Delete Qwen2.5-1.5B-FULL-ES-2/Qwen2.5-1.5B-FULL-ES-2
Browse files- Qwen2.5-1.5B-FULL-ES-2/Qwen2.5-1.5B-FULL-ES-2/config.yaml +0 -36
- Qwen2.5-1.5B-FULL-ES-2/Qwen2.5-1.5B-FULL-ES-2/eval_log/custom/gsm8k-hard.json +0 -3
- Qwen2.5-1.5B-FULL-ES-2/Qwen2.5-1.5B-FULL-ES-2/eval_log/custom/multiarith.json +0 -3
- Qwen2.5-1.5B-FULL-ES-2/Qwen2.5-1.5B-FULL-ES-2/eval_log/custom/summary.json +0 -3
- Qwen2.5-1.5B-FULL-ES-2/Qwen2.5-1.5B-FULL-ES-2/eval_log/gsm8k.json +0 -3
- Qwen2.5-1.5B-FULL-ES-2/Qwen2.5-1.5B-FULL-ES-2/eval_log/svamp.json +0 -3
- Qwen2.5-1.5B-FULL-ES-2/Qwen2.5-1.5B-FULL-ES-2/eval_log/tensorboard/gsm8k/events.out.tfevents.1781505856.liu-SGASL90-002.3433504.0 +0 -3
- Qwen2.5-1.5B-FULL-ES-2/Qwen2.5-1.5B-FULL-ES-2/eval_log/tensorboard/svamp/events.out.tfevents.1781505886.liu-SGASL90-002.3437480.0 +0 -3
- Qwen2.5-1.5B-FULL-ES-2/Qwen2.5-1.5B-FULL-ES-2/history.json +0 -3
- Qwen2.5-1.5B-FULL-ES-2/Qwen2.5-1.5B-FULL-ES-2/merged/added_tokens.json +0 -3
- Qwen2.5-1.5B-FULL-ES-2/Qwen2.5-1.5B-FULL-ES-2/merged/chat_template.jinja +0 -54
- Qwen2.5-1.5B-FULL-ES-2/Qwen2.5-1.5B-FULL-ES-2/merged/config.json +0 -3
- Qwen2.5-1.5B-FULL-ES-2/Qwen2.5-1.5B-FULL-ES-2/merged/merges.txt +0 -0
- Qwen2.5-1.5B-FULL-ES-2/Qwen2.5-1.5B-FULL-ES-2/merged/model.safetensors +0 -3
- Qwen2.5-1.5B-FULL-ES-2/Qwen2.5-1.5B-FULL-ES-2/merged/special_tokens_map.json +0 -3
- Qwen2.5-1.5B-FULL-ES-2/Qwen2.5-1.5B-FULL-ES-2/merged/tokenizer.json +0 -3
- Qwen2.5-1.5B-FULL-ES-2/Qwen2.5-1.5B-FULL-ES-2/merged/tokenizer_config.json +0 -3
- Qwen2.5-1.5B-FULL-ES-2/Qwen2.5-1.5B-FULL-ES-2/merged/vocab.json +0 -3
Qwen2.5-1.5B-FULL-ES-2/Qwen2.5-1.5B-FULL-ES-2/config.yaml
DELETED
|
@@ -1,36 +0,0 @@
|
|
| 1 |
-
es:
|
| 2 |
-
n_epochs: 10
|
| 3 |
-
batch_size: 100
|
| 4 |
-
sigma: 0.0015
|
| 5 |
-
alpha: 0.0002
|
| 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/gpu01_epoch10/full_es_gpu01_ep10_alpha0.0002_20260531_172025_256099
|
| 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-2/Qwen2.5-1.5B-FULL-ES-2/eval_log/custom/gsm8k-hard.json
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:e3de4e6e7a0a3da49384ad6a2429c3c23eccc6b9d80707959e6c23c31f3d351b
|
| 3 |
-
size 2296588
|
|
|
|
|
|
|
|
|
|
|
|
Qwen2.5-1.5B-FULL-ES-2/Qwen2.5-1.5B-FULL-ES-2/eval_log/custom/multiarith.json
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:ca62eebf31bb7c8ff32597d5536b5b5df7b6d980c2f874d673ebb9b138dff097
|
| 3 |
-
size 189152
|
|
|
|
|
|
|
|
|
|
|
|
Qwen2.5-1.5B-FULL-ES-2/Qwen2.5-1.5B-FULL-ES-2/eval_log/custom/summary.json
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:9ceb9ee1f47f3470af47be795ae1e88bc6394ce4ce24a3ccf7903a16f7b3bb3d
|
| 3 |
-
size 189075
|
|
|
|
|
|
|
|
|
|
|
|
Qwen2.5-1.5B-FULL-ES-2/Qwen2.5-1.5B-FULL-ES-2/eval_log/gsm8k.json
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:dcadb336ba46ce1e13bc5f445cfcee8f2d1594165cbea6d2fd3fd7f13aca987c
|
| 3 |
-
size 2007103
|
|
|
|
|
|
|
|
|
|
|
|
Qwen2.5-1.5B-FULL-ES-2/Qwen2.5-1.5B-FULL-ES-2/eval_log/svamp.json
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:2abec5dead4de882368c2c092d3608820b0c37fea23285c9a6ae0cda64f3fb43
|
| 3 |
-
size 350047
|
|
|
|
|
|
|
|
|
|
|
|
Qwen2.5-1.5B-FULL-ES-2/Qwen2.5-1.5B-FULL-ES-2/eval_log/tensorboard/gsm8k/events.out.tfevents.1781505856.liu-SGASL90-002.3433504.0
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:55a532a7ca9cf30d96acaa471aad5ca5e2fe18a6e03d5763c80a66de57f4c040
|
| 3 |
-
size 657
|
|
|
|
|
|
|
|
|
|
|
|
Qwen2.5-1.5B-FULL-ES-2/Qwen2.5-1.5B-FULL-ES-2/eval_log/tensorboard/svamp/events.out.tfevents.1781505886.liu-SGASL90-002.3437480.0
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:ae26e025d410b6a4c19d6d2c8e14a0be3722d53793b1627f24cd12a9463dd8c5
|
| 3 |
-
size 657
|
|
|
|
|
|
|
|
|
|
|
|
Qwen2.5-1.5B-FULL-ES-2/Qwen2.5-1.5B-FULL-ES-2/history.json
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:a1757577c87ef968c9cd683718ba79fba9aab26e6bf8dbd5cf16054c5cd048ec
|
| 3 |
-
size 100245
|
|
|
|
|
|
|
|
|
|
|
|
Qwen2.5-1.5B-FULL-ES-2/Qwen2.5-1.5B-FULL-ES-2/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-2/Qwen2.5-1.5B-FULL-ES-2/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-2/Qwen2.5-1.5B-FULL-ES-2/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-2/Qwen2.5-1.5B-FULL-ES-2/merged/merges.txt
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
Qwen2.5-1.5B-FULL-ES-2/Qwen2.5-1.5B-FULL-ES-2/merged/model.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:8002e9ea0d78a3adbdb1bf8ad08c9637de0bb761cfea19e019b58670790d5b4b
|
| 3 |
-
size 3554214720
|
|
|
|
|
|
|
|
|
|
|
|
Qwen2.5-1.5B-FULL-ES-2/Qwen2.5-1.5B-FULL-ES-2/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-2/Qwen2.5-1.5B-FULL-ES-2/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-2/Qwen2.5-1.5B-FULL-ES-2/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-2/Qwen2.5-1.5B-FULL-ES-2/merged/vocab.json
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910
|
| 3 |
-
size 2776833
|
|
|
|
|
|
|
|
|
|
|
|