{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.04317323259579061,
  "eval_steps": 5,
  "global_step": 40,
  "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
    },
    {
      "epoch": 0.02266594711279007,
      "grad_norm": 1.5158495903015137,
      "learning_rate": 0.00019876883405951377,
      "loss": 2.988,
      "step": 21
    },
    {
      "epoch": 0.025903939557474366,
      "grad_norm": 1.3392220735549927,
      "learning_rate": 0.00018090169943749476,
      "loss": 3.0968,
      "step": 24
    },
    {
      "epoch": 0.026983270372369132,
      "eval_loss": 3.1669328212738037,
      "eval_runtime": 7.5519,
      "eval_samples_per_second": 51.642,
      "eval_steps_per_second": 12.977,
      "step": 25
    },
    {
      "epoch": 0.02914193200215866,
      "grad_norm": 1.2332943677902222,
      "learning_rate": 0.00014539904997395468,
      "loss": 2.9231,
      "step": 27
    },
    {
      "epoch": 0.032379924446842956,
      "grad_norm": 1.3963645696640015,
      "learning_rate": 0.0001,
      "loss": 3.0644,
      "step": 30
    },
    {
      "epoch": 0.032379924446842956,
      "eval_loss": 3.1443722248077393,
      "eval_runtime": 7.4828,
      "eval_samples_per_second": 52.119,
      "eval_steps_per_second": 13.097,
      "step": 30
    },
    {
      "epoch": 0.035617916891527254,
      "grad_norm": 1.5139225721359253,
      "learning_rate": 5.4600950026045326e-05,
      "loss": 3.0966,
      "step": 33
    },
    {
      "epoch": 0.037776578521316787,
      "eval_loss": 3.131291389465332,
      "eval_runtime": 7.4899,
      "eval_samples_per_second": 52.07,
      "eval_steps_per_second": 13.084,
      "step": 35
    },
    {
      "epoch": 0.038855909336211546,
      "grad_norm": 1.2610831260681152,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 3.0009,
      "step": 36
    },
    {
      "epoch": 0.042093901780895844,
      "grad_norm": 1.1377670764923096,
      "learning_rate": 1.231165940486234e-06,
      "loss": 2.957,
      "step": 39
    },
    {
      "epoch": 0.04317323259579061,
      "eval_loss": 3.1287739276885986,
      "eval_runtime": 7.4409,
      "eval_samples_per_second": 52.413,
      "eval_steps_per_second": 13.17,
      "step": 40
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 720954300825600.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}