ljq34952 commited on
Commit
3fd51d4
·
verified ·
1 Parent(s): 1e12f05

Delete Qwen2.5-1.5B-FULL-ES-1/Qwen2.5-1.5B-FULL-ES-1

Browse files
Files changed (18) hide show
  1. Qwen2.5-1.5B-FULL-ES-1/Qwen2.5-1.5B-FULL-ES-1/config.yaml +0 -36
  2. Qwen2.5-1.5B-FULL-ES-1/Qwen2.5-1.5B-FULL-ES-1/eval_log/custom/gsm8k-hard.json +0 -3
  3. Qwen2.5-1.5B-FULL-ES-1/Qwen2.5-1.5B-FULL-ES-1/eval_log/custom/multiarith.json +0 -3
  4. Qwen2.5-1.5B-FULL-ES-1/Qwen2.5-1.5B-FULL-ES-1/eval_log/custom/summary.json +0 -3
  5. Qwen2.5-1.5B-FULL-ES-1/Qwen2.5-1.5B-FULL-ES-1/eval_log/gsm8k.json +0 -3
  6. Qwen2.5-1.5B-FULL-ES-1/Qwen2.5-1.5B-FULL-ES-1/eval_log/svamp.json +0 -3
  7. Qwen2.5-1.5B-FULL-ES-1/Qwen2.5-1.5B-FULL-ES-1/eval_log/tensorboard/gsm8k/events.out.tfevents.1781502695.liu-SGASL90-002.3248093.0 +0 -3
  8. Qwen2.5-1.5B-FULL-ES-1/Qwen2.5-1.5B-FULL-ES-1/eval_log/tensorboard/svamp/events.out.tfevents.1781502725.liu-SGASL90-002.3252521.0 +0 -3
  9. Qwen2.5-1.5B-FULL-ES-1/Qwen2.5-1.5B-FULL-ES-1/history.json +0 -3
  10. Qwen2.5-1.5B-FULL-ES-1/Qwen2.5-1.5B-FULL-ES-1/merged/added_tokens.json +0 -3
  11. Qwen2.5-1.5B-FULL-ES-1/Qwen2.5-1.5B-FULL-ES-1/merged/chat_template.jinja +0 -54
  12. Qwen2.5-1.5B-FULL-ES-1/Qwen2.5-1.5B-FULL-ES-1/merged/config.json +0 -3
  13. Qwen2.5-1.5B-FULL-ES-1/Qwen2.5-1.5B-FULL-ES-1/merged/merges.txt +0 -0
  14. Qwen2.5-1.5B-FULL-ES-1/Qwen2.5-1.5B-FULL-ES-1/merged/model.safetensors +0 -3
  15. Qwen2.5-1.5B-FULL-ES-1/Qwen2.5-1.5B-FULL-ES-1/merged/special_tokens_map.json +0 -3
  16. Qwen2.5-1.5B-FULL-ES-1/Qwen2.5-1.5B-FULL-ES-1/merged/tokenizer.json +0 -3
  17. Qwen2.5-1.5B-FULL-ES-1/Qwen2.5-1.5B-FULL-ES-1/merged/tokenizer_config.json +0 -3
  18. Qwen2.5-1.5B-FULL-ES-1/Qwen2.5-1.5B-FULL-ES-1/merged/vocab.json +0 -3
Qwen2.5-1.5B-FULL-ES-1/Qwen2.5-1.5B-FULL-ES-1/config.yaml DELETED
@@ -1,36 +0,0 @@
1
- es:
2
- n_epochs: 10
3
- batch_size: 100
4
- sigma: 0.0015
5
- alpha: 0.00025
6
- pop_size: 60
7
- reward_normalization: none
8
- sync_engines_on_validate: true
9
- sync_engine_reference: 0
10
- schedule_mode: keep_tail_per_epoch
11
- reward_normalization_ddof: 0
12
- reward_normalization_eps: 1.0e-08
13
- raw_train_size: 7473
14
- effective_train_size: 7473
15
- max_steps: 750
16
- config_version: 2
17
- method: es
18
- finetune:
19
- type: full
20
- method_params:
21
- target_modules: null
22
- output:
23
- seed: 42
24
- dir: /home/zhi/ljq/ES4LLM/.runtime_storage/results/full_es/gpu23_epoch10/full_es_gpu23_ep10_20260531_162124_134576
25
- dtype: bfloat16
26
- benchmark: gsm8k
27
- checkpoint:
28
- save_freq: 30
29
- export_merged_freq: 30
30
- keep_last: null
31
- generation:
32
- max_new_tokens: 2048
33
- format_reward: 0.1
34
- model: /home/zhi/meta-llama/Qwen2.5-1.5B-Instruct
35
- runtime:
36
- model: /home/zhi/meta-llama/Qwen2.5-1.5B-Instruct
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
Qwen2.5-1.5B-FULL-ES-1/Qwen2.5-1.5B-FULL-ES-1/eval_log/custom/gsm8k-hard.json DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:b28e51a1f88bbdf104eeedf46edd96825f218fde441ecccf9a6dfaaa284830f8
3
- size 2297774
 
 
 
 
Qwen2.5-1.5B-FULL-ES-1/Qwen2.5-1.5B-FULL-ES-1/eval_log/custom/multiarith.json DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:1df7215df35a5ef56515f4469e30be8964868c50b018b79bdf87101f2e26f752
3
- size 190292
 
 
 
 
Qwen2.5-1.5B-FULL-ES-1/Qwen2.5-1.5B-FULL-ES-1/eval_log/custom/summary.json DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:60c514e4799ab843772609bb22ffad97e9028a442d9ec17b781d8d8fa0572ae1
3
- size 190215
 
 
 
 
Qwen2.5-1.5B-FULL-ES-1/Qwen2.5-1.5B-FULL-ES-1/eval_log/gsm8k.json DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:4a7cdd0362ac5e302dc8a05c4dcdae9637c629353b42dfbe91ea999e59432c57
3
- size 1994612
 
 
 
 
Qwen2.5-1.5B-FULL-ES-1/Qwen2.5-1.5B-FULL-ES-1/eval_log/svamp.json DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:d5c8d0f27d386cdbef9446d1557c6e18c68a5fe160b204e1849114add94d83c9
3
- size 357443
 
 
 
 
Qwen2.5-1.5B-FULL-ES-1/Qwen2.5-1.5B-FULL-ES-1/eval_log/tensorboard/gsm8k/events.out.tfevents.1781502695.liu-SGASL90-002.3248093.0 DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:2cb456082da74ba150bae168a96424684b4ee4bd785f196094c4faa892ffc2e8
3
- size 657
 
 
 
 
Qwen2.5-1.5B-FULL-ES-1/Qwen2.5-1.5B-FULL-ES-1/eval_log/tensorboard/svamp/events.out.tfevents.1781502725.liu-SGASL90-002.3252521.0 DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:2f93f262ade89ebb97c50fd8491921e76b09f1b49117abae5edc36e8efd6fdbd
3
- size 657
 
 
 
 
Qwen2.5-1.5B-FULL-ES-1/Qwen2.5-1.5B-FULL-ES-1/history.json DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:edf83da467afea279f3d7be0fddd4f507e35ed16c4ed7925b1f4e4578ce9b2f0
3
- size 100622
 
 
 
 
Qwen2.5-1.5B-FULL-ES-1/Qwen2.5-1.5B-FULL-ES-1/merged/added_tokens.json DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:58b54bbe36fc752f79a24a271ef66a0a0830054b4dfad94bde757d851968060b
3
- size 605
 
 
 
 
Qwen2.5-1.5B-FULL-ES-1/Qwen2.5-1.5B-FULL-ES-1/merged/chat_template.jinja DELETED
@@ -1,54 +0,0 @@
1
- {%- if tools %}
2
- {{- '<|im_start|>system\n' }}
3
- {%- if messages[0]['role'] == 'system' %}
4
- {{- messages[0]['content'] }}
5
- {%- else %}
6
- {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
7
- {%- endif %}
8
- {{- "\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>" }}
9
- {%- for tool in tools %}
10
- {{- "\n" }}
11
- {{- tool | tojson }}
12
- {%- endfor %}
13
- {{- "\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" }}
14
- {%- else %}
15
- {%- if messages[0]['role'] == 'system' %}
16
- {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
17
- {%- else %}
18
- {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
19
- {%- endif %}
20
- {%- endif %}
21
- {%- for message in messages %}
22
- {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
23
- {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
24
- {%- elif message.role == "assistant" %}
25
- {{- '<|im_start|>' + message.role }}
26
- {%- if message.content %}
27
- {{- '\n' + message.content }}
28
- {%- endif %}
29
- {%- for tool_call in message.tool_calls %}
30
- {%- if tool_call.function is defined %}
31
- {%- set tool_call = tool_call.function %}
32
- {%- endif %}
33
- {{- '\n<tool_call>\n{"name": "' }}
34
- {{- tool_call.name }}
35
- {{- '", "arguments": ' }}
36
- {{- tool_call.arguments | tojson }}
37
- {{- '}\n</tool_call>' }}
38
- {%- endfor %}
39
- {{- '<|im_end|>\n' }}
40
- {%- elif message.role == "tool" %}
41
- {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
42
- {{- '<|im_start|>user' }}
43
- {%- endif %}
44
- {{- '\n<tool_response>\n' }}
45
- {{- message.content }}
46
- {{- '\n</tool_response>' }}
47
- {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
48
- {{- '<|im_end|>\n' }}
49
- {%- endif %}
50
- {%- endif %}
51
- {%- endfor %}
52
- {%- if add_generation_prompt %}
53
- {{- '<|im_start|>assistant\n' }}
54
- {%- endif %}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
Qwen2.5-1.5B-FULL-ES-1/Qwen2.5-1.5B-FULL-ES-1/merged/config.json DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c056f4a27d910748710a6cfb66061c3a2d36ca5b2ff0c7df9380cd17bf9e2d2b
3
- size 1400
 
 
 
 
Qwen2.5-1.5B-FULL-ES-1/Qwen2.5-1.5B-FULL-ES-1/merged/merges.txt DELETED
The diff for this file is too large to render. See raw diff
 
Qwen2.5-1.5B-FULL-ES-1/Qwen2.5-1.5B-FULL-ES-1/merged/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:ca8185dcd9f1d4e2cfb31f191126c1ced9af490d83e21c911122a18c5d542d32
3
- size 3554214720
 
 
 
 
Qwen2.5-1.5B-FULL-ES-1/Qwen2.5-1.5B-FULL-ES-1/merged/special_tokens_map.json DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd
3
- size 613
 
 
 
 
Qwen2.5-1.5B-FULL-ES-1/Qwen2.5-1.5B-FULL-ES-1/merged/tokenizer.json DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
- size 11421896
 
 
 
 
Qwen2.5-1.5B-FULL-ES-1/Qwen2.5-1.5B-FULL-ES-1/merged/tokenizer_config.json DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:0a04a9d7d4a62b28482bdfe726c122756de85714fb64166ace92ae75b8f57614
3
- size 4686
 
 
 
 
Qwen2.5-1.5B-FULL-ES-1/Qwen2.5-1.5B-FULL-ES-1/merged/vocab.json DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910
3
- size 2776833