{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.006837606837606838,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006837606837606838,
      "grad_norm": 1.0365716218948364,
      "learning_rate": 2e-05,
      "loss": 2.584,
      "step": 1
    },
    {
      "epoch": 0.0006837606837606838,
      "eval_loss": 2.547212600708008,
      "eval_runtime": 36.1706,
      "eval_samples_per_second": 17.03,
      "eval_steps_per_second": 8.515,
      "step": 1
    },
    {
      "epoch": 0.0013675213675213675,
      "grad_norm": 1.0296660661697388,
      "learning_rate": 4e-05,
      "loss": 2.5779,
      "step": 2
    },
    {
      "epoch": 0.0020512820512820513,
      "grad_norm": 1.046919584274292,
      "learning_rate": 6e-05,
      "loss": 2.5322,
      "step": 3
    },
    {
      "epoch": 0.0020512820512820513,
      "eval_loss": 2.5373823642730713,
      "eval_runtime": 35.1743,
      "eval_samples_per_second": 17.513,
      "eval_steps_per_second": 8.756,
      "step": 3
    },
    {
      "epoch": 0.002735042735042735,
      "grad_norm": 1.3378914594650269,
      "learning_rate": 8e-05,
      "loss": 2.473,
      "step": 4
    },
    {
      "epoch": 0.003418803418803419,
      "grad_norm": 1.1634753942489624,
      "learning_rate": 0.0001,
      "loss": 2.5014,
      "step": 5
    },
    {
      "epoch": 0.0041025641025641026,
      "grad_norm": 1.2586262226104736,
      "learning_rate": 0.00012,
      "loss": 2.4906,
      "step": 6
    },
    {
      "epoch": 0.0041025641025641026,
      "eval_loss": 2.4004569053649902,
      "eval_runtime": 35.1674,
      "eval_samples_per_second": 17.516,
      "eval_steps_per_second": 8.758,
      "step": 6
    },
    {
      "epoch": 0.004786324786324786,
      "grad_norm": 0.9394276738166809,
      "learning_rate": 0.00014,
      "loss": 2.3886,
      "step": 7
    },
    {
      "epoch": 0.00547008547008547,
      "grad_norm": 0.7189363837242126,
      "learning_rate": 0.00016,
      "loss": 2.2585,
      "step": 8
    },
    {
      "epoch": 0.006153846153846154,
      "grad_norm": 0.8059253692626953,
      "learning_rate": 0.00018,
      "loss": 2.3444,
      "step": 9
    },
    {
      "epoch": 0.006153846153846154,
      "eval_loss": 2.279796600341797,
      "eval_runtime": 35.1772,
      "eval_samples_per_second": 17.511,
      "eval_steps_per_second": 8.756,
      "step": 9
    },
    {
      "epoch": 0.006837606837606838,
      "grad_norm": 1.2544615268707275,
      "learning_rate": 0.0002,
      "loss": 2.3451,
      "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": 3699128496291840.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}