FOGmiaow commited on
Commit
85b58c1
·
verified ·
1 Parent(s): d64faab

Add files using upload-large-folder tool

Browse files
Files changed (33) hide show
  1. .gitattributes +1 -0
  2. coding-uv-1.5e6-16k-ds-r1-1.5b-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6/global_step_80/actor/extra_state_world_size_8_rank_0.pt +3 -0
  3. coding-uv-1.5e6-16k-ds-r1-1.5b-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6/global_step_80/actor/extra_state_world_size_8_rank_1.pt +3 -0
  4. coding-uv-1.5e6-16k-ds-r1-1.5b-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6/global_step_80/actor/extra_state_world_size_8_rank_2.pt +3 -0
  5. coding-uv-1.5e6-16k-ds-r1-1.5b-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6/global_step_80/actor/extra_state_world_size_8_rank_3.pt +3 -0
  6. coding-uv-1.5e6-16k-ds-r1-1.5b-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6/global_step_80/actor/extra_state_world_size_8_rank_4.pt +3 -0
  7. coding-uv-1.5e6-16k-ds-r1-1.5b-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6/global_step_80/actor/extra_state_world_size_8_rank_5.pt +3 -0
  8. coding-uv-1.5e6-16k-ds-r1-1.5b-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6/global_step_80/actor/extra_state_world_size_8_rank_6.pt +3 -0
  9. coding-uv-1.5e6-16k-ds-r1-1.5b-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6/global_step_80/actor/extra_state_world_size_8_rank_7.pt +3 -0
  10. coding-uv-1.5e6-16k-ds-r1-1.5b-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6/global_step_80/actor/fsdp_config.json +4 -0
  11. coding-uv-1.5e6-16k-ds-r1-1.5b-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6/global_step_80/actor/huggingface/chat_template.jinja +1 -0
  12. coding-uv-1.5e6-16k-ds-r1-1.5b-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6/global_step_80/actor/huggingface/config.json +60 -0
  13. coding-uv-1.5e6-16k-ds-r1-1.5b-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6/global_step_80/actor/huggingface/generation_config.json +9 -0
  14. coding-uv-1.5e6-16k-ds-r1-1.5b-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6/global_step_80/actor/huggingface/special_tokens_map.json +23 -0
  15. coding-uv-1.5e6-16k-ds-r1-1.5b-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6/global_step_80/actor/huggingface/tokenizer.json +3 -0
  16. coding-uv-1.5e6-16k-ds-r1-1.5b-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6/global_step_80/actor/huggingface/tokenizer_config.json +194 -0
  17. coding-uv-1.5e6-16k-ds-r1-1.5b-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6/global_step_80/actor/model_world_size_8_rank_0.pt +3 -0
  18. coding-uv-1.5e6-16k-ds-r1-1.5b-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6/global_step_80/actor/model_world_size_8_rank_1.pt +3 -0
  19. coding-uv-1.5e6-16k-ds-r1-1.5b-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6/global_step_80/actor/model_world_size_8_rank_2.pt +3 -0
  20. coding-uv-1.5e6-16k-ds-r1-1.5b-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6/global_step_80/actor/model_world_size_8_rank_3.pt +3 -0
  21. coding-uv-1.5e6-16k-ds-r1-1.5b-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6/global_step_80/actor/model_world_size_8_rank_4.pt +3 -0
  22. coding-uv-1.5e6-16k-ds-r1-1.5b-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6/global_step_80/actor/model_world_size_8_rank_5.pt +3 -0
  23. coding-uv-1.5e6-16k-ds-r1-1.5b-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6/global_step_80/actor/model_world_size_8_rank_6.pt +3 -0
  24. coding-uv-1.5e6-16k-ds-r1-1.5b-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6/global_step_80/actor/model_world_size_8_rank_7.pt +3 -0
  25. coding-uv-1.5e6-16k-ds-r1-1.5b-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6/global_step_80/actor/optim_world_size_8_rank_0.pt +3 -0
  26. coding-uv-1.5e6-16k-ds-r1-1.5b-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6/global_step_80/actor/optim_world_size_8_rank_1.pt +3 -0
  27. coding-uv-1.5e6-16k-ds-r1-1.5b-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6/global_step_80/actor/optim_world_size_8_rank_2.pt +3 -0
  28. coding-uv-1.5e6-16k-ds-r1-1.5b-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6/global_step_80/actor/optim_world_size_8_rank_3.pt +3 -0
  29. coding-uv-1.5e6-16k-ds-r1-1.5b-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6/global_step_80/actor/optim_world_size_8_rank_4.pt +3 -0
  30. coding-uv-1.5e6-16k-ds-r1-1.5b-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6/global_step_80/actor/optim_world_size_8_rank_5.pt +3 -0
  31. coding-uv-1.5e6-16k-ds-r1-1.5b-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6/global_step_80/actor/optim_world_size_8_rank_6.pt +3 -0
  32. coding-uv-1.5e6-16k-ds-r1-1.5b-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6/global_step_80/actor/optim_world_size_8_rank_7.pt +3 -0
  33. coding-uv-1.5e6-16k-ds-r1-1.5b-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6/global_step_80/data.pt +3 -0
.gitattributes CHANGED
@@ -54,3 +54,4 @@ mn-coding-muon-1e5-32k-ds-r1-1.5b-muon-muonlr1e-5-spectral_norm-muonadamlr1e-6/g
54
  mn-coding-uv-muoninside-1e4-spec-32k-ds-r1-1.5b-svd_muon-ulr1e-4-vlr1e-4-none-muonadamlr1e-6/global_step_240/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
55
  mn-coding-uv-muoninside-1e5-spec-32k-ds-r1-1.5b-svd_muon-ulr1e-5-vlr1e-5-none-muonadamlr1e-6/global_step_320/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
56
  mn-coding-uv-muoninside-5e5-spec-32k-ds-r1-1.5b-svd_muon-ulr5e-5-vlr5e-5-none-muonadamlr1e-6/global_step_320/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
54
  mn-coding-uv-muoninside-1e4-spec-32k-ds-r1-1.5b-svd_muon-ulr1e-4-vlr1e-4-none-muonadamlr1e-6/global_step_240/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
55
  mn-coding-uv-muoninside-1e5-spec-32k-ds-r1-1.5b-svd_muon-ulr1e-5-vlr1e-5-none-muonadamlr1e-6/global_step_320/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
56
  mn-coding-uv-muoninside-5e5-spec-32k-ds-r1-1.5b-svd_muon-ulr5e-5-vlr5e-5-none-muonadamlr1e-6/global_step_320/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
57
+ coding-uv-1.5e6-16k-ds-r1-1.5b-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6/global_step_80/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
coding-uv-1.5e6-16k-ds-r1-1.5b-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6/global_step_80/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 sha256:9e99a11629caf182968a0e9cdef6c6963813c7bac5dad71ab9260020666e1f72
3
+ size 15141
coding-uv-1.5e6-16k-ds-r1-1.5b-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6/global_step_80/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 sha256:2141500363d834f83ec46d5714b1bc230875750fa244d3ceea3361851ec2c7d9
3
+ size 15141
coding-uv-1.5e6-16k-ds-r1-1.5b-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6/global_step_80/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 sha256:5c1d4086ad31714fa641c39e1b3e69bcb6b7f238a1ee8f2ab1cd463892d0e8ce
3
+ size 15141
coding-uv-1.5e6-16k-ds-r1-1.5b-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6/global_step_80/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 sha256:767d901a2907de1abcb8c18e9d227d261b8be52f5613a3eee0022ab2e9c5a1c6
3
+ size 15141
coding-uv-1.5e6-16k-ds-r1-1.5b-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6/global_step_80/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 sha256:1c14e836c18f9080d02e8d1f7e1d86ac305d838b31ba8a8b5128a27f0f6f8f4c
3
+ size 15141
coding-uv-1.5e6-16k-ds-r1-1.5b-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6/global_step_80/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 sha256:94b7831b973e94130b483488cdf7597bbcd8e42213882f368f2e74f4d3e9b91e
3
+ size 15141
coding-uv-1.5e6-16k-ds-r1-1.5b-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6/global_step_80/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 sha256:1a6f6a577b07f99d03eb88488a1dea6fba123eb0b3f4c32bc2dc0d0622babe81
3
+ size 15141
coding-uv-1.5e6-16k-ds-r1-1.5b-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6/global_step_80/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 sha256:2c69fb75056260eccd04fe7f7776f53a3bf8583725f345eff03805872afeb0ce
3
+ size 15141
coding-uv-1.5e6-16k-ds-r1-1.5b-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6/global_step_80/actor/fsdp_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "FSDP_version": 2,
3
+ "world_size": 8
4
+ }
coding-uv-1.5e6-16k-ds-r1-1.5b-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6/global_step_80/actor/huggingface/chat_template.jinja ADDED
@@ -0,0 +1 @@
 
 
1
+ {% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<|User|>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<|Assistant|><|tool▁calls▁begin|><|tool▁call▁begin|>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<|tool▁call▁end|>'}}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<|tool▁call▁begin|>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<|tool▁call▁end|>'}}{{'<|tool▁calls▁end|><|end▁of▁sentence|>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<|tool▁outputs▁end|>' + message['content'] + '<|end▁of▁sentence|>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<|Assistant|>' + content + '<|end▁of▁sentence|>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<|tool▁outputs▁begin|><|tool▁output▁begin|>' + message['content'] + '<|tool▁output▁end|>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<|tool▁output▁begin|>' + message['content'] + '<|tool▁output▁end|>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<|tool▁outputs▁end|>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<|Assistant|><think>\n'}}{% endif %}
coding-uv-1.5e6-16k-ds-r1-1.5b-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6/global_step_80/actor/huggingface/config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151646,
7
+ "dtype": "float32",
8
+ "eos_token_id": 151643,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 1536,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 8960,
13
+ "layer_types": [
14
+ "full_attention",
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention"
42
+ ],
43
+ "max_position_embeddings": 131072,
44
+ "max_window_layers": 21,
45
+ "model_type": "qwen2",
46
+ "num_attention_heads": 12,
47
+ "num_hidden_layers": 28,
48
+ "num_key_value_heads": 2,
49
+ "pad_token_id": 151643,
50
+ "rms_norm_eps": 1e-06,
51
+ "rope_scaling": null,
52
+ "rope_theta": 10000,
53
+ "sliding_window": null,
54
+ "tie_word_embeddings": false,
55
+ "transformers_version": "4.57.6",
56
+ "use_cache": true,
57
+ "use_mrope": false,
58
+ "use_sliding_window": false,
59
+ "vocab_size": 151936
60
+ }
coding-uv-1.5e6-16k-ds-r1-1.5b-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6/global_step_80/actor/huggingface/generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 151646,
4
+ "do_sample": true,
5
+ "eos_token_id": 151643,
6
+ "temperature": 0.6,
7
+ "top_p": 0.95,
8
+ "transformers_version": "4.57.6"
9
+ }
coding-uv-1.5e6-16k-ds-r1-1.5b-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6/global_step_80/actor/huggingface/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin▁of▁sentence|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|end▁of▁sentence|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|end▁of▁sentence|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
coding-uv-1.5e6-16k-ds-r1-1.5b-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6/global_step_80/actor/huggingface/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
3
+ size 11422778
coding-uv-1.5e6-16k-ds-r1-1.5b-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6/global_step_80/actor/huggingface/tokenizer_config.json ADDED
@@ -0,0 +1,194 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "151643": {
7
+ "content": "<|end▁of▁sentence|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "151644": {
15
+ "content": "<|User|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": false
21
+ },
22
+ "151645": {
23
+ "content": "<|Assistant|>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": false
29
+ },
30
+ "151646": {
31
+ "content": "<|begin▁of▁sentence|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "151647": {
39
+ "content": "<|EOT|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": false
45
+ },
46
+ "151648": {
47
+ "content": "<think>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": false
53
+ },
54
+ "151649": {
55
+ "content": "</think>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": false
61
+ },
62
+ "151650": {
63
+ "content": "<|quad_start|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "151651": {
71
+ "content": "<|quad_end|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "151652": {
79
+ "content": "<|vision_start|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "151653": {
87
+ "content": "<|vision_end|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "151654": {
95
+ "content": "<|vision_pad|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "151655": {
103
+ "content": "<|image_pad|>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "151656": {
111
+ "content": "<|video_pad|>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": true
117
+ },
118
+ "151657": {
119
+ "content": "<tool_call>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": false
125
+ },
126
+ "151658": {
127
+ "content": "</tool_call>",
128
+ "lstrip": false,
129
+ "normalized": false,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": false
133
+ },
134
+ "151659": {
135
+ "content": "<|fim_prefix|>",
136
+ "lstrip": false,
137
+ "normalized": false,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": false
141
+ },
142
+ "151660": {
143
+ "content": "<|fim_middle|>",
144
+ "lstrip": false,
145
+ "normalized": false,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": false
149
+ },
150
+ "151661": {
151
+ "content": "<|fim_suffix|>",
152
+ "lstrip": false,
153
+ "normalized": false,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": false
157
+ },
158
+ "151662": {
159
+ "content": "<|fim_pad|>",
160
+ "lstrip": false,
161
+ "normalized": false,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": false
165
+ },
166
+ "151663": {
167
+ "content": "<|repo_name|>",
168
+ "lstrip": false,
169
+ "normalized": false,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": false
173
+ },
174
+ "151664": {
175
+ "content": "<|file_sep|>",
176
+ "lstrip": false,
177
+ "normalized": false,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": false
181
+ }
182
+ },
183
+ "bos_token": "<|begin▁of▁sentence|>",
184
+ "clean_up_tokenization_spaces": false,
185
+ "eos_token": "<|end▁of▁sentence|>",
186
+ "extra_special_tokens": {},
187
+ "legacy": true,
188
+ "model_max_length": 16384,
189
+ "pad_token": "<|end▁of▁sentence|>",
190
+ "sp_model_kwargs": {},
191
+ "tokenizer_class": "LlamaTokenizerFast",
192
+ "unk_token": null,
193
+ "use_default_system_prompt": false
194
+ }
coding-uv-1.5e6-16k-ds-r1-1.5b-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6/global_step_80/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:b19a07f8479eee42a4eb0a9ee9babeb917aad2ef32cb4d0885bbe0f635b27eb2
3
+ size 888719595
coding-uv-1.5e6-16k-ds-r1-1.5b-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6/global_step_80/actor/model_world_size_8_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07fe347bf824d56b2eb40fda3b6bf2ae81c6db7d0cace208e521bad15105cd95
3
+ size 888719595
coding-uv-1.5e6-16k-ds-r1-1.5b-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6/global_step_80/actor/model_world_size_8_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c76ae860df25a8b0f0b374053fc8d5784c69ca04da78649297547f5a851b2b7
3
+ size 888719595
coding-uv-1.5e6-16k-ds-r1-1.5b-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6/global_step_80/actor/model_world_size_8_rank_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97bdbc27ccb9fe72c2992037346947cf40efe119da83d3773aef4f6f851afff6
3
+ size 888719595
coding-uv-1.5e6-16k-ds-r1-1.5b-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6/global_step_80/actor/model_world_size_8_rank_4.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77dd8f4dd7e3c4fbedd033d5e6ce3f537a45f95c7e9903e141950e17fd592d5c
3
+ size 888719595
coding-uv-1.5e6-16k-ds-r1-1.5b-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6/global_step_80/actor/model_world_size_8_rank_5.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bb84c2714589e6d7ccaae1f78e38813d62ce19bb453255bd726ddda1436742d
3
+ size 888719595
coding-uv-1.5e6-16k-ds-r1-1.5b-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6/global_step_80/actor/model_world_size_8_rank_6.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c538ac082d0a2d840d9f0adee0dd98758ca5dee653d63cde4f24a121ae751b0
3
+ size 888719595
coding-uv-1.5e6-16k-ds-r1-1.5b-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6/global_step_80/actor/model_world_size_8_rank_7.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:623b1586151fa51af7fdbbf03836581805ed971d1a28972f0a90fa64bcb5ab5c
3
+ size 888719595
coding-uv-1.5e6-16k-ds-r1-1.5b-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6/global_step_80/actor/optim_world_size_8_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9aad950938473cc5c581c9c423d5c184f31156d820773ba1ce24274393be77bc
3
+ size 2936571574
coding-uv-1.5e6-16k-ds-r1-1.5b-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6/global_step_80/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:af9f81200f4555ff12762939b90d113eb945220dd1820a6de5e14665a5576c9e
3
+ size 2936571574
coding-uv-1.5e6-16k-ds-r1-1.5b-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6/global_step_80/actor/optim_world_size_8_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ae5c6511a34bd2f8f1796330219cd4f3308739b53472cae23cd305710d50636
3
+ size 2936571574
coding-uv-1.5e6-16k-ds-r1-1.5b-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6/global_step_80/actor/optim_world_size_8_rank_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f22d92a9ca5594841f964043f709724fd09742099784db4139f791211efa2d0
3
+ size 2936571574
coding-uv-1.5e6-16k-ds-r1-1.5b-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6/global_step_80/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:d3f78e4c57b3f61baecbfab39e682f83e0c4c8f941b9388e3c573ef6fa353132
3
+ size 2936571574
coding-uv-1.5e6-16k-ds-r1-1.5b-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6/global_step_80/actor/optim_world_size_8_rank_5.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d496f01597a3ebf61aab51d8cda2f06fc4aa228a387aa90c4eb97bbf3b8d61b
3
+ size 2936571574
coding-uv-1.5e6-16k-ds-r1-1.5b-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6/global_step_80/actor/optim_world_size_8_rank_6.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:942bcdf6be1af0314d45dee62e041bed81159604abe5eb91476a13497fe70e50
3
+ size 2936571574
coding-uv-1.5e6-16k-ds-r1-1.5b-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6/global_step_80/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:ee28f5eaeb618a46b3e2a9a96a56664db0b1bc6bf8554e5e2fb1ecddfdeb5f83
3
+ size 2936571574
coding-uv-1.5e6-16k-ds-r1-1.5b-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6/global_step_80/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9e6f7c12a5e86149f88845cd8537f5a93c6c8e05338bb677a68733d723499d0
3
+ size 1947