{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.7092198581560284,
  "eval_steps": 20,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07092198581560284,
      "grad_norm": 0.4411725103855133,
      "learning_rate": 9.775413711583924e-05,
      "loss": 0.4587,
      "step": 20
    },
    {
      "epoch": 0.07092198581560284,
      "eval_valid_loss": 0.5579081773757935,
      "eval_valid_runtime": 0.5769,
      "eval_valid_samples_per_second": 26.003,
      "eval_valid_steps_per_second": 3.467,
      "step": 20
    },
    {
      "epoch": 0.07092198581560284,
      "eval_test_loss": 0.4375748336315155,
      "eval_test_runtime": 17.9126,
      "eval_test_samples_per_second": 26.797,
      "eval_test_steps_per_second": 3.35,
      "step": 20
    },
    {
      "epoch": 0.14184397163120568,
      "grad_norm": 0.3396584689617157,
      "learning_rate": 9.539007092198582e-05,
      "loss": 0.39,
      "step": 40
    },
    {
      "epoch": 0.14184397163120568,
      "eval_valid_loss": 0.5398206114768982,
      "eval_valid_runtime": 0.576,
      "eval_valid_samples_per_second": 26.044,
      "eval_valid_steps_per_second": 3.472,
      "step": 40
    },
    {
      "epoch": 0.14184397163120568,
      "eval_test_loss": 0.4187872111797333,
      "eval_test_runtime": 17.9258,
      "eval_test_samples_per_second": 26.777,
      "eval_test_steps_per_second": 3.347,
      "step": 40
    },
    {
      "epoch": 0.2127659574468085,
      "grad_norm": 0.40809884667396545,
      "learning_rate": 9.302600472813238e-05,
      "loss": 0.3838,
      "step": 60
    },
    {
      "epoch": 0.2127659574468085,
      "eval_valid_loss": 0.5342534184455872,
      "eval_valid_runtime": 0.576,
      "eval_valid_samples_per_second": 26.04,
      "eval_valid_steps_per_second": 3.472,
      "step": 60
    },
    {
      "epoch": 0.2127659574468085,
      "eval_test_loss": 0.4113999009132385,
      "eval_test_runtime": 17.9356,
      "eval_test_samples_per_second": 26.762,
      "eval_test_steps_per_second": 3.345,
      "step": 60
    },
    {
      "epoch": 0.28368794326241137,
      "grad_norm": 0.3752501904964447,
      "learning_rate": 9.066193853427897e-05,
      "loss": 0.3455,
      "step": 80
    },
    {
      "epoch": 0.28368794326241137,
      "eval_valid_loss": 0.5170475244522095,
      "eval_valid_runtime": 0.5767,
      "eval_valid_samples_per_second": 26.01,
      "eval_valid_steps_per_second": 3.468,
      "step": 80
    },
    {
      "epoch": 0.28368794326241137,
      "eval_test_loss": 0.40657365322113037,
      "eval_test_runtime": 17.9295,
      "eval_test_samples_per_second": 26.772,
      "eval_test_steps_per_second": 3.346,
      "step": 80
    },
    {
      "epoch": 0.3546099290780142,
      "grad_norm": 0.399515300989151,
      "learning_rate": 8.829787234042553e-05,
      "loss": 0.3501,
      "step": 100
    },
    {
      "epoch": 0.3546099290780142,
      "eval_valid_loss": 0.5137313604354858,
      "eval_valid_runtime": 0.5779,
      "eval_valid_samples_per_second": 25.958,
      "eval_valid_steps_per_second": 3.461,
      "step": 100
    },
    {
      "epoch": 0.3546099290780142,
      "eval_test_loss": 0.40371188521385193,
      "eval_test_runtime": 17.9374,
      "eval_test_samples_per_second": 26.76,
      "eval_test_steps_per_second": 3.345,
      "step": 100
    },
    {
      "epoch": 0.425531914893617,
      "grad_norm": 0.3764987885951996,
      "learning_rate": 8.593380614657211e-05,
      "loss": 0.3521,
      "step": 120
    },
    {
      "epoch": 0.425531914893617,
      "eval_valid_loss": 0.5120474100112915,
      "eval_valid_runtime": 0.577,
      "eval_valid_samples_per_second": 25.996,
      "eval_valid_steps_per_second": 3.466,
      "step": 120
    },
    {
      "epoch": 0.425531914893617,
      "eval_test_loss": 0.40052852034568787,
      "eval_test_runtime": 17.9379,
      "eval_test_samples_per_second": 26.759,
      "eval_test_steps_per_second": 3.345,
      "step": 120
    },
    {
      "epoch": 0.49645390070921985,
      "grad_norm": 0.4307573437690735,
      "learning_rate": 8.356973995271869e-05,
      "loss": 0.3523,
      "step": 140
    },
    {
      "epoch": 0.49645390070921985,
      "eval_valid_loss": 0.5145517587661743,
      "eval_valid_runtime": 0.5771,
      "eval_valid_samples_per_second": 25.992,
      "eval_valid_steps_per_second": 3.466,
      "step": 140
    },
    {
      "epoch": 0.49645390070921985,
      "eval_test_loss": 0.3979322016239166,
      "eval_test_runtime": 17.9342,
      "eval_test_samples_per_second": 26.765,
      "eval_test_steps_per_second": 3.346,
      "step": 140
    },
    {
      "epoch": 0.5673758865248227,
      "grad_norm": 0.42571648955345154,
      "learning_rate": 8.120567375886525e-05,
      "loss": 0.3463,
      "step": 160
    },
    {
      "epoch": 0.5673758865248227,
      "eval_valid_loss": 0.5077592134475708,
      "eval_valid_runtime": 0.5775,
      "eval_valid_samples_per_second": 25.972,
      "eval_valid_steps_per_second": 3.463,
      "step": 160
    },
    {
      "epoch": 0.5673758865248227,
      "eval_test_loss": 0.39705216884613037,
      "eval_test_runtime": 17.9327,
      "eval_test_samples_per_second": 26.767,
      "eval_test_steps_per_second": 3.346,
      "step": 160
    },
    {
      "epoch": 0.6382978723404256,
      "grad_norm": 0.43494898080825806,
      "learning_rate": 7.884160756501182e-05,
      "loss": 0.3345,
      "step": 180
    },
    {
      "epoch": 0.6382978723404256,
      "eval_valid_loss": 0.5126659274101257,
      "eval_valid_runtime": 0.577,
      "eval_valid_samples_per_second": 25.999,
      "eval_valid_steps_per_second": 3.466,
      "step": 180
    },
    {
      "epoch": 0.6382978723404256,
      "eval_test_loss": 0.39509347081184387,
      "eval_test_runtime": 17.9456,
      "eval_test_samples_per_second": 26.747,
      "eval_test_steps_per_second": 3.343,
      "step": 180
    },
    {
      "epoch": 0.7092198581560284,
      "grad_norm": 0.4940604269504547,
      "learning_rate": 7.64775413711584e-05,
      "loss": 0.3194,
      "step": 200
    },
    {
      "epoch": 0.7092198581560284,
      "eval_valid_loss": 0.5195654034614563,
      "eval_valid_runtime": 0.5773,
      "eval_valid_samples_per_second": 25.984,
      "eval_valid_steps_per_second": 3.465,
      "step": 200
    },
    {
      "epoch": 0.7092198581560284,
      "eval_test_loss": 0.39300256967544556,
      "eval_test_runtime": 17.9386,
      "eval_test_samples_per_second": 26.758,
      "eval_test_steps_per_second": 3.345,
      "step": 200
    }
  ],
  "logging_steps": 20,
  "max_steps": 846,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.64884088471552e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}