Skip to main content

Upup-ashton-wang's group workspace

Timestamps visible
2025-05-31 19:56:30
  "tie_word_embeddings": false,
2025-05-31 19:56:30
  "torch_dtype": "bfloat16",
2025-05-31 19:56:30
  "transformers_version": "4.50.0",
2025-05-31 19:56:30
  "use_cache": true,
2025-05-31 19:56:30
  "use_mrope": false,
2025-05-31 19:56:30
  "use_sliding_window": false,
2025-05-31 19:56:30
  "vocab_size": 151936
2025-05-31 19:56:30
}
2025-05-31 19:56:30

2025-05-31 19:56:30
tokenizer config file saved in /home/omer/shangshang/project/reasoning/reasoning-sae/ckpts/models/DeepSeek-R1-Distill-Qwen-1.5B/grpo_curated_still/checkpoint-50/distill/curated_still/model.layers.12/sft_r1_distill/tokenizer_config.json
2025-05-31 19:56:30
Special tokens file saved in /home/omer/shangshang/project/reasoning/reasoning-sae/ckpts/models/DeepSeek-R1-Distill-Qwen-1.5B/grpo_curated_still/checkpoint-50/distill/curated_still/model.layers.12/sft_r1_distill/special_tokens_map.json
2025-05-31 19:56:30
Final model saved to /home/omer/shangshang/project/reasoning/reasoning-sae/ckpts/models/DeepSeek-R1-Distill-Qwen-1.5B/grpo_curated_still/checkpoint-50/distill/curated_still/model.layers.12/sft_r1_distill
2025-05-31 19:56:30
Training finished.