Hugging Face's logo

williamium
/
AdaptRL

Model card Files
xet
 Community
williamium commited on
Commit
ae5589b
·
verified ·
1 Parent(s): 46a5587

Upload folder using huggingface_hub

Browse files
Files changed (13) hide show
  1. planning_2509_DeepSeek-R1-Distill-Qwen-7B_grpo/actor/extra_state_world_size_4_rank_0.pt +1 -1
  2. planning_2509_DeepSeek-R1-Distill-Qwen-7B_grpo/actor/extra_state_world_size_4_rank_1.pt +1 -1
  3. planning_2509_DeepSeek-R1-Distill-Qwen-7B_grpo/actor/extra_state_world_size_4_rank_2.pt +1 -1
  4. planning_2509_DeepSeek-R1-Distill-Qwen-7B_grpo/actor/extra_state_world_size_4_rank_3.pt +1 -1
  5. planning_2509_DeepSeek-R1-Distill-Qwen-7B_grpo/actor/model_world_size_4_rank_0.pt +1 -1
  6. planning_2509_DeepSeek-R1-Distill-Qwen-7B_grpo/actor/model_world_size_4_rank_1.pt +1 -1
  7. planning_2509_DeepSeek-R1-Distill-Qwen-7B_grpo/actor/model_world_size_4_rank_2.pt +1 -1
  8. planning_2509_DeepSeek-R1-Distill-Qwen-7B_grpo/actor/model_world_size_4_rank_3.pt +1 -1
  9. planning_2509_DeepSeek-R1-Distill-Qwen-7B_grpo/actor/optim_world_size_4_rank_0.pt +1 -1
  10. planning_2509_DeepSeek-R1-Distill-Qwen-7B_grpo/actor/optim_world_size_4_rank_1.pt +1 -1
  11. planning_2509_DeepSeek-R1-Distill-Qwen-7B_grpo/actor/optim_world_size_4_rank_2.pt +1 -1
  12. planning_2509_DeepSeek-R1-Distill-Qwen-7B_grpo/actor/optim_world_size_4_rank_3.pt +1 -1
  13. planning_2509_DeepSeek-R1-Distill-Qwen-7B_grpo/data.pt +1 -1
planning_2509_DeepSeek-R1-Distill-Qwen-7B_grpo/actor/extra_state_world_size_4_rank_0.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cccf548cb7ea17a8148eee53cf2c87dc0b03de2335ee4eb4b8cc43d970b4a383
3
  size 15077
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:766a1cebb346f9c9433166fef12b6868a22e629b80c588eb4187c34acada72dc
3
  size 15077
planning_2509_DeepSeek-R1-Distill-Qwen-7B_grpo/actor/extra_state_world_size_4_rank_1.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:495adc68d1094b0516825e25fa50fbe5516dde052c51b8360c9d0cabf0673b47
3
  size 15077
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48b5c7b90ce0f4a509dfc562300603255eeef992804cc0d4475b3cf433b88273
3
  size 15077
planning_2509_DeepSeek-R1-Distill-Qwen-7B_grpo/actor/extra_state_world_size_4_rank_2.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e715576ae559000e6040f94e9cc61e4772618dc4b508b88aa25630be6ffe503
3
  size 15077
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f194f73b1d29812dad2b4c402899e3f82dcf27ddbed830184db0741b4cf5cf4f
3
  size 15077
planning_2509_DeepSeek-R1-Distill-Qwen-7B_grpo/actor/extra_state_world_size_4_rank_3.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:028640f5cbb38b06bd0fdac9e4a03a058392d5cbb696574643906ef00adedb97
3
  size 15077
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e1b9969d25b8a5896e23f86fd28b29293983366563f34c1f4baa68eb24bd27f
3
  size 15077
planning_2509_DeepSeek-R1-Distill-Qwen-7B_grpo/actor/model_world_size_4_rank_0.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a0a749bffc2abac898473ff0717c48fdc7e9cdb677a783f7a57c1dadb6faa46d
3
  size 7615805455
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0969622371d9abc9af9ff23ddb6d050eec33cadad92d15e3fd9970189a67ad4
3
  size 7615805455
planning_2509_DeepSeek-R1-Distill-Qwen-7B_grpo/actor/model_world_size_4_rank_1.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:26a9c0d79dcb40c5d976300dc19140e519f3397bb3568f4a4447ad4e69484ed0
3
  size 7615805455
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:991cda288e435425ecdd98af8f626bbc9a5c4d1d4ecfbbc0d33b0cde867fec83
3
  size 7615805455
planning_2509_DeepSeek-R1-Distill-Qwen-7B_grpo/actor/model_world_size_4_rank_2.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:53098e0ad7b65fb28e47d4be2e105cbf0125d8c81327abf3cbce179dad4bcb65
3
  size 7615805455
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6866a8e3d47633ec7975cbf13286a2926b74757c99e4aa6c89b0dbf832fe47e8
3
  size 7615805455
planning_2509_DeepSeek-R1-Distill-Qwen-7B_grpo/actor/model_world_size_4_rank_3.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c0968489d33edca44ea7fa51fc2392daa78df81461bd78682c861705185f1c5f
3
  size 7615805455
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75cf2648c2f5e2d8348ea9ae970714ff986e60fc1b09a90987f4683e47ad940f
3
  size 7615805455
planning_2509_DeepSeek-R1-Distill-Qwen-7B_grpo/actor/optim_world_size_4_rank_0.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f0607e48bc93965675c60136700fb95f099f369b6b4502d30ef675a83fee980e
3
  size 15231259716
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86ed083fc300760f72d29cf473b077ccae557d145e6d803cfb2ed1719066b2b0
3
  size 15231259716
planning_2509_DeepSeek-R1-Distill-Qwen-7B_grpo/actor/optim_world_size_4_rank_1.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:59e70725519f689bc9ceda442d509967222cb8cf1942f88c0785360ea0efee0a
3
  size 15231259716
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f55c6ce5edd7253a68c56f212b8d346fe95c471c221cf4bb2aa354518415d19a
3
  size 15231259716
planning_2509_DeepSeek-R1-Distill-Qwen-7B_grpo/actor/optim_world_size_4_rank_2.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ae3c723ba6b17a009ab0a9087985f982b3effe5bc8016dbe848e524a36eeeff
3
  size 15231259716
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffffa68ba6cadff1a8e575ac8289f23fd8545edd8af3af0fbf3051ad427cc349
3
  size 15231259716
planning_2509_DeepSeek-R1-Distill-Qwen-7B_grpo/actor/optim_world_size_4_rank_3.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2074614bdfc9526cd9ec587dff33c8baf4d5435f580213901819aa19a2e45fdf
3
  size 15231259716
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f837483661a6a0d9f7ff5726f408acf4187d1218d5ac77813e75b4f9631115e3
3
  size 15231259716
planning_2509_DeepSeek-R1-Distill-Qwen-7B_grpo/data.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:223c9809d3578c638066ddfc7b0129dacc82e2365da9a86347c61c1afa4ed9d8
3
  size 1947
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c296fb8b9a8d13076408bcc47ac54057b7604c18abe105123f604d98b6bed08c
3
  size 1947