diff --git a/.gitattributes b/.gitattributes index b14da0ac74fc6e3df3fbff0abd38fcb7bc53454a..c01346e9cd083a12eccb02a635f7ad94b3779228 100644 --- a/.gitattributes +++ b/.gitattributes @@ -35,3 +35,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text *tfevents* filter=lfs diff=lfs merge=lfs -text Prompt-R1-gpt-oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text grpo-qwen3-4b-gpt-4o-mini/global_step_320/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text +checkpoint/4o-mini/global_step_320/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text +checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/Prompt-R1-gpt-oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/extra_state_world_size_8_rank_0.pt b/checkpoint/4o-mini/global_step_320/actor/extra_state_world_size_8_rank_0.pt similarity index 100% rename from Prompt-R1-gpt-oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/extra_state_world_size_8_rank_0.pt rename to checkpoint/4o-mini/global_step_320/actor/extra_state_world_size_8_rank_0.pt diff --git a/Prompt-R1-gpt-oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/extra_state_world_size_8_rank_1.pt b/checkpoint/4o-mini/global_step_320/actor/extra_state_world_size_8_rank_1.pt similarity index 100% rename from Prompt-R1-gpt-oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/extra_state_world_size_8_rank_1.pt rename to checkpoint/4o-mini/global_step_320/actor/extra_state_world_size_8_rank_1.pt diff --git a/Prompt-R1-gpt-oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/extra_state_world_size_8_rank_2.pt b/checkpoint/4o-mini/global_step_320/actor/extra_state_world_size_8_rank_2.pt similarity index 100% rename from Prompt-R1-gpt-oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/extra_state_world_size_8_rank_2.pt rename to checkpoint/4o-mini/global_step_320/actor/extra_state_world_size_8_rank_2.pt diff --git a/Prompt-R1-gpt-oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/extra_state_world_size_8_rank_3.pt b/checkpoint/4o-mini/global_step_320/actor/extra_state_world_size_8_rank_3.pt similarity index 100% rename from Prompt-R1-gpt-oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/extra_state_world_size_8_rank_3.pt rename to checkpoint/4o-mini/global_step_320/actor/extra_state_world_size_8_rank_3.pt diff --git a/Prompt-R1-gpt-oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/extra_state_world_size_8_rank_4.pt b/checkpoint/4o-mini/global_step_320/actor/extra_state_world_size_8_rank_4.pt similarity index 100% rename from Prompt-R1-gpt-oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/extra_state_world_size_8_rank_4.pt rename to checkpoint/4o-mini/global_step_320/actor/extra_state_world_size_8_rank_4.pt diff --git a/Prompt-R1-gpt-oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/extra_state_world_size_8_rank_5.pt b/checkpoint/4o-mini/global_step_320/actor/extra_state_world_size_8_rank_5.pt similarity index 100% rename from Prompt-R1-gpt-oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/extra_state_world_size_8_rank_5.pt rename to checkpoint/4o-mini/global_step_320/actor/extra_state_world_size_8_rank_5.pt diff --git a/Prompt-R1-gpt-oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/extra_state_world_size_8_rank_6.pt b/checkpoint/4o-mini/global_step_320/actor/extra_state_world_size_8_rank_6.pt similarity index 100% rename from Prompt-R1-gpt-oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/extra_state_world_size_8_rank_6.pt rename to checkpoint/4o-mini/global_step_320/actor/extra_state_world_size_8_rank_6.pt diff --git a/Prompt-R1-gpt-oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/extra_state_world_size_8_rank_7.pt b/checkpoint/4o-mini/global_step_320/actor/extra_state_world_size_8_rank_7.pt similarity index 100% rename from Prompt-R1-gpt-oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/extra_state_world_size_8_rank_7.pt rename to checkpoint/4o-mini/global_step_320/actor/extra_state_world_size_8_rank_7.pt diff --git a/Prompt-R1-gpt-oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/huggingface/added_tokens.json b/checkpoint/4o-mini/global_step_320/actor/huggingface/added_tokens.json similarity index 100% rename from Prompt-R1-gpt-oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/huggingface/added_tokens.json rename to checkpoint/4o-mini/global_step_320/actor/huggingface/added_tokens.json diff --git a/Prompt-R1-gpt-oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/huggingface/chat_template.jinja b/checkpoint/4o-mini/global_step_320/actor/huggingface/chat_template.jinja similarity index 100% rename from Prompt-R1-gpt-oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/huggingface/chat_template.jinja rename to checkpoint/4o-mini/global_step_320/actor/huggingface/chat_template.jinja diff --git a/Prompt-R1-gpt-oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/huggingface/config.json b/checkpoint/4o-mini/global_step_320/actor/huggingface/config.json similarity index 100% rename from Prompt-R1-gpt-oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/huggingface/config.json rename to checkpoint/4o-mini/global_step_320/actor/huggingface/config.json diff --git a/Prompt-R1-gpt-oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/huggingface/merges.txt b/checkpoint/4o-mini/global_step_320/actor/huggingface/merges.txt similarity index 100% rename from Prompt-R1-gpt-oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/huggingface/merges.txt rename to checkpoint/4o-mini/global_step_320/actor/huggingface/merges.txt diff --git a/Prompt-R1-gpt-oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/huggingface/special_tokens_map.json b/checkpoint/4o-mini/global_step_320/actor/huggingface/special_tokens_map.json similarity index 100% rename from Prompt-R1-gpt-oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/huggingface/special_tokens_map.json rename to checkpoint/4o-mini/global_step_320/actor/huggingface/special_tokens_map.json diff --git a/Prompt-R1-gpt-oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/huggingface/tokenizer.json b/checkpoint/4o-mini/global_step_320/actor/huggingface/tokenizer.json similarity index 100% rename from Prompt-R1-gpt-oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/huggingface/tokenizer.json rename to checkpoint/4o-mini/global_step_320/actor/huggingface/tokenizer.json diff --git a/Prompt-R1-gpt-oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/huggingface/tokenizer_config.json b/checkpoint/4o-mini/global_step_320/actor/huggingface/tokenizer_config.json similarity index 100% rename from Prompt-R1-gpt-oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/huggingface/tokenizer_config.json rename to checkpoint/4o-mini/global_step_320/actor/huggingface/tokenizer_config.json diff --git a/Prompt-R1-gpt-oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/huggingface/vocab.json b/checkpoint/4o-mini/global_step_320/actor/huggingface/vocab.json similarity index 100% rename from Prompt-R1-gpt-oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/huggingface/vocab.json rename to checkpoint/4o-mini/global_step_320/actor/huggingface/vocab.json diff --git a/grpo-qwen3-4b-gpt-4o-mini/global_step_320/actor/model_world_size_8_rank_0.pt b/checkpoint/4o-mini/global_step_320/actor/model_world_size_8_rank_0.pt similarity index 100% rename from grpo-qwen3-4b-gpt-4o-mini/global_step_320/actor/model_world_size_8_rank_0.pt rename to checkpoint/4o-mini/global_step_320/actor/model_world_size_8_rank_0.pt diff --git a/grpo-qwen3-4b-gpt-4o-mini/global_step_320/actor/model_world_size_8_rank_1.pt b/checkpoint/4o-mini/global_step_320/actor/model_world_size_8_rank_1.pt similarity index 100% rename from grpo-qwen3-4b-gpt-4o-mini/global_step_320/actor/model_world_size_8_rank_1.pt rename to checkpoint/4o-mini/global_step_320/actor/model_world_size_8_rank_1.pt diff --git a/grpo-qwen3-4b-gpt-4o-mini/global_step_320/actor/model_world_size_8_rank_2.pt b/checkpoint/4o-mini/global_step_320/actor/model_world_size_8_rank_2.pt similarity index 100% rename from grpo-qwen3-4b-gpt-4o-mini/global_step_320/actor/model_world_size_8_rank_2.pt rename to checkpoint/4o-mini/global_step_320/actor/model_world_size_8_rank_2.pt diff --git a/grpo-qwen3-4b-gpt-4o-mini/global_step_320/actor/model_world_size_8_rank_3.pt b/checkpoint/4o-mini/global_step_320/actor/model_world_size_8_rank_3.pt similarity index 100% rename from grpo-qwen3-4b-gpt-4o-mini/global_step_320/actor/model_world_size_8_rank_3.pt rename to checkpoint/4o-mini/global_step_320/actor/model_world_size_8_rank_3.pt diff --git a/grpo-qwen3-4b-gpt-4o-mini/global_step_320/actor/model_world_size_8_rank_4.pt b/checkpoint/4o-mini/global_step_320/actor/model_world_size_8_rank_4.pt similarity index 100% rename from grpo-qwen3-4b-gpt-4o-mini/global_step_320/actor/model_world_size_8_rank_4.pt rename to checkpoint/4o-mini/global_step_320/actor/model_world_size_8_rank_4.pt diff --git a/grpo-qwen3-4b-gpt-4o-mini/global_step_320/actor/model_world_size_8_rank_5.pt b/checkpoint/4o-mini/global_step_320/actor/model_world_size_8_rank_5.pt similarity index 100% rename from grpo-qwen3-4b-gpt-4o-mini/global_step_320/actor/model_world_size_8_rank_5.pt rename to checkpoint/4o-mini/global_step_320/actor/model_world_size_8_rank_5.pt diff --git a/grpo-qwen3-4b-gpt-4o-mini/global_step_320/actor/model_world_size_8_rank_6.pt b/checkpoint/4o-mini/global_step_320/actor/model_world_size_8_rank_6.pt similarity index 100% rename from grpo-qwen3-4b-gpt-4o-mini/global_step_320/actor/model_world_size_8_rank_6.pt rename to checkpoint/4o-mini/global_step_320/actor/model_world_size_8_rank_6.pt diff --git a/grpo-qwen3-4b-gpt-4o-mini/global_step_320/actor/model_world_size_8_rank_7.pt b/checkpoint/4o-mini/global_step_320/actor/model_world_size_8_rank_7.pt similarity index 100% rename from grpo-qwen3-4b-gpt-4o-mini/global_step_320/actor/model_world_size_8_rank_7.pt rename to checkpoint/4o-mini/global_step_320/actor/model_world_size_8_rank_7.pt diff --git a/grpo-qwen3-4b-gpt-4o-mini/global_step_320/actor/optim_world_size_8_rank_0.pt b/checkpoint/4o-mini/global_step_320/actor/optim_world_size_8_rank_0.pt similarity index 100% rename from grpo-qwen3-4b-gpt-4o-mini/global_step_320/actor/optim_world_size_8_rank_0.pt rename to checkpoint/4o-mini/global_step_320/actor/optim_world_size_8_rank_0.pt diff --git a/grpo-qwen3-4b-gpt-4o-mini/global_step_320/actor/optim_world_size_8_rank_1.pt b/checkpoint/4o-mini/global_step_320/actor/optim_world_size_8_rank_1.pt similarity index 100% rename from grpo-qwen3-4b-gpt-4o-mini/global_step_320/actor/optim_world_size_8_rank_1.pt rename to checkpoint/4o-mini/global_step_320/actor/optim_world_size_8_rank_1.pt diff --git a/grpo-qwen3-4b-gpt-4o-mini/global_step_320/actor/optim_world_size_8_rank_2.pt b/checkpoint/4o-mini/global_step_320/actor/optim_world_size_8_rank_2.pt similarity index 100% rename from grpo-qwen3-4b-gpt-4o-mini/global_step_320/actor/optim_world_size_8_rank_2.pt rename to checkpoint/4o-mini/global_step_320/actor/optim_world_size_8_rank_2.pt diff --git a/grpo-qwen3-4b-gpt-4o-mini/global_step_320/actor/optim_world_size_8_rank_3.pt b/checkpoint/4o-mini/global_step_320/actor/optim_world_size_8_rank_3.pt similarity index 100% rename from grpo-qwen3-4b-gpt-4o-mini/global_step_320/actor/optim_world_size_8_rank_3.pt rename to checkpoint/4o-mini/global_step_320/actor/optim_world_size_8_rank_3.pt diff --git a/grpo-qwen3-4b-gpt-4o-mini/global_step_320/actor/optim_world_size_8_rank_4.pt b/checkpoint/4o-mini/global_step_320/actor/optim_world_size_8_rank_4.pt similarity index 100% rename from grpo-qwen3-4b-gpt-4o-mini/global_step_320/actor/optim_world_size_8_rank_4.pt rename to checkpoint/4o-mini/global_step_320/actor/optim_world_size_8_rank_4.pt diff --git a/grpo-qwen3-4b-gpt-4o-mini/global_step_320/actor/optim_world_size_8_rank_5.pt b/checkpoint/4o-mini/global_step_320/actor/optim_world_size_8_rank_5.pt similarity index 100% rename from grpo-qwen3-4b-gpt-4o-mini/global_step_320/actor/optim_world_size_8_rank_5.pt rename to checkpoint/4o-mini/global_step_320/actor/optim_world_size_8_rank_5.pt diff --git a/grpo-qwen3-4b-gpt-4o-mini/global_step_320/actor/optim_world_size_8_rank_6.pt b/checkpoint/4o-mini/global_step_320/actor/optim_world_size_8_rank_6.pt similarity index 100% rename from grpo-qwen3-4b-gpt-4o-mini/global_step_320/actor/optim_world_size_8_rank_6.pt rename to checkpoint/4o-mini/global_step_320/actor/optim_world_size_8_rank_6.pt diff --git a/grpo-qwen3-4b-gpt-4o-mini/global_step_320/actor/optim_world_size_8_rank_7.pt b/checkpoint/4o-mini/global_step_320/actor/optim_world_size_8_rank_7.pt similarity index 100% rename from grpo-qwen3-4b-gpt-4o-mini/global_step_320/actor/optim_world_size_8_rank_7.pt rename to checkpoint/4o-mini/global_step_320/actor/optim_world_size_8_rank_7.pt diff --git a/grpo-qwen3-4b-gpt-4o-mini/global_step_320/data.pt b/checkpoint/4o-mini/global_step_320/data.pt similarity index 100% rename from grpo-qwen3-4b-gpt-4o-mini/global_step_320/data.pt rename to checkpoint/4o-mini/global_step_320/data.pt diff --git a/grpo-qwen3-4b-gpt-4o-mini/global_step_320/actor/extra_state_world_size_8_rank_0.pt b/checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/extra_state_world_size_8_rank_0.pt similarity index 100% rename from grpo-qwen3-4b-gpt-4o-mini/global_step_320/actor/extra_state_world_size_8_rank_0.pt rename to checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/extra_state_world_size_8_rank_0.pt diff --git a/grpo-qwen3-4b-gpt-4o-mini/global_step_320/actor/extra_state_world_size_8_rank_1.pt b/checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/extra_state_world_size_8_rank_1.pt similarity index 100% rename from grpo-qwen3-4b-gpt-4o-mini/global_step_320/actor/extra_state_world_size_8_rank_1.pt rename to checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/extra_state_world_size_8_rank_1.pt diff --git a/grpo-qwen3-4b-gpt-4o-mini/global_step_320/actor/extra_state_world_size_8_rank_2.pt b/checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/extra_state_world_size_8_rank_2.pt similarity index 100% rename from grpo-qwen3-4b-gpt-4o-mini/global_step_320/actor/extra_state_world_size_8_rank_2.pt rename to checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/extra_state_world_size_8_rank_2.pt diff --git a/grpo-qwen3-4b-gpt-4o-mini/global_step_320/actor/extra_state_world_size_8_rank_3.pt b/checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/extra_state_world_size_8_rank_3.pt similarity index 100% rename from grpo-qwen3-4b-gpt-4o-mini/global_step_320/actor/extra_state_world_size_8_rank_3.pt rename to checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/extra_state_world_size_8_rank_3.pt diff --git a/grpo-qwen3-4b-gpt-4o-mini/global_step_320/actor/extra_state_world_size_8_rank_4.pt b/checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/extra_state_world_size_8_rank_4.pt similarity index 100% rename from grpo-qwen3-4b-gpt-4o-mini/global_step_320/actor/extra_state_world_size_8_rank_4.pt rename to checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/extra_state_world_size_8_rank_4.pt diff --git a/grpo-qwen3-4b-gpt-4o-mini/global_step_320/actor/extra_state_world_size_8_rank_5.pt b/checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/extra_state_world_size_8_rank_5.pt similarity index 100% rename from grpo-qwen3-4b-gpt-4o-mini/global_step_320/actor/extra_state_world_size_8_rank_5.pt rename to checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/extra_state_world_size_8_rank_5.pt diff --git a/grpo-qwen3-4b-gpt-4o-mini/global_step_320/actor/extra_state_world_size_8_rank_6.pt b/checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/extra_state_world_size_8_rank_6.pt similarity index 100% rename from grpo-qwen3-4b-gpt-4o-mini/global_step_320/actor/extra_state_world_size_8_rank_6.pt rename to checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/extra_state_world_size_8_rank_6.pt diff --git a/grpo-qwen3-4b-gpt-4o-mini/global_step_320/actor/extra_state_world_size_8_rank_7.pt b/checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/extra_state_world_size_8_rank_7.pt similarity index 100% rename from grpo-qwen3-4b-gpt-4o-mini/global_step_320/actor/extra_state_world_size_8_rank_7.pt rename to checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/extra_state_world_size_8_rank_7.pt diff --git a/grpo-qwen3-4b-gpt-4o-mini/global_step_320/actor/huggingface/added_tokens.json b/checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/huggingface/added_tokens.json similarity index 100% rename from grpo-qwen3-4b-gpt-4o-mini/global_step_320/actor/huggingface/added_tokens.json rename to checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/huggingface/added_tokens.json diff --git a/grpo-qwen3-4b-gpt-4o-mini/global_step_320/actor/huggingface/chat_template.jinja b/checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/huggingface/chat_template.jinja similarity index 100% rename from grpo-qwen3-4b-gpt-4o-mini/global_step_320/actor/huggingface/chat_template.jinja rename to checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/huggingface/chat_template.jinja diff --git a/grpo-qwen3-4b-gpt-4o-mini/global_step_320/actor/huggingface/config.json b/checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/huggingface/config.json similarity index 100% rename from grpo-qwen3-4b-gpt-4o-mini/global_step_320/actor/huggingface/config.json rename to checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/huggingface/config.json diff --git a/grpo-qwen3-4b-gpt-4o-mini/global_step_320/actor/huggingface/merges.txt b/checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/huggingface/merges.txt similarity index 100% rename from grpo-qwen3-4b-gpt-4o-mini/global_step_320/actor/huggingface/merges.txt rename to checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/huggingface/merges.txt diff --git a/grpo-qwen3-4b-gpt-4o-mini/global_step_320/actor/huggingface/special_tokens_map.json b/checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/huggingface/special_tokens_map.json similarity index 100% rename from grpo-qwen3-4b-gpt-4o-mini/global_step_320/actor/huggingface/special_tokens_map.json rename to checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/huggingface/special_tokens_map.json diff --git a/grpo-qwen3-4b-gpt-4o-mini/global_step_320/actor/huggingface/tokenizer.json b/checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/huggingface/tokenizer.json similarity index 100% rename from grpo-qwen3-4b-gpt-4o-mini/global_step_320/actor/huggingface/tokenizer.json rename to checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/huggingface/tokenizer.json diff --git a/grpo-qwen3-4b-gpt-4o-mini/global_step_320/actor/huggingface/tokenizer_config.json b/checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/huggingface/tokenizer_config.json similarity index 100% rename from grpo-qwen3-4b-gpt-4o-mini/global_step_320/actor/huggingface/tokenizer_config.json rename to checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/huggingface/tokenizer_config.json diff --git a/grpo-qwen3-4b-gpt-4o-mini/global_step_320/actor/huggingface/vocab.json b/checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/huggingface/vocab.json similarity index 100% rename from grpo-qwen3-4b-gpt-4o-mini/global_step_320/actor/huggingface/vocab.json rename to checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/huggingface/vocab.json diff --git a/Prompt-R1-gpt-oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/model_world_size_8_rank_0.pt b/checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/model_world_size_8_rank_0.pt similarity index 100% rename from Prompt-R1-gpt-oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/model_world_size_8_rank_0.pt rename to checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/model_world_size_8_rank_0.pt diff --git a/Prompt-R1-gpt-oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/model_world_size_8_rank_1.pt b/checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/model_world_size_8_rank_1.pt similarity index 100% rename from Prompt-R1-gpt-oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/model_world_size_8_rank_1.pt rename to checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/model_world_size_8_rank_1.pt diff --git a/Prompt-R1-gpt-oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/model_world_size_8_rank_2.pt b/checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/model_world_size_8_rank_2.pt similarity index 100% rename from Prompt-R1-gpt-oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/model_world_size_8_rank_2.pt rename to checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/model_world_size_8_rank_2.pt diff --git a/Prompt-R1-gpt-oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/model_world_size_8_rank_3.pt b/checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/model_world_size_8_rank_3.pt similarity index 100% rename from Prompt-R1-gpt-oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/model_world_size_8_rank_3.pt rename to checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/model_world_size_8_rank_3.pt diff --git a/Prompt-R1-gpt-oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/model_world_size_8_rank_4.pt b/checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/model_world_size_8_rank_4.pt similarity index 100% rename from Prompt-R1-gpt-oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/model_world_size_8_rank_4.pt rename to checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/model_world_size_8_rank_4.pt diff --git a/Prompt-R1-gpt-oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/model_world_size_8_rank_5.pt b/checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/model_world_size_8_rank_5.pt similarity index 100% rename from Prompt-R1-gpt-oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/model_world_size_8_rank_5.pt rename to checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/model_world_size_8_rank_5.pt diff --git a/Prompt-R1-gpt-oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/model_world_size_8_rank_6.pt b/checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/model_world_size_8_rank_6.pt similarity index 100% rename from Prompt-R1-gpt-oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/model_world_size_8_rank_6.pt rename to checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/model_world_size_8_rank_6.pt diff --git a/Prompt-R1-gpt-oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/model_world_size_8_rank_7.pt b/checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/model_world_size_8_rank_7.pt similarity index 100% rename from Prompt-R1-gpt-oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/model_world_size_8_rank_7.pt rename to checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/model_world_size_8_rank_7.pt diff --git a/Prompt-R1-gpt-oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/optim_world_size_8_rank_0.pt b/checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/optim_world_size_8_rank_0.pt similarity index 100% rename from Prompt-R1-gpt-oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/optim_world_size_8_rank_0.pt rename to checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/optim_world_size_8_rank_0.pt diff --git a/Prompt-R1-gpt-oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/optim_world_size_8_rank_1.pt b/checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/optim_world_size_8_rank_1.pt similarity index 100% rename from Prompt-R1-gpt-oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/optim_world_size_8_rank_1.pt rename to checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/optim_world_size_8_rank_1.pt diff --git a/Prompt-R1-gpt-oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/optim_world_size_8_rank_2.pt b/checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/optim_world_size_8_rank_2.pt similarity index 100% rename from Prompt-R1-gpt-oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/optim_world_size_8_rank_2.pt rename to checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/optim_world_size_8_rank_2.pt diff --git a/Prompt-R1-gpt-oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/optim_world_size_8_rank_3.pt b/checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/optim_world_size_8_rank_3.pt similarity index 100% rename from Prompt-R1-gpt-oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/optim_world_size_8_rank_3.pt rename to checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/optim_world_size_8_rank_3.pt diff --git a/Prompt-R1-gpt-oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/optim_world_size_8_rank_4.pt b/checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/optim_world_size_8_rank_4.pt similarity index 100% rename from Prompt-R1-gpt-oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/optim_world_size_8_rank_4.pt rename to checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/optim_world_size_8_rank_4.pt diff --git a/Prompt-R1-gpt-oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/optim_world_size_8_rank_5.pt b/checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/optim_world_size_8_rank_5.pt similarity index 100% rename from Prompt-R1-gpt-oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/optim_world_size_8_rank_5.pt rename to checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/optim_world_size_8_rank_5.pt diff --git a/Prompt-R1-gpt-oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/optim_world_size_8_rank_6.pt b/checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/optim_world_size_8_rank_6.pt similarity index 100% rename from Prompt-R1-gpt-oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/optim_world_size_8_rank_6.pt rename to checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/optim_world_size_8_rank_6.pt diff --git a/Prompt-R1-gpt-oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/optim_world_size_8_rank_7.pt b/checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/optim_world_size_8_rank_7.pt similarity index 100% rename from Prompt-R1-gpt-oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/optim_world_size_8_rank_7.pt rename to checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/optim_world_size_8_rank_7.pt diff --git a/Prompt-R1-gpt-oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/data.pt b/checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/data.pt similarity index 100% rename from Prompt-R1-gpt-oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/data.pt rename to checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/data.pt diff --git a/Prompt-R1-gpt-oss/grpo-qwen3-4b-gpt-oss-20b/latest_checkpointed_iteration.txt b/checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/latest_checkpointed_iteration.txt similarity index 100% rename from Prompt-R1-gpt-oss/grpo-qwen3-4b-gpt-oss-20b/latest_checkpointed_iteration.txt rename to checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/latest_checkpointed_iteration.txt