_second": 8.122,
      "step": 6
    },
    {
      "epoch": 0.005818786367414797,
      "grad_norm": 1.2552434206008911,
      "learning_rate": 0.00014,
      "loss": 9.9641,
      "step": 7
    },
    {
      "epoch": 0.006650041562759767,
      "grad_norm": 1.5967458486557007,
      "learning_rate": 0.00016,
      "loss": 10.1167,
      "step": 8
    },
    {
      "epoch": 0.007481296758104738,
      "grad_norm": 1.300879716873169,
      "learning_rate": 0.00018,
      "loss": 7.8274,
      "step": 9
    },
    {
      "epoch": 0.007481296758104738,
      "eval_loss": 2.4344730377197266,
      "eval_runtime": 31.3026,
      "eval_samples_per_second": 16.197,
      "eval_steps_per_second": 8.114,
      "step": 9
    },
    {
      "epoch": 0.00831255195344971,
      "grad_norm": 2.4216034412384033,
      "learning_rate": 0.0002,
      "loss": 8.5235,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3562002343526400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}