Hugging Face's logo

bensondccnqwc
/
tmp-yv08a

Safetensors
Model card Files
xet
Community
bensondccnqwc commited on
Commit
858b7bc
·
verified ·
1 Parent(s): e54b9e4

Add files using upload-large-folder tool

Browse files
Files changed (10) hide show
  1. .gitattributes +2 -0
  2. global_step_90/actor/huggingface/model.safetensors +3 -0
  3. reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/global_step_0/actor/huggingface/model-00001-of-00005.safetensors +3 -0
  4. reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/global_step_0/actor/huggingface/model-00002-of-00005.safetensors +3 -0
  5. reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/global_step_0/actor/huggingface/model-00003-of-00005.safetensors +3 -0
  6. reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/global_step_0/actor/huggingface/model-00005-of-00005.safetensors +3 -0
  7. reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/global_step_100/actor/huggingface/tokenizer.json +3 -0
  8. reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/global_step_20/actor/huggingface/tokenizer.json +3 -0
  9. reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/global_step_20/data.pt +3 -0
  10. reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/global_step_30/data.pt +3 -0
.gitattributes CHANGED
@@ -64,3 +64,5 @@ reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response409
64
  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
65
  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
66
  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
 
 
 
64
  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
65
  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
66
  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
67
+ 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
68
+ 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
global_step_90/actor/huggingface/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32b1e8b4a4e1ec5fc335e52f5b84642db7d4ae397203385ee224da8073c32823
3
+ size 4063515640
reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/global_step_0/actor/huggingface/model-00001-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9983f1b9ef2f60e7c3730d9bc11ada914e6ec630639b5b020a89bd158cd0446b
3
+ size 3996250744
reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/global_step_0/actor/huggingface/model-00002-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9aa12339835bf7a093d3d0b0a0d2d77f8538301cfc7f8e7ec7a585858ebf7a1f
3
+ size 3993160032
reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/global_step_0/actor/huggingface/model-00003-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7dd5a191c8da555def0714550375b3c0117751add408fcdda0c2a79ac0186bc
3
+ size 3959604768
reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/global_step_0/actor/huggingface/model-00005-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbf24915d47ea030bb68ab0b9488f4515a907185baa6dc26837c9c3f2326a550
3
+ size 1244659840
reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/global_step_100/actor/huggingface/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/global_step_20/actor/huggingface/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/global_step_20/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9bdf362aff01ad7b93bc63313ec5786fe5a30d7f70b5b845b9d824c957a7be1
3
+ size 1947
reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/global_step_30/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24a6147ae9c59fb95eaca2c041603aa399dddfe3bf9ef94e44b8fb0c114c9ee1
3
+ size 1947