isarth commited on
Commit
b99b8c6
·
1 Parent(s): 9ebcb16

Upload 13 files

Browse files
README.md CHANGED
@@ -1,3 +1,448 @@
1
  ---
2
- license: apache-2.0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ tags:
3
+ - generated_from_trainer
4
+ datasets:
5
+ - tmp/cnn_clean_chatgpt_data/
6
+ metrics:
7
+ - accuracy
8
+ model-index:
9
+ - name: chatgpt-mlm
10
+ results:
11
+ - task:
12
+ name: Masked Language Modeling
13
+ type: fill-mask
14
+ dataset:
15
+ name: tmp/cnn_clean_chatgpt_data/
16
+ type: tmp/cnn_clean_chatgpt_data/
17
+ config: 1.0.0
18
+ split: train
19
+ args: 1.0.0
20
+ metrics:
21
+ - name: Accuracy
22
+ type: accuracy
23
+ value: 0.701455194792215
24
  ---
25
+
26
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
27
+ should probably proofread and complete it, then remove this comment. -->
28
+
29
+ # chatgpt-mlm
30
+
31
+ This model is a fine-tuned version of [](https://huggingface.co/) on the tmp/cnn_clean_chatgpt_data/ dataset.
32
+ It achieves the following results on the evaluation set:
33
+ - Loss: 1.4969
34
+ - Accuracy: 0.7015
35
+
36
+ ## Model description
37
+
38
+ More information needed
39
+
40
+ ## Intended uses & limitations
41
+
42
+ More information needed
43
+
44
+ ## Training and evaluation data
45
+
46
+ More information needed
47
+
48
+ ## Training procedure
49
+
50
+ ### Training hyperparameters
51
+
52
+ The following hyperparameters were used during training:
53
+ - learning_rate: 5e-05
54
+ - train_batch_size: 8
55
+ - eval_batch_size: 8
56
+ - seed: 42
57
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
58
+ - lr_scheduler_type: linear
59
+ - lr_scheduler_warmup_steps: 6
60
+ - num_epochs: 75.0
61
+
62
+ ### Training results
63
+
64
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
65
+ |:-------------:|:-----:|:------:|:---------------:|:--------:|
66
+ | 7.2061 | 0.2 | 500 | 6.6958 | 0.1161 |
67
+ | 6.6051 | 0.4 | 1000 | 6.5527 | 0.1303 |
68
+ | 6.5016 | 0.6 | 1500 | 6.4720 | 0.1382 |
69
+ | 6.4189 | 0.8 | 2000 | 6.3796 | 0.1424 |
70
+ | 6.3648 | 1.0 | 2500 | 6.3224 | 0.1448 |
71
+ | 6.2787 | 1.2 | 3000 | 6.2787 | 0.1411 |
72
+ | 6.2583 | 1.4 | 3500 | 6.2467 | 0.1446 |
73
+ | 6.2211 | 1.6 | 4000 | 6.2162 | 0.1475 |
74
+ | 6.1897 | 1.8 | 4500 | 6.1933 | 0.1466 |
75
+ | 6.1625 | 2.0 | 5000 | 6.1704 | 0.1483 |
76
+ | 6.1412 | 2.2 | 5500 | 6.1527 | 0.1484 |
77
+ | 6.1062 | 2.4 | 6000 | 6.1296 | 0.1492 |
78
+ | 6.1003 | 2.6 | 6500 | 6.1275 | 0.1483 |
79
+ | 6.0944 | 2.8 | 7000 | 6.0983 | 0.1496 |
80
+ | 6.077 | 3.0 | 7500 | 6.0839 | 0.1509 |
81
+ | 6.0419 | 3.2 | 8000 | 6.0747 | 0.1504 |
82
+ | 6.0264 | 3.4 | 8500 | 6.0729 | 0.1506 |
83
+ | 6.0222 | 3.6 | 9000 | 6.0585 | 0.1504 |
84
+ | 6.0067 | 3.8 | 9500 | 6.0518 | 0.1500 |
85
+ | 6.0045 | 4.0 | 10000 | 6.0300 | 0.1504 |
86
+ | 5.9659 | 4.2 | 10500 | 6.0248 | 0.1504 |
87
+ | 5.9542 | 4.4 | 11000 | 6.0143 | 0.1512 |
88
+ | 5.9479 | 4.6 | 11500 | 5.9891 | 0.1514 |
89
+ | 5.9506 | 4.8 | 12000 | 5.9827 | 0.1517 |
90
+ | 5.9358 | 5.0 | 12500 | 5.9973 | 0.1509 |
91
+ | 5.9114 | 5.2 | 13000 | 5.9761 | 0.1505 |
92
+ | 5.9089 | 5.4 | 13500 | 5.9637 | 0.1516 |
93
+ | 5.9008 | 5.6 | 14000 | 5.9535 | 0.1515 |
94
+ | 5.9007 | 5.8 | 14500 | 5.9343 | 0.1530 |
95
+ | 5.8734 | 6.0 | 15000 | 5.9255 | 0.1532 |
96
+ | 5.8519 | 6.2 | 15500 | 5.9213 | 0.1527 |
97
+ | 5.8383 | 6.4 | 16000 | 5.9126 | 0.1513 |
98
+ | 5.8461 | 6.6 | 16500 | 5.9041 | 0.1525 |
99
+ | 5.8387 | 6.8 | 17000 | 5.8923 | 0.1517 |
100
+ | 5.831 | 7.0 | 17500 | 5.8782 | 0.1558 |
101
+ | 5.8003 | 7.2 | 18000 | 5.8660 | 0.1554 |
102
+ | 5.7832 | 7.4 | 18500 | 5.8508 | 0.1560 |
103
+ | 5.7902 | 7.6 | 19000 | 5.8495 | 0.1558 |
104
+ | 5.7707 | 7.8 | 19500 | 5.8376 | 0.1553 |
105
+ | 5.7638 | 8.0 | 20000 | 5.8289 | 0.1564 |
106
+ | 5.741 | 8.2 | 20500 | 5.8230 | 0.1574 |
107
+ | 5.7291 | 8.4 | 21000 | 5.8110 | 0.1574 |
108
+ | 5.7206 | 8.6 | 21500 | 5.8014 | 0.1575 |
109
+ | 5.6974 | 8.8 | 22000 | 5.7644 | 0.1605 |
110
+ | 5.6954 | 9.0 | 22500 | 5.7404 | 0.1638 |
111
+ | 5.6467 | 9.2 | 23000 | 5.7040 | 0.1668 |
112
+ | 5.6134 | 9.4 | 23500 | 5.6656 | 0.1738 |
113
+ | 5.5855 | 9.6 | 24000 | 5.6262 | 0.1787 |
114
+ | 5.5374 | 9.8 | 24500 | 5.5587 | 0.1883 |
115
+ | 5.4678 | 10.0 | 25000 | 5.4388 | 0.2009 |
116
+ | 5.3324 | 10.2 | 25500 | 5.2703 | 0.2203 |
117
+ | 5.1849 | 10.4 | 26000 | 5.0908 | 0.2434 |
118
+ | 5.0273 | 10.6 | 26500 | 4.9103 | 0.2657 |
119
+ | 4.8718 | 10.8 | 27000 | 4.7637 | 0.2844 |
120
+ | 4.7523 | 11.0 | 27500 | 4.6064 | 0.3023 |
121
+ | 4.5814 | 11.2 | 28000 | 4.4398 | 0.3220 |
122
+ | 4.4627 | 11.4 | 28500 | 4.3005 | 0.3376 |
123
+ | 4.3228 | 11.6 | 29000 | 4.1771 | 0.3520 |
124
+ | 4.1885 | 11.8 | 29500 | 4.0783 | 0.3632 |
125
+ | 4.0772 | 12.0 | 30000 | 3.9658 | 0.3765 |
126
+ | 3.9602 | 12.2 | 30500 | 3.8686 | 0.3880 |
127
+ | 3.8622 | 12.4 | 31000 | 3.7886 | 0.3968 |
128
+ | 3.7958 | 12.6 | 31500 | 3.6968 | 0.4074 |
129
+ | 3.7245 | 12.8 | 32000 | 3.6480 | 0.4129 |
130
+ | 3.6503 | 13.0 | 32500 | 3.5771 | 0.4204 |
131
+ | 3.5569 | 13.2 | 33000 | 3.5103 | 0.4286 |
132
+ | 3.5151 | 13.4 | 33500 | 3.4611 | 0.4358 |
133
+ | 3.4388 | 13.6 | 34000 | 3.4119 | 0.4410 |
134
+ | 3.41 | 13.8 | 34500 | 3.3570 | 0.4486 |
135
+ | 3.3447 | 14.0 | 35000 | 3.3158 | 0.4518 |
136
+ | 3.2678 | 14.2 | 35500 | 3.2717 | 0.4585 |
137
+ | 3.2395 | 14.4 | 36000 | 3.2234 | 0.4629 |
138
+ | 3.2033 | 14.6 | 36500 | 3.1723 | 0.4697 |
139
+ | 3.1739 | 14.8 | 37000 | 3.1409 | 0.4747 |
140
+ | 3.1467 | 15.0 | 37500 | 3.1042 | 0.4782 |
141
+ | 3.0736 | 15.2 | 38000 | 3.0561 | 0.4839 |
142
+ | 3.0468 | 15.4 | 38500 | 3.0275 | 0.4869 |
143
+ | 3.0105 | 15.6 | 39000 | 3.0051 | 0.4898 |
144
+ | 2.9828 | 15.8 | 39500 | 2.9689 | 0.4950 |
145
+ | 2.9523 | 16.0 | 40000 | 2.9481 | 0.4959 |
146
+ | 2.8951 | 16.2 | 40500 | 2.8918 | 0.5039 |
147
+ | 2.8614 | 16.4 | 41000 | 2.8734 | 0.5054 |
148
+ | 2.8422 | 16.6 | 41500 | 2.8487 | 0.5083 |
149
+ | 2.8184 | 16.8 | 42000 | 2.8223 | 0.5138 |
150
+ | 2.7806 | 17.0 | 42500 | 2.7965 | 0.5167 |
151
+ | 2.7356 | 17.2 | 43000 | 2.7596 | 0.5209 |
152
+ | 2.7357 | 17.4 | 43500 | 2.7407 | 0.5250 |
153
+ | 2.7015 | 17.6 | 44000 | 2.7135 | 0.5272 |
154
+ | 2.688 | 17.8 | 44500 | 2.6935 | 0.5289 |
155
+ | 2.6582 | 18.0 | 45000 | 2.6572 | 0.5342 |
156
+ | 2.6186 | 18.2 | 45500 | 2.6396 | 0.5357 |
157
+ | 2.6071 | 18.4 | 46000 | 2.6270 | 0.5377 |
158
+ | 2.5891 | 18.6 | 46500 | 2.6110 | 0.5407 |
159
+ | 2.558 | 18.8 | 47000 | 2.5874 | 0.5435 |
160
+ | 2.5521 | 19.0 | 47500 | 2.5540 | 0.5465 |
161
+ | 2.5086 | 19.2 | 48000 | 2.5296 | 0.5504 |
162
+ | 2.4933 | 19.4 | 48500 | 2.5199 | 0.5523 |
163
+ | 2.4924 | 19.6 | 49000 | 2.5037 | 0.5550 |
164
+ | 2.4633 | 19.8 | 49500 | 2.4792 | 0.5567 |
165
+ | 2.4426 | 20.0 | 50000 | 2.4724 | 0.5600 |
166
+ | 2.4106 | 20.2 | 50500 | 2.4396 | 0.5626 |
167
+ | 2.4103 | 20.4 | 51000 | 2.4259 | 0.5631 |
168
+ | 2.3783 | 20.6 | 51500 | 2.4072 | 0.5672 |
169
+ | 2.3712 | 20.8 | 52000 | 2.4055 | 0.5679 |
170
+ | 2.3616 | 21.0 | 52500 | 2.3781 | 0.5724 |
171
+ | 2.3274 | 21.2 | 53000 | 2.3627 | 0.5746 |
172
+ | 2.3133 | 21.4 | 53500 | 2.3586 | 0.5751 |
173
+ | 2.3076 | 21.6 | 54000 | 2.3207 | 0.5785 |
174
+ | 2.2991 | 21.8 | 54500 | 2.3152 | 0.5796 |
175
+ | 2.2831 | 22.0 | 55000 | 2.3001 | 0.5815 |
176
+ | 2.2461 | 22.2 | 55500 | 2.2944 | 0.5822 |
177
+ | 2.2467 | 22.4 | 56000 | 2.2849 | 0.5856 |
178
+ | 2.2199 | 22.6 | 56500 | 2.2776 | 0.5863 |
179
+ | 2.2279 | 22.8 | 57000 | 2.2577 | 0.5885 |
180
+ | 2.2048 | 23.0 | 57500 | 2.2566 | 0.5886 |
181
+ | 2.1704 | 23.2 | 58000 | 2.2453 | 0.5914 |
182
+ | 2.1682 | 23.4 | 58500 | 2.2314 | 0.5927 |
183
+ | 2.1592 | 23.6 | 59000 | 2.2097 | 0.5961 |
184
+ | 2.1547 | 23.8 | 59500 | 2.1984 | 0.5972 |
185
+ | 2.1558 | 24.0 | 60000 | 2.1866 | 0.5993 |
186
+ | 2.1189 | 24.2 | 60500 | 2.1675 | 0.6009 |
187
+ | 2.1088 | 24.4 | 61000 | 2.1613 | 0.6028 |
188
+ | 2.1164 | 24.6 | 61500 | 2.1531 | 0.6046 |
189
+ | 2.094 | 24.8 | 62000 | 2.1507 | 0.6041 |
190
+ | 2.0977 | 25.0 | 62500 | 2.1299 | 0.6063 |
191
+ | 2.0657 | 25.2 | 63000 | 2.1218 | 0.6071 |
192
+ | 2.051 | 25.4 | 63500 | 2.1233 | 0.6083 |
193
+ | 2.0482 | 25.6 | 64000 | 2.1069 | 0.6100 |
194
+ | 2.04 | 25.8 | 64500 | 2.0985 | 0.6120 |
195
+ | 2.0341 | 26.0 | 65000 | 2.0929 | 0.6128 |
196
+ | 2.0207 | 26.2 | 65500 | 2.0767 | 0.6151 |
197
+ | 2.0044 | 26.4 | 66000 | 2.0672 | 0.6162 |
198
+ | 2.0037 | 26.6 | 66500 | 2.0623 | 0.6159 |
199
+ | 2.0081 | 26.8 | 67000 | 2.0614 | 0.6164 |
200
+ | 1.9847 | 27.0 | 67500 | 2.0499 | 0.6186 |
201
+ | 1.9465 | 27.2 | 68000 | 2.0399 | 0.6200 |
202
+ | 1.9573 | 27.4 | 68500 | 2.0353 | 0.6210 |
203
+ | 1.9682 | 27.6 | 69000 | 2.0187 | 0.6227 |
204
+ | 1.9573 | 27.8 | 69500 | 2.0251 | 0.6229 |
205
+ | 1.9491 | 28.0 | 70000 | 2.0086 | 0.6245 |
206
+ | 1.903 | 28.2 | 70500 | 2.0067 | 0.6246 |
207
+ | 1.9152 | 28.4 | 71000 | 1.9929 | 0.6264 |
208
+ | 1.9188 | 28.6 | 71500 | 1.9857 | 0.6274 |
209
+ | 1.9232 | 28.8 | 72000 | 1.9796 | 0.6287 |
210
+ | 1.9011 | 29.0 | 72500 | 1.9791 | 0.6289 |
211
+ | 1.8733 | 29.2 | 73000 | 1.9700 | 0.6289 |
212
+ | 1.8731 | 29.4 | 73500 | 1.9584 | 0.6303 |
213
+ | 1.8812 | 29.6 | 74000 | 1.9573 | 0.6323 |
214
+ | 1.8674 | 29.8 | 74500 | 1.9501 | 0.6318 |
215
+ | 1.8572 | 30.0 | 75000 | 1.9454 | 0.6333 |
216
+ | 1.849 | 30.2 | 75500 | 1.9375 | 0.6352 |
217
+ | 1.8332 | 30.4 | 76000 | 1.9344 | 0.6343 |
218
+ | 1.8413 | 30.6 | 76500 | 1.9293 | 0.6340 |
219
+ | 1.8298 | 30.8 | 77000 | 1.9228 | 0.6371 |
220
+ | 1.8336 | 31.0 | 77500 | 1.9215 | 0.6372 |
221
+ | 1.8122 | 31.2 | 78000 | 1.9133 | 0.6387 |
222
+ | 1.8001 | 31.4 | 78500 | 1.9119 | 0.6383 |
223
+ | 1.7934 | 31.6 | 79000 | 1.9088 | 0.6387 |
224
+ | 1.8079 | 31.8 | 79500 | 1.8940 | 0.6417 |
225
+ | 1.8017 | 32.0 | 80000 | 1.8889 | 0.6410 |
226
+ | 1.7789 | 32.2 | 80500 | 1.8883 | 0.6423 |
227
+ | 1.7739 | 32.4 | 81000 | 1.8836 | 0.6419 |
228
+ | 1.7602 | 32.6 | 81500 | 1.8795 | 0.6433 |
229
+ | 1.7731 | 32.8 | 82000 | 1.8769 | 0.6439 |
230
+ | 1.7784 | 33.0 | 82500 | 1.8590 | 0.6467 |
231
+ | 1.7506 | 33.2 | 83000 | 1.8664 | 0.6447 |
232
+ | 1.7307 | 33.4 | 83500 | 1.8553 | 0.6472 |
233
+ | 1.748 | 33.6 | 84000 | 1.8523 | 0.6470 |
234
+ | 1.7285 | 33.8 | 84500 | 1.8397 | 0.6491 |
235
+ | 1.7426 | 34.0 | 85000 | 1.8321 | 0.6492 |
236
+ | 1.7128 | 34.2 | 85500 | 1.8220 | 0.6507 |
237
+ | 1.7155 | 34.4 | 86000 | 1.8487 | 0.6479 |
238
+ | 1.7143 | 34.6 | 86500 | 1.8267 | 0.6504 |
239
+ | 1.7197 | 34.8 | 87000 | 1.8368 | 0.6499 |
240
+ | 1.7043 | 35.0 | 87500 | 1.8128 | 0.6524 |
241
+ | 1.6931 | 35.2 | 88000 | 1.8212 | 0.6517 |
242
+ | 1.6873 | 35.4 | 88500 | 1.8110 | 0.6531 |
243
+ | 1.684 | 35.6 | 89000 | 1.8145 | 0.6529 |
244
+ | 1.6802 | 35.8 | 89500 | 1.8046 | 0.6537 |
245
+ | 1.6807 | 36.0 | 90000 | 1.8016 | 0.6550 |
246
+ | 1.6612 | 36.2 | 90500 | 1.7997 | 0.6539 |
247
+ | 1.6586 | 36.4 | 91000 | 1.8014 | 0.6537 |
248
+ | 1.658 | 36.6 | 91500 | 1.7938 | 0.6565 |
249
+ | 1.6623 | 36.8 | 92000 | 1.7776 | 0.6586 |
250
+ | 1.6618 | 37.0 | 92500 | 1.7884 | 0.6573 |
251
+ | 1.6453 | 37.2 | 93000 | 1.7871 | 0.6571 |
252
+ | 1.6462 | 37.4 | 93500 | 1.7781 | 0.6585 |
253
+ | 1.6353 | 37.6 | 94000 | 1.7808 | 0.6583 |
254
+ | 1.6507 | 37.8 | 94500 | 1.7666 | 0.6603 |
255
+ | 1.6383 | 38.0 | 95000 | 1.7624 | 0.6606 |
256
+ | 1.6299 | 38.2 | 95500 | 1.7653 | 0.6605 |
257
+ | 1.6085 | 38.4 | 96000 | 1.7523 | 0.6610 |
258
+ | 1.6155 | 38.6 | 96500 | 1.7521 | 0.6612 |
259
+ | 1.6106 | 38.8 | 97000 | 1.7634 | 0.6605 |
260
+ | 1.6201 | 39.0 | 97500 | 1.7461 | 0.6625 |
261
+ | 1.5835 | 39.2 | 98000 | 1.7505 | 0.6617 |
262
+ | 1.5885 | 39.4 | 98500 | 1.7477 | 0.6623 |
263
+ | 1.5988 | 39.6 | 99000 | 1.7445 | 0.6635 |
264
+ | 1.6013 | 39.8 | 99500 | 1.7407 | 0.6637 |
265
+ | 1.594 | 40.0 | 100000 | 1.7336 | 0.6656 |
266
+ | 1.5741 | 40.2 | 100500 | 1.7348 | 0.6637 |
267
+ | 1.5744 | 40.4 | 101000 | 1.7242 | 0.6653 |
268
+ | 1.5809 | 40.6 | 101500 | 1.7262 | 0.6661 |
269
+ | 1.5723 | 40.8 | 102000 | 1.7257 | 0.6665 |
270
+ | 1.5695 | 41.0 | 102500 | 1.7182 | 0.6664 |
271
+ | 1.5462 | 41.2 | 103000 | 1.7257 | 0.6660 |
272
+ | 1.5545 | 41.4 | 103500 | 1.7101 | 0.6686 |
273
+ | 1.5574 | 41.6 | 104000 | 1.7108 | 0.6684 |
274
+ | 1.5485 | 41.8 | 104500 | 1.7164 | 0.6665 |
275
+ | 1.5487 | 42.0 | 105000 | 1.7080 | 0.6694 |
276
+ | 1.5278 | 42.2 | 105500 | 1.7092 | 0.6686 |
277
+ | 1.5282 | 42.4 | 106000 | 1.7052 | 0.6690 |
278
+ | 1.5468 | 42.6 | 106500 | 1.7058 | 0.6704 |
279
+ | 1.5375 | 42.8 | 107000 | 1.7020 | 0.6689 |
280
+ | 1.5301 | 43.0 | 107500 | 1.6950 | 0.6710 |
281
+ | 1.5224 | 43.2 | 108000 | 1.6990 | 0.6702 |
282
+ | 1.5105 | 43.4 | 108500 | 1.6919 | 0.6715 |
283
+ | 1.5179 | 43.6 | 109000 | 1.6845 | 0.6724 |
284
+ | 1.518 | 43.8 | 109500 | 1.6838 | 0.6721 |
285
+ | 1.5191 | 44.0 | 110000 | 1.6877 | 0.6715 |
286
+ | 1.4984 | 44.2 | 110500 | 1.6923 | 0.6712 |
287
+ | 1.5051 | 44.4 | 111000 | 1.6842 | 0.6722 |
288
+ | 1.4993 | 44.6 | 111500 | 1.6768 | 0.6741 |
289
+ | 1.5035 | 44.8 | 112000 | 1.6817 | 0.6727 |
290
+ | 1.5047 | 45.0 | 112500 | 1.6728 | 0.6733 |
291
+ | 1.4788 | 45.2 | 113000 | 1.6825 | 0.6720 |
292
+ | 1.4841 | 45.4 | 113500 | 1.6770 | 0.6735 |
293
+ | 1.4863 | 45.6 | 114000 | 1.6588 | 0.6753 |
294
+ | 1.4859 | 45.8 | 114500 | 1.6681 | 0.6741 |
295
+ | 1.4839 | 46.0 | 115000 | 1.6658 | 0.6740 |
296
+ | 1.4633 | 46.2 | 115500 | 1.6601 | 0.6765 |
297
+ | 1.4725 | 46.4 | 116000 | 1.6587 | 0.6753 |
298
+ | 1.4703 | 46.6 | 116500 | 1.6643 | 0.6756 |
299
+ | 1.4763 | 46.8 | 117000 | 1.6583 | 0.6759 |
300
+ | 1.4825 | 47.0 | 117500 | 1.6488 | 0.6766 |
301
+ | 1.4496 | 47.2 | 118000 | 1.6490 | 0.6772 |
302
+ | 1.457 | 47.4 | 118500 | 1.6462 | 0.6778 |
303
+ | 1.4541 | 47.6 | 119000 | 1.6368 | 0.6799 |
304
+ | 1.4561 | 47.8 | 119500 | 1.6404 | 0.6778 |
305
+ | 1.4547 | 48.0 | 120000 | 1.6385 | 0.6790 |
306
+ | 1.4406 | 48.2 | 120500 | 1.6374 | 0.6799 |
307
+ | 1.4374 | 48.4 | 121000 | 1.6319 | 0.6799 |
308
+ | 1.4395 | 48.6 | 121500 | 1.6425 | 0.6787 |
309
+ | 1.4347 | 48.8 | 122000 | 1.6252 | 0.6814 |
310
+ | 1.4392 | 49.0 | 122500 | 1.6360 | 0.6801 |
311
+ | 1.439 | 49.2 | 123000 | 1.6233 | 0.6826 |
312
+ | 1.4223 | 49.4 | 123500 | 1.6262 | 0.6809 |
313
+ | 1.4292 | 49.6 | 124000 | 1.6292 | 0.6811 |
314
+ | 1.4237 | 49.8 | 124500 | 1.6227 | 0.6812 |
315
+ | 1.4241 | 50.0 | 125000 | 1.6230 | 0.6810 |
316
+ | 1.4118 | 50.2 | 125500 | 1.6256 | 0.6822 |
317
+ | 1.4225 | 50.4 | 126000 | 1.6251 | 0.6817 |
318
+ | 1.4122 | 50.6 | 126500 | 1.6178 | 0.6827 |
319
+ | 1.4081 | 50.8 | 127000 | 1.6190 | 0.6813 |
320
+ | 1.4058 | 51.0 | 127500 | 1.6183 | 0.6836 |
321
+ | 1.3985 | 51.2 | 128000 | 1.6199 | 0.6817 |
322
+ | 1.3967 | 51.4 | 128500 | 1.6168 | 0.6829 |
323
+ | 1.4113 | 51.6 | 129000 | 1.6123 | 0.6832 |
324
+ | 1.3876 | 51.8 | 129500 | 1.6078 | 0.6841 |
325
+ | 1.4027 | 52.0 | 130000 | 1.6028 | 0.6847 |
326
+ | 1.3939 | 52.2 | 130500 | 1.6081 | 0.6845 |
327
+ | 1.391 | 52.4 | 131000 | 1.6034 | 0.6849 |
328
+ | 1.3895 | 52.6 | 131500 | 1.6016 | 0.6850 |
329
+ | 1.3858 | 52.8 | 132000 | 1.6010 | 0.6847 |
330
+ | 1.3852 | 53.0 | 132500 | 1.5886 | 0.6862 |
331
+ | 1.3716 | 53.2 | 133000 | 1.5964 | 0.6862 |
332
+ | 1.3727 | 53.4 | 133500 | 1.5952 | 0.6875 |
333
+ | 1.3656 | 53.6 | 134000 | 1.6031 | 0.6850 |
334
+ | 1.3873 | 53.8 | 134500 | 1.5927 | 0.6867 |
335
+ | 1.3742 | 54.0 | 135000 | 1.5970 | 0.6858 |
336
+ | 1.3687 | 54.2 | 135500 | 1.5954 | 0.6863 |
337
+ | 1.359 | 54.4 | 136000 | 1.5854 | 0.6873 |
338
+ | 1.3696 | 54.6 | 136500 | 1.5902 | 0.6878 |
339
+ | 1.38 | 54.8 | 137000 | 1.5870 | 0.6871 |
340
+ | 1.3529 | 55.0 | 137500 | 1.5888 | 0.6879 |
341
+ | 1.3479 | 55.2 | 138000 | 1.5720 | 0.6889 |
342
+ | 1.3558 | 55.4 | 138500 | 1.5810 | 0.6877 |
343
+ | 1.3565 | 55.6 | 139000 | 1.5687 | 0.6909 |
344
+ | 1.351 | 55.8 | 139500 | 1.5762 | 0.6897 |
345
+ | 1.3698 | 56.0 | 140000 | 1.5785 | 0.6881 |
346
+ | 1.3388 | 56.2 | 140500 | 1.5767 | 0.6882 |
347
+ | 1.3433 | 56.4 | 141000 | 1.5752 | 0.6896 |
348
+ | 1.3505 | 56.6 | 141500 | 1.5754 | 0.6890 |
349
+ | 1.3429 | 56.8 | 142000 | 1.5772 | 0.6896 |
350
+ | 1.337 | 57.0 | 142500 | 1.5732 | 0.6900 |
351
+ | 1.3398 | 57.2 | 143000 | 1.5681 | 0.6904 |
352
+ | 1.3334 | 57.4 | 143500 | 1.5696 | 0.6900 |
353
+ | 1.3384 | 57.6 | 144000 | 1.5674 | 0.6908 |
354
+ | 1.33 | 57.8 | 144500 | 1.5592 | 0.6916 |
355
+ | 1.327 | 58.0 | 145000 | 1.5498 | 0.6924 |
356
+ | 1.3234 | 58.2 | 145500 | 1.5626 | 0.6910 |
357
+ | 1.3266 | 58.4 | 146000 | 1.5743 | 0.6893 |
358
+ | 1.3152 | 58.6 | 146500 | 1.5680 | 0.6912 |
359
+ | 1.3279 | 58.8 | 147000 | 1.5581 | 0.6919 |
360
+ | 1.3172 | 59.0 | 147500 | 1.5645 | 0.6917 |
361
+ | 1.3073 | 59.2 | 148000 | 1.5579 | 0.6924 |
362
+ | 1.307 | 59.4 | 148500 | 1.5468 | 0.6939 |
363
+ | 1.3164 | 59.6 | 149000 | 1.5519 | 0.6930 |
364
+ | 1.3037 | 59.8 | 149500 | 1.5628 | 0.6917 |
365
+ | 1.3171 | 60.0 | 150000 | 1.5489 | 0.6934 |
366
+ | 1.3035 | 60.2 | 150500 | 1.5499 | 0.6931 |
367
+ | 1.3109 | 60.4 | 151000 | 1.5608 | 0.6922 |
368
+ | 1.304 | 60.6 | 151500 | 1.5612 | 0.6915 |
369
+ | 1.3104 | 60.8 | 152000 | 1.5511 | 0.6933 |
370
+ | 1.3071 | 61.0 | 152500 | 1.5469 | 0.6935 |
371
+ | 1.2935 | 61.2 | 153000 | 1.5485 | 0.6942 |
372
+ | 1.2866 | 61.4 | 153500 | 1.5463 | 0.6940 |
373
+ | 1.2926 | 61.6 | 154000 | 1.5406 | 0.6956 |
374
+ | 1.3029 | 61.8 | 154500 | 1.5424 | 0.6945 |
375
+ | 1.2921 | 62.0 | 155000 | 1.5446 | 0.6944 |
376
+ | 1.2765 | 62.2 | 155500 | 1.5397 | 0.6953 |
377
+ | 1.275 | 62.4 | 156000 | 1.5469 | 0.6945 |
378
+ | 1.2909 | 62.6 | 156500 | 1.5427 | 0.6945 |
379
+ | 1.2869 | 62.8 | 157000 | 1.5388 | 0.6949 |
380
+ | 1.2883 | 63.0 | 157500 | 1.5375 | 0.6948 |
381
+ | 1.2673 | 63.2 | 158000 | 1.5423 | 0.6948 |
382
+ | 1.2754 | 63.4 | 158500 | 1.5360 | 0.6957 |
383
+ | 1.2772 | 63.6 | 159000 | 1.5331 | 0.6952 |
384
+ | 1.283 | 63.8 | 159500 | 1.5354 | 0.6955 |
385
+ | 1.2737 | 64.0 | 160000 | 1.5388 | 0.6961 |
386
+ | 1.2681 | 64.2 | 160500 | 1.5382 | 0.6952 |
387
+ | 1.2769 | 64.4 | 161000 | 1.5350 | 0.6958 |
388
+ | 1.2668 | 64.6 | 161500 | 1.5345 | 0.6956 |
389
+ | 1.2795 | 64.8 | 162000 | 1.5198 | 0.6984 |
390
+ | 1.2632 | 65.0 | 162500 | 1.5324 | 0.6965 |
391
+ | 1.2646 | 65.2 | 163000 | 1.5420 | 0.6963 |
392
+ | 1.2739 | 65.4 | 163500 | 1.5308 | 0.6972 |
393
+ | 1.2667 | 65.6 | 164000 | 1.5220 | 0.6978 |
394
+ | 1.26 | 65.8 | 164500 | 1.5283 | 0.6961 |
395
+ | 1.2714 | 66.0 | 165000 | 1.5235 | 0.6977 |
396
+ | 1.2652 | 66.2 | 165500 | 1.5270 | 0.6973 |
397
+ | 1.2554 | 66.4 | 166000 | 1.5356 | 0.6959 |
398
+ | 1.2666 | 66.6 | 166500 | 1.5231 | 0.6968 |
399
+ | 1.2634 | 66.8 | 167000 | 1.5170 | 0.6994 |
400
+ | 1.2485 | 67.0 | 167500 | 1.5205 | 0.6988 |
401
+ | 1.2397 | 67.2 | 168000 | 1.5263 | 0.6982 |
402
+ | 1.2416 | 67.4 | 168500 | 1.5133 | 0.7001 |
403
+ | 1.2615 | 67.6 | 169000 | 1.5150 | 0.6990 |
404
+ | 1.254 | 67.8 | 169500 | 1.5213 | 0.6990 |
405
+ | 1.2463 | 68.0 | 170000 | 1.5157 | 0.6995 |
406
+ | 1.2412 | 68.2 | 170500 | 1.5082 | 0.7000 |
407
+ | 1.248 | 68.4 | 171000 | 1.5168 | 0.6992 |
408
+ | 1.2468 | 68.6 | 171500 | 1.5187 | 0.6991 |
409
+ | 1.246 | 68.8 | 172000 | 1.5094 | 0.7001 |
410
+ | 1.2443 | 69.0 | 172500 | 1.5186 | 0.6984 |
411
+ | 1.2451 | 69.2 | 173000 | 1.5157 | 0.6988 |
412
+ | 1.2375 | 69.4 | 173500 | 1.5102 | 0.7002 |
413
+ | 1.2441 | 69.6 | 174000 | 1.5143 | 0.7000 |
414
+ | 1.2335 | 69.8 | 174500 | 1.5173 | 0.6985 |
415
+ | 1.2361 | 70.0 | 175000 | 1.5102 | 0.7001 |
416
+ | 1.23 | 70.2 | 175500 | 1.5155 | 0.6997 |
417
+ | 1.2401 | 70.4 | 176000 | 1.5027 | 0.7005 |
418
+ | 1.2346 | 70.6 | 176500 | 1.5123 | 0.6995 |
419
+ | 1.2306 | 70.8 | 177000 | 1.5151 | 0.6984 |
420
+ | 1.2333 | 71.0 | 177500 | 1.5125 | 0.7000 |
421
+ | 1.2248 | 71.2 | 178000 | 1.5199 | 0.6992 |
422
+ | 1.2385 | 71.4 | 178500 | 1.5108 | 0.7000 |
423
+ | 1.2278 | 71.6 | 179000 | 1.5092 | 0.7000 |
424
+ | 1.2278 | 71.8 | 179500 | 1.5163 | 0.6989 |
425
+ | 1.2242 | 72.0 | 180000 | 1.5056 | 0.7010 |
426
+ | 1.2208 | 72.2 | 180500 | 1.4968 | 0.7023 |
427
+ | 1.2216 | 72.4 | 181000 | 1.5097 | 0.7006 |
428
+ | 1.2271 | 72.6 | 181500 | 1.4988 | 0.7013 |
429
+ | 1.2302 | 72.8 | 182000 | 1.5141 | 0.6997 |
430
+ | 1.2268 | 73.0 | 182500 | 1.4996 | 0.7016 |
431
+ | 1.2258 | 73.2 | 183000 | 1.5016 | 0.7008 |
432
+ | 1.2244 | 73.4 | 183500 | 1.5032 | 0.7012 |
433
+ | 1.2117 | 73.6 | 184000 | 1.5097 | 0.7003 |
434
+ | 1.2279 | 73.8 | 184500 | 1.5058 | 0.7012 |
435
+ | 1.2274 | 74.0 | 185000 | 1.5030 | 0.7015 |
436
+ | 1.2117 | 74.2 | 185500 | 1.5086 | 0.7008 |
437
+ | 1.2223 | 74.4 | 186000 | 1.4998 | 0.7018 |
438
+ | 1.227 | 74.6 | 186500 | 1.5059 | 0.7014 |
439
+ | 1.2168 | 74.8 | 187000 | 1.4984 | 0.7011 |
440
+ | 1.2093 | 75.0 | 187500 | 1.5077 | 0.7018 |
441
+
442
+
443
+ ### Framework versions
444
+
445
+ - Transformers 4.25.1
446
+ - Pytorch 1.13.1+cu117
447
+ - Datasets 2.11.0
448
+ - Tokenizers 0.13.2
all_results.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 75.0,
3
+ "eval_accuracy": 0.701455194792215,
4
+ "eval_loss": 1.4969074726104736,
5
+ "eval_runtime": 232.9475,
6
+ "eval_samples": 5000,
7
+ "eval_samples_per_second": 21.464,
8
+ "eval_steps_per_second": 2.683,
9
+ "perplexity": 4.467850732884341,
10
+ "train_loss": 2.3812346901041668,
11
+ "train_runtime": 293209.3669,
12
+ "train_samples": 20000,
13
+ "train_samples_per_second": 5.116,
14
+ "train_steps_per_second": 0.639
15
+ }
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "RobertaForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": null,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 514,
16
+ "model_type": "roberta",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 1,
20
+ "position_embedding_type": "absolute",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.25.1",
23
+ "type_vocab_size": 2,
24
+ "use_cache": true,
25
+ "vocab_size": 50265
26
+ }
eval_results.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 75.0,
3
+ "eval_accuracy": 0.701455194792215,
4
+ "eval_loss": 1.4969074726104736,
5
+ "eval_runtime": 232.9475,
6
+ "eval_samples": 5000,
7
+ "eval_samples_per_second": 21.464,
8
+ "eval_steps_per_second": 2.683,
9
+ "perplexity": 4.467850732884341
10
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f350bd2256bb4a5e7ca9c888e9323f161b4311131001699ae896c3a78ac68a5
3
+ size 498866489
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<s>",
4
+ "cls_token": "<s>",
5
+ "eos_token": "</s>",
6
+ "errors": "replace",
7
+ "mask_token": {
8
+ "__type": "AddedToken",
9
+ "content": "<mask>",
10
+ "lstrip": true,
11
+ "normalized": false,
12
+ "rstrip": false,
13
+ "single_word": false
14
+ },
15
+ "model_max_length": 512,
16
+ "name_or_path": "chatgpt_tokenizer/",
17
+ "pad_token": "<pad>",
18
+ "sep_token": "</s>",
19
+ "special_tokens_map_file": null,
20
+ "tokenizer_class": "RobertaTokenizer",
21
+ "trim_offsets": true,
22
+ "unk_token": "<unk>"
23
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 75.0,
3
+ "train_loss": 2.3812346901041668,
4
+ "train_runtime": 293209.3669,
5
+ "train_samples": 20000,
6
+ "train_samples_per_second": 5.116,
7
+ "train_steps_per_second": 0.639
8
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9622e9d8fb015c7dd5186c4a8249458402d4bb66d08e920ead015b4a7f0acdb8
3
+ size 3451
vocab.json ADDED
The diff for this file is too large to render. See raw diff