{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.014641288433382138,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0014641288433382138,
      "grad_norm": 0.01089260820299387,
      "learning_rate": 2e-05,
      "loss": 11.9308,
      "step": 1
    },
    {
      "epoch": 0.0014641288433382138,
      "eval_loss": 11.931859016418457,
      "eval_runtime": 1.1103,
      "eval_samples_per_second": 259.39,
      "eval_steps_per_second": 129.695,
      "step": 1
    },
    {
      "epoch": 0.0029282576866764276,
      "grad_norm": 0.006957495119422674,
      "learning_rate": 4e-05,
      "loss": 11.9318,
      "step": 2
    },
    {
      "epoch": 0.004392386530014641,
      "grad_norm": 0.008773264475166798,
      "learning_rate": 6e-05,
      "loss": 11.9333,
      "step": 3
    },
    {
      "epoch": 0.004392386530014641,
      "eval_loss": 11.931854248046875,
      "eval_runtime": 1.1567,
      "eval_samples_per_second": 248.983,
      "eval_steps_per_second": 124.491,
      "step": 3
    },
    {
      "epoch": 0.005856515373352855,
      "grad_norm": 0.009967818856239319,
      "learning_rate": 8e-05,
      "loss": 11.9306,
      "step": 4
    },
    {
      "epoch": 0.007320644216691069,
      "grad_norm": 0.00853413064032793,
      "learning_rate": 0.0001,
      "loss": 11.9301,
      "step": 5
    },
    {
      "epoch": 0.008784773060029283,
      "grad_norm": 0.01145976223051548,
      "learning_rate": 0.00012,
      "loss": 11.9311,
      "step": 6
    },
    {
      "epoch": 0.008784773060029283,
      "eval_loss": 11.931822776794434,
      "eval_runtime": 1.189,
      "eval_samples_per_second": 242.217,
      "eval_steps_per_second": 121.109,
      "step": 6
    },
    {
      "epoch": 0.010248901903367497,
      "grad_norm": 0.01229225005954504,
      "learning_rate": 0.00014,
      "loss": 11.9311,
      "step": 7
    },
    {
      "epoch": 0.01171303074670571,
      "grad_norm": 0.01089850626885891,
      "learning_rate": 0.00016,
      "loss": 11.9303,
      "step": 8
    },
    {
      "epoch": 0.013177159590043924,
      "grad_norm": 0.0077802687883377075,
      "learning_rate": 0.00018,
      "loss": 11.9302,
      "step": 9
    },
    {
      "epoch": 0.013177159590043924,
      "eval_loss": 11.931767463684082,
      "eval_runtime": 1.1672,
      "eval_samples_per_second": 246.738,
      "eval_steps_per_second": 123.369,
      "step": 9
    },
    {
      "epoch": 0.014641288433382138,
      "grad_norm": 0.008720969781279564,
      "learning_rate": 0.0002,
      "loss": 11.9318,
      "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": 1181614080.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}