trainer_state.json

{
  "best_metric": 0.0001206793385790661,
  "best_model_checkpoint": "/Users/noga/Work_folder/Notebooks/LLM/classifier/new_classifier/complex_q_model/deberta-v3-bass-complex-questions_classifier/checkpoint-500",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 636,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.358490566037736,
      "grad_norm": 0.005825825501233339,
      "learning_rate": 1.069182389937107e-05,
      "loss": 0.0532,
      "step": 500
    },
    {
      "epoch": 2.358490566037736,
      "eval_Accuracy": 1.0,
      "eval_F1": 1.0,
      "eval_Precision": 1.0,
      "eval_Recall": 1.0,
      "eval_loss": 0.0001206793385790661,
      "eval_runtime": 4.3,
      "eval_samples_per_second": 49.303,
      "eval_steps_per_second": 6.279,
      "step": 500
    },
    {
      "epoch": 3.0,
      "step": 636,
      "total_flos": 175087193647410.0,
      "train_loss": 0.04188158509538234,
      "train_runtime": 276.1616,
      "train_samples_per_second": 18.413,
      "train_steps_per_second": 2.303
    },
    {
      "epoch": 3.0,
      "eval_Accuracy": 1.0,
      "eval_F1": 1.0,
      "eval_Precision": 1.0,
      "eval_Recall": 1.0,
      "eval_loss": 0.0001206793385790661,
      "eval_runtime": 3.6877,
      "eval_samples_per_second": 57.489,
      "eval_steps_per_second": 7.322,
      "step": 636
    },
    {
      "epoch": 3.0,
      "eval_Accuracy": 1.0,
      "eval_F1": 1.0,
      "eval_Precision": 1.0,
      "eval_Recall": 1.0,
      "eval_loss": 0.0001206793385790661,
      "eval_runtime": 3.1147,
      "eval_samples_per_second": 68.065,
      "eval_steps_per_second": 8.669,
      "step": 636
    },
    {
      "epoch": 3.0,
      "eval_Accuracy": 1.0,
      "eval_F1": 1.0,
      "eval_Precision": 1.0,
      "eval_Recall": 1.0,
      "eval_loss": 0.0001206793385790661,
      "eval_runtime": 3.4495,
      "eval_samples_per_second": 61.459,
      "eval_steps_per_second": 7.827,
      "step": 636
    }
  ],
  "logging_steps": 500,
  "max_steps": 636,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 175087193647410.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}