| *.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 | |
| global_step_10/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text | |
| global_step_100/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text | |
| global_step_20/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text | |
| global_step_30/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text | |
| global_step_40/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text | |
| global_step_50/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text | |
| global_step_60/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text | |
| global_step_70/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text | |
| global_step_80/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text | |
| global_step_90/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text | |
| reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/eval_results/plots/eval_results_acc_keywords.png filter=lfs diff=lfs merge=lfs -text | |
| reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/eval_results/plots/eval_results_acc_pass_acc.png filter=lfs diff=lfs merge=lfs -text | |
| reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/eval_results/plots/eval_results_acc_tokens.png filter=lfs diff=lfs merge=lfs -text | |
| reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/eval_results/plots/eval_results_avg_stop_tokens.png filter=lfs diff=lfs merge=lfs -text | |
| reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/eval_results/plots/eval_results_box_ratio_and_token_length.png filter=lfs diff=lfs merge=lfs -text | |
| reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/eval_results/plots/eval_results_clip_ratio.png filter=lfs diff=lfs merge=lfs -text | |
| reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/eval_results/plots/eval_results_correct_tokens.png filter=lfs diff=lfs merge=lfs -text | |
| reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/eval_results/plots/eval_results_repeat_ratio_and_token_length.png filter=lfs diff=lfs merge=lfs -text | |
| reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/eval_results/plots/eval_results_tokens_keywords.png filter=lfs diff=lfs merge=lfs -text | |
| reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/eval_results/plots/eval_results_wrong_tokens.png filter=lfs diff=lfs merge=lfs -text | |
| reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/eval_results_avg4/plots/eval_results_avg4_acc_keywords.png filter=lfs diff=lfs merge=lfs -text | |
| reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/eval_results_avg4/plots/eval_results_avg4_acc_pass_acc.png filter=lfs diff=lfs merge=lfs -text | |
| reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/eval_results_avg4/plots/eval_results_avg4_acc_tokens.png filter=lfs diff=lfs merge=lfs -text | |
| reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/eval_results_avg4/plots/eval_results_avg4_avg_stop_tokens.png filter=lfs diff=lfs merge=lfs -text | |
| reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/eval_results_avg4/plots/eval_results_avg4_clip_ratio.png filter=lfs diff=lfs merge=lfs -text | |
| reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/eval_results_avg4/plots/eval_results_avg4_box_ratio_and_token_length.png filter=lfs diff=lfs merge=lfs -text | |
| reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/eval_results_avg4/plots/eval_results_avg4_correct_tokens.png filter=lfs diff=lfs merge=lfs -text | |
| reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/eval_results_avg4/plots/eval_results_avg4_repeat_ratio_and_token_length.png filter=lfs diff=lfs merge=lfs -text | |
| reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/eval_results_avg4/plots/eval_results_avg4_wrong_tokens.png filter=lfs diff=lfs merge=lfs -text | |
| reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/eval_results_avg4/plots/eval_results_avg4_tokens_keywords.png filter=lfs diff=lfs merge=lfs -text | |
| reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/global_step_10/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text | |
| reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/global_step_100/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text | |
| reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/global_step_20/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text | |
| reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/global_step_30/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text | |
| reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/global_step_40/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text | |
| reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/global_step_50/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text | |
| reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/global_step_60/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text | |
| reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/global_step_70/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text | |
| reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/global_step_80/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text | |
| reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/global_step_90/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text | |