mothnaZl commited on
Commit
243db57
·
verified ·
1 Parent(s): de40c1d

Model save

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,122 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: mit
4
+ base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: genrm-deepseek-ai-DeepSeek-R1-Distill-Qwen-14B
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # genrm-deepseek-ai-DeepSeek-R1-Distill-Qwen-14B
16
+
17
+ This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Qwen-14B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.2953
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 3e-07
39
+ - train_batch_size: 1
40
+ - eval_batch_size: 1
41
+ - seed: 42
42
+ - distributed_type: multi-GPU
43
+ - num_devices: 8
44
+ - total_train_batch_size: 8
45
+ - total_eval_batch_size: 8
46
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
47
+ - lr_scheduler_type: linear
48
+ - num_epochs: 1
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss |
53
+ |:-------------:|:------:|:-----:|:---------------:|
54
+ | 0.2028 | 0.0163 | 200 | 0.3168 |
55
+ | 0.1841 | 0.0326 | 400 | 0.3174 |
56
+ | 0.178 | 0.0489 | 600 | 0.3028 |
57
+ | 0.193 | 0.0652 | 800 | 0.3068 |
58
+ | 0.1912 | 0.0815 | 1000 | 0.3044 |
59
+ | 0.189 | 0.0979 | 1200 | 0.3004 |
60
+ | 0.1857 | 0.1142 | 1400 | 0.3047 |
61
+ | 0.175 | 0.1305 | 1600 | 0.3043 |
62
+ | 0.1717 | 0.1468 | 1800 | 0.2981 |
63
+ | 0.1779 | 0.1631 | 2000 | 0.3049 |
64
+ | 0.1727 | 0.1794 | 2200 | 0.3041 |
65
+ | 0.1796 | 0.1957 | 2400 | 0.3054 |
66
+ | 0.1843 | 0.2120 | 2600 | 0.2994 |
67
+ | 0.1832 | 0.2283 | 2800 | 0.3020 |
68
+ | 0.1642 | 0.2446 | 3000 | 0.3049 |
69
+ | 0.1954 | 0.2609 | 3200 | 0.2988 |
70
+ | 0.1884 | 0.2773 | 3400 | 0.2992 |
71
+ | 0.1717 | 0.2936 | 3600 | 0.2983 |
72
+ | 0.1744 | 0.3099 | 3800 | 0.2982 |
73
+ | 0.1717 | 0.3262 | 4000 | 0.3021 |
74
+ | 0.1519 | 0.3425 | 4200 | 0.2989 |
75
+ | 0.1857 | 0.3588 | 4400 | 0.2981 |
76
+ | 0.1802 | 0.3751 | 4600 | 0.3004 |
77
+ | 0.1637 | 0.3914 | 4800 | 0.2981 |
78
+ | 0.1611 | 0.4077 | 5000 | 0.2993 |
79
+ | 0.1957 | 0.4240 | 5200 | 0.2973 |
80
+ | 0.169 | 0.4403 | 5400 | 0.2950 |
81
+ | 0.1542 | 0.4567 | 5600 | 0.2972 |
82
+ | 0.1669 | 0.4730 | 5800 | 0.2943 |
83
+ | 0.1667 | 0.4893 | 6000 | 0.2944 |
84
+ | 0.1742 | 0.5056 | 6200 | 0.2963 |
85
+ | 0.1676 | 0.5219 | 6400 | 0.2951 |
86
+ | 0.1537 | 0.5382 | 6600 | 0.2975 |
87
+ | 0.1876 | 0.5545 | 6800 | 0.2979 |
88
+ | 0.1543 | 0.5708 | 7000 | 0.2980 |
89
+ | 0.1709 | 0.5871 | 7200 | 0.2981 |
90
+ | 0.1608 | 0.6034 | 7400 | 0.2967 |
91
+ | 0.1727 | 0.6198 | 7600 | 0.2973 |
92
+ | 0.1659 | 0.6361 | 7800 | 0.2959 |
93
+ | 0.1862 | 0.6524 | 8000 | 0.2990 |
94
+ | 0.1758 | 0.6687 | 8200 | 0.2974 |
95
+ | 0.1981 | 0.6850 | 8400 | 0.2965 |
96
+ | 0.1616 | 0.7013 | 8600 | 0.2943 |
97
+ | 0.1738 | 0.7176 | 8800 | 0.2943 |
98
+ | 0.1775 | 0.7339 | 9000 | 0.2958 |
99
+ | 0.1683 | 0.7502 | 9200 | 0.2949 |
100
+ | 0.1632 | 0.7665 | 9400 | 0.2946 |
101
+ | 0.1702 | 0.7828 | 9600 | 0.2937 |
102
+ | 0.1937 | 0.7992 | 9800 | 0.2944 |
103
+ | 0.162 | 0.8155 | 10000 | 0.2964 |
104
+ | 0.167 | 0.8318 | 10200 | 0.2968 |
105
+ | 0.1708 | 0.8481 | 10400 | 0.2963 |
106
+ | 0.16 | 0.8644 | 10600 | 0.2970 |
107
+ | 0.1695 | 0.8807 | 10800 | 0.2944 |
108
+ | 0.1568 | 0.8970 | 11000 | 0.2948 |
109
+ | 0.1708 | 0.9133 | 11200 | 0.2952 |
110
+ | 0.1561 | 0.9296 | 11400 | 0.2961 |
111
+ | 0.158 | 0.9459 | 11600 | 0.2950 |
112
+ | 0.1763 | 0.9622 | 11800 | 0.2948 |
113
+ | 0.1579 | 0.9786 | 12000 | 0.2950 |
114
+ | 0.1512 | 0.9949 | 12200 | 0.2953 |
115
+
116
+
117
+ ### Framework versions
118
+
119
+ - Transformers 4.46.1
120
+ - Pytorch 2.5.1+cu124
121
+ - Datasets 3.1.0
122
+ - Tokenizers 0.20.3
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": "4.46.1"
9
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|fim_pad|>"
17
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
3
+ size 11422778
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
+ "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
+ "legacy": true,
188
+ "model_max_length": 16384,
189
+ "pad_token": "<|fim_pad|>",
190
+ "sp_model_kwargs": {},
191
+ "tokenizer_class": "LlamaTokenizer",
192
+ "unk_token": null,
193
+ "use_default_system_prompt": false
194
+ }