bensondccnqwc commited on
Commit
95368b8
·
verified ·
1 Parent(s): 85bba9c

Add files using upload-large-folder tool

Browse files
Files changed (30) hide show
  1. .gitattributes +10 -0
  2. eval_results_ood/global_step_0/details/_home_work_minzijun_rl_output_checkpoints_verl_role_sft_dapo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_align_dapo_global_step_0_actor_huggingface/2025-08-28T14-49-18.189800/details_extended|ifeval|0_2025-08-28T14-49-18.189800.csv +3 -0
  3. eval_results_ood/global_step_10/details/_home_work_minzijun_rl_output_checkpoints_verl_role_sft_dapo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_align_dapo_global_step_10_actor_huggingface/2025-08-28T14-45-33.476438/details_extended|ifeval|0_2025-08-28T14-45-33.476438.csv +3 -0
  4. eval_results_ood/global_step_15/details/_home_work_minzijun_rl_output_checkpoints_verl_role_sft_dapo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_align_dapo_global_step_15_actor_huggingface/2025-08-28T14-50-01.895931/details_extended|ifeval|0_2025-08-28T14-50-01.895931.csv +3 -0
  5. eval_results_ood/global_step_20/details/_home_work_minzijun_rl_output_checkpoints_verl_role_sft_dapo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_align_dapo_global_step_20_actor_huggingface/2025-08-28T14-41-15.471222/details_extended|ifeval|0_2025-08-28T14-41-15.471222.csv +3 -0
  6. eval_results_ood/global_step_25/details/_home_work_minzijun_rl_output_checkpoints_verl_role_sft_dapo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_align_dapo_global_step_25_actor_huggingface/2025-08-28T14-39-58.153080/details_extended|ifeval|0_2025-08-28T14-39-58.153080.csv +3 -0
  7. eval_results_ood/global_step_30/details/_home_work_minzijun_rl_output_checkpoints_verl_role_sft_dapo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_align_dapo_global_step_30_actor_huggingface/2025-08-28T14-37-15.799096/details_extended|ifeval|0_2025-08-28T14-37-15.799096.csv +3 -0
  8. eval_results_ood/global_step_35/details/_home_work_minzijun_rl_output_checkpoints_verl_role_sft_dapo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_align_dapo_global_step_35_actor_huggingface/2025-08-28T15-24-51.351310/details_extended|ifeval|0_2025-08-28T15-24-51.351310.csv +3 -0
  9. eval_results_ood/global_step_40/details/_home_work_minzijun_rl_output_checkpoints_verl_role_sft_dapo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_align_dapo_global_step_40_actor_huggingface/2025-08-28T15-15-30.916653/details_extended|ifeval|0_2025-08-28T15-15-30.916653.csv +3 -0
  10. eval_results_ood/global_step_45/details/_home_work_minzijun_rl_output_checkpoints_verl_role_sft_dapo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_align_dapo_global_step_45_actor_huggingface/2025-08-28T15-20-14.907955/details_extended|ifeval|0_2025-08-28T15-20-14.907955.csv +3 -0
  11. eval_results_ood/global_step_5/details/_home_work_minzijun_rl_output_checkpoints_verl_role_sft_dapo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_align_dapo_global_step_5_actor_huggingface/2025-08-28T14-50-06.798449/details_extended|ifeval|0_2025-08-28T14-50-06.798449.csv +3 -0
  12. global_step_10/actor/huggingface/tokenizer.json +3 -0
  13. global_step_10/data.pt +3 -0
  14. global_step_15/actor/huggingface/tokenizer.json +3 -0
  15. global_step_15/data.pt +3 -0
  16. global_step_20/actor/huggingface/tokenizer.json +3 -0
  17. global_step_20/data.pt +3 -0
  18. global_step_25/actor/huggingface/tokenizer.json +3 -0
  19. global_step_25/data.pt +3 -0
  20. global_step_30/actor/huggingface/tokenizer.json +3 -0
  21. global_step_30/data.pt +3 -0
  22. global_step_35/actor/huggingface/tokenizer.json +3 -0
  23. global_step_35/data.pt +3 -0
  24. global_step_40/actor/huggingface/tokenizer.json +3 -0
  25. global_step_40/data.pt +3 -0
  26. global_step_45/actor/huggingface/tokenizer.json +3 -0
  27. global_step_45/data.pt +3 -0
  28. global_step_5/actor/huggingface/tokenizer.json +3 -0
  29. global_step_5/data.pt +3 -0
  30. global_step_50/data.pt +3 -0
.gitattributes CHANGED
@@ -77,3 +77,13 @@ eval_results_avg4/plots/eval_results_avg4_correct_tokens.png filter=lfs diff=lfs
77
  eval_results_avg4/plots/eval_results_avg4_repeat_ratio_and_token_length.png filter=lfs diff=lfs merge=lfs -text
78
  eval_results_avg4/plots/eval_results_avg4_tokens_keywords.png filter=lfs diff=lfs merge=lfs -text
79
  eval_results_avg4/plots/eval_results_avg4_wrong_tokens.png filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
77
  eval_results_avg4/plots/eval_results_avg4_repeat_ratio_and_token_length.png filter=lfs diff=lfs merge=lfs -text
78
  eval_results_avg4/plots/eval_results_avg4_tokens_keywords.png filter=lfs diff=lfs merge=lfs -text
79
  eval_results_avg4/plots/eval_results_avg4_wrong_tokens.png filter=lfs diff=lfs merge=lfs -text
80
+ eval_results_ood/global_step_0/details/_home_work_minzijun_rl_output_checkpoints_verl_role_sft_dapo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_align_dapo_global_step_0_actor_huggingface/2025-08-28T14-49-18.189800/details_extended|ifeval|0_2025-08-28T14-49-18.189800.csv filter=lfs diff=lfs merge=lfs -text
81
+ eval_results_ood/global_step_35/details/_home_work_minzijun_rl_output_checkpoints_verl_role_sft_dapo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_align_dapo_global_step_35_actor_huggingface/2025-08-28T15-24-51.351310/details_extended|ifeval|0_2025-08-28T15-24-51.351310.csv filter=lfs diff=lfs merge=lfs -text
82
+ eval_results_ood/global_step_30/details/_home_work_minzijun_rl_output_checkpoints_verl_role_sft_dapo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_align_dapo_global_step_30_actor_huggingface/2025-08-28T14-37-15.799096/details_extended|ifeval|0_2025-08-28T14-37-15.799096.csv filter=lfs diff=lfs merge=lfs -text
83
+ eval_results_ood/global_step_40/details/_home_work_minzijun_rl_output_checkpoints_verl_role_sft_dapo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_align_dapo_global_step_40_actor_huggingface/2025-08-28T15-15-30.916653/details_extended|ifeval|0_2025-08-28T15-15-30.916653.csv filter=lfs diff=lfs merge=lfs -text
84
+ eval_results_ood/global_step_20/details/_home_work_minzijun_rl_output_checkpoints_verl_role_sft_dapo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_align_dapo_global_step_20_actor_huggingface/2025-08-28T14-41-15.471222/details_extended|ifeval|0_2025-08-28T14-41-15.471222.csv filter=lfs diff=lfs merge=lfs -text
85
+ eval_results_ood/global_step_10/details/_home_work_minzijun_rl_output_checkpoints_verl_role_sft_dapo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_align_dapo_global_step_10_actor_huggingface/2025-08-28T14-45-33.476438/details_extended|ifeval|0_2025-08-28T14-45-33.476438.csv filter=lfs diff=lfs merge=lfs -text
86
+ eval_results_ood/global_step_25/details/_home_work_minzijun_rl_output_checkpoints_verl_role_sft_dapo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_align_dapo_global_step_25_actor_huggingface/2025-08-28T14-39-58.153080/details_extended|ifeval|0_2025-08-28T14-39-58.153080.csv filter=lfs diff=lfs merge=lfs -text
87
+ eval_results_ood/global_step_45/details/_home_work_minzijun_rl_output_checkpoints_verl_role_sft_dapo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_align_dapo_global_step_45_actor_huggingface/2025-08-28T15-20-14.907955/details_extended|ifeval|0_2025-08-28T15-20-14.907955.csv filter=lfs diff=lfs merge=lfs -text
88
+ eval_results_ood/global_step_5/details/_home_work_minzijun_rl_output_checkpoints_verl_role_sft_dapo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_align_dapo_global_step_5_actor_huggingface/2025-08-28T14-50-06.798449/details_extended|ifeval|0_2025-08-28T14-50-06.798449.csv filter=lfs diff=lfs merge=lfs -text
89
+ eval_results_ood/global_step_15/details/_home_work_minzijun_rl_output_checkpoints_verl_role_sft_dapo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_align_dapo_global_step_15_actor_huggingface/2025-08-28T14-50-01.895931/details_extended|ifeval|0_2025-08-28T14-50-01.895931.csv filter=lfs diff=lfs merge=lfs -text
eval_results_ood/global_step_0/details/_home_work_minzijun_rl_output_checkpoints_verl_role_sft_dapo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_align_dapo_global_step_0_actor_huggingface/2025-08-28T14-49-18.189800/details_extended|ifeval|0_2025-08-28T14-49-18.189800.csv ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c27102d18786e89704a36ea91a14882eb30db7dba6cae5513ed12a21e5ba7cd
3
+ size 16685852
eval_results_ood/global_step_10/details/_home_work_minzijun_rl_output_checkpoints_verl_role_sft_dapo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_align_dapo_global_step_10_actor_huggingface/2025-08-28T14-45-33.476438/details_extended|ifeval|0_2025-08-28T14-45-33.476438.csv ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f225ec1644fa8d518c9563eff95094e5d10845391aed0a47b7a418a5463ba496
3
+ size 16249075
eval_results_ood/global_step_15/details/_home_work_minzijun_rl_output_checkpoints_verl_role_sft_dapo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_align_dapo_global_step_15_actor_huggingface/2025-08-28T14-50-01.895931/details_extended|ifeval|0_2025-08-28T14-50-01.895931.csv ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0224949609c31edd0f60326d37b96910a8cf20d5ee0310e08cc387055075ad1
3
+ size 17118864
eval_results_ood/global_step_20/details/_home_work_minzijun_rl_output_checkpoints_verl_role_sft_dapo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_align_dapo_global_step_20_actor_huggingface/2025-08-28T14-41-15.471222/details_extended|ifeval|0_2025-08-28T14-41-15.471222.csv ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c0d087a0978492a3b2a6f6823acd7f4d878ca8188c37cc7ecd90cea1eef3508
3
+ size 15633937
eval_results_ood/global_step_25/details/_home_work_minzijun_rl_output_checkpoints_verl_role_sft_dapo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_align_dapo_global_step_25_actor_huggingface/2025-08-28T14-39-58.153080/details_extended|ifeval|0_2025-08-28T14-39-58.153080.csv ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a47853812c1c0fd74ecd6e05c1b42b583e0bf3d05d3a087614e456d485af0f9
3
+ size 14910227
eval_results_ood/global_step_30/details/_home_work_minzijun_rl_output_checkpoints_verl_role_sft_dapo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_align_dapo_global_step_30_actor_huggingface/2025-08-28T14-37-15.799096/details_extended|ifeval|0_2025-08-28T14-37-15.799096.csv ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a25e3996ce2e055cbabaf37709543415a84387a96822da3c0d56dc0866301041
3
+ size 12880092
eval_results_ood/global_step_35/details/_home_work_minzijun_rl_output_checkpoints_verl_role_sft_dapo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_align_dapo_global_step_35_actor_huggingface/2025-08-28T15-24-51.351310/details_extended|ifeval|0_2025-08-28T15-24-51.351310.csv ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b56162bf96c951f1b02b0a4d9745be33f73ce0a46171233e882c96b01d5a61a3
3
+ size 11762883
eval_results_ood/global_step_40/details/_home_work_minzijun_rl_output_checkpoints_verl_role_sft_dapo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_align_dapo_global_step_40_actor_huggingface/2025-08-28T15-15-30.916653/details_extended|ifeval|0_2025-08-28T15-15-30.916653.csv ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7778f4378f81ae3ae571f6b52aeed39b71f781790a1c66a5e3fdf4d9d4ba5427
3
+ size 10731717
eval_results_ood/global_step_45/details/_home_work_minzijun_rl_output_checkpoints_verl_role_sft_dapo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_align_dapo_global_step_45_actor_huggingface/2025-08-28T15-20-14.907955/details_extended|ifeval|0_2025-08-28T15-20-14.907955.csv ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d0620d19457ef66177169ff45355327f6c0f15127303708aea4a8bc3899ce6d
3
+ size 11451144
eval_results_ood/global_step_5/details/_home_work_minzijun_rl_output_checkpoints_verl_role_sft_dapo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_align_dapo_global_step_5_actor_huggingface/2025-08-28T14-50-06.798449/details_extended|ifeval|0_2025-08-28T14-50-06.798449.csv ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:940f7d26038408f89aa466f6b78949051fd84e5aa929a8c3fc4544b420689d4e
3
+ size 15837207
global_step_10/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
global_step_10/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:214ac93d9011cdd1d98f536b37a7c227059b83bc145fb8505e1939f70db67f83
3
+ size 1947
global_step_15/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
global_step_15/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75da11b59b7b1226f88b1726de50d126462e7436fc23fbf7111edf3d9b287462
3
+ size 1947
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
global_step_20/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72e33e9b6f7bdc0c09e06d31bfecd034d8424837d21615bff114353bc19d87fa
3
+ size 1947
global_step_25/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
global_step_25/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95c2c1a44caeaf3d4790c2c4bc78cf98b5ca8b6f40cba6a18d3bd6e8168a87aa
3
+ size 1947
global_step_30/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
global_step_30/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a17a33102f90e3bdd66c421ecac2f8ad785b9dacc25d5e77a1831a7275891098
3
+ size 1947
global_step_35/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
global_step_35/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:651af360b7769a6d6bc6358c2e17e9b1cb3e09f519bac4a159ad79223ed2b6ad
3
+ size 1947
global_step_40/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
global_step_40/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d44ccbf7dfb2fa13a2b4837e9b39ef914aaa734dd5102af388eed01784767a8c
3
+ size 1947
global_step_45/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
global_step_45/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8c199e6ef7fbdf1a2d9a5dde3adba1af1e5bf2815e14849880a93d708eabdc8
3
+ size 1947
global_step_5/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
global_step_5/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2992b2cc112c17909523cbac5e557a34d07f6b78865dc3fa8b87774fb020ed7a
3
+ size 1947
global_step_50/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d41b6f9f4720353e4f53eb4e923fddcb4ef39ee6bd8397d421e74c05bfa83f2
3
+ size 1947