{
  "status": "completed",
  "task": "ViFactCheck-gold-evidence",
  "dataset": "ViFactCheck",
  "model_key": "cafebert",
  "model_name": "CafeBERT",
  "model_id": "uitnlp/CafeBERT",
  "base_revision": "af76fcf2a04096b2b54b348a3e4eb48253c93c5d",
  "seed": 22,
  "split_seed": 42,
  "smoke_test": false,
  "epochs": 3,
  "num_labels": 3,
  "max_length": 256,
  "micro_batch_size": 8,
  "gradient_accumulation_steps": 1,
  "effective_batch_size": 8,
  "pair_truncation": "only_second",
  "per_device_eval_batch_size": 8,
  "bf16": true,
  "tf32": true,
  "text_mode_resolved": "raw",
  "tokenizer_class": "XLMRobertaTokenizer",
  "model_class": "XLMRobertaForSequenceClassification",
  "model_type": "xlm-roberta",
  "best_checkpoint": "/content/EACL_2027_ViFactCheck/runs_ml256_bs8_a10080_fast3/vifactcheck-gold-evidence/cafebert/seed-22/trainer_mb8_ga1/checkpoint-1448",
  "best_metric": 0.877927163365246,
  "best_model_dir": "/content/EACL_2027_ViFactCheck/runs_ml256_bs8_a10080_fast3/vifactcheck-gold-evidence/cafebert/seed-22/best_model",
  "train_loss": 0.4863966841724037,
  "wall_seconds": 1002.8455836772919,
  "dev_accuracy": 0.8782849239280774,
  "dev_macro_precision": 0.8855009427422408,
  "dev_macro_recall": 0.8775841720945765,
  "dev_macro_f1": 0.877927163365246,
  "dev_weighted_f1": 0.8777865391744495,
  "test_accuracy": 0.8660220994475138,
  "test_macro_precision": 0.8717446695992885,
  "test_macro_recall": 0.865115061196397,
  "test_macro_f1": 0.8648359689576693,
  "test_weighted_f1": 0.8647007066624405,
  "completed_at_utc": "2026-07-23T12:21:41.410322+00:00"
}