checkpoint-6/trainer_state.json

{
  "best_metric": 1.6360101699829102,
  "best_model_checkpoint": "autotrain-ai-detection/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": 67.11053466796875,
      "learning_rate": 5e-05,
      "loss": 0.2288,
      "step": 1
    },
    {
      "epoch": 1.0,
      "grad_norm": 12.405567169189453,
      "learning_rate": 4e-05,
      "loss": 0.0293,
      "step": 2
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6666666666666666,
      "eval_auc": 0.0,
      "eval_f1": 0.0,
      "eval_loss": 2.797226667404175,
      "eval_precision": 0.0,
      "eval_recall": 0.0,
      "eval_runtime": 1.0634,
      "eval_samples_per_second": 2.821,
      "eval_steps_per_second": 0.94,
      "step": 2
    },
    {
      "epoch": 1.5,
      "grad_norm": 172.7128448486328,
      "learning_rate": 3e-05,
      "loss": 0.9881,
      "step": 3
    },
    {
      "epoch": 2.0,
      "grad_norm": 365.2555847167969,
      "learning_rate": 2e-05,
      "loss": 5.6348,
      "step": 4
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.6666666666666666,
      "eval_auc": 0.0,
      "eval_f1": 0.0,
      "eval_loss": 2.092874765396118,
      "eval_precision": 0.0,
      "eval_recall": 0.0,
      "eval_runtime": 1.119,
      "eval_samples_per_second": 2.681,
      "eval_steps_per_second": 0.894,
      "step": 4
    },
    {
      "epoch": 2.5,
      "grad_norm": 6.614980220794678,
      "learning_rate": 1e-05,
      "loss": 0.0195,
      "step": 5
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.002860192209482193,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.6666666666666666,
      "eval_auc": 0.0,
      "eval_f1": 0.0,
      "eval_loss": 1.6360101699829102,
      "eval_precision": 0.0,
      "eval_recall": 0.0,
      "eval_runtime": 1.229,
      "eval_samples_per_second": 2.441,
      "eval_steps_per_second": 0.814,
      "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": 2115330001956864.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}