checkpoint-6/trainer_state.json

{
  "best_metric": 0.15136542916297913,
  "best_model_checkpoint": "autotrain-wisph-pzwcz/checkpoint-6",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 6,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.5,
      "grad_norm": 12.090883255004883,
      "learning_rate": 5e-05,
      "loss": 0.5994,
      "step": 1
    },
    {
      "epoch": 1.0,
      "grad_norm": 9.593999862670898,
      "learning_rate": 4e-05,
      "loss": 0.4986,
      "step": 2
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 1.0,
      "eval_auc": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.4374377727508545,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 7.1327,
      "eval_samples_per_second": 0.28,
      "eval_steps_per_second": 0.14,
      "step": 2
    },
    {
      "epoch": 1.5,
      "grad_norm": 7.516317367553711,
      "learning_rate": 3e-05,
      "loss": 0.2894,
      "step": 3
    },
    {
      "epoch": 2.0,
      "grad_norm": 3.77394437789917,
      "learning_rate": 2e-05,
      "loss": 0.1336,
      "step": 4
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 1.0,
      "eval_auc": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.22340981662273407,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 6.9914,
      "eval_samples_per_second": 0.286,
      "eval_steps_per_second": 0.143,
      "step": 4
    },
    {
      "epoch": 2.5,
      "grad_norm": 2.1505138874053955,
      "learning_rate": 1e-05,
      "loss": 0.0764,
      "step": 5
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.035268783569336,
      "learning_rate": 0.0,
      "loss": 0.0292,
      "step": 6
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 1.0,
      "eval_auc": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.15136542916297913,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 6.8242,
      "eval_samples_per_second": 0.293,
      "eval_steps_per_second": 0.147,
      "step": 6
    }
  ],
  "logging_steps": 1,
  "max_steps": 6,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.01
      },
      "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": 1.9345532750659584e+16,
  "train_batch_size": 5,
  "trial_name": null,
  "trial_params": null
}