Hugging Face's logo

DouglasPontes
/
2020-Q2-90p-filtered

Fill-Mask
Transformers
PyTorch
roberta
Generated from Trainer
Inference Endpoints
Model card Files Community
DouglasPontes commited on
Commit
b1c47ca
·
verified ·
1 Parent(s): 7bd5974

Model save

Browse files
Files changed (2) hide show
  1. README.md +356 -0
  2. pytorch_model.bin +1 -1
README.md ADDED
@@ -0,0 +1,356 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: cardiffnlp/twitter-roberta-base-2019-90m
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: 2020-Q2-90p-filtered
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # 2020-Q2-90p-filtered
15
+
16
+ This model is a fine-tuned version of [cardiffnlp/twitter-roberta-base-2019-90m](https://huggingface.co/cardiffnlp/twitter-roberta-base-2019-90m) on an unknown dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 3.5386
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 4.1e-07
38
+ - train_batch_size: 16
39
+ - eval_batch_size: 16
40
+ - seed: 42
41
+ - optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-08
42
+ - lr_scheduler_type: linear
43
+ - training_steps: 2400000
44
+
45
+ ### Training results
46
+
47
+ | Training Loss | Epoch | Step | Validation Loss |
48
+ |:-------------:|:-----:|:-------:|:---------------:|
49
+ | No log | 0.17 | 8000 | 4.0640 |
50
+ | 4.2654 | 0.34 | 16000 | 3.9414 |
51
+ | 4.2654 | 0.51 | 24000 | 3.8956 |
52
+ | 4.0459 | 0.67 | 32000 | 3.8527 |
53
+ | 4.0459 | 0.84 | 40000 | 3.8232 |
54
+ | 3.9781 | 1.01 | 48000 | 3.7806 |
55
+ | 3.9781 | 1.18 | 56000 | 3.7861 |
56
+ | 3.9323 | 1.35 | 64000 | 3.7930 |
57
+ | 3.9323 | 1.52 | 72000 | 3.7814 |
58
+ | 3.9224 | 1.68 | 80000 | 3.7815 |
59
+ | 3.9224 | 1.85 | 88000 | 3.7403 |
60
+ | 3.8924 | 2.02 | 96000 | 3.7468 |
61
+ | 3.8924 | 2.19 | 104000 | 3.7400 |
62
+ | 3.879 | 2.36 | 112000 | 3.7283 |
63
+ | 3.879 | 2.53 | 120000 | 3.7381 |
64
+ | 3.8806 | 2.69 | 128000 | 3.7073 |
65
+ | 3.8806 | 2.86 | 136000 | 3.7083 |
66
+ | 3.8659 | 3.03 | 144000 | 3.6992 |
67
+ | 3.8659 | 3.2 | 152000 | 3.6956 |
68
+ | 3.8634 | 3.37 | 160000 | 3.6745 |
69
+ | 3.8634 | 3.54 | 168000 | 3.7017 |
70
+ | 3.8632 | 3.71 | 176000 | 3.6960 |
71
+ | 3.8632 | 3.87 | 184000 | 3.7202 |
72
+ | 3.8416 | 4.04 | 192000 | 3.7109 |
73
+ | 3.8416 | 4.21 | 200000 | 3.6942 |
74
+ | 3.8368 | 4.38 | 208000 | 3.6944 |
75
+ | 3.8368 | 4.55 | 216000 | 3.6751 |
76
+ | 3.8359 | 4.72 | 224000 | 3.6815 |
77
+ | 3.8359 | 4.88 | 232000 | 3.6915 |
78
+ | 3.8411 | 5.05 | 240000 | 3.6796 |
79
+ | 3.8411 | 5.22 | 248000 | 3.6847 |
80
+ | 3.8359 | 5.39 | 256000 | 3.6988 |
81
+ | 3.8359 | 5.56 | 264000 | 3.6799 |
82
+ | 3.8268 | 5.73 | 272000 | 3.6810 |
83
+ | 3.8268 | 5.89 | 280000 | 3.6639 |
84
+ | 3.8172 | 6.06 | 288000 | 3.6663 |
85
+ | 3.8172 | 6.23 | 296000 | 3.6838 |
86
+ | 3.8263 | 6.4 | 304000 | 3.6756 |
87
+ | 3.8263 | 6.57 | 312000 | 3.6507 |
88
+ | 3.8215 | 6.74 | 320000 | 3.6409 |
89
+ | 3.8215 | 6.91 | 328000 | 3.6790 |
90
+ | 3.8189 | 7.07 | 336000 | 3.6679 |
91
+ | 3.8189 | 7.24 | 344000 | 3.6443 |
92
+ | 3.8155 | 7.41 | 352000 | 3.6588 |
93
+ | 3.8155 | 7.58 | 360000 | 3.6448 |
94
+ | 3.8075 | 7.75 | 368000 | 3.6520 |
95
+ | 3.8075 | 7.92 | 376000 | 3.6541 |
96
+ | 3.8064 | 8.08 | 384000 | 3.6569 |
97
+ | 3.8064 | 8.25 | 392000 | 3.6586 |
98
+ | 3.8092 | 8.42 | 400000 | 3.6701 |
99
+ | 3.8092 | 8.59 | 408000 | 3.6544 |
100
+ | 3.8032 | 8.76 | 416000 | 3.6668 |
101
+ | 3.8032 | 8.93 | 424000 | 3.6631 |
102
+ | 3.8062 | 9.09 | 432000 | 3.6481 |
103
+ | 3.8062 | 9.26 | 440000 | 3.6392 |
104
+ | 3.7987 | 9.43 | 448000 | 3.6482 |
105
+ | 3.7987 | 9.6 | 456000 | 3.6357 |
106
+ | 3.7954 | 9.77 | 464000 | 3.6333 |
107
+ | 3.7954 | 9.94 | 472000 | 3.6653 |
108
+ | 3.7938 | 10.11 | 480000 | 3.6267 |
109
+ | 3.7938 | 10.27 | 488000 | 3.6490 |
110
+ | 3.7901 | 10.44 | 496000 | 3.6417 |
111
+ | 3.7901 | 10.61 | 504000 | 3.6263 |
112
+ | 3.7935 | 10.78 | 512000 | 3.6523 |
113
+ | 3.7935 | 10.95 | 520000 | 3.6444 |
114
+ | 3.7951 | 11.12 | 528000 | 3.6226 |
115
+ | 3.7951 | 11.28 | 536000 | 3.6347 |
116
+ | 3.7861 | 11.45 | 544000 | 3.6372 |
117
+ | 3.7861 | 11.62 | 552000 | 3.6163 |
118
+ | 3.7846 | 11.79 | 560000 | 3.6299 |
119
+ | 3.7846 | 11.96 | 568000 | 3.6330 |
120
+ | 3.7778 | 12.13 | 576000 | 3.6371 |
121
+ | 3.7778 | 12.29 | 584000 | 3.6343 |
122
+ | 3.777 | 12.46 | 592000 | 3.6242 |
123
+ | 3.777 | 12.63 | 600000 | 3.6119 |
124
+ | 3.778 | 12.8 | 608000 | 3.6167 |
125
+ | 3.778 | 12.97 | 616000 | 3.6191 |
126
+ | 3.7795 | 13.14 | 624000 | 3.6225 |
127
+ | 3.7795 | 13.3 | 632000 | 3.6056 |
128
+ | 3.7766 | 13.47 | 640000 | 3.6135 |
129
+ | 3.7766 | 13.64 | 648000 | 3.6169 |
130
+ | 3.7729 | 13.81 | 656000 | 3.6035 |
131
+ | 3.7729 | 13.98 | 664000 | 3.6109 |
132
+ | 3.7846 | 14.15 | 672000 | 3.6180 |
133
+ | 3.7846 | 14.32 | 680000 | 3.6171 |
134
+ | 3.7726 | 14.48 | 688000 | 3.6182 |
135
+ | 3.7726 | 14.65 | 696000 | 3.6086 |
136
+ | 3.7717 | 14.82 | 704000 | 3.5852 |
137
+ | 3.7717 | 14.99 | 712000 | 3.5883 |
138
+ | 3.7713 | 15.16 | 720000 | 3.6056 |
139
+ | 3.7713 | 15.33 | 728000 | 3.6004 |
140
+ | 3.7745 | 15.49 | 736000 | 3.6059 |
141
+ | 3.7745 | 15.66 | 744000 | 3.6156 |
142
+ | 3.7557 | 15.83 | 752000 | 3.6029 |
143
+ | 3.7557 | 16.0 | 760000 | 3.6099 |
144
+ | 3.7628 | 16.17 | 768000 | 3.6016 |
145
+ | 3.7628 | 16.34 | 776000 | 3.6008 |
146
+ | 3.7717 | 16.5 | 784000 | 3.5972 |
147
+ | 3.7717 | 16.67 | 792000 | 3.5838 |
148
+ | 3.7616 | 16.84 | 800000 | 3.5868 |
149
+ | 3.7616 | 17.01 | 808000 | 3.5834 |
150
+ | 3.7608 | 17.18 | 816000 | 3.6066 |
151
+ | 3.7608 | 17.35 | 824000 | 3.5911 |
152
+ | 3.7625 | 17.52 | 832000 | 3.5997 |
153
+ | 3.7625 | 17.68 | 840000 | 3.5855 |
154
+ | 3.7634 | 17.85 | 848000 | 3.5861 |
155
+ | 3.7634 | 18.02 | 856000 | 3.6021 |
156
+ | 3.75 | 18.19 | 864000 | 3.5966 |
157
+ | 3.75 | 18.36 | 872000 | 3.5761 |
158
+ | 3.7492 | 18.53 | 880000 | 3.5757 |
159
+ | 3.7492 | 18.69 | 888000 | 3.6123 |
160
+ | 3.7522 | 18.86 | 896000 | 3.5841 |
161
+ | 3.7522 | 19.03 | 904000 | 3.5831 |
162
+ | 3.7482 | 19.2 | 912000 | 3.5860 |
163
+ | 3.7482 | 19.37 | 920000 | 3.5804 |
164
+ | 3.75 | 19.54 | 928000 | 3.5730 |
165
+ | 3.75 | 19.7 | 936000 | 3.5955 |
166
+ | 3.755 | 19.87 | 944000 | 3.5868 |
167
+ | 3.755 | 20.04 | 952000 | 3.5992 |
168
+ | 3.7549 | 20.21 | 960000 | 3.5657 |
169
+ | 3.7549 | 20.38 | 968000 | 3.5780 |
170
+ | 3.743 | 20.55 | 976000 | 3.5828 |
171
+ | 3.743 | 20.72 | 984000 | 3.5676 |
172
+ | 3.75 | 20.88 | 992000 | 3.5724 |
173
+ | 3.75 | 21.05 | 1000000 | 3.5850 |
174
+ | 3.7483 | 21.22 | 1008000 | 3.5873 |
175
+ | 3.7483 | 21.39 | 1016000 | 3.5799 |
176
+ | 3.7523 | 21.56 | 1024000 | 3.5974 |
177
+ | 3.7523 | 21.73 | 1032000 | 3.5790 |
178
+ | 3.7458 | 21.89 | 1040000 | 3.5884 |
179
+ | 3.7458 | 22.06 | 1048000 | 3.5904 |
180
+ | 3.7498 | 22.23 | 1056000 | 3.5851 |
181
+ | 3.7498 | 22.4 | 1064000 | 3.5776 |
182
+ | 3.7496 | 22.57 | 1072000 | 3.5685 |
183
+ | 3.7496 | 22.74 | 1080000 | 3.5731 |
184
+ | 3.7395 | 22.9 | 1088000 | 3.5858 |
185
+ | 3.7395 | 23.07 | 1096000 | 3.5931 |
186
+ | 3.7466 | 23.24 | 1104000 | 3.5614 |
187
+ | 3.7466 | 23.41 | 1112000 | 3.5456 |
188
+ | 3.7503 | 23.58 | 1120000 | 3.5895 |
189
+ | 3.7503 | 23.75 | 1128000 | 3.5608 |
190
+ | 3.7484 | 23.92 | 1136000 | 3.5696 |
191
+ | 3.7484 | 24.08 | 1144000 | 3.5653 |
192
+ | 3.7435 | 24.25 | 1152000 | 3.5721 |
193
+ | 3.7435 | 24.42 | 1160000 | 3.5510 |
194
+ | 3.7348 | 24.59 | 1168000 | 3.5631 |
195
+ | 3.7348 | 24.76 | 1176000 | 3.5727 |
196
+ | 3.7341 | 24.93 | 1184000 | 3.5835 |
197
+ | 3.7341 | 25.09 | 1192000 | 3.5766 |
198
+ | 3.7435 | 25.26 | 1200000 | 3.5606 |
199
+ | 3.7435 | 25.43 | 1208000 | 3.5497 |
200
+ | 3.732 | 25.6 | 1216000 | 3.5433 |
201
+ | 3.732 | 25.77 | 1224000 | 3.5420 |
202
+ | 3.7343 | 25.94 | 1232000 | 3.5987 |
203
+ | 3.7343 | 26.1 | 1240000 | 3.5956 |
204
+ | 3.7336 | 26.27 | 1248000 | 3.5673 |
205
+ | 3.7336 | 26.44 | 1256000 | 3.5643 |
206
+ | 3.7444 | 26.61 | 1264000 | 3.5848 |
207
+ | 3.7444 | 26.78 | 1272000 | 3.5693 |
208
+ | 3.7395 | 26.95 | 1280000 | 3.5745 |
209
+ | 3.7395 | 27.12 | 1288000 | 3.5758 |
210
+ | 3.7389 | 27.28 | 1296000 | 3.5685 |
211
+ | 3.7389 | 27.45 | 1304000 | 3.5712 |
212
+ | 3.7416 | 27.62 | 1312000 | 3.5693 |
213
+ | 3.7416 | 27.79 | 1320000 | 3.5740 |
214
+ | 3.7305 | 27.96 | 1328000 | 3.5803 |
215
+ | 3.7305 | 28.13 | 1336000 | 3.5682 |
216
+ | 3.7268 | 28.29 | 1344000 | 3.5928 |
217
+ | 3.7268 | 28.46 | 1352000 | 3.5608 |
218
+ | 3.7363 | 28.63 | 1360000 | 3.5587 |
219
+ | 3.7363 | 28.8 | 1368000 | 3.5603 |
220
+ | 3.7325 | 28.97 | 1376000 | 3.5711 |
221
+ | 3.7325 | 29.14 | 1384000 | 3.5828 |
222
+ | 3.7337 | 29.3 | 1392000 | 3.5790 |
223
+ | 3.7337 | 29.47 | 1400000 | 3.5795 |
224
+ | 3.7367 | 29.64 | 1408000 | 3.5528 |
225
+ | 3.7367 | 29.81 | 1416000 | 3.5766 |
226
+ | 3.7313 | 29.98 | 1424000 | 3.5610 |
227
+ | 3.7313 | 30.15 | 1432000 | 3.5834 |
228
+ | 3.7277 | 30.32 | 1440000 | 3.5546 |
229
+ | 3.7277 | 30.48 | 1448000 | 3.5534 |
230
+ | 3.7296 | 30.65 | 1456000 | 3.5646 |
231
+ | 3.7296 | 30.82 | 1464000 | 3.5436 |
232
+ | 3.7411 | 30.99 | 1472000 | 3.5778 |
233
+ | 3.7411 | 31.16 | 1480000 | 3.5541 |
234
+ | 3.7233 | 31.33 | 1488000 | 3.5720 |
235
+ | 3.7233 | 31.49 | 1496000 | 3.5567 |
236
+ | 3.7291 | 31.66 | 1504000 | 3.5477 |
237
+ | 3.7291 | 31.83 | 1512000 | 3.5557 |
238
+ | 3.7265 | 32.0 | 1520000 | 3.5643 |
239
+ | 3.7265 | 32.17 | 1528000 | 3.5739 |
240
+ | 3.7352 | 32.34 | 1536000 | 3.5628 |
241
+ | 3.7352 | 32.5 | 1544000 | 3.5542 |
242
+ | 3.7353 | 32.67 | 1552000 | 3.5496 |
243
+ | 3.7353 | 32.84 | 1560000 | 3.5737 |
244
+ | 3.7243 | 33.01 | 1568000 | 3.5788 |
245
+ | 3.7243 | 33.18 | 1576000 | 3.5631 |
246
+ | 3.7192 | 33.35 | 1584000 | 3.5438 |
247
+ | 3.7192 | 33.52 | 1592000 | 3.5554 |
248
+ | 3.7266 | 33.68 | 1600000 | 3.5748 |
249
+ | 3.7266 | 33.85 | 1608000 | 3.5620 |
250
+ | 3.73 | 34.02 | 1616000 | 3.5464 |
251
+ | 3.73 | 34.19 | 1624000 | 3.5670 |
252
+ | 3.7264 | 34.36 | 1632000 | 3.5626 |
253
+ | 3.7264 | 34.53 | 1640000 | 3.5640 |
254
+ | 3.7317 | 34.69 | 1648000 | 3.5650 |
255
+ | 3.7317 | 34.86 | 1656000 | 3.5458 |
256
+ | 3.7332 | 35.03 | 1664000 | 3.5567 |
257
+ | 3.7332 | 35.2 | 1672000 | 3.5610 |
258
+ | 3.7248 | 35.37 | 1680000 | 3.5650 |
259
+ | 3.7248 | 35.54 | 1688000 | 3.5580 |
260
+ | 3.7232 | 35.7 | 1696000 | 3.5829 |
261
+ | 3.7232 | 35.87 | 1704000 | 3.5532 |
262
+ | 3.729 | 36.04 | 1712000 | 3.5723 |
263
+ | 3.729 | 36.21 | 1720000 | 3.5454 |
264
+ | 3.7273 | 36.38 | 1728000 | 3.5623 |
265
+ | 3.7273 | 36.55 | 1736000 | 3.5462 |
266
+ | 3.7261 | 36.72 | 1744000 | 3.5743 |
267
+ | 3.7261 | 36.88 | 1752000 | 3.5638 |
268
+ | 3.7208 | 37.05 | 1760000 | 3.5519 |
269
+ | 3.7208 | 37.22 | 1768000 | 3.5584 |
270
+ | 3.7183 | 37.39 | 1776000 | 3.5308 |
271
+ | 3.7183 | 37.56 | 1784000 | 3.5549 |
272
+ | 3.7193 | 37.73 | 1792000 | 3.5409 |
273
+ | 3.7193 | 37.89 | 1800000 | 3.5396 |
274
+ | 3.7271 | 38.06 | 1808000 | 3.5536 |
275
+ | 3.7271 | 38.23 | 1816000 | 3.5452 |
276
+ | 3.7284 | 38.4 | 1824000 | 3.5582 |
277
+ | 3.7284 | 38.57 | 1832000 | 3.5668 |
278
+ | 3.714 | 38.74 | 1840000 | 3.5673 |
279
+ | 3.714 | 38.9 | 1848000 | 3.5477 |
280
+ | 3.7105 | 39.07 | 1856000 | 3.5662 |
281
+ | 3.7105 | 39.24 | 1864000 | 3.5498 |
282
+ | 3.7189 | 39.41 | 1872000 | 3.5493 |
283
+ | 3.7189 | 39.58 | 1880000 | 3.5676 |
284
+ | 3.7203 | 39.75 | 1888000 | 3.5640 |
285
+ | 3.7203 | 39.91 | 1896000 | 3.5747 |
286
+ | 3.7271 | 40.08 | 1904000 | 3.5592 |
287
+ | 3.7271 | 40.25 | 1912000 | 3.5515 |
288
+ | 3.7237 | 40.42 | 1920000 | 3.5704 |
289
+ | 3.7237 | 40.59 | 1928000 | 3.5642 |
290
+ | 3.723 | 40.76 | 1936000 | 3.5300 |
291
+ | 3.723 | 40.93 | 1944000 | 3.5482 |
292
+ | 3.7224 | 41.09 | 1952000 | 3.5586 |
293
+ | 3.7224 | 41.26 | 1960000 | 3.5463 |
294
+ | 3.715 | 41.43 | 1968000 | 3.5323 |
295
+ | 3.715 | 41.6 | 1976000 | 3.5426 |
296
+ | 3.7209 | 41.77 | 1984000 | 3.5513 |
297
+ | 3.7209 | 41.94 | 1992000 | 3.5614 |
298
+ | 3.7183 | 42.1 | 2000000 | 3.5678 |
299
+ | 3.7183 | 42.27 | 2008000 | 3.5304 |
300
+ | 3.7161 | 42.44 | 2016000 | 3.5631 |
301
+ | 3.7161 | 42.61 | 2024000 | 3.5589 |
302
+ | 3.7215 | 42.78 | 2032000 | 3.5639 |
303
+ | 3.7215 | 42.95 | 2040000 | 3.5376 |
304
+ | 3.7205 | 43.11 | 2048000 | 3.5478 |
305
+ | 3.7205 | 43.28 | 2056000 | 3.5511 |
306
+ | 3.7178 | 43.45 | 2064000 | 3.5285 |
307
+ | 3.7178 | 43.62 | 2072000 | 3.5428 |
308
+ | 3.7232 | 43.79 | 2080000 | 3.5347 |
309
+ | 3.7232 | 43.96 | 2088000 | 3.5501 |
310
+ | 3.7167 | 44.13 | 2096000 | 3.5422 |
311
+ | 3.7167 | 44.29 | 2104000 | 3.5487 |
312
+ | 3.7253 | 44.46 | 2112000 | 3.5540 |
313
+ | 3.7253 | 44.63 | 2120000 | 3.5432 |
314
+ | 3.7139 | 44.8 | 2128000 | 3.5502 |
315
+ | 3.7139 | 44.97 | 2136000 | 3.5450 |
316
+ | 3.7194 | 45.14 | 2144000 | 3.5564 |
317
+ | 3.7194 | 45.3 | 2152000 | 3.5441 |
318
+ | 3.7167 | 45.47 | 2160000 | 3.5549 |
319
+ | 3.7167 | 45.64 | 2168000 | 3.5429 |
320
+ | 3.7202 | 45.81 | 2176000 | 3.5613 |
321
+ | 3.7202 | 45.98 | 2184000 | 3.5469 |
322
+ | 3.7193 | 46.15 | 2192000 | 3.5467 |
323
+ | 3.7193 | 46.31 | 2200000 | 3.5493 |
324
+ | 3.717 | 46.48 | 2208000 | 3.5652 |
325
+ | 3.717 | 46.65 | 2216000 | 3.5669 |
326
+ | 3.7164 | 46.82 | 2224000 | 3.5755 |
327
+ | 3.7164 | 46.99 | 2232000 | 3.5580 |
328
+ | 3.715 | 47.16 | 2240000 | 3.5403 |
329
+ | 3.715 | 47.33 | 2248000 | 3.5521 |
330
+ | 3.7091 | 47.49 | 2256000 | 3.5604 |
331
+ | 3.7091 | 47.66 | 2264000 | 3.5401 |
332
+ | 3.7199 | 47.83 | 2272000 | 3.5408 |
333
+ | 3.7199 | 48.0 | 2280000 | 3.5509 |
334
+ | 3.7238 | 48.17 | 2288000 | 3.5348 |
335
+ | 3.7238 | 48.34 | 2296000 | 3.5530 |
336
+ | 3.7193 | 48.5 | 2304000 | 3.5447 |
337
+ | 3.7193 | 48.67 | 2312000 | 3.5453 |
338
+ | 3.7195 | 48.84 | 2320000 | 3.5487 |
339
+ | 3.7195 | 49.01 | 2328000 | 3.5357 |
340
+ | 3.7187 | 49.18 | 2336000 | 3.5404 |
341
+ | 3.7187 | 49.35 | 2344000 | 3.5247 |
342
+ | 3.7157 | 49.51 | 2352000 | 3.5557 |
343
+ | 3.7157 | 49.68 | 2360000 | 3.5532 |
344
+ | 3.7144 | 49.85 | 2368000 | 3.5453 |
345
+ | 3.7144 | 50.02 | 2376000 | 3.5421 |
346
+ | 3.715 | 50.19 | 2384000 | 3.5183 |
347
+ | 3.715 | 50.36 | 2392000 | 3.5473 |
348
+ | 3.7208 | 50.53 | 2400000 | 3.5386 |
349
+
350
+
351
+ ### Framework versions
352
+
353
+ - Transformers 4.35.0.dev0
354
+ - Pytorch 2.0.1+cu117
355
+ - Datasets 2.14.5
356
+ - Tokenizers 0.14.0
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9fee54adb491e33f9aeb7893993c74eeb469503a04d6559490bf8607a9419425
3
  size 498859189
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cd1962047cd3afca2f193fc6ec9130c28e8771bac6871118a810f8b5236b2c9
3
  size 498859189