codegood commited on
Commit
08eae84
1 Parent(s): f9529fd

codegood/AWS_Mistral_SC/

Browse files
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
- license: other
3
- base_model: microsoft/phi-1_5
4
  tags:
5
  - generated_from_trainer
6
  model-index:
@@ -13,9 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
13
 
14
  # results
15
 
16
- This model is a fine-tuned version of [microsoft/phi-1_5](https://huggingface.co/microsoft/phi-1_5) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.2032
19
 
20
  ## Model description
21
 
@@ -41,24 +41,23 @@ The following hyperparameters were used during training:
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: cosine
43
  - lr_scheduler_warmup_ratio: 0.05
44
- - num_epochs: 3.0
45
 
46
  ### Training results
47
 
48
  | Training Loss | Epoch | Step | Validation Loss |
49
  |:-------------:|:-----:|:----:|:---------------:|
50
- | 0.7562 | 0.39 | 500 | 0.4813 |
51
- | 0.71 | 0.77 | 1000 | 0.4007 |
52
- | 0.6006 | 1.16 | 1500 | 0.3466 |
53
- | 0.4935 | 1.55 | 2000 | 0.2830 |
54
- | 0.5042 | 1.93 | 2500 | 0.2403 |
55
- | 0.356 | 2.32 | 3000 | 0.2103 |
56
- | 0.3393 | 2.71 | 3500 | 0.2032 |
57
 
58
 
59
  ### Framework versions
60
 
61
- - Transformers 4.36.0.dev0
62
- - Pytorch 2.1.0+cu118
63
- - Datasets 2.15.0
64
  - Tokenizers 0.15.0
 
1
  ---
2
+ license: apache-2.0
3
+ base_model: bn22/Mistral-7B-Instruct-v0.1-sharded
4
  tags:
5
  - generated_from_trainer
6
  model-index:
 
13
 
14
  # results
15
 
16
+ This model is a fine-tuned version of [bn22/Mistral-7B-Instruct-v0.1-sharded](https://huggingface.co/bn22/Mistral-7B-Instruct-v0.1-sharded) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 1.9447
19
 
20
  ## Model description
21
 
 
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: cosine
43
  - lr_scheduler_warmup_ratio: 0.05
44
+ - training_steps: 600
45
 
46
  ### Training results
47
 
48
  | Training Loss | Epoch | Step | Validation Loss |
49
  |:-------------:|:-----:|:----:|:---------------:|
50
+ | 2.4418 | 0.07 | 100 | 2.2922 |
51
+ | 2.1884 | 0.15 | 200 | 2.1105 |
52
+ | 2.0871 | 0.22 | 300 | 2.0371 |
53
+ | 2.011 | 0.29 | 400 | 1.9835 |
54
+ | 1.9346 | 0.37 | 500 | 1.9517 |
55
+ | 1.9721 | 0.44 | 600 | 1.9447 |
 
56
 
57
 
58
  ### Framework versions
59
 
60
+ - Transformers 4.35.2
61
+ - Pytorch 2.0.0
62
+ - Datasets 2.11.0
63
  - Tokenizers 0.15.0
adapter_config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
- "base_model_name_or_path": "microsoft/phi-1_5",
5
  "bias": "none",
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,
@@ -19,10 +19,11 @@
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
22
- "out_proj",
23
- "fc1",
24
- "fc2",
25
- "Wqkv"
 
26
  ],
27
  "task_type": "CAUSAL_LM"
28
  }
 
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
+ "base_model_name_or_path": "bn22/Mistral-7B-Instruct-v0.1-sharded",
5
  "bias": "none",
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,
 
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
22
+ "k_proj",
23
+ "q_proj",
24
+ "o_proj",
25
+ "v_proj",
26
+ "gate_proj"
27
  ],
28
  "task_type": "CAUSAL_LM"
29
  }
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6be00427cecbbd3d5b5422fc91bfb337116734ab718e4322580638434d0f4aca
3
- size 201350248
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61965e4bd4a997696781f46af81b9860bd3b6f9c9dbc2d790a3a26efdf4cc4ba
3
+ size 369142184
special_tokens_map.json CHANGED
@@ -1,6 +1,24 @@
1
  {
2
- "bos_token": "<|endoftext|>",
3
- "eos_token": "<|endoftext|>",
4
- "pad_token": "<|endoftext|>",
5
- "unk_token": "<|endoftext|>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6
  }
 
1
  {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,325 +1,41 @@
1
  {
2
- "add_prefix_space": false,
3
  "added_tokens_decoder": {
4
- "50256": {
5
- "content": "<|endoftext|>",
6
- "lstrip": false,
7
- "normalized": false,
8
- "rstrip": false,
9
- "single_word": false,
10
- "special": true
11
- },
12
- "50257": {
13
- "content": " ",
14
- "lstrip": false,
15
- "normalized": true,
16
- "rstrip": false,
17
- "single_word": false,
18
- "special": false
19
- },
20
- "50258": {
21
- "content": " ",
22
- "lstrip": false,
23
- "normalized": true,
24
- "rstrip": false,
25
- "single_word": false,
26
- "special": false
27
- },
28
- "50259": {
29
- "content": " ",
30
- "lstrip": false,
31
- "normalized": true,
32
- "rstrip": false,
33
- "single_word": false,
34
- "special": false
35
- },
36
- "50260": {
37
- "content": " ",
38
- "lstrip": false,
39
- "normalized": true,
40
- "rstrip": false,
41
- "single_word": false,
42
- "special": false
43
- },
44
- "50261": {
45
- "content": " ",
46
- "lstrip": false,
47
- "normalized": true,
48
- "rstrip": false,
49
- "single_word": false,
50
- "special": false
51
- },
52
- "50262": {
53
- "content": " ",
54
- "lstrip": false,
55
- "normalized": true,
56
- "rstrip": false,
57
- "single_word": false,
58
- "special": false
59
- },
60
- "50263": {
61
- "content": " ",
62
- "lstrip": false,
63
- "normalized": true,
64
- "rstrip": false,
65
- "single_word": false,
66
- "special": false
67
- },
68
- "50264": {
69
- "content": " ",
70
- "lstrip": false,
71
- "normalized": true,
72
- "rstrip": false,
73
- "single_word": false,
74
- "special": false
75
- },
76
- "50265": {
77
- "content": " ",
78
- "lstrip": false,
79
- "normalized": true,
80
- "rstrip": false,
81
- "single_word": false,
82
- "special": false
83
- },
84
- "50266": {
85
- "content": " ",
86
- "lstrip": false,
87
- "normalized": true,
88
- "rstrip": false,
89
- "single_word": false,
90
- "special": false
91
- },
92
- "50267": {
93
- "content": " ",
94
- "lstrip": false,
95
- "normalized": true,
96
- "rstrip": false,
97
- "single_word": false,
98
- "special": false
99
- },
100
- "50268": {
101
- "content": " ",
102
- "lstrip": false,
103
- "normalized": true,
104
- "rstrip": false,
105
- "single_word": false,
106
- "special": false
107
- },
108
- "50269": {
109
- "content": " ",
110
- "lstrip": false,
111
- "normalized": true,
112
- "rstrip": false,
113
- "single_word": false,
114
- "special": false
115
- },
116
- "50270": {
117
- "content": " ",
118
- "lstrip": false,
119
- "normalized": true,
120
- "rstrip": false,
121
- "single_word": false,
122
- "special": false
123
- },
124
- "50271": {
125
- "content": " ",
126
  "lstrip": false,
127
  "normalized": true,
128
  "rstrip": false,
129
  "single_word": false,
130
- "special": false
131
- },
132
- "50272": {
133
- "content": " ",
134
- "lstrip": false,
135
- "normalized": true,
136
- "rstrip": false,
137
- "single_word": false,
138
- "special": false
139
- },
140
- "50273": {
141
- "content": " ",
142
- "lstrip": false,
143
- "normalized": true,
144
- "rstrip": false,
145
- "single_word": false,
146
- "special": false
147
- },
148
- "50274": {
149
- "content": " ",
150
- "lstrip": false,
151
- "normalized": true,
152
- "rstrip": false,
153
- "single_word": false,
154
- "special": false
155
- },
156
- "50275": {
157
- "content": " ",
158
- "lstrip": false,
159
- "normalized": true,
160
- "rstrip": false,
161
- "single_word": false,
162
- "special": false
163
- },
164
- "50276": {
165
- "content": " ",
166
- "lstrip": false,
167
- "normalized": true,
168
- "rstrip": false,
169
- "single_word": false,
170
- "special": false
171
- },
172
- "50277": {
173
- "content": " ",
174
- "lstrip": false,
175
- "normalized": true,
176
- "rstrip": false,
177
- "single_word": false,
178
- "special": false
179
- },
180
- "50278": {
181
- "content": " ",
182
- "lstrip": false,
183
- "normalized": true,
184
- "rstrip": false,
185
- "single_word": false,
186
- "special": false
187
- },
188
- "50279": {
189
- "content": " ",
190
- "lstrip": false,
191
- "normalized": true,
192
- "rstrip": false,
193
- "single_word": false,
194
- "special": false
195
- },
196
- "50280": {
197
- "content": " ",
198
- "lstrip": false,
199
- "normalized": true,
200
- "rstrip": false,
201
- "single_word": false,
202
- "special": false
203
- },
204
- "50281": {
205
- "content": " ",
206
- "lstrip": false,
207
- "normalized": true,
208
- "rstrip": false,
209
- "single_word": false,
210
- "special": false
211
- },
212
- "50282": {
213
- "content": " ",
214
- "lstrip": false,
215
- "normalized": true,
216
- "rstrip": false,
217
- "single_word": false,
218
- "special": false
219
- },
220
- "50283": {
221
- "content": " ",
222
- "lstrip": false,
223
- "normalized": true,
224
- "rstrip": false,
225
- "single_word": false,
226
- "special": false
227
- },
228
- "50284": {
229
- "content": " ",
230
- "lstrip": false,
231
- "normalized": true,
232
- "rstrip": false,
233
- "single_word": false,
234
- "special": false
235
- },
236
- "50285": {
237
- "content": " ",
238
- "lstrip": false,
239
- "normalized": true,
240
- "rstrip": false,
241
- "single_word": false,
242
- "special": false
243
- },
244
- "50286": {
245
- "content": " ",
246
- "lstrip": false,
247
- "normalized": true,
248
- "rstrip": false,
249
- "single_word": false,
250
- "special": false
251
- },
252
- "50287": {
253
- "content": "\t\t\t\t\t\t\t\t\t",
254
- "lstrip": false,
255
- "normalized": true,
256
- "rstrip": false,
257
- "single_word": false,
258
- "special": false
259
- },
260
- "50288": {
261
- "content": "\t\t\t\t\t\t\t\t",
262
- "lstrip": false,
263
- "normalized": true,
264
- "rstrip": false,
265
- "single_word": false,
266
- "special": false
267
- },
268
- "50289": {
269
- "content": "\t\t\t\t\t\t\t",
270
- "lstrip": false,
271
- "normalized": true,
272
- "rstrip": false,
273
- "single_word": false,
274
- "special": false
275
- },
276
- "50290": {
277
- "content": "\t\t\t\t\t\t",
278
- "lstrip": false,
279
- "normalized": true,
280
- "rstrip": false,
281
- "single_word": false,
282
- "special": false
283
- },
284
- "50291": {
285
- "content": "\t\t\t\t\t",
286
- "lstrip": false,
287
- "normalized": true,
288
- "rstrip": false,
289
- "single_word": false,
290
- "special": false
291
- },
292
- "50292": {
293
- "content": "\t\t\t\t",
294
- "lstrip": false,
295
- "normalized": true,
296
- "rstrip": false,
297
- "single_word": false,
298
- "special": false
299
  },
300
- "50293": {
301
- "content": "\t\t\t",
302
  "lstrip": false,
303
  "normalized": true,
304
  "rstrip": false,
305
  "single_word": false,
306
- "special": false
307
  },
308
- "50294": {
309
- "content": "\t\t",
310
  "lstrip": false,
311
  "normalized": true,
312
  "rstrip": false,
313
  "single_word": false,
314
- "special": false
315
  }
316
  },
317
- "bos_token": "<|endoftext|>",
318
- "clean_up_tokenization_spaces": true,
319
- "eos_token": "<|endoftext|>",
320
- "model_max_length": 2048,
321
- "pad_token": "<|endoftext|>",
322
- "tokenizer_class": "CodeGenTokenizer",
323
- "torch_dtype": "auto",
324
- "unk_token": "<|endoftext|>"
 
 
 
 
 
325
  }
 
1
  {
 
2
  "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  "lstrip": false,
6
  "normalized": true,
7
  "rstrip": false,
8
  "single_word": false,
9
+ "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
10
  },
11
+ "1": {
12
+ "content": "<s>",
13
  "lstrip": false,
14
  "normalized": true,
15
  "rstrip": false,
16
  "single_word": false,
17
+ "special": true
18
  },
19
+ "2": {
20
+ "content": "</s>",
21
  "lstrip": false,
22
  "normalized": true,
23
  "rstrip": false,
24
  "single_word": false,
25
+ "special": true
26
  }
27
  },
28
+ "additional_special_tokens": [],
29
+ "bos_token": "<s>",
30
+ "clean_up_tokenization_spaces": false,
31
+ "device_map": "auto",
32
+ "eos_token": "</s>",
33
+ "legacy": true,
34
+ "model_max_length": 1000000000000000019884624838656,
35
+ "pad_token": "</s>",
36
+ "sp_model_kwargs": {},
37
+ "spaces_between_special_tokens": false,
38
+ "tokenizer_class": "LlamaTokenizer",
39
+ "unk_token": "<unk>",
40
+ "use_default_system_prompt": true
41
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5da540b2350a59a744c709ca5d8f323c4c62ae3e18c8d1a193fb34ec9bba6d3e
3
- size 4664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c78c6d371e675608a6248617f3f15cef6616718c149eb7f6252e5188c29580a
3
+ size 4091