{
  "best_global_step": 640,
  "best_metric": 0.4830421377183967,
  "best_model_checkpoint": "/content/drive/MyDrive/project/MODELS/Surrogates/RoBERTa_LIAR/checkpoint-640",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 640,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.15625,
      "grad_norm": 1.4061976671218872,
      "learning_rate": 1.485e-05,
      "loss": 0.6982453918457031,
      "step": 100
    },
    {
      "epoch": 0.3125,
      "grad_norm": 2.2753427028656006,
      "learning_rate": 2.985e-05,
      "loss": 0.6896881866455078,
      "step": 200
    },
    {
      "epoch": 0.46875,
      "grad_norm": 6.735152721405029,
      "learning_rate": 2.8741525423728816e-05,
      "loss": 0.683045654296875,
      "step": 300
    },
    {
      "epoch": 0.625,
      "grad_norm": 1.8760987520217896,
      "learning_rate": 2.7470338983050847e-05,
      "loss": 0.6780765533447266,
      "step": 400
    },
    {
      "epoch": 0.78125,
      "grad_norm": 1.938730001449585,
      "learning_rate": 2.6199152542372882e-05,
      "loss": 0.6746772766113281,
      "step": 500
    },
    {
      "epoch": 0.9375,
      "grad_norm": 4.237790584564209,
      "learning_rate": 2.4927966101694917e-05,
      "loss": 0.6706379699707031,
      "step": 600
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6082554517133957,
      "eval_f1": 0.4830421377183967,
      "eval_loss": 0.6857937574386597,
      "eval_runtime": 9.9211,
      "eval_samples_per_second": 129.421,
      "eval_steps_per_second": 8.164,
      "step": 640
    }
  ],
  "logging_steps": 100,
  "max_steps": 2560,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "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": 673564301721600.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}