TheBlackCat22 commited on
Commit
c879897
·
verified ·
1 Parent(s): 6bf2f69

Add files using upload-large-folder tool

Browse files
Files changed (50) hide show
  1. .gitattributes +13 -0
  2. atpo_hotpotqa_qwen8b/20260506_124901/global_step_250/actor/added_tokens.json +28 -0
  3. atpo_hotpotqa_qwen8b/20260506_124901/global_step_250/actor/config.json +31 -0
  4. atpo_hotpotqa_qwen8b/20260506_124901/global_step_250/actor/extra_state_world_size_8_rank_0.pt +3 -0
  5. atpo_hotpotqa_qwen8b/20260506_124901/global_step_250/actor/extra_state_world_size_8_rank_1.pt +3 -0
  6. atpo_hotpotqa_qwen8b/20260506_124901/global_step_250/actor/extra_state_world_size_8_rank_2.pt +3 -0
  7. atpo_hotpotqa_qwen8b/20260506_124901/global_step_250/actor/extra_state_world_size_8_rank_3.pt +3 -0
  8. atpo_hotpotqa_qwen8b/20260506_124901/global_step_250/actor/extra_state_world_size_8_rank_4.pt +3 -0
  9. atpo_hotpotqa_qwen8b/20260506_124901/global_step_250/actor/extra_state_world_size_8_rank_5.pt +3 -0
  10. atpo_hotpotqa_qwen8b/20260506_124901/global_step_250/actor/extra_state_world_size_8_rank_6.pt +3 -0
  11. atpo_hotpotqa_qwen8b/20260506_124901/global_step_250/actor/extra_state_world_size_8_rank_7.pt +3 -0
  12. atpo_hotpotqa_qwen8b/20260506_124901/global_step_250/actor/generation_config.json +13 -0
  13. atpo_hotpotqa_qwen8b/20260506_124901/global_step_250/actor/merges.txt +0 -0
  14. atpo_hotpotqa_qwen8b/20260506_124901/global_step_250/actor/model_world_size_8_rank_0.pt +3 -0
  15. atpo_hotpotqa_qwen8b/20260506_124901/global_step_250/actor/model_world_size_8_rank_1.pt +3 -0
  16. atpo_hotpotqa_qwen8b/20260506_124901/global_step_250/actor/model_world_size_8_rank_2.pt +3 -0
  17. atpo_hotpotqa_qwen8b/20260506_124901/global_step_250/actor/model_world_size_8_rank_3.pt +3 -0
  18. atpo_hotpotqa_qwen8b/20260506_124901/global_step_250/actor/model_world_size_8_rank_4.pt +3 -0
  19. atpo_hotpotqa_qwen8b/20260506_124901/global_step_250/actor/model_world_size_8_rank_5.pt +3 -0
  20. atpo_hotpotqa_qwen8b/20260506_124901/global_step_250/actor/model_world_size_8_rank_6.pt +3 -0
  21. atpo_hotpotqa_qwen8b/20260506_124901/global_step_250/actor/model_world_size_8_rank_7.pt +3 -0
  22. atpo_hotpotqa_qwen8b/20260506_124901/global_step_250/actor/optim_world_size_8_rank_0.pt +3 -0
  23. atpo_hotpotqa_qwen8b/20260506_124901/global_step_250/actor/optim_world_size_8_rank_1.pt +3 -0
  24. atpo_hotpotqa_qwen8b/20260506_124901/global_step_250/actor/optim_world_size_8_rank_2.pt +3 -0
  25. atpo_hotpotqa_qwen8b/20260506_124901/global_step_250/actor/optim_world_size_8_rank_3.pt +3 -0
  26. atpo_hotpotqa_qwen8b/20260506_124901/global_step_250/actor/optim_world_size_8_rank_4.pt +3 -0
  27. atpo_hotpotqa_qwen8b/20260506_124901/global_step_250/actor/optim_world_size_8_rank_5.pt +3 -0
  28. atpo_hotpotqa_qwen8b/20260506_124901/global_step_250/actor/optim_world_size_8_rank_6.pt +3 -0
  29. atpo_hotpotqa_qwen8b/20260506_124901/global_step_250/actor/optim_world_size_8_rank_7.pt +3 -0
  30. atpo_hotpotqa_qwen8b/20260506_124901/global_step_250/actor/special_tokens_map.json +31 -0
  31. atpo_hotpotqa_qwen8b/20260506_124901/global_step_250/actor/tokenizer.json +3 -0
  32. atpo_hotpotqa_qwen8b/20260506_124901/global_step_250/actor/tokenizer_config.json +240 -0
  33. atpo_hotpotqa_qwen8b/20260506_124901/global_step_250/actor/vocab.json +0 -0
  34. atpo_hotpotqa_qwen8b/20260506_124901/global_step_250/data.pt +3 -0
  35. atpo_hotpotqa_qwen8b/20260506_124901/latest_checkpointed_iteration.txt +1 -0
  36. atpo_hotpotqa_qwen8b/20260506_124901/rollout/240.jsonl +3 -0
  37. atpo_hotpotqa_qwen8b/20260506_124901/rollout/241.jsonl +3 -0
  38. atpo_hotpotqa_qwen8b/20260506_124901/rollout/242.jsonl +3 -0
  39. atpo_hotpotqa_qwen8b/20260506_124901/rollout/243.jsonl +3 -0
  40. atpo_hotpotqa_qwen8b/20260506_124901/rollout/244.jsonl +3 -0
  41. atpo_hotpotqa_qwen8b/20260506_124901/rollout/245.jsonl +3 -0
  42. atpo_hotpotqa_qwen8b/20260506_124901/rollout/246.jsonl +3 -0
  43. atpo_hotpotqa_qwen8b/20260506_124901/rollout/247.jsonl +3 -0
  44. atpo_hotpotqa_qwen8b/20260506_124901/rollout/248.jsonl +3 -0
  45. atpo_hotpotqa_qwen8b/20260506_124901/rollout/249.jsonl +3 -0
  46. atpo_hotpotqa_qwen8b/20260506_124901/rollout/250.jsonl +3 -0
  47. atpo_hotpotqa_qwen8b/20260506_124901/rollout/251.jsonl +3 -0
  48. atpo_hotpotqa_qwen8b/20260506_124901/run.log +0 -0
  49. atpo_hotpotqa_qwen8b/20260506_124901/validation/240.jsonl +0 -0
  50. atpo_hotpotqa_qwen8b/20260506_124901/validation/250.jsonl +0 -0
.gitattributes CHANGED
@@ -1215,3 +1215,16 @@ atpo_hotpotqa_qwen8b/20260506_124901/rollout/238.jsonl filter=lfs diff=lfs merge
1215
  atpo_hotpotqa_qwen8b/20260506_124901/rollout/237.jsonl filter=lfs diff=lfs merge=lfs -text
1216
  cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/244.jsonl filter=lfs diff=lfs merge=lfs -text
1217
  atpo_hotpotqa_qwen8b/20260506_124901/rollout/231.jsonl filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1215
  atpo_hotpotqa_qwen8b/20260506_124901/rollout/237.jsonl filter=lfs diff=lfs merge=lfs -text
1216
  cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/244.jsonl filter=lfs diff=lfs merge=lfs -text
1217
  atpo_hotpotqa_qwen8b/20260506_124901/rollout/231.jsonl filter=lfs diff=lfs merge=lfs -text
1218
+ atpo_hotpotqa_qwen8b/20260506_124901/rollout/248.jsonl filter=lfs diff=lfs merge=lfs -text
1219
+ atpo_hotpotqa_qwen8b/20260506_124901/rollout/251.jsonl filter=lfs diff=lfs merge=lfs -text
1220
+ atpo_hotpotqa_qwen8b/20260506_124901/rollout/240.jsonl filter=lfs diff=lfs merge=lfs -text
1221
+ atpo_hotpotqa_qwen8b/20260506_124901/rollout/244.jsonl filter=lfs diff=lfs merge=lfs -text
1222
+ atpo_hotpotqa_qwen8b/20260506_124901/rollout/242.jsonl filter=lfs diff=lfs merge=lfs -text
1223
+ atpo_hotpotqa_qwen8b/20260506_124901/global_step_250/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1224
+ atpo_hotpotqa_qwen8b/20260506_124901/rollout/241.jsonl filter=lfs diff=lfs merge=lfs -text
1225
+ atpo_hotpotqa_qwen8b/20260506_124901/rollout/243.jsonl filter=lfs diff=lfs merge=lfs -text
1226
+ atpo_hotpotqa_qwen8b/20260506_124901/rollout/247.jsonl filter=lfs diff=lfs merge=lfs -text
1227
+ atpo_hotpotqa_qwen8b/20260506_124901/rollout/246.jsonl filter=lfs diff=lfs merge=lfs -text
1228
+ atpo_hotpotqa_qwen8b/20260506_124901/rollout/250.jsonl filter=lfs diff=lfs merge=lfs -text
1229
+ atpo_hotpotqa_qwen8b/20260506_124901/rollout/245.jsonl filter=lfs diff=lfs merge=lfs -text
1230
+ atpo_hotpotqa_qwen8b/20260506_124901/rollout/249.jsonl filter=lfs diff=lfs merge=lfs -text
atpo_hotpotqa_qwen8b/20260506_124901/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
+ }
atpo_hotpotqa_qwen8b/20260506_124901/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": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 12288,
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": false,
26
+ "torch_dtype": "float32",
27
+ "transformers_version": "4.51.3",
28
+ "use_cache": true,
29
+ "use_sliding_window": false,
30
+ "vocab_size": 151936
31
+ }
atpo_hotpotqa_qwen8b/20260506_124901/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
atpo_hotpotqa_qwen8b/20260506_124901/global_step_250/actor/extra_state_world_size_8_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed16a8eeb716045b1d5e340e5b092cb348c4130394c58f5028089ecf4ce98e1f
3
+ size 14632
atpo_hotpotqa_qwen8b/20260506_124901/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
atpo_hotpotqa_qwen8b/20260506_124901/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
atpo_hotpotqa_qwen8b/20260506_124901/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
atpo_hotpotqa_qwen8b/20260506_124901/global_step_250/actor/extra_state_world_size_8_rank_5.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9555d4f192660933e164807d87641992b0d03cf16ee5c29ee322a96332d100a3
3
+ size 14632
atpo_hotpotqa_qwen8b/20260506_124901/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
atpo_hotpotqa_qwen8b/20260506_124901/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
atpo_hotpotqa_qwen8b/20260506_124901/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
+ }
atpo_hotpotqa_qwen8b/20260506_124901/global_step_250/actor/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
atpo_hotpotqa_qwen8b/20260506_124901/global_step_250/actor/model_world_size_8_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c96cfeb1e7e39ec65918d54cef965ff9ea1170598b696fe27ad8d33dc8c91a50
3
+ size 4095600634
atpo_hotpotqa_qwen8b/20260506_124901/global_step_250/actor/model_world_size_8_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76d7c049a23c840a4ad0d1f717abbaf5f181d164b99aae02e0e35893a2d1dd30
3
+ size 4095600634
atpo_hotpotqa_qwen8b/20260506_124901/global_step_250/actor/model_world_size_8_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5edb13f690eac3929636813760730bbed740a442f359c66e12cea659c42404e3
3
+ size 4095600634
atpo_hotpotqa_qwen8b/20260506_124901/global_step_250/actor/model_world_size_8_rank_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:583ee8e2f06c044b58f1a1d6f5d33100948ab5487d903c7ddcbd72ff1fe06b30
3
+ size 4095600634
atpo_hotpotqa_qwen8b/20260506_124901/global_step_250/actor/model_world_size_8_rank_4.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:329f5ca928b53810091da9590333f79b19383a38d4fcda0d7c571fce1b34c56a
3
+ size 4095600634
atpo_hotpotqa_qwen8b/20260506_124901/global_step_250/actor/model_world_size_8_rank_5.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f2eba9c82de3e510549d414e8bdd06b4208171e0706fa49468e26170a8fd440
3
+ size 4095600634
atpo_hotpotqa_qwen8b/20260506_124901/global_step_250/actor/model_world_size_8_rank_6.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e62cace39e9ec68b85dc565aa7df2b4751eed259f31a773cabdf37409df260d
3
+ size 4095600634
atpo_hotpotqa_qwen8b/20260506_124901/global_step_250/actor/model_world_size_8_rank_7.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc043e5d5097fa0937125a0b844d62e4622b9540acd706051c3c2f473b39f436
3
+ size 4095600634
atpo_hotpotqa_qwen8b/20260506_124901/global_step_250/actor/optim_world_size_8_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65effcb080f85c5abe75de0cb32a3cb84841283599e4a4ce5296e57567bc86eb
3
+ size 8190769318
atpo_hotpotqa_qwen8b/20260506_124901/global_step_250/actor/optim_world_size_8_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b1e1935c868c36628316529a4c49e224a3209412a4638551cb46e3ab914a2ab
3
+ size 8190769318
atpo_hotpotqa_qwen8b/20260506_124901/global_step_250/actor/optim_world_size_8_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5c6fe392a65b7ddfef93f83c5ebcfa6605cffa8ff5645caa3a0371fb670bcf4
3
+ size 8190769318
atpo_hotpotqa_qwen8b/20260506_124901/global_step_250/actor/optim_world_size_8_rank_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8137801355ea9008e79404efbab8e7b6df5ed604d6f7e12d8c8111459f45d8a4
3
+ size 8190769318
atpo_hotpotqa_qwen8b/20260506_124901/global_step_250/actor/optim_world_size_8_rank_4.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d32197d9ca18243cf05749f8c0421f430e8d0649aa115ea9e17d2f6b3e493c8c
3
+ size 8190769318
atpo_hotpotqa_qwen8b/20260506_124901/global_step_250/actor/optim_world_size_8_rank_5.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aee3fed3ae0d9b467978d5b529c901b372613070564d6bbb3b5168d7a62c26ff
3
+ size 8190769318
atpo_hotpotqa_qwen8b/20260506_124901/global_step_250/actor/optim_world_size_8_rank_6.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e58e35f6ac9debc3527f2dbb75f84d8f39cb5ed5d523fafce8c76363a23f1dc1
3
+ size 8190769318
atpo_hotpotqa_qwen8b/20260506_124901/global_step_250/actor/optim_world_size_8_rank_7.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bee28a4f0ea790bca2db80a11dbee5e6a8da72f04d74411e7d90df841ef30950
3
+ size 8190769318
atpo_hotpotqa_qwen8b/20260506_124901/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
+ }
atpo_hotpotqa_qwen8b/20260506_124901/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
atpo_hotpotqa_qwen8b/20260506_124901/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
+ }
atpo_hotpotqa_qwen8b/20260506_124901/global_step_250/actor/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
atpo_hotpotqa_qwen8b/20260506_124901/global_step_250/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d193930ab30e440b5495fcf3414c6ae67e7c2c51bc537159c7defc2f5945f05
3
+ size 1492
atpo_hotpotqa_qwen8b/20260506_124901/latest_checkpointed_iteration.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ 250
atpo_hotpotqa_qwen8b/20260506_124901/rollout/240.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7fb7b46dc15b71ae0cbc296e387cbd9b7e1d68b57146f41999c46602cdc2db4
3
+ size 13846012
atpo_hotpotqa_qwen8b/20260506_124901/rollout/241.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:791a493686ec15e3f399b9c693744f1f9af90fef2d894295963c9a96063e566f
3
+ size 14103691
atpo_hotpotqa_qwen8b/20260506_124901/rollout/242.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30789f5f0b027ea8978eb16ddb38d97a89c0472b310cc61e4b6b87a41a9ad6dd
3
+ size 13475899
atpo_hotpotqa_qwen8b/20260506_124901/rollout/243.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5486b3ca7ab6cf1e7bca42133d3371df358de68e88ce65bcd7d4f087aed80015
3
+ size 14208924
atpo_hotpotqa_qwen8b/20260506_124901/rollout/244.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8c6df8a5a0dad5a914300f07adb8dc6faec3423eb27957c62018b0f2bf4d64d
3
+ size 15575181
atpo_hotpotqa_qwen8b/20260506_124901/rollout/245.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98f2eb47881dc01b43d1e43ddafe1a82de1de069bd3c60dd4d169dddb2c395f8
3
+ size 14736778
atpo_hotpotqa_qwen8b/20260506_124901/rollout/246.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23159cc22954ee469e6d11f00aa65f390802279751f75b673be7089fdb7f8fa9
3
+ size 14822956
atpo_hotpotqa_qwen8b/20260506_124901/rollout/247.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4bd4a20755ebf2148cd9a02a59ef327adcc35f26a82f568502cfaab2944b842
3
+ size 14959907
atpo_hotpotqa_qwen8b/20260506_124901/rollout/248.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f3f5e47e6e15a8bf3b9e1171d008191caa5447d05403c8bbdd523d09848784d
3
+ size 15697932
atpo_hotpotqa_qwen8b/20260506_124901/rollout/249.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6c7b7973e9ca24e102b826fa42401a5c64b497fab16d368e95cb2b9ded57e92
3
+ size 15052945
atpo_hotpotqa_qwen8b/20260506_124901/rollout/250.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd03e42b7d2e633219df8bb7914c341076bd348242d1d570b22bac3687034648
3
+ size 14994174
atpo_hotpotqa_qwen8b/20260506_124901/rollout/251.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:135d00a83263822a3befbf87590a67a2721ecb9de37a68ce55d5af4a9e030805
3
+ size 15663613
atpo_hotpotqa_qwen8b/20260506_124901/run.log CHANGED
The diff for this file is too large to render. See raw diff
 
atpo_hotpotqa_qwen8b/20260506_124901/validation/240.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
atpo_hotpotqa_qwen8b/20260506_124901/validation/250.jsonl ADDED
The diff for this file is too large to render. See raw diff