{
  "best_metric": 0.5292332172393799,
  "best_model_checkpoint": "./opt_trained3/checkpoint-30",
  "epoch": 9.353982300884956,
  "eval_steps": 500,
  "global_step": 140,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 0.535097062587738,
      "eval_runtime": 6.0207,
      "eval_samples_per_second": 49.828,
      "eval_steps_per_second": 12.457,
      "step": 15
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.5292332172393799,
      "eval_runtime": 5.9588,
      "eval_samples_per_second": 50.346,
      "eval_steps_per_second": 12.586,
      "step": 30
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.529732346534729,
      "eval_runtime": 5.9913,
      "eval_samples_per_second": 50.073,
      "eval_steps_per_second": 12.518,
      "step": 45
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.5341577529907227,
      "eval_runtime": 6.015,
      "eval_samples_per_second": 49.875,
      "eval_steps_per_second": 12.469,
      "step": 60
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.5368334054946899,
      "eval_runtime": 5.9942,
      "eval_samples_per_second": 50.048,
      "eval_steps_per_second": 12.512,
      "step": 75
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.5420440435409546,
      "eval_runtime": 5.985,
      "eval_samples_per_second": 50.126,
      "eval_steps_per_second": 12.531,
      "step": 90
    },
    {
      "epoch": 7.0,
      "eval_loss": 0.5421682000160217,
      "eval_runtime": 6.0,
      "eval_samples_per_second": 50.0,
      "eval_steps_per_second": 12.5,
      "step": 105
    },
    {
      "epoch": 8.0,
      "eval_loss": 0.5438395142555237,
      "eval_runtime": 6.004,
      "eval_samples_per_second": 49.967,
      "eval_steps_per_second": 12.492,
      "step": 120
    },
    {
      "epoch": 9.0,
      "eval_loss": 0.5451622009277344,
      "eval_runtime": 5.9841,
      "eval_samples_per_second": 50.133,
      "eval_steps_per_second": 12.533,
      "step": 135
    },
    {
      "epoch": 9.353982300884956,
      "eval_loss": 0.5451804399490356,
      "eval_runtime": 6.0344,
      "eval_samples_per_second": 49.715,
      "eval_steps_per_second": 12.429,
      "step": 140
    }
  ],
  "logging_steps": 500,
  "max_steps": 140,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5207869157760000.0,
  "train_batch_size": 24,
  "trial_name": null,
  "trial_params": null
}