strongpear commited on
Commit
53adea2
·
verified ·
1 Parent(s): ca20433

strongpear/Llama3.1-8B-QA_CoT-WIKI-Instruct-r64

Browse files
Files changed (2) hide show
  1. README.md +247 -0
  2. adapter_model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,247 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: llama3.1
4
+ base_model: meta-llama/Llama-3.1-8B
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: Llama3.1-8B-QA_CoT-WIKI-Instruct-r64
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
+ # Llama3.1-8B-QA_CoT-WIKI-Instruct-r64
16
+
17
+ This model is a fine-tuned version of [meta-llama/Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.9065
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: 3.6e-05
39
+ - train_batch_size: 4
40
+ - eval_batch_size: 4
41
+ - seed: 42
42
+ - optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
43
+ - lr_scheduler_type: cosine
44
+ - lr_scheduler_warmup_steps: 100
45
+ - num_epochs: 1
46
+ - mixed_precision_training: Native AMP
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss |
51
+ |:-------------:|:------:|:-----:|:---------------:|
52
+ | 1.1313 | 0.0053 | 200 | 1.1573 |
53
+ | 1.133 | 0.0107 | 400 | 1.1453 |
54
+ | 1.1442 | 0.016 | 600 | 1.1396 |
55
+ | 1.1934 | 0.0213 | 800 | 1.1356 |
56
+ | 1.0369 | 0.0267 | 1000 | 1.1301 |
57
+ | 1.1972 | 0.032 | 1200 | 1.1274 |
58
+ | 1.1383 | 0.0373 | 1400 | 1.1250 |
59
+ | 1.0974 | 0.0427 | 1600 | 1.1228 |
60
+ | 1.0448 | 0.048 | 1800 | 1.1210 |
61
+ | 1.1374 | 0.0533 | 2000 | 1.1175 |
62
+ | 1.1452 | 0.0587 | 2200 | 1.1154 |
63
+ | 1.1512 | 0.064 | 2400 | 1.1124 |
64
+ | 1.1899 | 0.0693 | 2600 | 1.1109 |
65
+ | 1.162 | 0.0747 | 2800 | 1.1079 |
66
+ | 1.1399 | 0.08 | 3000 | 1.1067 |
67
+ | 1.193 | 0.0853 | 3200 | 1.1039 |
68
+ | 1.0879 | 0.0907 | 3400 | 1.1012 |
69
+ | 1.1232 | 0.096 | 3600 | 1.1001 |
70
+ | 0.9941 | 0.1013 | 3800 | 1.0988 |
71
+ | 1.0458 | 0.1067 | 4000 | 1.0964 |
72
+ | 1.1045 | 0.112 | 4200 | 1.0950 |
73
+ | 1.0275 | 0.1173 | 4400 | 1.0931 |
74
+ | 1.1429 | 0.1227 | 4600 | 1.0906 |
75
+ | 1.1454 | 0.128 | 4800 | 1.0896 |
76
+ | 1.0742 | 0.1333 | 5000 | 1.0881 |
77
+ | 1.0694 | 0.1387 | 5200 | 1.0864 |
78
+ | 1.0187 | 0.144 | 5400 | 1.0848 |
79
+ | 1.1096 | 0.1493 | 5600 | 1.0824 |
80
+ | 1.1191 | 0.1547 | 5800 | 1.0804 |
81
+ | 1.1421 | 0.16 | 6000 | 1.0797 |
82
+ | 1.0974 | 0.1653 | 6200 | 1.0774 |
83
+ | 1.0815 | 0.1707 | 6400 | 1.0764 |
84
+ | 1.0659 | 0.176 | 6600 | 1.0740 |
85
+ | 1.1023 | 0.1813 | 6800 | 1.0720 |
86
+ | 1.0861 | 0.1867 | 7000 | 1.0704 |
87
+ | 1.1006 | 0.192 | 7200 | 1.0691 |
88
+ | 1.0768 | 0.1973 | 7400 | 1.0684 |
89
+ | 1.087 | 0.2027 | 7600 | 1.0664 |
90
+ | 1.1712 | 0.208 | 7800 | 1.0645 |
91
+ | 1.1151 | 0.2133 | 8000 | 1.0621 |
92
+ | 1.0282 | 0.2187 | 8200 | 1.0609 |
93
+ | 1.1077 | 0.224 | 8400 | 1.0591 |
94
+ | 1.0568 | 0.2293 | 8600 | 1.0569 |
95
+ | 1.0618 | 0.2347 | 8800 | 1.0554 |
96
+ | 1.07 | 0.24 | 9000 | 1.0538 |
97
+ | 1.0269 | 0.2453 | 9200 | 1.0524 |
98
+ | 1.0519 | 0.2507 | 9400 | 1.0507 |
99
+ | 1.0626 | 0.256 | 9600 | 1.0492 |
100
+ | 0.9715 | 0.2613 | 9800 | 1.0483 |
101
+ | 1.1142 | 0.2667 | 10000 | 1.0454 |
102
+ | 1.0678 | 0.272 | 10200 | 1.0436 |
103
+ | 1.0614 | 0.2773 | 10400 | 1.0418 |
104
+ | 1.0819 | 0.2827 | 10600 | 1.0407 |
105
+ | 1.0125 | 0.288 | 10800 | 1.0390 |
106
+ | 0.9855 | 0.2933 | 11000 | 1.0376 |
107
+ | 1.1239 | 0.2987 | 11200 | 1.0352 |
108
+ | 1.0943 | 0.304 | 11400 | 1.0337 |
109
+ | 0.9119 | 0.3093 | 11600 | 1.0318 |
110
+ | 1.035 | 0.3147 | 11800 | 1.0297 |
111
+ | 1.0769 | 0.32 | 12000 | 1.0291 |
112
+ | 0.999 | 0.3253 | 12200 | 1.0263 |
113
+ | 1.03 | 0.3307 | 12400 | 1.0243 |
114
+ | 0.954 | 0.336 | 12600 | 1.0234 |
115
+ | 1.1006 | 0.3413 | 12800 | 1.0215 |
116
+ | 0.9556 | 0.3467 | 13000 | 1.0213 |
117
+ | 1.0479 | 0.352 | 13200 | 1.0194 |
118
+ | 1.0575 | 0.3573 | 13400 | 1.0184 |
119
+ | 1.0642 | 0.3627 | 13600 | 1.0159 |
120
+ | 0.9822 | 0.368 | 13800 | 1.0150 |
121
+ | 0.9071 | 0.3733 | 14000 | 1.0148 |
122
+ | 0.9964 | 0.3787 | 14200 | 1.0113 |
123
+ | 0.9453 | 0.384 | 14400 | 1.0111 |
124
+ | 1.087 | 0.3893 | 14600 | 1.0093 |
125
+ | 0.9752 | 0.3947 | 14800 | 1.0072 |
126
+ | 1.0191 | 0.4 | 15000 | 1.0055 |
127
+ | 0.9155 | 0.4053 | 15200 | 1.0046 |
128
+ | 0.993 | 0.4107 | 15400 | 1.0037 |
129
+ | 0.9751 | 0.416 | 15600 | 1.0017 |
130
+ | 0.9106 | 0.4213 | 15800 | 1.0005 |
131
+ | 1.0481 | 0.4267 | 16000 | 0.9984 |
132
+ | 1.0122 | 0.432 | 16200 | 0.9972 |
133
+ | 1.0139 | 0.4373 | 16400 | 0.9962 |
134
+ | 0.9695 | 0.4427 | 16600 | 0.9947 |
135
+ | 0.9901 | 0.448 | 16800 | 0.9931 |
136
+ | 1.0267 | 0.4533 | 17000 | 0.9915 |
137
+ | 1.023 | 0.4587 | 17200 | 0.9905 |
138
+ | 0.9115 | 0.464 | 17400 | 0.9887 |
139
+ | 0.992 | 0.4693 | 17600 | 0.9875 |
140
+ | 0.9825 | 0.4747 | 17800 | 0.9859 |
141
+ | 1.0156 | 0.48 | 18000 | 0.9844 |
142
+ | 0.9752 | 0.4853 | 18200 | 0.9821 |
143
+ | 0.9341 | 0.4907 | 18400 | 0.9809 |
144
+ | 1.0059 | 0.496 | 18600 | 0.9787 |
145
+ | 0.957 | 0.5013 | 18800 | 0.9776 |
146
+ | 1.0018 | 0.5067 | 19000 | 0.9761 |
147
+ | 1.0889 | 0.512 | 19200 | 0.9749 |
148
+ | 1.0207 | 0.5173 | 19400 | 0.9733 |
149
+ | 1.0471 | 0.5227 | 19600 | 0.9714 |
150
+ | 0.9102 | 0.528 | 19800 | 0.9702 |
151
+ | 1.0149 | 0.5333 | 20000 | 0.9690 |
152
+ | 0.9784 | 0.5387 | 20200 | 0.9678 |
153
+ | 0.9302 | 0.544 | 20400 | 0.9658 |
154
+ | 0.9773 | 0.5493 | 20600 | 0.9643 |
155
+ | 1.0273 | 0.5547 | 20800 | 0.9627 |
156
+ | 0.8573 | 0.56 | 21000 | 0.9610 |
157
+ | 0.9683 | 0.5653 | 21200 | 0.9594 |
158
+ | 1.0293 | 0.5707 | 21400 | 0.9579 |
159
+ | 0.9456 | 0.576 | 21600 | 0.9567 |
160
+ | 0.9811 | 0.5813 | 21800 | 0.9559 |
161
+ | 0.9632 | 0.5867 | 22000 | 0.9541 |
162
+ | 1.0088 | 0.592 | 22200 | 0.9528 |
163
+ | 1.0229 | 0.5973 | 22400 | 0.9516 |
164
+ | 0.9801 | 0.6027 | 22600 | 0.9502 |
165
+ | 0.9992 | 0.608 | 22800 | 0.9486 |
166
+ | 0.8908 | 0.6133 | 23000 | 0.9475 |
167
+ | 0.9329 | 0.6187 | 23200 | 0.9467 |
168
+ | 0.9937 | 0.624 | 23400 | 0.9452 |
169
+ | 0.9478 | 0.6293 | 23600 | 0.9444 |
170
+ | 0.8929 | 0.6347 | 23800 | 0.9431 |
171
+ | 0.9073 | 0.64 | 24000 | 0.9421 |
172
+ | 0.9182 | 0.6453 | 24200 | 0.9409 |
173
+ | 0.956 | 0.6507 | 24400 | 0.9397 |
174
+ | 0.923 | 0.656 | 24600 | 0.9387 |
175
+ | 0.9523 | 0.6613 | 24800 | 0.9376 |
176
+ | 0.976 | 0.6667 | 25000 | 0.9364 |
177
+ | 0.839 | 0.672 | 25200 | 0.9356 |
178
+ | 0.9245 | 0.6773 | 25400 | 0.9345 |
179
+ | 0.9345 | 0.6827 | 25600 | 0.9333 |
180
+ | 0.8861 | 0.688 | 25800 | 0.9323 |
181
+ | 0.9134 | 0.6933 | 26000 | 0.9312 |
182
+ | 0.9297 | 0.6987 | 26200 | 0.9302 |
183
+ | 0.8873 | 0.704 | 26400 | 0.9291 |
184
+ | 0.963 | 0.7093 | 26600 | 0.9281 |
185
+ | 1.0326 | 0.7147 | 26800 | 0.9274 |
186
+ | 0.8596 | 0.72 | 27000 | 0.9263 |
187
+ | 0.8968 | 0.7253 | 27200 | 0.9252 |
188
+ | 0.9147 | 0.7307 | 27400 | 0.9241 |
189
+ | 0.9149 | 0.736 | 27600 | 0.9230 |
190
+ | 0.9049 | 0.7413 | 27800 | 0.9222 |
191
+ | 0.9949 | 0.7467 | 28000 | 0.9215 |
192
+ | 0.8797 | 0.752 | 28200 | 0.9207 |
193
+ | 0.8369 | 0.7573 | 28400 | 0.9199 |
194
+ | 1.0025 | 0.7627 | 28600 | 0.9192 |
195
+ | 0.9577 | 0.768 | 28800 | 0.9184 |
196
+ | 0.9422 | 0.7733 | 29000 | 0.9177 |
197
+ | 0.971 | 0.7787 | 29200 | 0.9170 |
198
+ | 0.8421 | 0.784 | 29400 | 0.9166 |
199
+ | 0.9989 | 0.7893 | 29600 | 0.9160 |
200
+ | 0.9053 | 0.7947 | 29800 | 0.9154 |
201
+ | 0.9312 | 0.8 | 30000 | 0.9146 |
202
+ | 0.8888 | 0.8053 | 30200 | 0.9141 |
203
+ | 0.9331 | 0.8107 | 30400 | 0.9135 |
204
+ | 0.9652 | 0.816 | 30600 | 0.9129 |
205
+ | 0.8413 | 0.8213 | 30800 | 0.9124 |
206
+ | 0.9307 | 0.8267 | 31000 | 0.9119 |
207
+ | 0.8598 | 0.832 | 31200 | 0.9115 |
208
+ | 0.921 | 0.8373 | 31400 | 0.9111 |
209
+ | 0.9171 | 0.8427 | 31600 | 0.9107 |
210
+ | 0.9949 | 0.848 | 31800 | 0.9103 |
211
+ | 0.8467 | 0.8533 | 32000 | 0.9099 |
212
+ | 0.8858 | 0.8587 | 32200 | 0.9097 |
213
+ | 0.9111 | 0.864 | 32400 | 0.9093 |
214
+ | 0.8814 | 0.8693 | 32600 | 0.9089 |
215
+ | 0.8701 | 0.8747 | 32800 | 0.9087 |
216
+ | 0.9566 | 0.88 | 33000 | 0.9084 |
217
+ | 0.9591 | 0.8853 | 33200 | 0.9082 |
218
+ | 0.8082 | 0.8907 | 33400 | 0.9080 |
219
+ | 0.9117 | 0.896 | 33600 | 0.9078 |
220
+ | 0.8463 | 0.9013 | 33800 | 0.9077 |
221
+ | 0.9023 | 0.9067 | 34000 | 0.9075 |
222
+ | 0.9993 | 0.912 | 34200 | 0.9073 |
223
+ | 0.9258 | 0.9173 | 34400 | 0.9072 |
224
+ | 0.9564 | 0.9227 | 34600 | 0.9071 |
225
+ | 0.8713 | 0.928 | 34800 | 0.9070 |
226
+ | 0.973 | 0.9333 | 35000 | 0.9069 |
227
+ | 0.9323 | 0.9387 | 35200 | 0.9068 |
228
+ | 0.9408 | 0.944 | 35400 | 0.9068 |
229
+ | 0.9596 | 0.9493 | 35600 | 0.9067 |
230
+ | 1.0151 | 0.9547 | 35800 | 0.9067 |
231
+ | 0.8714 | 0.96 | 36000 | 0.9066 |
232
+ | 0.9274 | 0.9653 | 36200 | 0.9066 |
233
+ | 0.9182 | 0.9707 | 36400 | 0.9066 |
234
+ | 0.984 | 0.976 | 36600 | 0.9065 |
235
+ | 0.9376 | 0.9813 | 36800 | 0.9065 |
236
+ | 0.8816 | 0.9867 | 37000 | 0.9065 |
237
+ | 0.9195 | 0.992 | 37200 | 0.9065 |
238
+ | 0.9351 | 0.9973 | 37400 | 0.9065 |
239
+
240
+
241
+ ### Framework versions
242
+
243
+ - PEFT 0.12.0
244
+ - Transformers 4.47.0
245
+ - Pytorch 2.5.1+cu124
246
+ - Datasets 3.0.0
247
+ - Tokenizers 0.21.0
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7674598c561fd8538d03e14b2c4e05c3c6037ed2fb09c65b3bbdb1c225359864
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:736870a558c6f00ad3bf41dacc339e7cf86d17309f0b8a45b7dc61e9acc83d93
3
  size 671149168