Instructions to use bimabk/environment_test with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use bimabk/environment_test with PEFT:
Task type is invalid.
- Transformers
How to use bimabk/environment_test with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="bimabk/environment_test")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("bimabk/environment_test", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use bimabk/environment_test with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "bimabk/environment_test" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "bimabk/environment_test", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/bimabk/environment_test
- SGLang
How to use bimabk/environment_test with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "bimabk/environment_test" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "bimabk/environment_test", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "bimabk/environment_test" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "bimabk/environment_test", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use bimabk/environment_test with Docker Model Runner:
docker model run hf.co/bimabk/environment_test
Upload task output 1
Browse files- README.md +1 -1
- adapter_config.json +2 -2
- adapter_model.safetensors +2 -2
- added_tokens.json +1 -20
- chat_template.jinja +6 -54
- special_tokens_map.json +1 -12
- tokenizer.json +2 -2
- tokenizer_config.json +1 -165
- trainer_state.json +23 -23
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -3,7 +3,7 @@ base_model: None
|
|
| 3 |
library_name: peft
|
| 4 |
pipeline_tag: text-generation
|
| 5 |
tags:
|
| 6 |
-
- base_model:adapter:/cache/models/Qwen--Qwen2
|
| 7 |
- grpo
|
| 8 |
- lora
|
| 9 |
- transformers
|
|
|
|
| 3 |
library_name: peft
|
| 4 |
pipeline_tag: text-generation
|
| 5 |
tags:
|
| 6 |
+
- base_model:adapter:/cache/models/Qwen--Qwen2-7B-Instruct
|
| 7 |
- grpo
|
| 8 |
- lora
|
| 9 |
- transformers
|
adapter_config.json
CHANGED
|
@@ -30,11 +30,11 @@
|
|
| 30 |
"revision": null,
|
| 31 |
"target_modules": [
|
| 32 |
"gate_proj",
|
|
|
|
| 33 |
"down_proj",
|
|
|
|
| 34 |
"k_proj",
|
| 35 |
"v_proj",
|
| 36 |
-
"o_proj",
|
| 37 |
-
"up_proj",
|
| 38 |
"q_proj"
|
| 39 |
],
|
| 40 |
"target_parameters": null,
|
|
|
|
| 30 |
"revision": null,
|
| 31 |
"target_modules": [
|
| 32 |
"gate_proj",
|
| 33 |
+
"o_proj",
|
| 34 |
"down_proj",
|
| 35 |
+
"up_proj",
|
| 36 |
"k_proj",
|
| 37 |
"v_proj",
|
|
|
|
|
|
|
| 38 |
"q_proj"
|
| 39 |
],
|
| 40 |
"target_parameters": null,
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d1e0fbd0ec6c150d20f1fa3a376a2cfb2ab4bc5b23e44af2c0452abddf82b6d
|
| 3 |
+
size 323014168
|
added_tokens.json
CHANGED
|
@@ -1,24 +1,5 @@
|
|
| 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 |
}
|
|
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"<|endoftext|>": 151643,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
"<|im_end|>": 151645,
|
| 4 |
+
"<|im_start|>": 151644
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
}
|
chat_template.jinja
CHANGED
|
@@ -1,54 +1,6 @@
|
|
| 1 |
-
{%
|
| 2 |
-
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
|
| 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 %}
|
|
|
|
| 1 |
+
{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
|
| 2 |
+
You are a helpful assistant.<|im_end|>
|
| 3 |
+
' }}{% endif %}{{'<|im_start|>' + message['role'] + '
|
| 4 |
+
' + message['content'] + '<|im_end|>' + '
|
| 5 |
+
'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
|
| 6 |
+
' }}{% endif %}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
special_tokens_map.json
CHANGED
|
@@ -1,18 +1,7 @@
|
|
| 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|>",
|
|
|
|
| 1 |
{
|
| 2 |
"additional_special_tokens": [
|
| 3 |
"<|im_start|>",
|
| 4 |
+
"<|im_end|>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
],
|
| 6 |
"eos_token": {
|
| 7 |
"content": "<|im_end|>",
|
tokenizer.json
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bcfe42da0a4497e8b2b172c1f9f4ec423a46dc12907f4349c55025f670422ba9
|
| 3 |
+
size 11418266
|
tokenizer_config.json
CHANGED
|
@@ -1,5 +1,4 @@
|
|
| 1 |
{
|
| 2 |
-
"add_bos_token": false,
|
| 3 |
"add_prefix_space": false,
|
| 4 |
"added_tokens_decoder": {
|
| 5 |
"151643": {
|
|
@@ -25,174 +24,11 @@
|
|
| 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 |
"clean_up_tokenization_spaces": false,
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"add_prefix_space": false,
|
| 3 |
"added_tokens_decoder": {
|
| 4 |
"151643": {
|
|
|
|
| 24 |
"rstrip": false,
|
| 25 |
"single_word": false,
|
| 26 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
}
|
| 28 |
},
|
| 29 |
"additional_special_tokens": [
|
| 30 |
"<|im_start|>",
|
| 31 |
+
"<|im_end|>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 32 |
],
|
| 33 |
"bos_token": null,
|
| 34 |
"clean_up_tokenization_spaces": false,
|
trainer_state.json
CHANGED
|
@@ -2,7 +2,7 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch":
|
| 6 |
"eval_steps": 500,
|
| 7 |
"global_step": 1,
|
| 8 |
"is_hyper_param_search": false,
|
|
@@ -16,36 +16,36 @@
|
|
| 16 |
"clip_ratio/low_min": 0.0,
|
| 17 |
"clip_ratio/region_mean": 0.0,
|
| 18 |
"completions/clipped_ratio": 0.0,
|
| 19 |
-
"completions/max_length":
|
| 20 |
-
"completions/max_terminated_length":
|
| 21 |
-
"completions/mean_length":
|
| 22 |
-
"completions/mean_terminated_length":
|
| 23 |
-
"completions/min_length":
|
| 24 |
-
"completions/min_terminated_length":
|
| 25 |
-
"entropy": 0.
|
| 26 |
-
"epoch":
|
| 27 |
"frac_reward_zero_std": 0.0,
|
| 28 |
-
"grad_norm":
|
| 29 |
"kl": 0.0,
|
| 30 |
"learning_rate": 0.0,
|
| 31 |
-
"loss": -0.
|
| 32 |
-
"num_tokens":
|
| 33 |
-
"reward": -0.
|
| 34 |
-
"reward_std": 0.
|
| 35 |
-
"rewards/rollout_reward_func/mean": -0.
|
| 36 |
-
"rewards/rollout_reward_func/std": 0.
|
| 37 |
-
"sampling/importance_sampling_ratio/max":
|
| 38 |
-
"sampling/importance_sampling_ratio/mean":
|
| 39 |
-
"sampling/importance_sampling_ratio/min": 0.
|
| 40 |
-
"sampling/sampling_logp_difference/max": 0.
|
| 41 |
-
"sampling/sampling_logp_difference/mean": 0.
|
| 42 |
"step": 1,
|
| 43 |
-
"step_time":
|
| 44 |
}
|
| 45 |
],
|
| 46 |
"logging_steps": 1.0,
|
| 47 |
"max_steps": 600,
|
| 48 |
-
"num_input_tokens_seen":
|
| 49 |
"num_train_epochs": 1,
|
| 50 |
"save_steps": 500,
|
| 51 |
"stateful_callbacks": {
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 4e-05,
|
| 6 |
"eval_steps": 500,
|
| 7 |
"global_step": 1,
|
| 8 |
"is_hyper_param_search": false,
|
|
|
|
| 16 |
"clip_ratio/low_min": 0.0,
|
| 17 |
"clip_ratio/region_mean": 0.0,
|
| 18 |
"completions/clipped_ratio": 0.0,
|
| 19 |
+
"completions/max_length": 1052.0,
|
| 20 |
+
"completions/max_terminated_length": 1052.0,
|
| 21 |
+
"completions/mean_length": 939.96875,
|
| 22 |
+
"completions/mean_terminated_length": 939.96875,
|
| 23 |
+
"completions/min_length": 286.0,
|
| 24 |
+
"completions/min_terminated_length": 286.0,
|
| 25 |
+
"entropy": 0.17989059770479798,
|
| 26 |
+
"epoch": 4e-05,
|
| 27 |
"frac_reward_zero_std": 0.0,
|
| 28 |
+
"grad_norm": 0.6168491840362549,
|
| 29 |
"kl": 0.0,
|
| 30 |
"learning_rate": 0.0,
|
| 31 |
+
"loss": -0.037,
|
| 32 |
+
"num_tokens": 130829.0,
|
| 33 |
+
"reward": -0.48928576707839966,
|
| 34 |
+
"reward_std": 0.16871649026870728,
|
| 35 |
+
"rewards/rollout_reward_func/mean": -0.48928576707839966,
|
| 36 |
+
"rewards/rollout_reward_func/std": 0.18516120314598083,
|
| 37 |
+
"sampling/importance_sampling_ratio/max": 1.2845007181167603,
|
| 38 |
+
"sampling/importance_sampling_ratio/mean": 0.9977670907974243,
|
| 39 |
+
"sampling/importance_sampling_ratio/min": 0.6358659267425537,
|
| 40 |
+
"sampling/sampling_logp_difference/max": 0.452767550945282,
|
| 41 |
+
"sampling/sampling_logp_difference/mean": 0.012648524716496468,
|
| 42 |
"step": 1,
|
| 43 |
+
"step_time": 24.471392321000167
|
| 44 |
}
|
| 45 |
],
|
| 46 |
"logging_steps": 1.0,
|
| 47 |
"max_steps": 600,
|
| 48 |
+
"num_input_tokens_seen": 130829,
|
| 49 |
"num_train_epochs": 1,
|
| 50 |
"save_steps": 500,
|
| 51 |
"stateful_callbacks": {
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 8145
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:62006adb6a5f6ef0ccf535fbf49cda0cd9c458d12dc2ad9e29abaa7fd5f9b059
|
| 3 |
size 8145
|