run-1/checkpoint-166/trainer_state.json

{
  "best_metric": 1.0041351318359375,
  "best_model_checkpoint": "satriadata/run-1/checkpoint-166",
  "epoch": 1.992,
  "eval_steps": 500,
  "global_step": 166,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.996,
      "eval_f1": 0.34139582972404187,
      "eval_loss": 1.5640060901641846,
      "eval_runtime": 15.1373,
      "eval_samples_per_second": 66.062,
      "eval_steps_per_second": 4.162,
      "step": 83
    },
    {
      "epoch": 1.992,
      "eval_f1": 0.6408845370670369,
      "eval_loss": 1.0041351318359375,
      "eval_runtime": 15.1161,
      "eval_samples_per_second": 66.155,
      "eval_steps_per_second": 4.168,
      "step": 166
    }
  ],
  "logging_steps": 500,
  "max_steps": 415,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": {
    "gradient_accumulation_steps": 3,
    "learning_rate": 8.484535826382634e-05,
    "optimizer": "sgd",
    "per_device_train_batch_size": 16,
    "warmup_ratio": 0.3,
    "weight_decay": 0.01
  }
}