flyyufelix commited on
Commit
8fba45d
·
verified ·
1 Parent(s): 191b655

Model save

Browse files
README.md CHANGED
@@ -1,5 +1,5 @@
1
  ---
2
- base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
3
  library_name: transformers
4
  model_name: Qwen-2.5-7B-Simple-RL
5
  tags:
@@ -11,7 +11,7 @@ licence: license
11
 
12
  # Model Card for Qwen-2.5-7B-Simple-RL
13
 
14
- This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B).
15
  It has been trained using [TRL](https://github.com/huggingface/trl).
16
 
17
  ## Quick start
@@ -35,7 +35,7 @@ This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing
35
  ### Framework versions
36
 
37
  - TRL: 0.16.0.dev0
38
- - Transformers: 4.49.0
39
  - Pytorch: 2.5.1
40
  - Datasets: 3.3.0
41
  - Tokenizers: 0.21.0
 
1
  ---
2
+ base_model: Qwen/Qwen2.5-0.5B
3
  library_name: transformers
4
  model_name: Qwen-2.5-7B-Simple-RL
5
  tags:
 
11
 
12
  # Model Card for Qwen-2.5-7B-Simple-RL
13
 
14
+ This model is a fine-tuned version of [Qwen/Qwen2.5-0.5B](https://huggingface.co/Qwen/Qwen2.5-0.5B).
15
  It has been trained using [TRL](https://github.com/huggingface/trl).
16
 
17
  ## Quick start
 
35
  ### Framework versions
36
 
37
  - TRL: 0.16.0.dev0
38
+ - Transformers: 4.47.1
39
  - Pytorch: 2.5.1
40
  - Datasets: 3.3.0
41
  - Tokenizers: 0.21.0
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "total_flos": 0.0,
3
  "train_loss": 0.0,
4
- "train_runtime": 49.2958,
5
  "train_samples": 7500,
6
- "train_samples_per_second": 0.325,
7
- "train_steps_per_second": 0.02
8
  }
 
1
  {
2
  "total_flos": 0.0,
3
  "train_loss": 0.0,
4
+ "train_runtime": 29.2169,
5
  "train_samples": 7500,
6
+ "train_samples_per_second": 0.548,
7
+ "train_steps_per_second": 0.034
8
  }
config.json CHANGED
@@ -1,6 +1,5 @@
1
  {
2
- "_attn_implementation_autoset": true,
3
- "_name_or_path": "Qwen/Qwen2.5-Math-7B",
4
  "architectures": [
5
  "Qwen2ForCausalLM"
6
  ],
@@ -8,24 +7,24 @@
8
  "bos_token_id": 151643,
9
  "eos_token_id": 151643,
10
  "hidden_act": "silu",
11
- "hidden_size": 3584,
12
  "initializer_range": 0.02,
13
- "intermediate_size": 18944,
14
- "max_position_embeddings": 4096,
15
- "max_window_layers": 28,
16
  "model_type": "qwen2",
17
- "num_attention_heads": 28,
18
- "num_hidden_layers": 28,
19
- "num_key_value_heads": 4,
20
  "rms_norm_eps": 1e-06,
21
  "rope_scaling": null,
22
- "rope_theta": 10000,
23
- "sliding_window": 4096,
24
- "tie_word_embeddings": false,
25
  "torch_dtype": "bfloat16",
26
- "transformers_version": "4.49.0",
27
- "use_cache": true,
28
  "use_mrope": false,
29
  "use_sliding_window": false,
30
- "vocab_size": 152064
31
  }
 
1
  {
2
+ "_name_or_path": "Qwen/Qwen2.5-0.5B",
 
3
  "architectures": [
4
  "Qwen2ForCausalLM"
5
  ],
 
7
  "bos_token_id": 151643,
8
  "eos_token_id": 151643,
9
  "hidden_act": "silu",
10
+ "hidden_size": 896,
11
  "initializer_range": 0.02,
12
+ "intermediate_size": 4864,
13
+ "max_position_embeddings": 32768,
14
+ "max_window_layers": 24,
15
  "model_type": "qwen2",
16
+ "num_attention_heads": 14,
17
+ "num_hidden_layers": 24,
18
+ "num_key_value_heads": 2,
19
  "rms_norm_eps": 1e-06,
20
  "rope_scaling": null,
21
+ "rope_theta": 1000000.0,
22
+ "sliding_window": null,
23
+ "tie_word_embeddings": true,
24
  "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.47.1",
26
+ "use_cache": false,
27
  "use_mrope": false,
28
  "use_sliding_window": false,
29
+ "vocab_size": 151936
30
  }
generation_config.json CHANGED
@@ -2,5 +2,5 @@
2
  "bos_token_id": 151643,
3
  "eos_token_id": 151643,
4
  "max_new_tokens": 2048,
5
- "transformers_version": "4.49.0"
6
  }
 
2
  "bos_token_id": 151643,
3
  "eos_token_id": 151643,
4
  "max_new_tokens": 2048,
5
+ "transformers_version": "4.47.1"
6
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:544472637a7b59b3256215f56e4da8920314f3bac08e3d129fc694c1dece31d5
3
- size 1260367448
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88c142557820ccad55bb59756bfcfcf891de9cc6202816bd346445188a0ed342
3
+ size 988097824
special_tokens_map.json CHANGED
@@ -1,20 +1,28 @@
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,
 
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,
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a4256422650d141f228fe954acee98679da412984c29a569877eefd3af69315a
3
- size 11422959
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5eee858c5123a4279c3e1f7b81247343f356ac767940b2692a928ad929543214
3
+ size 11422063
tokenizer_config.json CHANGED
@@ -1,10 +1,9 @@
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,
@@ -12,23 +11,23 @@
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,
@@ -36,28 +35,28 @@
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|>",
@@ -180,16 +179,30 @@
180
  "special": false
181
  }
182
  },
183
- "bos_token": "<|begin▁of▁sentence|>",
184
- "chat_template": "{% 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 %}",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
185
  "clean_up_tokenization_spaces": false,
186
- "eos_token": "<|end▁of▁sentence|>",
 
187
  "extra_special_tokens": {},
188
- "legacy": true,
189
- "model_max_length": 16384,
190
- "pad_token": "<|end▁of▁sentence|>",
191
- "sp_model_kwargs": {},
192
- "tokenizer_class": "LlamaTokenizerFast",
193
- "unk_token": null,
194
- "use_default_system_prompt": false
195
  }
 
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,
 
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,
 
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|>",
 
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 {{- 'You are a helpful assistant.' }}\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\\nYou are a helpful assistant.<|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
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "total_flos": 0.0,
3
  "train_loss": 0.0,
4
- "train_runtime": 49.2958,
5
  "train_samples": 7500,
6
- "train_samples_per_second": 0.325,
7
- "train_steps_per_second": 0.02
8
  }
 
1
  {
2
  "total_flos": 0.0,
3
  "train_loss": 0.0,
4
+ "train_runtime": 29.2169,
5
  "train_samples": 7500,
6
+ "train_samples_per_second": 0.548,
7
+ "train_steps_per_second": 0.034
8
  }
trainer_state.json CHANGED
@@ -10,7 +10,7 @@
10
  "log_history": [
11
  {
12
  "clip_ratio": 0.0,
13
- "completion_length": 256.0,
14
  "epoch": 0.0010666666666666667,
15
  "grad_norm": 0.0,
16
  "kl": 0.0,
@@ -27,9 +27,9 @@
27
  "step": 1,
28
  "total_flos": 0.0,
29
  "train_loss": 0.0,
30
- "train_runtime": 49.2958,
31
- "train_samples_per_second": 0.325,
32
- "train_steps_per_second": 0.02
33
  }
34
  ],
35
  "logging_steps": 5,
 
10
  "log_history": [
11
  {
12
  "clip_ratio": 0.0,
13
+ "completion_length": 242.3125,
14
  "epoch": 0.0010666666666666667,
15
  "grad_norm": 0.0,
16
  "kl": 0.0,
 
27
  "step": 1,
28
  "total_flos": 0.0,
29
  "train_loss": 0.0,
30
+ "train_runtime": 29.2169,
31
+ "train_samples_per_second": 0.548,
32
+ "train_steps_per_second": 0.034
33
  }
34
  ],
35
  "logging_steps": 5,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7a583b94977bd994f0e18110bd26ee8dce871621ac897bf26644714c54342d23
3
  size 6520
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b22a4ab5c171170644575774d43badfbd904431c614da51d0bc7170607b4d447
3
  size 6520