trainer_state.json

{
  "best_metric": 0.6923076923076923,
  "best_model_checkpoint": "Output_llama70B_70-15-15/checkpoint-460",
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 460,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5448717948717948,
      "eval_balanced_accuracy": 0.5634387351778656,
      "eval_loss": 0.7988640069961548,
      "eval_runtime": 1019.3156,
      "eval_samples_per_second": 0.153,
      "eval_steps_per_second": 0.01,
      "step": 46
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.5448717948717948,
      "eval_balanced_accuracy": 0.5440013183915623,
      "eval_loss": 0.6930041909217834,
      "eval_runtime": 1019.1843,
      "eval_samples_per_second": 0.153,
      "eval_steps_per_second": 0.01,
      "step": 92
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.6025641025641025,
      "eval_balanced_accuracy": 0.6321133412042503,
      "eval_loss": 0.6272755861282349,
      "eval_runtime": 1019.1074,
      "eval_samples_per_second": 0.153,
      "eval_steps_per_second": 0.01,
      "step": 138
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.5833333333333334,
      "eval_balanced_accuracy": 0.5862126245847177,
      "eval_loss": 0.6713263988494873,
      "eval_runtime": 1019.4022,
      "eval_samples_per_second": 0.153,
      "eval_steps_per_second": 0.01,
      "step": 184
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.6217948717948718,
      "eval_balanced_accuracy": 0.6298076923076923,
      "eval_loss": 0.6084591746330261,
      "eval_runtime": 1018.424,
      "eval_samples_per_second": 0.153,
      "eval_steps_per_second": 0.01,
      "step": 230
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.6538461538461539,
      "eval_balanced_accuracy": 0.6622862286228623,
      "eval_loss": 0.600964367389679,
      "eval_runtime": 1018.008,
      "eval_samples_per_second": 0.153,
      "eval_steps_per_second": 0.01,
      "step": 276
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.6730769230769231,
      "eval_balanced_accuracy": 0.6799788881069668,
      "eval_loss": 0.5909102559089661,
      "eval_runtime": 1019.21,
      "eval_samples_per_second": 0.153,
      "eval_steps_per_second": 0.01,
      "step": 322
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.6602564102564102,
      "eval_balanced_accuracy": 0.6645833333333333,
      "eval_loss": 0.5873510837554932,
      "eval_runtime": 1019.1861,
      "eval_samples_per_second": 0.153,
      "eval_steps_per_second": 0.01,
      "step": 368
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.6666666666666666,
      "eval_balanced_accuracy": 0.6721998951598812,
      "eval_loss": 0.5819327235221863,
      "eval_runtime": 1019.2331,
      "eval_samples_per_second": 0.153,
      "eval_steps_per_second": 0.01,
      "step": 414
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.6923076923076923,
      "eval_balanced_accuracy": 0.7044104410441044,
      "eval_loss": 0.573430061340332,
      "eval_runtime": 1019.4135,
      "eval_samples_per_second": 0.153,
      "eval_steps_per_second": 0.01,
      "step": 460
    },
    {
      "epoch": 10.0,
      "step": 460,
      "total_flos": 2.4377643132882125e+18,
      "train_loss": 0.6270130323327106,
      "train_runtime": 147963.5893,
      "train_samples_per_second": 0.049,
      "train_steps_per_second": 0.003
    }
  ],
  "logging_steps": 500,
  "max_steps": 460,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 10,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.4377643132882125e+18,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}