| *.7z filter=lfs diff=lfs merge=lfs -text |
| *.arrow filter=lfs diff=lfs merge=lfs -text |
| *.bin filter=lfs diff=lfs merge=lfs -text |
| *.bz2 filter=lfs diff=lfs merge=lfs -text |
| *.ckpt filter=lfs diff=lfs merge=lfs -text |
| *.ftz filter=lfs diff=lfs merge=lfs -text |
| *.gz filter=lfs diff=lfs merge=lfs -text |
| *.h5 filter=lfs diff=lfs merge=lfs -text |
| *.joblib filter=lfs diff=lfs merge=lfs -text |
| *.lfs.* filter=lfs diff=lfs merge=lfs -text |
| *.mlmodel filter=lfs diff=lfs merge=lfs -text |
| *.model filter=lfs diff=lfs merge=lfs -text |
| *.msgpack filter=lfs diff=lfs merge=lfs -text |
| *.npy filter=lfs diff=lfs merge=lfs -text |
| *.npz filter=lfs diff=lfs merge=lfs -text |
| *.onnx filter=lfs diff=lfs merge=lfs -text |
| *.ot filter=lfs diff=lfs merge=lfs -text |
| *.parquet filter=lfs diff=lfs merge=lfs -text |
| *.pb filter=lfs diff=lfs merge=lfs -text |
| *.pickle filter=lfs diff=lfs merge=lfs -text |
| *.pkl filter=lfs diff=lfs merge=lfs -text |
| *.pt filter=lfs diff=lfs merge=lfs -text |
| *.pth filter=lfs diff=lfs merge=lfs -text |
| *.rar filter=lfs diff=lfs merge=lfs -text |
| *.safetensors filter=lfs diff=lfs merge=lfs -text |
| saved_model/**/* filter=lfs diff=lfs merge=lfs -text |
| *.tar.* filter=lfs diff=lfs merge=lfs -text |
| *.tar filter=lfs diff=lfs merge=lfs -text |
| *.tflite filter=lfs diff=lfs merge=lfs -text |
| *.tgz filter=lfs diff=lfs merge=lfs -text |
| *.wasm filter=lfs diff=lfs merge=lfs -text |
| *.xz filter=lfs diff=lfs merge=lfs -text |
| *.zip filter=lfs diff=lfs merge=lfs -text |
| *.zst filter=lfs diff=lfs merge=lfs -text |
| *tfevents* filter=lfs diff=lfs merge=lfs -text |
| Qwen2.5-3B-Instruct-polaris-AdamW-GRPO-bsz16-step64/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Qwen2.5-3B-Instruct-polaris-AdamW-GRPO-bsz32-step64/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Qwen2.5-3B-Instruct-polaris-AdamW-GRPO/bsz32/step64/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Qwen2.5-3B-Instruct-polaris-AdamW-GRPO/bsz32/step128/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Qwen2.5-3B-Instruct-polaris-AdamW-GRPO/bsz32/step192/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Qwen2.5-3B-Instruct-polaris-AdamW-GRPO/bsz32/step256/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Qwen2.5-3B-Instruct-polaris-AdamW-GRPO/bsz64/step64/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Qwen2.5-3B-Instruct-polaris-AdamW-GRPO/bsz64/step128/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Qwen2.5-3B-Instruct-polaris-AdamW-GRPO/bsz64/step192/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Qwen2.5-3B-Instruct-polaris-AdamW-GRPO/bsz64/step256/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Qwen2.5-3B-Instruct-polaris-AdamW-GRPO/bsz32/step320/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Qwen2.5-3B-Instruct-polaris-AdamW-GRPO/bsz32/step384/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Qwen2.5-3B-Instruct-polaris-AdamW-GRPO/bsz32/step448/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Qwen2.5-3B-Instruct-polaris-AdamW-GRPO/bsz32/step512/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Qwen2.5-3B-Instruct-polaris-AdamW-GRPO/bsz64/step384/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Qwen2.5-3B-Instruct-polaris-AdamW-GRPO/bsz64/step448/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Qwen2.5-3B-Instruct-polaris-AdamW-GRPO/bsz64/step512/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Qwen2.5-3B-Instruct-polaris-AdamW-GRPO/bsz128/step64/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Qwen2.5-3B-Instruct-polaris-AdamW-GRPO/bsz128/step128/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Qwen2.5-3B-Instruct-polaris-AdamW-GRPO/bsz128/step192/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Qwen2.5-3B-Instruct-polaris-AdamW-GRPO/bsz128/step256/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Qwen2.5-3B-Instruct-polaris-AdamW-GRPO/bsz128/step320/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Qwen2.5-3B-Instruct-polaris-AdamW-GRPO/bsz128/step384/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Qwen2.5-3B-Instruct-polaris-AdamW-GRPO/bsz128/step448/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Qwen2.5-3B-Instruct-polaris-AdamW-GRPO/bsz128/step512/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Qwen2.5-3B-Instruct-polaris-AdamW-GRPO/bsz256/step64/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Qwen2.5-3B-Instruct-polaris-AdamW-GRPO/bsz256/step128/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Qwen2.5-3B-Instruct-polaris-AdamW-GRPO/bsz256/step192/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Qwen2.5-3B-Instruct-polaris-AdamW-GRPO/bsz256/step256/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Qwen2.5-3B-Instruct-polaris-AdamW-GRPO/bsz256/step320/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Qwen2.5-3B-Instruct-polaris-AdamW-GRPO/bsz256/step384/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Qwen2.5-3B-Instruct-polaris-AdamW-GRPO/bsz256/step448/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Qwen2.5-3B-Instruct-polaris-AdamW-GRPO/bsz256/step512/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Llama-3.2-3B-Instruct-polaris-GRPO--bsz32/global_step_192/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_64/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Llama-3.2-3B-Instruct-polaris-GRPO--bsz256/global_step_512/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Llama-3.2-3B-Instruct-polaris-GRPO--bsz512/global_step_192/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_256/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_192/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Llama-3.2-3B-Instruct-polaris-GRPO--bsz32/global_step_320/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Llama-3.2-3B-Instruct-polaris-GRPO--bsz32/global_step_512/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_256/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Llama-3.2-3B-Instruct-polaris-GRPO--bsz64/global_step_320/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_128/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Llama-3.2-3B-Instruct-polaris-GRPO--bsz256/global_step_128/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Llama-3.2-3B-Instruct-polaris-GRPO--bsz32/global_step_256/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Llama-3.2-3B-Instruct-polaris-GRPO--bsz256/global_step_384/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Llama-3.2-3B-Instruct-polaris-GRPO--bsz512/global_step_448/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Llama-3.2-3B-Instruct-polaris-GRPO--bsz64/global_step_192/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Llama-3.2-3B-Instruct-polaris-GRPO--bsz512/global_step_384/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_512/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_128/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Llama-3.2-3B-Instruct-polaris-GRPO--bsz256/global_step_448/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_512/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Llama-3.2-3B-Instruct-polaris-GRPO--bsz512/global_step_320/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Llama-3.2-3B-Instruct-polaris-GRPO--bsz64/global_step_128/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Llama-3.2-3B-Instruct-polaris-GRPO--bsz64/global_step_256/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Llama-3.2-3B-Instruct-polaris-GRPO--bsz64/global_step_384/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Llama-3.2-3B-Instruct-polaris-GRPO--bsz64/global_step_64/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Llama-3.2-3B-Instruct-polaris-GRPO--bsz256/global_step_256/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Llama-3.2-3B-Instruct-polaris-GRPO--bsz64/global_step_448/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_64/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Llama-3.2-3B-Instruct-polaris-GRPO--bsz256/global_step_320/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_448/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Llama-3.2-3B-Instruct-polaris-GRPO--bsz512/global_step_512/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_448/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Llama-3.2-3B-Instruct-polaris-GRPO--bsz64/global_step_512/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Llama-3.2-3B-Instruct-polaris-GRPO--bsz32/global_step_448/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Llama-3.2-3B-Instruct-polaris-GRPO--bsz32/global_step_64/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Llama-3.2-3B-Instruct-polaris-GRPO--bsz256/global_step_192/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Llama-3.2-3B-Instruct-polaris-GRPO--bsz512/global_step_256/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Llama-3.2-3B-Instruct-polaris-GRPO--bsz32/global_step_128/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_192/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Llama-3.2-3B-Instruct-polaris-GRPO--bsz512/global_step_128/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Llama-3.2-3B-Instruct-polaris-GRPO--bsz512/global_step_64/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_384/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_384/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_320/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Llama-3.2-3B-Instruct-polaris-GRPO--bsz32/global_step_384/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_320/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Llama-3.2-3B-Instruct-polaris-GRPO--bsz256/global_step_64/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| synthetic/Qwen2.5-0.5B-GSM8k-synthetic.jsonl filter=lfs diff=lfs merge=lfs -text |
| synthetic/Qwen2.5-3B-Instruct-Polaris/polaris_t0.7_p1.0_n32-MNT3072.jsonl filter=lfs diff=lfs merge=lfs -text |
| global_step_124/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| global_step_186/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| global_step_248/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| global_step_310/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| global_step_372/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| global_step_434/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| global_step_496/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| global_step_62/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Qwen2.5-3B-Instruct-polaris-AdamW-GRPO/bsz16/step512/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Qwen2.5-3B-Instruct-polaris-AdamW-GRPO/bsz1024/step512/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| Qwen2.5-3B-Instruct-polaris-AdamW-GRPO/bsz2048/step512/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/base/aime24_t0.6_p0.95_n1280-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/base/aime25_t0.6_p0.95_n1280-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/base/math-500_t0.6_p0.95_n192-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/base/minerva_t0.6_p0.95_n192-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/base/olympiad-bench_t0.6_p0.95_n192-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/global_step_128/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/global_step_192/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/global_step_256/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/global_step_320/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/global_step_384/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/global_step_448/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/global_step_512/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/global_step_64/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-3/global_step_128/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-3/global_step_192/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-3/global_step_256/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-3/global_step_320/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-3/global_step_384/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-3/global_step_448/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-3/global_step_512/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-3/global_step_64/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-4/global_step_128/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-4/global_step_192/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-4/global_step_256/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-4/global_step_320/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-4/global_step_384/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-4/global_step_448/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-4/global_step_512/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-4/global_step_64/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-5e-3/global_step_128/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-5e-3/global_step_192/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-5e-3/global_step_256/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-5e-3/global_step_320/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-5e-3/global_step_384/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-5e-3/global_step_448/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-5e-3/global_step_512/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-5e-3/global_step_64/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-polaris-GRPO-SGD-1e-2/global_step_128/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-polaris-GRPO-SGD-1e-2/global_step_192/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-polaris-GRPO-SGD-1e-2/global_step_64/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-polaris-GRPO-SGD-1e-3/global_step_128/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-polaris-GRPO-SGD-1e-3/global_step_192/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-polaris-GRPO-SGD-1e-3/global_step_256/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-polaris-GRPO-SGD-1e-3/global_step_320/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-polaris-GRPO-SGD-1e-3/global_step_384/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-polaris-GRPO-SGD-1e-3/global_step_448/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-polaris-GRPO-SGD-1e-3/global_step_512/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-polaris-GRPO-SGD-1e-3/global_step_64/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-polaris-GRPO-SGD-1e-4/global_step_128/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-polaris-GRPO-SGD-1e-4/global_step_192/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-polaris-GRPO-SGD-1e-4/global_step_256/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-polaris-GRPO-SGD-1e-4/global_step_320/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-polaris-GRPO-SGD-1e-4/global_step_384/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-polaris-GRPO-SGD-1e-4/global_step_448/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-polaris-GRPO-SGD-1e-4/global_step_512/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-polaris-GRPO-SGD-1e-4/global_step_64/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-polaris-GRPO-SGD-5e-3/global_step_128/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-polaris-GRPO-SGD-5e-3/global_step_192/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-polaris-GRPO-SGD-5e-3/global_step_256/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-polaris-GRPO-SGD-5e-3/global_step_320/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-polaris-GRPO-SGD-5e-3/global_step_384/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-polaris-GRPO-SGD-5e-3/global_step_448/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-polaris-GRPO-SGD-5e-3/global_step_512/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-polaris-GRPO-SGD-5e-3/global_step_64/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_bsz1024_step512_adamw/aime24_t0.6_p0.95_n1280-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_bsz1024_step512_adamw/aime25_t0.6_p0.95_n1280-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_bsz1024_step512_adamw/math-500_t0.6_p0.95_n192-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_bsz1024_step512_adamw/minerva_t0.6_p0.95_n192-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_bsz1024_step512_adamw/olympiad-bench_t0.6_p0.95_n192-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_bsz128_step512_adamw/aime24_t0.6_p0.95_n1280-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_bsz128_step512_adamw/aime25_t0.6_p0.95_n1280-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_bsz128_step512_adamw/math-500_t0.6_p0.95_n192-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_bsz128_step512_adamw/minerva_t0.6_p0.95_n192-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_bsz128_step512_adamw/olympiad-bench_t0.6_p0.95_n192-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_bsz16_step512_adamw/aime24_t0.6_p0.95_n1280-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_bsz16_step512_adamw/aime25_t0.6_p0.95_n1280-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_bsz16_step512_adamw/math-500_t0.6_p0.95_n192-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_bsz16_step512_adamw/minerva_t0.6_p0.95_n192-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_bsz16_step512_adamw/olympiad-bench_t0.6_p0.95_n192-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_bsz2048_step512_adamw/aime24_t0.6_p0.95_n1280-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_bsz2048_step512_adamw/aime25_t0.6_p0.95_n1280-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_bsz2048_step512_adamw/math-500_t0.6_p0.95_n192-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_bsz2048_step512_adamw/minerva_t0.6_p0.95_n192-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_bsz2048_step512_adamw/olympiad-bench_t0.6_p0.95_n192-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_bsz256_step512_adamw/aime24_t0.6_p0.95_n1280-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_bsz256_step512_adamw/aime25_t0.6_p0.95_n1280-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_bsz256_step512_adamw/math-500_t0.6_p0.95_n192-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_bsz256_step512_adamw/minerva_t0.6_p0.95_n192-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_bsz256_step512_adamw/olympiad-bench_t0.6_p0.95_n192-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_bsz32_step512_adamw/aime24_t0.6_p0.95_n1280-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_bsz32_step512_adamw/aime25_t0.6_p0.95_n1280-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_bsz32_step512_adamw/math-500_t0.6_p0.95_n192-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_bsz32_step512_adamw/minerva_t0.6_p0.95_n192-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_bsz32_step512_adamw/olympiad-bench_t0.6_p0.95_n192-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_bsz512_step512_adamw/aime24_t0.6_p0.95_n1280-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_bsz512_step512_adamw/aime25_t0.6_p0.95_n1280-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_bsz512_step512_adamw/math-500_t0.6_p0.95_n192-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_bsz512_step512_adamw/minerva_t0.6_p0.95_n192-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_bsz512_step512_adamw/olympiad-bench_t0.6_p0.95_n192-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_bsz64_step512_adamw/aime24_t0.6_p0.95_n1280-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_bsz64_step512_adamw/aime25_t0.6_p0.95_n1280-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_bsz64_step512_adamw/math-500_t0.6_p0.95_n192-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_bsz64_step512_adamw/minerva_t0.6_p0.95_n192-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_bsz64_step512_adamw/olympiad-bench_t0.6_p0.95_n192-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_justrl_plus_plus_step512_adamw/aime24_t0.6_p0.95_n1280-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_justrl_plus_plus_step512_adamw/aime25_t0.6_p0.95_n1280-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_justrl_plus_plus_step512_adamw/math-500_t0.6_p0.95_n192-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_justrl_plus_plus_step512_adamw/minerva_t0.6_p0.95_n192-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_justrl_plus_plus_step512_adamw/olympiad-bench_t0.6_p0.95_n192-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_justrl_plus_plus_step512_rmsprop/aime24_t0.6_p0.95_n1280-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_justrl_plus_plus_step512_rmsprop/aime25_t0.6_p0.95_n1280-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_justrl_plus_plus_step512_rmsprop/math-500_t0.6_p0.95_n192-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_justrl_plus_plus_step512_rmsprop/minerva_t0.6_p0.95_n192-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_justrl_plus_plus_step512_rmsprop/olympiad-bench_t0.6_p0.95_n192-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_rollout_sz128_step512_adamw/aime24_t0.6_p0.95_n1280-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_rollout_sz128_step512_adamw/aime25_t0.6_p0.95_n1280-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_rollout_sz128_step512_adamw/math-500_t0.6_p0.95_n192-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_rollout_sz128_step512_adamw/minerva_t0.6_p0.95_n192-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_rollout_sz128_step512_adamw/olympiad-bench_t0.6_p0.95_n192-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_rollout_sz256_step512_adamw/aime24_t0.6_p0.95_n1280-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_rollout_sz256_step512_adamw/aime25_t0.6_p0.95_n1280-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_rollout_sz256_step512_adamw/math-500_t0.6_p0.95_n192-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_rollout_sz256_step512_adamw/minerva_t0.6_p0.95_n192-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_rollout_sz256_step512_adamw/olympiad-bench_t0.6_p0.95_n192-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_rollout_sz2_step512_adamw/aime24_t0.6_p0.95_n1280-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_rollout_sz2_step512_adamw/aime25_t0.6_p0.95_n1280-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_rollout_sz2_step512_adamw/math-500_t0.6_p0.95_n192-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_rollout_sz2_step512_adamw/minerva_t0.6_p0.95_n192-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_rollout_sz2_step512_adamw/olympiad-bench_t0.6_p0.95_n192-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_rollout_sz4_step512_adamw/aime24_t0.6_p0.95_n1280-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_rollout_sz4_step512_adamw/aime25_t0.6_p0.95_n1280-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_rollout_sz4_step512_adamw/math-500_t0.6_p0.95_n192-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_rollout_sz4_step512_adamw/minerva_t0.6_p0.95_n192-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_rollout_sz4_step512_adamw/olympiad-bench_t0.6_p0.95_n192-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_rollout_sz512_step512_adamw/olympiad-bench_t0.6_p0.95_n192-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_rollout_sz8_step512_adamw/aime24_t0.6_p0.95_n1280-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_rollout_sz8_step512_adamw/aime25_t0.6_p0.95_n1280-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_rollout_sz8_step512_adamw/math-500_t0.6_p0.95_n192-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_rollout_sz8_step512_adamw/minerva_t0.6_p0.95_n192-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/full_polaris_rollout_sz8_step512_adamw/olympiad-bench_t0.6_p0.95_n192-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/lora_polaris_rollout_sz16_rank16_step512_adamw/aime24_t0.6_p0.95_n1280-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/lora_polaris_rollout_sz16_rank16_step512_adamw/aime25_t0.6_p0.95_n1280-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/lora_polaris_rollout_sz16_rank16_step512_adamw/math-500_t0.6_p0.95_n192-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/lora_polaris_rollout_sz16_rank16_step512_adamw/minerva_t0.6_p0.95_n192-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/lora_polaris_rollout_sz16_rank16_step512_adamw/olympiad-bench_t0.6_p0.95_n192-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/lora_polaris_rollout_sz16_rank32_step512_adamw/aime24_t0.6_p0.95_n1280-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/lora_polaris_rollout_sz16_rank32_step512_adamw/aime25_t0.6_p0.95_n1280-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/lora_polaris_rollout_sz16_rank32_step512_adamw/math-500_t0.6_p0.95_n192-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/lora_polaris_rollout_sz16_rank32_step512_adamw/minerva_t0.6_p0.95_n192-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/lora_polaris_rollout_sz16_rank32_step512_adamw/olympiad-bench_t0.6_p0.95_n192-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/lora_polaris_rollout_sz16_rank64_step512_adamw/aime24_t0.6_p0.95_n1280-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/lora_polaris_rollout_sz16_rank64_step512_adamw/aime25_t0.6_p0.95_n1280-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/lora_polaris_rollout_sz16_rank64_step512_adamw/math-500_t0.6_p0.95_n192-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/lora_polaris_rollout_sz16_rank64_step512_adamw/minerva_t0.6_p0.95_n192-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/lora_polaris_rollout_sz16_rank64_step512_adamw/olympiad-bench_t0.6_p0.95_n192-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/lora_polaris_rollout_sz16_rank8_step512_adamw/math-500_t0.6_p0.95_n192-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/lora_polaris_rollout_sz16_rank8_step512_adamw/minerva_t0.6_p0.95_n192-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| gen_outputs/step512/lora_polaris_rollout_sz16_rank8_step512_adamw/olympiad-bench_t0.6_p0.95_n192-MNT4096.jsonl filter=lfs diff=lfs merge=lfs -text |
| SFT/Qwen2.5-3B-Instruct-s1k_16/global_step_124/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| SFT/Qwen2.5-3B-Instruct-s1k_16/global_step_186/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| SFT/Qwen2.5-3B-Instruct-s1k_16/global_step_248/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| SFT/Qwen2.5-3B-Instruct-s1k_16/global_step_310/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| SFT/Qwen2.5-3B-Instruct-s1k_16/global_step_372/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| SFT/Qwen2.5-3B-Instruct-s1k_16/global_step_434/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| SFT/Qwen2.5-3B-Instruct-s1k_16/global_step_496/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| SFT/Qwen2.5-3B-Instruct-s1k_16/global_step_62/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| SFT/Qwen2.5-3B-Instruct-s1k_32/global_step_124/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| SFT/Qwen2.5-3B-Instruct-s1k_32/global_step_186/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| SFT/Qwen2.5-3B-Instruct-s1k_32/global_step_248/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| SFT/Qwen2.5-3B-Instruct-s1k_32/global_step_310/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| SFT/Qwen2.5-3B-Instruct-s1k_32/global_step_372/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| SFT/Qwen2.5-3B-Instruct-s1k_32/global_step_434/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| SFT/Qwen2.5-3B-Instruct-s1k_32/global_step_496/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| SFT/Qwen2.5-3B-Instruct-s1k_32/global_step_62/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| SFT/Qwen2.5-3B-Instruct-s1k_64/global_step_124/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| SFT/Qwen2.5-3B-Instruct-s1k_64/global_step_186/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| SFT/Qwen2.5-3B-Instruct-s1k_64/global_step_248/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| SFT/Qwen2.5-3B-Instruct-s1k_64/global_step_310/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| SFT/Qwen2.5-3B-Instruct-s1k_64/global_step_372/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| SFT/Qwen2.5-3B-Instruct-s1k_64/global_step_434/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| SFT/Qwen2.5-3B-Instruct-s1k_64/global_step_496/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| SFT/Qwen2.5-3B-Instruct-s1k_64/global_step_62/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| SFT/Qwen2.5-3B-Instruct-s1k_8/global_step_124/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| SFT/Qwen2.5-3B-Instruct-s1k_8/global_step_186/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| SFT/Qwen2.5-3B-Instruct-s1k_8/global_step_248/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| SFT/Qwen2.5-3B-Instruct-s1k_8/global_step_310/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| SFT/Qwen2.5-3B-Instruct-s1k_8/global_step_372/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| SFT/Qwen2.5-3B-Instruct-s1k_8/global_step_434/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| SFT/Qwen2.5-3B-Instruct-s1k_8/global_step_496/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
| SFT/Qwen2.5-3B-Instruct-s1k_8/global_step_62/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text |
|
|