{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.014831294030404153,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0014831294030404152,
      "grad_norm": 8.164679527282715,
      "learning_rate": 2e-05,
      "loss": 1.7006,
      "step": 1
    },
    {
      "epoch": 0.0014831294030404152,
      "eval_loss": 1.4715429544448853,
      "eval_runtime": 18.4035,
      "eval_samples_per_second": 30.483,
      "eval_steps_per_second": 15.269,
      "step": 1
    },
    {
      "epoch": 0.0029662588060808304,
      "grad_norm": 7.999344825744629,
      "learning_rate": 4e-05,
      "loss": 1.6064,
      "step": 2
    },
    {
      "epoch": 0.004449388209121246,
      "grad_norm": 5.094561576843262,
      "learning_rate": 6e-05,
      "loss": 1.3025,
      "step": 3
    },
    {
      "epoch": 0.004449388209121246,
      "eval_loss": 1.320305585861206,
      "eval_runtime": 17.8677,
      "eval_samples_per_second": 31.397,
      "eval_steps_per_second": 15.727,
      "step": 3
    },
    {
      "epoch": 0.005932517612161661,
      "grad_norm": 6.03741979598999,
      "learning_rate": 8e-05,
      "loss": 1.3999,
      "step": 4
    },
    {
      "epoch": 0.007415647015202077,
      "grad_norm": 3.8657264709472656,
      "learning_rate": 0.0001,
      "loss": 0.8344,
      "step": 5
    },
    {
      "epoch": 0.008898776418242492,
      "grad_norm": 5.049862861633301,
      "learning_rate": 0.00012,
      "loss": 1.1745,
      "step": 6
    },
    {
      "epoch": 0.008898776418242492,
      "eval_loss": 0.8342015743255615,
      "eval_runtime": 17.985,
      "eval_samples_per_second": 31.193,
      "eval_steps_per_second": 15.624,
      "step": 6
    },
    {
      "epoch": 0.010381905821282907,
      "grad_norm": 3.3451175689697266,
      "learning_rate": 0.00014,
      "loss": 0.7574,
      "step": 7
    },
    {
      "epoch": 0.011865035224323322,
      "grad_norm": 2.8645260334014893,
      "learning_rate": 0.00016,
      "loss": 0.7327,
      "step": 8
    },
    {
      "epoch": 0.013348164627363738,
      "grad_norm": 2.9985406398773193,
      "learning_rate": 0.00018,
      "loss": 0.5756,
      "step": 9
    },
    {
      "epoch": 0.013348164627363738,
      "eval_loss": 0.5900692939758301,
      "eval_runtime": 17.9785,
      "eval_samples_per_second": 31.204,
      "eval_steps_per_second": 15.63,
      "step": 9
    },
    {
      "epoch": 0.014831294030404153,
      "grad_norm": 3.1295952796936035,
      "learning_rate": 0.0002,
      "loss": 0.6475,
      "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": 720954300825600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}