Skip to main content

Upup-ashton-wang's group workspace

Timestamps visible
2025-05-09 21:20:08
  "tie_word_embeddings": false,
2025-05-09 21:20:08
  "torch_dtype": "bfloat16",
2025-05-09 21:20:08
  "transformers_version": "4.51.1",
2025-05-09 21:20:08
  "use_cache": true,
2025-05-09 21:20:08
  "use_mrope": false,
2025-05-09 21:20:08
  "use_sliding_window": false,
2025-05-09 21:20:08
  "vocab_size": 151936
2025-05-09 21:20:08
}
2025-05-09 21:20:08

2025-05-09 21:20:08
tokenizer config file saved in /project/neiswang_1391/shangsha/reasoning/reasoning-sae/ckpts/models/DeepSeek-R1-Distill-Qwen-1.5B/grpo_curated_still/checkpoint-2000/distill/model.layers.26/sft_r1_distill/tokenizer_config.json
2025-05-09 21:20:08
Special tokens file saved in /project/neiswang_1391/shangsha/reasoning/reasoning-sae/ckpts/models/DeepSeek-R1-Distill-Qwen-1.5B/grpo_curated_still/checkpoint-2000/distill/model.layers.26/sft_r1_distill/special_tokens_map.json
2025-05-09 21:20:08
Final model saved to /project/neiswang_1391/shangsha/reasoning/reasoning-sae/ckpts/models/DeepSeek-R1-Distill-Qwen-1.5B/grpo_curated_still/checkpoint-2000/distill/model.layers.26/sft_r1_distill
2025-05-09 21:20:08
Training finished.