{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.022026431718061675,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0022026431718061676,
      "grad_norm": 0.04563008248806,
      "learning_rate": 2e-05,
      "loss": 10.3793,
      "step": 1
    },
    {
      "epoch": 0.0022026431718061676,
      "eval_loss": 10.370171546936035,
      "eval_runtime": 1.9856,
      "eval_samples_per_second": 96.695,
      "eval_steps_per_second": 48.348,
      "step": 1
    },
    {
      "epoch": 0.004405286343612335,
      "grad_norm": 0.05347393825650215,
      "learning_rate": 4e-05,
      "loss": 10.3731,
      "step": 2
    },
    {
      "epoch": 0.006607929515418502,
      "grad_norm": 0.04277149960398674,
      "learning_rate": 6e-05,
      "loss": 10.3613,
      "step": 3
    },
    {
      "epoch": 0.006607929515418502,
      "eval_loss": 10.370158195495605,
      "eval_runtime": 1.9827,
      "eval_samples_per_second": 96.838,
      "eval_steps_per_second": 48.419,
      "step": 3
    },
    {
      "epoch": 0.00881057268722467,
      "grad_norm": 0.037200022488832474,
      "learning_rate": 8e-05,
      "loss": 10.3669,
      "step": 4
    },
    {
      "epoch": 0.011013215859030838,
      "grad_norm": 0.05965028330683708,
      "learning_rate": 0.0001,
      "loss": 10.3635,
      "step": 5
    },
    {
      "epoch": 0.013215859030837005,
      "grad_norm": 0.03880951926112175,
      "learning_rate": 0.00012,
      "loss": 10.3662,
      "step": 6
    },
    {
      "epoch": 0.013215859030837005,
      "eval_loss": 10.370064735412598,
      "eval_runtime": 1.9989,
      "eval_samples_per_second": 96.053,
      "eval_steps_per_second": 48.026,
      "step": 6
    },
    {
      "epoch": 0.015418502202643172,
      "grad_norm": 0.04487929865717888,
      "learning_rate": 0.00014,
      "loss": 10.3632,
      "step": 7
    },
    {
      "epoch": 0.01762114537444934,
      "grad_norm": 0.05759178474545479,
      "learning_rate": 0.00016,
      "loss": 10.3781,
      "step": 8
    },
    {
      "epoch": 0.019823788546255508,
      "grad_norm": 0.04608412832021713,
      "learning_rate": 0.00018,
      "loss": 10.3643,
      "step": 9
    },
    {
      "epoch": 0.019823788546255508,
      "eval_loss": 10.369918823242188,
      "eval_runtime": 2.0082,
      "eval_samples_per_second": 95.609,
      "eval_steps_per_second": 47.805,
      "step": 9
    },
    {
      "epoch": 0.022026431718061675,
      "grad_norm": 0.04317212104797363,
      "learning_rate": 0.0002,
      "loss": 10.3794,
      "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": 129309081600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}