{
  "model": "DeBERTa-large",
  "dataset": "ANLI",
  "backbone": "microsoft/deberta-large",
  "run_seed": 1299843651,
  "validation_accuracy": 0.6221875,
  "training": {
    "epochs": 3,
    "batch_size": 16,
    "gradient_accumulation_steps": 2,
    "learning_rate": 1.6958369168519958e-05,
    "weight_decay": 0.1,
    "warmup_ratio": 0.1828387398995507,
    "label_smoothing_factor": 0.1,
    "adam_beta2": 0.999,
    "adam_epsilon": 1e-08,
    "max_grad_norm": 1.0,
    "max_seq_len": 128,
    "fp16": "auto",
    "amp": "fp32"
  },
  "baseline_eval": {
    "validation_accuracy": 0.6221875,
    "test_accuracy": 0.6178125,
    "validation_examples": 3200,
    "test_examples": 3200,
    "validation_split": "dev",
    "test_split": "test"
  },
  "repository": "Lidor-Mashiach/deberta-large-anli",
  "license": "cc-by-nc-4.0",
  "base_model_license": "mit",
  "training_data": "facebook/anli",
  "training_data_license": "cc-by-nc-4.0"
}