{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.000613299397433342,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.13299397433342e-05,
      "grad_norm": 0.8806752562522888,
      "learning_rate": 2e-05,
      "loss": 2.357,
      "step": 1
    },
    {
      "epoch": 6.13299397433342e-05,
      "eval_loss": 2.4521021842956543,
      "eval_runtime": 141.4541,
      "eval_samples_per_second": 48.539,
      "eval_steps_per_second": 24.269,
      "step": 1
    },
    {
      "epoch": 0.0001226598794866684,
      "grad_norm": 0.7658063769340515,
      "learning_rate": 4e-05,
      "loss": 2.4779,
      "step": 2
    },
    {
      "epoch": 0.00018398981923000262,
      "grad_norm": 0.9293619394302368,
      "learning_rate": 6e-05,
      "loss": 2.4326,
      "step": 3
    },
    {
      "epoch": 0.00018398981923000262,
      "eval_loss": 2.4500784873962402,
      "eval_runtime": 140.4939,
      "eval_samples_per_second": 48.87,
      "eval_steps_per_second": 24.435,
      "step": 3
    },
    {
      "epoch": 0.0002453197589733368,
      "grad_norm": 0.7990126609802246,
      "learning_rate": 8e-05,
      "loss": 2.4868,
      "step": 4
    },
    {
      "epoch": 0.000306649698716671,
      "grad_norm": 0.8882917165756226,
      "learning_rate": 0.0001,
      "loss": 2.4513,
      "step": 5
    },
    {
      "epoch": 0.00036797963846000524,
      "grad_norm": 0.8733172416687012,
      "learning_rate": 0.00012,
      "loss": 2.3003,
      "step": 6
    },
    {
      "epoch": 0.00036797963846000524,
      "eval_loss": 2.428741931915283,
      "eval_runtime": 140.9904,
      "eval_samples_per_second": 48.698,
      "eval_steps_per_second": 24.349,
      "step": 6
    },
    {
      "epoch": 0.00042930957820333943,
      "grad_norm": 1.02459716796875,
      "learning_rate": 0.00014,
      "loss": 2.836,
      "step": 7
    },
    {
      "epoch": 0.0004906395179466736,
      "grad_norm": 0.8016303777694702,
      "learning_rate": 0.00016,
      "loss": 2.2533,
      "step": 8
    },
    {
      "epoch": 0.0005519694576900078,
      "grad_norm": 1.0335389375686646,
      "learning_rate": 0.00018,
      "loss": 2.5549,
      "step": 9
    },
    {
      "epoch": 0.0005519694576900078,
      "eval_loss": 2.4033775329589844,
      "eval_runtime": 140.9265,
      "eval_samples_per_second": 48.72,
      "eval_steps_per_second": 24.36,
      "step": 9
    },
    {
      "epoch": 0.000613299397433342,
      "grad_norm": 0.8975516557693481,
      "learning_rate": 0.0002,
      "loss": 2.4865,
      "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": 100167934279680.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}