checkpoint-10/trainer_state.json

{
  "best_metric": 0.02143952250480652,
  "best_model_checkpoint": "autotrain-lr1y2-upf18/checkpoint-10",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.5,
      "grad_norm": 9.743551254272461,
      "learning_rate": 5e-05,
      "loss": 0.7475,
      "step": 1
    },
    {
      "epoch": 1.0,
      "grad_norm": 8.557718276977539,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 0.6613,
      "step": 2
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 1.0,
      "eval_auc": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.31733882427215576,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 0.7944,
      "eval_samples_per_second": 5.035,
      "eval_steps_per_second": 1.259,
      "step": 2
    },
    {
      "epoch": 1.5,
      "grad_norm": 5.864255428314209,
      "learning_rate": 3.888888888888889e-05,
      "loss": 0.3906,
      "step": 3
    },
    {
      "epoch": 2.0,
      "grad_norm": 5.040473937988281,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.2288,
      "step": 4
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 1.0,
      "eval_auc": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.10309673100709915,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 0.875,
      "eval_samples_per_second": 4.572,
      "eval_steps_per_second": 1.143,
      "step": 4
    },
    {
      "epoch": 2.5,
      "grad_norm": 2.2815959453582764,
      "learning_rate": 2.777777777777778e-05,
      "loss": 0.1414,
      "step": 5
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.7566968202590942,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 0.0916,
      "step": 6
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 1.0,
      "eval_auc": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.043794408440589905,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 0.9691,
      "eval_samples_per_second": 4.127,
      "eval_steps_per_second": 1.032,
      "step": 6
    },
    {
      "epoch": 3.5,
      "grad_norm": 1.2300028800964355,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.0645,
      "step": 7
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.9242731332778931,
      "learning_rate": 1.1111111111111112e-05,
      "loss": 0.0478,
      "step": 8
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 1.0,
      "eval_auc": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.026518918573856354,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 0.9106,
      "eval_samples_per_second": 4.393,
      "eval_steps_per_second": 1.098,
      "step": 8
    },
    {
      "epoch": 4.5,
      "grad_norm": 0.726085901260376,
      "learning_rate": 5.555555555555556e-06,
      "loss": 0.0379,
      "step": 9
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.7212420701980591,
      "learning_rate": 0.0,
      "loss": 0.035,
      "step": 10
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 1.0,
      "eval_auc": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.02143952250480652,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 0.961,
      "eval_samples_per_second": 4.162,
      "eval_steps_per_second": 1.041,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.01
      },
      "attributes": {
        "early_stopping_patience_counter": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5262221107200.0,
  "train_batch_size": 10,
  "trial_name": null,
  "trial_params": null
}