MilaWang commited on
Commit
cab1d58
·
verified ·
1 Parent(s): 648d3cc

Upload folder using huggingface_hub

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 +15 -0
  2. es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1040/actor/extra_state_world_size_8_rank_0.pt +3 -0
  3. es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1040/actor/extra_state_world_size_8_rank_1.pt +3 -0
  4. es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1040/actor/extra_state_world_size_8_rank_2.pt +3 -0
  5. es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1040/actor/extra_state_world_size_8_rank_3.pt +3 -0
  6. es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1040/actor/extra_state_world_size_8_rank_4.pt +3 -0
  7. es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1040/actor/extra_state_world_size_8_rank_5.pt +3 -0
  8. es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1040/actor/extra_state_world_size_8_rank_6.pt +3 -0
  9. es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1040/actor/extra_state_world_size_8_rank_7.pt +3 -0
  10. es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1040/actor/huggingface/added_tokens.json +24 -0
  11. es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1040/actor/huggingface/config.json +30 -0
  12. es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1040/actor/huggingface/merges.txt +0 -0
  13. es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1040/actor/huggingface/special_tokens_map.json +31 -0
  14. es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1040/actor/huggingface/tokenizer.json +3 -0
  15. es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1040/actor/huggingface/tokenizer_config.json +208 -0
  16. es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1040/actor/huggingface/vocab.json +0 -0
  17. es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1040/actor/model_world_size_8_rank_0.pt +3 -0
  18. es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1040/actor/model_world_size_8_rank_1.pt +3 -0
  19. es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1040/actor/model_world_size_8_rank_2.pt +3 -0
  20. es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1040/actor/model_world_size_8_rank_3.pt +3 -0
  21. es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1040/actor/model_world_size_8_rank_4.pt +3 -0
  22. es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1040/actor/model_world_size_8_rank_5.pt +3 -0
  23. es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1040/actor/model_world_size_8_rank_6.pt +3 -0
  24. es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1040/actor/model_world_size_8_rank_7.pt +3 -0
  25. es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1040/actor/optim_world_size_8_rank_0.pt +3 -0
  26. es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1040/actor/optim_world_size_8_rank_1.pt +3 -0
  27. es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1040/actor/optim_world_size_8_rank_2.pt +3 -0
  28. es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1040/actor/optim_world_size_8_rank_3.pt +3 -0
  29. es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1040/actor/optim_world_size_8_rank_4.pt +3 -0
  30. es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1040/actor/optim_world_size_8_rank_5.pt +3 -0
  31. es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1040/actor/optim_world_size_8_rank_6.pt +3 -0
  32. es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1040/actor/optim_world_size_8_rank_7.pt +3 -0
  33. es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1040/data.pt +3 -0
  34. es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1120/actor/extra_state_world_size_8_rank_0.pt +3 -0
  35. es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1120/actor/extra_state_world_size_8_rank_1.pt +3 -0
  36. es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1120/actor/extra_state_world_size_8_rank_2.pt +3 -0
  37. es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1120/actor/extra_state_world_size_8_rank_3.pt +3 -0
  38. es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1120/actor/extra_state_world_size_8_rank_4.pt +3 -0
  39. es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1120/actor/extra_state_world_size_8_rank_5.pt +3 -0
  40. es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1120/actor/extra_state_world_size_8_rank_6.pt +3 -0
  41. es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1120/actor/extra_state_world_size_8_rank_7.pt +3 -0
  42. es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1120/actor/huggingface/added_tokens.json +24 -0
  43. es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1120/actor/huggingface/config.json +30 -0
  44. es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1120/actor/huggingface/merges.txt +0 -0
  45. es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1120/actor/huggingface/special_tokens_map.json +31 -0
  46. es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1120/actor/huggingface/tokenizer.json +3 -0
  47. es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1120/actor/huggingface/tokenizer_config.json +208 -0
  48. es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1120/actor/huggingface/vocab.json +0 -0
  49. es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1120/actor/model_world_size_8_rank_0.pt +3 -0
  50. es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1120/actor/model_world_size_8_rank_1.pt +3 -0
.gitattributes CHANGED
@@ -42,3 +42,18 @@ es-qwen-math-base-7b-3k-stage2-6k-t4-ds_o2_aug-kl0.01/global_step_720_hf/tokeniz
42
  es-qwen-math-base-7b-3k-stage2-6k-t4-ds_o2_aug-kl0.01/global_step_880_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text
43
  es-qwen-math-base-7b-3k-stage2-6k-t4-ds_o2_aug-kl0.01/global_step_960/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
44
  es-qwen-math-base-7b-3k-stage2-6k-t4-ds_o2_aug-kl0.01/global_step_960_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
42
  es-qwen-math-base-7b-3k-stage2-6k-t4-ds_o2_aug-kl0.01/global_step_880_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text
43
  es-qwen-math-base-7b-3k-stage2-6k-t4-ds_o2_aug-kl0.01/global_step_960/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
44
  es-qwen-math-base-7b-3k-stage2-6k-t4-ds_o2_aug-kl0.01/global_step_960_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text
45
+ es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1040/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
46
+ es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1120/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
47
+ es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1200/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
48
+ es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_160/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
49
+ es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_240/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
50
+ es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_320/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
51
+ es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_400/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
52
+ es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_480/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
53
+ es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_560/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
54
+ es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_640/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
55
+ es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_720/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
56
+ es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_80/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
57
+ es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_800/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
58
+ es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_880/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
59
+ es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_960/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1040/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:b4adfcb557ea4b856e5fabc330744aa37de3994a646b45049fe98826010194ac
3
+ size 14632
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1040/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:e8c2c83604905fae5955608157c85e2499cf9872d155b41670df4e9f5e04c04f
3
+ size 14632
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1040/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 sha256:02c705cf8008a7812bed83c25829f7cb1d530f025bc29a0fee1e464d11270b9d
3
+ size 14632
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1040/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:caa0204a0f36f391198360cca1d416b36f1b7594788c4a37bc4765afdd04716f
3
+ size 14632
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1040/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:ade3a4b46b66fa98c0091ff76a77e3841c90dbeb55fb92270ca92ad723967801
3
+ size 14632
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1040/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:a0d850efd9efc758196280c2794c1f00eddc391f3a7e915c4c6bf8812e94166a
3
+ size 14632
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1040/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 sha256:381b77133ff423d3d272913471fcf480a4cfa8d47f20555d1b93cf7d581bbd7b
3
+ size 14632
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1040/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 sha256:532d594698542e75f7e416304c873cd8f45e7fc97f5918b80b8ec2ebcd605700
3
+ size 14632
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1040/actor/huggingface/added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1040/actor/huggingface/config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_attn_implementation_autoset": true,
3
+ "architectures": [
4
+ "Qwen2ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "eos_token_id": 151643,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 3584,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 18944,
12
+ "max_position_embeddings": 4096,
13
+ "max_window_layers": 28,
14
+ "model_type": "qwen2",
15
+ "num_attention_heads": 28,
16
+ "num_hidden_layers": 28,
17
+ "num_key_value_heads": 4,
18
+ "pad_token_id": 151643,
19
+ "rms_norm_eps": 1e-06,
20
+ "rope_scaling": null,
21
+ "rope_theta": 10000,
22
+ "sliding_window": 4096,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "float32",
25
+ "transformers_version": "4.50.3",
26
+ "use_cache": true,
27
+ "use_mrope": false,
28
+ "use_sliding_window": false,
29
+ "vocab_size": 152064
30
+ }
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1040/actor/huggingface/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1040/actor/huggingface/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": "<|endoftext|>",
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
+ }
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1040/actor/huggingface/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1040/actor/huggingface/tokenizer_config.json ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'Please reason step by step, and put your final answer within \\\\boxed{}.' }}\n {%- endif %}\n {{- \"\\n\\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 {%- else %}\n {{- '<|im_start|>system\\nPlease reason step by step, and put your final answer within \\\\boxed{}.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.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{%- endif %}\n",
199
+ "clean_up_tokenization_spaces": false,
200
+ "eos_token": "<|endoftext|>",
201
+ "errors": "replace",
202
+ "extra_special_tokens": {},
203
+ "model_max_length": 131072,
204
+ "pad_token": "<|endoftext|>",
205
+ "split_special_tokens": false,
206
+ "tokenizer_class": "Qwen2Tokenizer",
207
+ "unk_token": null
208
+ }
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1040/actor/huggingface/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1040/actor/model_world_size_8_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22ad5808c4486ee3b875cdd6df827ffd2a52d8239e80729e3b3ea8ce0dc1ad9c
3
+ size 3807995194
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1040/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:c964a4a6aac01c27c69ce30019ec3b1b4f83c0c1ba042aefcd1948608ef0c3a7
3
+ size 3807995194
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1040/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:beab0c4bb42d143682848a19f408f5538fad8748286e4c49ab341a37f8637061
3
+ size 3807995194
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1040/actor/model_world_size_8_rank_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73598caa254dc3c6199d9d189dec74204b5adbaf42d5dd0fa90d9537fbcd0388
3
+ size 3807995194
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1040/actor/model_world_size_8_rank_4.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d39ffe2ac9577f74265a98c199f86c85b0ef8166f068a19cf9921910e5542a4
3
+ size 3807995194
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1040/actor/model_world_size_8_rank_5.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3582d64dc259201d22f046904d406152a8e8e3d3318d1724d011397edf53f1db
3
+ size 3807995194
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1040/actor/model_world_size_8_rank_6.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:473a1ac9db580ed32165b30a1d7825b41f352c6eca0d37dd8a3b523ab75f630b
3
+ size 3807995194
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1040/actor/model_world_size_8_rank_7.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35705388ccdbc7586f6fab47faf85ab2ba1e376b79fd1bb139a9f6db648f6277
3
+ size 3807995194
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1040/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:c6e2b0369b596ac648b3ebe676a25314ad97f90c59bece424f8d060811c750aa
3
+ size 7615643215
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1040/actor/optim_world_size_8_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:790bed9c7488beb8ba6b3933dcc28c4239bec5b833fe78ffaf186f69e0c6cd87
3
+ size 7615643215
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1040/actor/optim_world_size_8_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d2f8bb39e99266ae2eee1feb78c1c92fc4ca2e0893a8bd56db79a1976d04f31
3
+ size 7615643215
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1040/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:e6146b1b3df39e347cef4c868de114887c5ec6bd82c4b4a4204e1025d963943a
3
+ size 7615643215
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1040/actor/optim_world_size_8_rank_4.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:622e0efaa8bee73ac64413903ceacf7f9e2e8e1d5ad7f6858be89652d0266a10
3
+ size 7615643215
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1040/actor/optim_world_size_8_rank_5.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35094173c690ea81c6163935e3247437eff5f5bb58c422d9cd85b6ae6a228f2e
3
+ size 7615643215
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1040/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:e97facc1a617d366fa2c2c3b9f3149b42c7b14e4b00588b3cf5ec2357f5cb3dd
3
+ size 7615643215
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1040/actor/optim_world_size_8_rank_7.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26bd9dacb85508f566ead7c7b9578dee6813e195e21d9bd506ceea0a9e07ba49
3
+ size 7615643215
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1040/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d33e7bef233ae8a573313fdfc37d13b4c0da78fa1892c80b444cbc358cf9ac8
3
+ size 6948621
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1120/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:e193661e2cbe6f8fc1c9dafb3eb3609c949292262d0ee98384884c621b58602a
3
+ size 14632
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1120/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 sha256:7b294eeb21c0c07edc9627585b40795f3a39f47dac6b78a4cda4e70a26b3cf57
3
+ size 14632
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1120/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:e4e3b9b83fc4efc70cd63547170db47173aa91f83f7dcc3c4da2d55ac758f8c5
3
+ size 14632
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1120/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:db952d92dc1261645e4477626e70445a3492733671e8e15824a6e720b07d08d2
3
+ size 14632
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1120/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 sha256:219e5cdd3c6b6edd1cc22631ea6a52c57e34892043056e2cb3274d88cb41b4fe
3
+ size 14632
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1120/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 sha256:172e29edbcf4d867dc319d8b8d6fefaeba952a7679a161673c3dda3c18668f43
3
+ size 14632
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1120/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 sha256:6dffdec02773cbcbb6f13427004489ace9d91cd99dc2d7d87245ebb7b1da7776
3
+ size 14632
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1120/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 sha256:591b13ce05b45ff3b792a01b5f063c56a48396d2ae609dc5b1e4348d3c047459
3
+ size 14632
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1120/actor/huggingface/added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1120/actor/huggingface/config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_attn_implementation_autoset": true,
3
+ "architectures": [
4
+ "Qwen2ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "eos_token_id": 151643,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 3584,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 18944,
12
+ "max_position_embeddings": 4096,
13
+ "max_window_layers": 28,
14
+ "model_type": "qwen2",
15
+ "num_attention_heads": 28,
16
+ "num_hidden_layers": 28,
17
+ "num_key_value_heads": 4,
18
+ "pad_token_id": 151643,
19
+ "rms_norm_eps": 1e-06,
20
+ "rope_scaling": null,
21
+ "rope_theta": 10000,
22
+ "sliding_window": 4096,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "float32",
25
+ "transformers_version": "4.50.3",
26
+ "use_cache": true,
27
+ "use_mrope": false,
28
+ "use_sliding_window": false,
29
+ "vocab_size": 152064
30
+ }
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1120/actor/huggingface/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1120/actor/huggingface/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": "<|endoftext|>",
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
+ }
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1120/actor/huggingface/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1120/actor/huggingface/tokenizer_config.json ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'Please reason step by step, and put your final answer within \\\\boxed{}.' }}\n {%- endif %}\n {{- \"\\n\\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 {%- else %}\n {{- '<|im_start|>system\\nPlease reason step by step, and put your final answer within \\\\boxed{}.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.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{%- endif %}\n",
199
+ "clean_up_tokenization_spaces": false,
200
+ "eos_token": "<|endoftext|>",
201
+ "errors": "replace",
202
+ "extra_special_tokens": {},
203
+ "model_max_length": 131072,
204
+ "pad_token": "<|endoftext|>",
205
+ "split_special_tokens": false,
206
+ "tokenizer_class": "Qwen2Tokenizer",
207
+ "unk_token": null
208
+ }
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1120/actor/huggingface/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1120/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:c5c8097e611c0db4b00dc80b250c87a1fe569a5153a3ef92a241e2e52c3a41be
3
+ size 3807995194
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2_aug-kl0.01/global_step_1120/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:f47f0b2c540ac4658268fef0575cae09ea49888775109f822bc8b13c05b94b8c
3
+ size 3807995194