{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0007082403767838804,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 7.082403767838805e-05,
      "grad_norm": 0.6373308897018433,
      "learning_rate": 2e-05,
      "loss": 3.6413,
      "step": 1
    },
    {
      "epoch": 7.082403767838805e-05,
      "eval_loss": 0.8914219737052917,
      "eval_runtime": 452.3696,
      "eval_samples_per_second": 13.144,
      "eval_steps_per_second": 6.572,
      "step": 1
    },
    {
      "epoch": 0.0001416480753567761,
      "grad_norm": 1.0103040933609009,
      "learning_rate": 4e-05,
      "loss": 2.9528,
      "step": 2
    },
    {
      "epoch": 0.00021247211303516414,
      "grad_norm": 0.8490130305290222,
      "learning_rate": 6e-05,
      "loss": 2.9759,
      "step": 3
    },
    {
      "epoch": 0.00021247211303516414,
      "eval_loss": 0.8907253742218018,
      "eval_runtime": 452.5713,
      "eval_samples_per_second": 13.138,
      "eval_steps_per_second": 6.569,
      "step": 3
    },
    {
      "epoch": 0.0002832961507135522,
      "grad_norm": 1.0399471521377563,
      "learning_rate": 8e-05,
      "loss": 3.8777,
      "step": 4
    },
    {
      "epoch": 0.0003541201883919402,
      "grad_norm": 0.7586168050765991,
      "learning_rate": 0.0001,
      "loss": 2.8813,
      "step": 5
    },
    {
      "epoch": 0.00042494422607032827,
      "grad_norm": 0.767803430557251,
      "learning_rate": 0.00012,
      "loss": 3.3608,
      "step": 6
    },
    {
      "epoch": 0.00042494422607032827,
      "eval_loss": 0.8848316669464111,
      "eval_runtime": 452.486,
      "eval_samples_per_second": 13.141,
      "eval_steps_per_second": 6.57,
      "step": 6
    },
    {
      "epoch": 0.0004957682637487163,
      "grad_norm": 1.7368426322937012,
      "learning_rate": 0.00014,
      "loss": 3.5641,
      "step": 7
    },
    {
      "epoch": 0.0005665923014271044,
      "grad_norm": 1.4394786357879639,
      "learning_rate": 0.00016,
      "loss": 3.8608,
      "step": 8
    },
    {
      "epoch": 0.0006374163391054924,
      "grad_norm": 1.658917784690857,
      "learning_rate": 0.00018,
      "loss": 3.5621,
      "step": 9
    },
    {
      "epoch": 0.0006374163391054924,
      "eval_loss": 0.8459430932998657,
      "eval_runtime": 452.4586,
      "eval_samples_per_second": 13.142,
      "eval_steps_per_second": 6.571,
      "step": 9
    },
    {
      "epoch": 0.0007082403767838804,
      "grad_norm": 1.6583317518234253,
      "learning_rate": 0.0002,
      "loss": 3.9243,
      "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": 4586445943603200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}