{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.021586616297895305,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0010793308148947653,
      "eval_loss": 3.4606893062591553,
      "eval_runtime": 8.2884,
      "eval_samples_per_second": 47.054,
      "eval_steps_per_second": 11.824,
      "step": 1
    },
    {
      "epoch": 0.0032379924446842958,
      "grad_norm": 1.5388087034225464,
      "learning_rate": 3e-05,
      "loss": 3.438,
      "step": 3
    },
    {
      "epoch": 0.005396654074473826,
      "eval_loss": 3.4399232864379883,
      "eval_runtime": 7.4909,
      "eval_samples_per_second": 52.063,
      "eval_steps_per_second": 13.083,
      "step": 5
    },
    {
      "epoch": 0.0064759848893685915,
      "grad_norm": 1.8104335069656372,
      "learning_rate": 6e-05,
      "loss": 3.4754,
      "step": 6
    },
    {
      "epoch": 0.009713977334052886,
      "grad_norm": 1.6199678182601929,
      "learning_rate": 9e-05,
      "loss": 3.4519,
      "step": 9
    },
    {
      "epoch": 0.010793308148947653,
      "eval_loss": 3.337660789489746,
      "eval_runtime": 7.4883,
      "eval_samples_per_second": 52.081,
      "eval_steps_per_second": 13.087,
      "step": 10
    },
    {
      "epoch": 0.012951969778737183,
      "grad_norm": 1.3170945644378662,
      "learning_rate": 0.00012,
      "loss": 3.1893,
      "step": 12
    },
    {
      "epoch": 0.016189962223421478,
      "grad_norm": 1.5403589010238647,
      "learning_rate": 0.00015000000000000001,
      "loss": 3.2198,
      "step": 15
    },
    {
      "epoch": 0.016189962223421478,
      "eval_loss": 3.258420944213867,
      "eval_runtime": 7.5131,
      "eval_samples_per_second": 51.909,
      "eval_steps_per_second": 13.044,
      "step": 15
    },
    {
      "epoch": 0.019427954668105773,
      "grad_norm": 1.4535117149353027,
      "learning_rate": 0.00018,
      "loss": 3.2669,
      "step": 18
    },
    {
      "epoch": 0.021586616297895305,
      "eval_loss": 3.2036073207855225,
      "eval_runtime": 7.5067,
      "eval_samples_per_second": 51.954,
      "eval_steps_per_second": 13.055,
      "step": 20
    }
  ],
  "logging_steps": 3,
  "max_steps": 40,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 20,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 360477150412800.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}