TheBlackCat22 commited on
Commit
2eb372b
·
verified ·
1 Parent(s): 118bfaa

Add files using upload-large-folder tool

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +26 -0
  2. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/104.jsonl +3 -0
  3. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/106.jsonl +3 -0
  4. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/110.jsonl +3 -0
  5. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/111.jsonl +3 -0
  6. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/112.jsonl +3 -0
  7. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/113.jsonl +3 -0
  8. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/114.jsonl +3 -0
  9. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/118.jsonl +3 -0
  10. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/run.log +0 -0
  11. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/validation/110.jsonl +0 -0
  12. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/validation/120.jsonl +0 -0
  13. cache_nq_qwen4b/20260504_160206/global_step_250/actor/added_tokens.json +28 -0
  14. cache_nq_qwen4b/20260504_160206/global_step_250/actor/config.json +31 -0
  15. cache_nq_qwen4b/20260504_160206/global_step_250/actor/extra_state_world_size_8_rank_0.pt +3 -0
  16. cache_nq_qwen4b/20260504_160206/global_step_250/actor/extra_state_world_size_8_rank_2.pt +3 -0
  17. cache_nq_qwen4b/20260504_160206/global_step_250/actor/extra_state_world_size_8_rank_3.pt +3 -0
  18. cache_nq_qwen4b/20260504_160206/global_step_250/actor/extra_state_world_size_8_rank_4.pt +3 -0
  19. cache_nq_qwen4b/20260504_160206/global_step_250/actor/extra_state_world_size_8_rank_6.pt +3 -0
  20. cache_nq_qwen4b/20260504_160206/global_step_250/actor/extra_state_world_size_8_rank_7.pt +3 -0
  21. cache_nq_qwen4b/20260504_160206/global_step_250/actor/generation_config.json +13 -0
  22. cache_nq_qwen4b/20260504_160206/global_step_250/actor/merges.txt +0 -0
  23. cache_nq_qwen4b/20260504_160206/global_step_250/actor/special_tokens_map.json +31 -0
  24. cache_nq_qwen4b/20260504_160206/global_step_250/actor/tokenizer.json +3 -0
  25. cache_nq_qwen4b/20260504_160206/global_step_250/actor/tokenizer_config.json +240 -0
  26. cache_nq_qwen4b/20260504_160206/global_step_250/actor/vocab.json +0 -0
  27. cache_nq_qwen4b/20260504_160206/global_step_250/data.pt +3 -0
  28. cache_nq_qwen4b/20260504_160206/latest_checkpointed_iteration.txt +1 -1
  29. cache_nq_qwen4b/20260504_160206/rollout/215.jsonl +3 -0
  30. cache_nq_qwen4b/20260504_160206/rollout/218.jsonl +3 -0
  31. cache_nq_qwen4b/20260504_160206/rollout/219.jsonl +3 -0
  32. cache_nq_qwen4b/20260504_160206/rollout/221.jsonl +3 -0
  33. cache_nq_qwen4b/20260504_160206/rollout/226.jsonl +3 -0
  34. cache_nq_qwen4b/20260504_160206/rollout/227.jsonl +3 -0
  35. cache_nq_qwen4b/20260504_160206/rollout/228.jsonl +3 -0
  36. cache_nq_qwen4b/20260504_160206/rollout/229.jsonl +3 -0
  37. cache_nq_qwen4b/20260504_160206/rollout/230.jsonl +3 -0
  38. cache_nq_qwen4b/20260504_160206/rollout/236.jsonl +3 -0
  39. cache_nq_qwen4b/20260504_160206/rollout/238.jsonl +3 -0
  40. cache_nq_qwen4b/20260504_160206/rollout/241.jsonl +3 -0
  41. cache_nq_qwen4b/20260504_160206/rollout/242.jsonl +3 -0
  42. cache_nq_qwen4b/20260504_160206/rollout/244.jsonl +3 -0
  43. cache_nq_qwen4b/20260504_160206/rollout/249.jsonl +3 -0
  44. cache_nq_qwen4b/20260504_160206/rollout/250.jsonl +3 -0
  45. cache_nq_qwen4b/20260504_160206/rollout/253.jsonl +3 -0
  46. cache_nq_qwen4b/20260504_160206/run.log +0 -0
  47. cache_nq_qwen4b/20260504_160206/validation/220.jsonl +0 -0
  48. cache_nq_qwen4b/20260504_160206/validation/230.jsonl +0 -0
  49. cache_nq_qwen4b/20260504_160206/validation/240.jsonl +0 -0
  50. cache_nq_qwen4b/20260504_160206/validation/250.jsonl +0 -0
.gitattributes CHANGED
@@ -933,3 +933,29 @@ cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/100.jsonl fil
933
  cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/61.jsonl filter=lfs diff=lfs merge=lfs -text
934
  cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/54.jsonl filter=lfs diff=lfs merge=lfs -text
935
  cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/35.jsonl filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
933
  cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/61.jsonl filter=lfs diff=lfs merge=lfs -text
934
  cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/54.jsonl filter=lfs diff=lfs merge=lfs -text
935
  cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/35.jsonl filter=lfs diff=lfs merge=lfs -text
936
+ cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/112.jsonl filter=lfs diff=lfs merge=lfs -text
937
+ cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/114.jsonl filter=lfs diff=lfs merge=lfs -text
938
+ cache_nq_qwen4b/20260504_160206/rollout/215.jsonl filter=lfs diff=lfs merge=lfs -text
939
+ cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/106.jsonl filter=lfs diff=lfs merge=lfs -text
940
+ cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/111.jsonl filter=lfs diff=lfs merge=lfs -text
941
+ cache_nq_qwen4b/20260504_160206/rollout/227.jsonl filter=lfs diff=lfs merge=lfs -text
942
+ cache_nq_qwen4b/20260504_160206/rollout/218.jsonl filter=lfs diff=lfs merge=lfs -text
943
+ cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/118.jsonl filter=lfs diff=lfs merge=lfs -text
944
+ cache_nq_qwen4b/20260504_160206/rollout/236.jsonl filter=lfs diff=lfs merge=lfs -text
945
+ cache_nq_qwen4b/20260504_160206/rollout/229.jsonl filter=lfs diff=lfs merge=lfs -text
946
+ cache_nq_qwen4b/20260504_160206/rollout/253.jsonl filter=lfs diff=lfs merge=lfs -text
947
+ cache_nq_qwen4b/20260504_160206/rollout/221.jsonl filter=lfs diff=lfs merge=lfs -text
948
+ cache_nq_qwen4b/20260504_160206/rollout/241.jsonl filter=lfs diff=lfs merge=lfs -text
949
+ cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/104.jsonl filter=lfs diff=lfs merge=lfs -text
950
+ cache_nq_qwen4b/20260504_160206/rollout/238.jsonl filter=lfs diff=lfs merge=lfs -text
951
+ cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/110.jsonl filter=lfs diff=lfs merge=lfs -text
952
+ cache_nq_qwen4b/20260504_160206/rollout/250.jsonl filter=lfs diff=lfs merge=lfs -text
953
+ cache_nq_qwen4b/20260504_160206/rollout/219.jsonl filter=lfs diff=lfs merge=lfs -text
954
+ cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/113.jsonl filter=lfs diff=lfs merge=lfs -text
955
+ cache_nq_qwen4b/20260504_160206/rollout/249.jsonl filter=lfs diff=lfs merge=lfs -text
956
+ cache_nq_qwen4b/20260504_160206/rollout/244.jsonl filter=lfs diff=lfs merge=lfs -text
957
+ cache_nq_qwen4b/20260504_160206/rollout/228.jsonl filter=lfs diff=lfs merge=lfs -text
958
+ cache_nq_qwen4b/20260504_160206/rollout/226.jsonl filter=lfs diff=lfs merge=lfs -text
959
+ cache_nq_qwen4b/20260504_160206/rollout/230.jsonl filter=lfs diff=lfs merge=lfs -text
960
+ cache_nq_qwen4b/20260504_160206/rollout/242.jsonl filter=lfs diff=lfs merge=lfs -text
961
+ cache_nq_qwen4b/20260504_160206/global_step_250/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/104.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec9cf34b35f8f0f9a5c9bbacf4ab42e0af05cd7dad39442a482bfc03a0a650a8
3
+ size 13947166
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/106.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cca22ce6ac041003abc9e47322fe9d98d210e1e729cefdfe9096cd39e2dfde2a
3
+ size 13535161
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/110.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d015f9bb3969751938eb173767fcc8a87bd986f85df8e5655c0d637bfbacbb8a
3
+ size 14840746
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/111.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:452693d7c528208962f399518ad1606cb425423f0272ed33e5c598c9fa97e037
3
+ size 14187386
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/112.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b723303dc9c12c86832f9a055bda0d03e91b017d9d8491743c131b19daf314e
3
+ size 14051384
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/113.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b6bf663846885a30fbdab586d5e9b0c78e4cbafd0cebae3c60f5a6187ba5d7e
3
+ size 15377466
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/114.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f42a3a2faf06e66f8387cccac7476f977afadf981c9d3925fc2d78d4a3c48117
3
+ size 14156043
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/118.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99083b5b83e00cc943dd5a7f0f03192be5e78864d97d0559c5ae2a514e58bfe3
3
+ size 14548777
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/run.log CHANGED
The diff for this file is too large to render. See raw diff
 
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/validation/110.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/validation/120.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
cache_nq_qwen4b/20260504_160206/global_step_250/actor/added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<think>": 151667,
6
+ "<tool_call>": 151657,
7
+ "<tool_response>": 151665,
8
+ "<|box_end|>": 151649,
9
+ "<|box_start|>": 151648,
10
+ "<|endoftext|>": 151643,
11
+ "<|file_sep|>": 151664,
12
+ "<|fim_middle|>": 151660,
13
+ "<|fim_pad|>": 151662,
14
+ "<|fim_prefix|>": 151659,
15
+ "<|fim_suffix|>": 151661,
16
+ "<|im_end|>": 151645,
17
+ "<|im_start|>": 151644,
18
+ "<|image_pad|>": 151655,
19
+ "<|object_ref_end|>": 151647,
20
+ "<|object_ref_start|>": 151646,
21
+ "<|quad_end|>": 151651,
22
+ "<|quad_start|>": 151650,
23
+ "<|repo_name|>": 151663,
24
+ "<|video_pad|>": 151656,
25
+ "<|vision_end|>": 151653,
26
+ "<|vision_pad|>": 151654,
27
+ "<|vision_start|>": 151652
28
+ }
cache_nq_qwen4b/20260504_160206/global_step_250/actor/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_attn_implementation_autoset": true,
3
+ "architectures": [
4
+ "Qwen3ForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "eos_token_id": 151645,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2560,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 9728,
14
+ "max_position_embeddings": 40960,
15
+ "max_window_layers": 36,
16
+ "model_type": "qwen3",
17
+ "num_attention_heads": 32,
18
+ "num_hidden_layers": 36,
19
+ "num_key_value_heads": 8,
20
+ "pad_token_id": 151643,
21
+ "rms_norm_eps": 1e-06,
22
+ "rope_scaling": null,
23
+ "rope_theta": 1000000,
24
+ "sliding_window": null,
25
+ "tie_word_embeddings": true,
26
+ "torch_dtype": "float32",
27
+ "transformers_version": "4.51.3",
28
+ "use_cache": true,
29
+ "use_sliding_window": false,
30
+ "vocab_size": 151936
31
+ }
cache_nq_qwen4b/20260504_160206/global_step_250/actor/extra_state_world_size_8_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9887fb9855e05264d3c726eb65eddeab7e18c53d7fde3a3e97f15512533653af
3
+ size 14632
cache_nq_qwen4b/20260504_160206/global_step_250/actor/extra_state_world_size_8_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:781b66d00559c781b19ee3e78b0eed2285359f085089841d5981fd2e983f2711
3
+ size 14632
cache_nq_qwen4b/20260504_160206/global_step_250/actor/extra_state_world_size_8_rank_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b559e560a1144b0b5ab5c95afcbe202fcdf640230dba332b359e0066b7632af
3
+ size 14632
cache_nq_qwen4b/20260504_160206/global_step_250/actor/extra_state_world_size_8_rank_4.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f83c10449771e26072bede3d467713ecd7e70bab52e7b394ecab4ff0abf46dce
3
+ size 14632
cache_nq_qwen4b/20260504_160206/global_step_250/actor/extra_state_world_size_8_rank_6.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cc792dcebd6e1928afb4b332ebf0f56adc55764695699fa6ebb9df3b4007612
3
+ size 14632
cache_nq_qwen4b/20260504_160206/global_step_250/actor/extra_state_world_size_8_rank_7.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:211415a6bbaf94c6b73e6ea260de303b2f6e2715a6385d4016867e56203bdde6
3
+ size 14632
cache_nq_qwen4b/20260504_160206/global_step_250/actor/generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "temperature": 0.6,
10
+ "top_k": 20,
11
+ "top_p": 0.95,
12
+ "transformers_version": "4.51.3"
13
+ }
cache_nq_qwen4b/20260504_160206/global_step_250/actor/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
cache_nq_qwen4b/20260504_160206/global_step_250/actor/special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
cache_nq_qwen4b/20260504_160206/global_step_250/actor/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
cache_nq_qwen4b/20260504_160206/global_step_250/actor/tokenizer_config.json ADDED
@@ -0,0 +1,240 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151666": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151667": {
198
+ "content": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ }
213
+ },
214
+ "additional_special_tokens": [
215
+ "<|im_start|>",
216
+ "<|im_end|>",
217
+ "<|object_ref_start|>",
218
+ "<|object_ref_end|>",
219
+ "<|box_start|>",
220
+ "<|box_end|>",
221
+ "<|quad_start|>",
222
+ "<|quad_end|>",
223
+ "<|vision_start|>",
224
+ "<|vision_end|>",
225
+ "<|vision_pad|>",
226
+ "<|image_pad|>",
227
+ "<|video_pad|>"
228
+ ],
229
+ "bos_token": null,
230
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if message.content is string %}\n {%- set content = message.content %}\n {%- else %}\n {%- set content = '' %}\n {%- endif %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in content %}\n {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- endif %}\n{%- endif %}",
231
+ "clean_up_tokenization_spaces": false,
232
+ "eos_token": "<|im_end|>",
233
+ "errors": "replace",
234
+ "extra_special_tokens": {},
235
+ "model_max_length": 131072,
236
+ "pad_token": "<|endoftext|>",
237
+ "split_special_tokens": false,
238
+ "tokenizer_class": "Qwen2Tokenizer",
239
+ "unk_token": null
240
+ }
cache_nq_qwen4b/20260504_160206/global_step_250/actor/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
cache_nq_qwen4b/20260504_160206/global_step_250/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d7a07113a0261db21f48a1711cb6223942d7b9d49768c8e65cd5d60ed055c82
3
+ size 1492
cache_nq_qwen4b/20260504_160206/latest_checkpointed_iteration.txt CHANGED
@@ -1 +1 @@
1
- 200
 
1
+ 250
cache_nq_qwen4b/20260504_160206/rollout/215.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3be17f741f4ea48bda25b5409a5eda1a736f664353ffdb28245412608629d064
3
+ size 11767511
cache_nq_qwen4b/20260504_160206/rollout/218.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cec8d7861cb86f5b907cca708e976f67ed2dc87a1d41876e4f16d7eb98dbff2a
3
+ size 12514851
cache_nq_qwen4b/20260504_160206/rollout/219.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8bd02f08b97eef1204c261634b793a2a9a16e29663048f12fcfdcd0cc8289e3
3
+ size 12773194
cache_nq_qwen4b/20260504_160206/rollout/221.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c48cf9520c3683feb9de7326db3ed6d3f591cfbf6b96a638cc7d91812168b1eb
3
+ size 11983176
cache_nq_qwen4b/20260504_160206/rollout/226.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a608e0ceb68e7fcbf068e8f7a667922e83dbe499ee1100a57b33949ba6ba1ebf
3
+ size 12274247
cache_nq_qwen4b/20260504_160206/rollout/227.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:033378864c4cf4bfd187e0f948207dd8968b0847d4e2d28f365cc5a531907e04
3
+ size 12503466
cache_nq_qwen4b/20260504_160206/rollout/228.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e91b0963b915c18a5e588c387892ee44d233a0bfd044ba839219c6c93e8a8b43
3
+ size 12211463
cache_nq_qwen4b/20260504_160206/rollout/229.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4a03e6586d8241c6803d0d80bf5b8ca0531d145d59cdbd97842e1965aa26266
3
+ size 11927682
cache_nq_qwen4b/20260504_160206/rollout/230.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba6b06756a42ad4aac25e942ddf913fbffc709da4288d953b40d8e7b08e6cd02
3
+ size 12160025
cache_nq_qwen4b/20260504_160206/rollout/236.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c817ffcb297be59376a556c7b5831448171c61b2d26f90fec78b626932dea14
3
+ size 11645785
cache_nq_qwen4b/20260504_160206/rollout/238.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c3871bb914e312b46b8a22cc98c5bd5fe60e7b51f328ce493c9ac30286edfaa
3
+ size 11358636
cache_nq_qwen4b/20260504_160206/rollout/241.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7ba024e12a78b8d2072e0c55012179f7675f2703c68ae9dbd3933e48921e443
3
+ size 11274691
cache_nq_qwen4b/20260504_160206/rollout/242.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bc3272da9fbac352d38784478a631f363804d9fe082f3370f350d569db95b23
3
+ size 11838425
cache_nq_qwen4b/20260504_160206/rollout/244.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e172b6aa7fadb41eac74508f08da02b5514bffc17cfc6e5de1cc90c0527a825c
3
+ size 11487771
cache_nq_qwen4b/20260504_160206/rollout/249.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f5ab749a8bee00257ed155f2b4784e008ad8db8f4b9a440d8a0275746c0b34a
3
+ size 11331363
cache_nq_qwen4b/20260504_160206/rollout/250.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b53333c69fadcc1c04f4bf3fda4b6b72db838395ace26d41215c5bc3a16d4ef3
3
+ size 11846216
cache_nq_qwen4b/20260504_160206/rollout/253.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:220d5ab0e2f917c8ac1d280146766a177be8b1b6c93d2f8fe018224e83916685
3
+ size 11013250
cache_nq_qwen4b/20260504_160206/run.log CHANGED
The diff for this file is too large to render. See raw diff
 
cache_nq_qwen4b/20260504_160206/validation/220.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
cache_nq_qwen4b/20260504_160206/validation/230.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
cache_nq_qwen4b/20260504_160206/validation/240.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
cache_nq_qwen4b/20260504_160206/validation/250.jsonl ADDED
The diff for this file is too large to render. See raw diff