Hugging Face's logo

DouglasPontes
/
2020-Q1-90p-filtered

Fill-Mask
Transformers
PyTorch
roberta
Generated from Trainer
Inference Endpoints
Model card Files Community
DouglasPontes commited on
Commit
7bd4188
•
1 Parent(s): edf0c45

Model save

Browse files
Files changed (2) hide show
  1. README.md +357 -0
  2. pytorch_model.bin +1 -1
README.md ADDED
@@ -0,0 +1,357 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-Q1-90p-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-Q1-90p-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: 3.6208
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: 1e-05
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
+ - lr_scheduler_warmup_steps: 1400
44
+ - training_steps: 2400000
45
+
46
+ ### Training results
47
+
48
+ | Training Loss | Epoch | Step | Validation Loss |
49
+ |:-------------:|:-----:|:-------:|:---------------:|
50
+ | No log | 0.16 | 8000 | 3.4495 |
51
+ | 3.5684 | 0.33 | 16000 | 3.4166 |
52
+ | 3.5684 | 0.49 | 24000 | 3.3847 |
53
+ | 3.3755 | 0.66 | 32000 | 3.3665 |
54
+ | 3.3755 | 0.82 | 40000 | 3.3654 |
55
+ | 3.3533 | 0.98 | 48000 | 3.3654 |
56
+ | 3.3533 | 1.15 | 56000 | 3.3328 |
57
+ | 3.3014 | 1.31 | 64000 | 3.3210 |
58
+ | 3.3014 | 1.48 | 72000 | 3.3492 |
59
+ | 3.2888 | 1.64 | 80000 | 3.3213 |
60
+ | 3.2888 | 1.8 | 88000 | 3.2708 |
61
+ | 3.2609 | 1.97 | 96000 | 3.2908 |
62
+ | 3.2609 | 2.13 | 104000 | 3.2767 |
63
+ | 3.2159 | 2.29 | 112000 | 3.2592 |
64
+ | 3.2159 | 2.46 | 120000 | 3.2411 |
65
+ | 3.2167 | 2.62 | 128000 | 3.2377 |
66
+ | 3.2167 | 2.79 | 136000 | 3.2485 |
67
+ | 3.199 | 2.95 | 144000 | 3.2609 |
68
+ | 3.199 | 3.11 | 152000 | 3.2553 |
69
+ | 3.1905 | 3.28 | 160000 | 3.2425 |
70
+ | 3.1905 | 3.44 | 168000 | 3.2422 |
71
+ | 3.1822 | 3.61 | 176000 | 3.2624 |
72
+ | 3.1822 | 3.77 | 184000 | 3.2507 |
73
+ | 3.1852 | 3.93 | 192000 | 3.2483 |
74
+ | 3.1852 | 4.1 | 200000 | 3.2514 |
75
+ | 3.1767 | 4.26 | 208000 | 3.2426 |
76
+ | 3.1767 | 4.43 | 216000 | 3.2348 |
77
+ | 3.1767 | 4.59 | 224000 | 3.2735 |
78
+ | 3.1767 | 4.75 | 232000 | 3.2472 |
79
+ | 3.1973 | 4.92 | 240000 | 3.2596 |
80
+ | 3.1973 | 5.08 | 248000 | 3.2606 |
81
+ | 3.1781 | 5.24 | 256000 | 3.2815 |
82
+ | 3.1781 | 5.41 | 264000 | 3.2734 |
83
+ | 3.1803 | 5.57 | 272000 | 3.2739 |
84
+ | 3.1803 | 5.74 | 280000 | 3.2712 |
85
+ | 3.1989 | 5.9 | 288000 | 3.2734 |
86
+ | 3.1989 | 6.06 | 296000 | 3.2939 |
87
+ | 3.1929 | 6.23 | 304000 | 3.2880 |
88
+ | 3.1929 | 6.39 | 312000 | 3.2894 |
89
+ | 3.2083 | 6.56 | 320000 | 3.3086 |
90
+ | 3.2083 | 6.72 | 328000 | 3.3067 |
91
+ | 3.2013 | 6.88 | 336000 | 3.2787 |
92
+ | 3.2013 | 7.05 | 344000 | 3.3153 |
93
+ | 3.2111 | 7.21 | 352000 | 3.3246 |
94
+ | 3.2111 | 7.38 | 360000 | 3.3323 |
95
+ | 3.2186 | 7.54 | 368000 | 3.2938 |
96
+ | 3.2186 | 7.7 | 376000 | 3.3500 |
97
+ | 3.2268 | 7.87 | 384000 | 3.3180 |
98
+ | 3.2268 | 8.03 | 392000 | 3.3171 |
99
+ | 3.233 | 8.2 | 400000 | 3.3462 |
100
+ | 3.233 | 8.36 | 408000 | 3.3413 |
101
+ | 3.2432 | 8.52 | 416000 | 3.3281 |
102
+ | 3.2432 | 8.69 | 424000 | 3.3420 |
103
+ | 3.2586 | 8.85 | 432000 | 3.3609 |
104
+ | 3.2586 | 9.01 | 440000 | 3.3527 |
105
+ | 3.2567 | 9.18 | 448000 | 3.3594 |
106
+ | 3.2567 | 9.34 | 456000 | 3.3497 |
107
+ | 3.2592 | 9.51 | 464000 | 3.3607 |
108
+ | 3.2592 | 9.67 | 472000 | 3.3840 |
109
+ | 3.2793 | 9.83 | 480000 | 3.3668 |
110
+ | 3.2793 | 10.0 | 488000 | 3.3609 |
111
+ | 3.257 | 10.16 | 496000 | 3.3682 |
112
+ | 3.257 | 10.33 | 504000 | 3.4006 |
113
+ | 3.2656 | 10.49 | 512000 | 3.3588 |
114
+ | 3.2656 | 10.65 | 520000 | 3.3799 |
115
+ | 3.2727 | 10.82 | 528000 | 3.3833 |
116
+ | 3.2727 | 10.98 | 536000 | 3.3566 |
117
+ | 3.2705 | 11.15 | 544000 | 3.3794 |
118
+ | 3.2705 | 11.31 | 552000 | 3.3838 |
119
+ | 3.2676 | 11.47 | 560000 | 3.3660 |
120
+ | 3.2676 | 11.64 | 568000 | 3.3938 |
121
+ | 3.258 | 11.8 | 576000 | 3.3661 |
122
+ | 3.258 | 11.97 | 584000 | 3.3490 |
123
+ | 3.2646 | 12.13 | 592000 | 3.3716 |
124
+ | 3.2646 | 12.29 | 600000 | 3.3877 |
125
+ | 3.2578 | 12.46 | 608000 | 3.3930 |
126
+ | 3.2578 | 12.62 | 616000 | 3.3921 |
127
+ | 3.2719 | 12.78 | 624000 | 3.3957 |
128
+ | 3.2719 | 12.95 | 632000 | 3.4196 |
129
+ | 3.2828 | 13.11 | 640000 | 3.4078 |
130
+ | 3.2828 | 13.28 | 648000 | 3.4203 |
131
+ | 3.2805 | 13.44 | 656000 | 3.3900 |
132
+ | 3.2805 | 13.6 | 664000 | 3.4038 |
133
+ | 3.2975 | 13.77 | 672000 | 3.4056 |
134
+ | 3.2975 | 13.93 | 680000 | 3.4284 |
135
+ | 3.2965 | 14.1 | 688000 | 3.4180 |
136
+ | 3.2965 | 14.26 | 696000 | 3.4196 |
137
+ | 3.3069 | 14.42 | 704000 | 3.4257 |
138
+ | 3.3069 | 14.59 | 712000 | 3.4299 |
139
+ | 3.3152 | 14.75 | 720000 | 3.4788 |
140
+ | 3.3152 | 14.92 | 728000 | 3.4425 |
141
+ | 3.3125 | 15.08 | 736000 | 3.4301 |
142
+ | 3.3125 | 15.24 | 744000 | 3.4441 |
143
+ | 3.3174 | 15.41 | 752000 | 3.4396 |
144
+ | 3.3174 | 15.57 | 760000 | 3.4639 |
145
+ | 3.3242 | 15.73 | 768000 | 3.4524 |
146
+ | 3.3242 | 15.9 | 776000 | 3.4560 |
147
+ | 3.3385 | 16.06 | 784000 | 3.4780 |
148
+ | 3.3385 | 16.23 | 792000 | 3.4774 |
149
+ | 3.3371 | 16.39 | 800000 | 3.4772 |
150
+ | 3.3371 | 16.55 | 808000 | 3.4955 |
151
+ | 3.3633 | 16.72 | 816000 | 3.4861 |
152
+ | 3.3633 | 16.88 | 824000 | 3.5063 |
153
+ | 3.3678 | 17.05 | 832000 | 3.5044 |
154
+ | 3.3678 | 17.21 | 840000 | 3.5202 |
155
+ | 3.3634 | 17.37 | 848000 | 3.4941 |
156
+ | 3.3634 | 17.54 | 856000 | 3.5223 |
157
+ | 3.3797 | 17.7 | 864000 | 3.5028 |
158
+ | 3.3797 | 17.87 | 872000 | 3.5264 |
159
+ | 3.3802 | 18.03 | 880000 | 3.5313 |
160
+ | 3.3802 | 18.19 | 888000 | 3.4963 |
161
+ | 3.357 | 18.36 | 896000 | 3.5171 |
162
+ | 3.357 | 18.52 | 904000 | 3.5307 |
163
+ | 3.3866 | 18.69 | 912000 | 3.5222 |
164
+ | 3.3866 | 18.85 | 920000 | 3.5319 |
165
+ | 3.3818 | 19.01 | 928000 | 3.5326 |
166
+ | 3.3818 | 19.18 | 936000 | 3.5116 |
167
+ | 3.3754 | 19.34 | 944000 | 3.5229 |
168
+ | 3.3754 | 19.5 | 952000 | 3.5383 |
169
+ | 3.3893 | 19.67 | 960000 | 3.5445 |
170
+ | 3.3893 | 19.83 | 968000 | 3.5231 |
171
+ | 3.3899 | 20.0 | 976000 | 3.5310 |
172
+ | 3.3899 | 20.16 | 984000 | 3.5329 |
173
+ | 3.3918 | 20.32 | 992000 | 3.5159 |
174
+ | 3.3918 | 20.49 | 1000000 | 3.5628 |
175
+ | 3.3786 | 20.65 | 1008000 | 3.5291 |
176
+ | 3.3786 | 20.82 | 1016000 | 3.5163 |
177
+ | 3.3862 | 20.98 | 1024000 | 3.5312 |
178
+ | 3.3862 | 21.14 | 1032000 | 3.5140 |
179
+ | 3.3855 | 21.31 | 1040000 | 3.5617 |
180
+ | 3.3855 | 21.47 | 1048000 | 3.5375 |
181
+ | 3.3872 | 21.64 | 1056000 | 3.5328 |
182
+ | 3.3872 | 21.8 | 1064000 | 3.5616 |
183
+ | 3.3931 | 21.96 | 1072000 | 3.5648 |
184
+ | 3.3931 | 22.13 | 1080000 | 3.5443 |
185
+ | 3.3708 | 22.29 | 1088000 | 3.5401 |
186
+ | 3.3708 | 22.45 | 1096000 | 3.5529 |
187
+ | 3.4099 | 22.62 | 1104000 | 3.5334 |
188
+ | 3.4099 | 22.78 | 1112000 | 3.5325 |
189
+ | 3.4027 | 22.95 | 1120000 | 3.5819 |
190
+ | 3.4027 | 23.11 | 1128000 | 3.5471 |
191
+ | 3.4035 | 23.27 | 1136000 | 3.5486 |
192
+ | 3.4035 | 23.44 | 1144000 | 3.5470 |
193
+ | 3.3964 | 23.6 | 1152000 | 3.5722 |
194
+ | 3.3964 | 23.77 | 1160000 | 3.5510 |
195
+ | 3.4115 | 23.93 | 1168000 | 3.5610 |
196
+ | 3.4115 | 24.09 | 1176000 | 3.5757 |
197
+ | 3.4173 | 24.26 | 1184000 | 3.5541 |
198
+ | 3.4173 | 24.42 | 1192000 | 3.5777 |
199
+ | 3.4169 | 24.59 | 1200000 | 3.5638 |
200
+ | 3.4169 | 24.75 | 1208000 | 3.5463 |
201
+ | 3.4031 | 24.91 | 1216000 | 3.5300 |
202
+ | 3.4031 | 25.08 | 1224000 | 3.5584 |
203
+ | 3.4094 | 25.24 | 1232000 | 3.5682 |
204
+ | 3.4094 | 25.41 | 1240000 | 3.5558 |
205
+ | 3.4116 | 25.57 | 1248000 | 3.5629 |
206
+ | 3.4116 | 25.73 | 1256000 | 3.5490 |
207
+ | 3.4199 | 25.9 | 1264000 | 3.5679 |
208
+ | 3.4199 | 26.06 | 1272000 | 3.5885 |
209
+ | 3.412 | 26.22 | 1280000 | 3.5579 |
210
+ | 3.412 | 26.39 | 1288000 | 3.5465 |
211
+ | 3.4123 | 26.55 | 1296000 | 3.5726 |
212
+ | 3.4123 | 26.72 | 1304000 | 3.5775 |
213
+ | 3.4132 | 26.88 | 1312000 | 3.5478 |
214
+ | 3.4132 | 27.04 | 1320000 | 3.5589 |
215
+ | 3.4161 | 27.21 | 1328000 | 3.5662 |
216
+ | 3.4161 | 27.37 | 1336000 | 3.5895 |
217
+ | 3.4097 | 27.54 | 1344000 | 3.5941 |
218
+ | 3.4097 | 27.7 | 1352000 | 3.5912 |
219
+ | 3.415 | 27.86 | 1360000 | 3.5658 |
220
+ | 3.415 | 28.03 | 1368000 | 3.5554 |
221
+ | 3.4193 | 28.19 | 1376000 | 3.5899 |
222
+ | 3.4193 | 28.36 | 1384000 | 3.5652 |
223
+ | 3.4136 | 28.52 | 1392000 | 3.5832 |
224
+ | 3.4136 | 28.68 | 1400000 | 3.5885 |
225
+ | 3.4294 | 28.85 | 1408000 | 3.5832 |
226
+ | 3.4294 | 29.01 | 1416000 | 3.6025 |
227
+ | 3.4243 | 29.17 | 1424000 | 3.6040 |
228
+ | 3.4243 | 29.34 | 1432000 | 3.5890 |
229
+ | 3.4427 | 29.5 | 1440000 | 3.5835 |
230
+ | 3.4427 | 29.67 | 1448000 | 3.6185 |
231
+ | 3.4293 | 29.83 | 1456000 | 3.6029 |
232
+ | 3.4293 | 29.99 | 1464000 | 3.6162 |
233
+ | 3.4363 | 30.16 | 1472000 | 3.6258 |
234
+ | 3.4363 | 30.32 | 1480000 | 3.6038 |
235
+ | 3.4532 | 30.49 | 1488000 | 3.6039 |
236
+ | 3.4532 | 30.65 | 1496000 | 3.6054 |
237
+ | 3.4401 | 30.81 | 1504000 | 3.6269 |
238
+ | 3.4401 | 30.98 | 1512000 | 3.6004 |
239
+ | 3.4491 | 31.14 | 1520000 | 3.6096 |
240
+ | 3.4491 | 31.31 | 1528000 | 3.6217 |
241
+ | 3.4438 | 31.47 | 1536000 | 3.6081 |
242
+ | 3.4438 | 31.63 | 1544000 | 3.6190 |
243
+ | 3.4337 | 31.8 | 1552000 | 3.6120 |
244
+ | 3.4337 | 31.96 | 1560000 | 3.5861 |
245
+ | 3.4475 | 32.13 | 1568000 | 3.6209 |
246
+ | 3.4475 | 32.29 | 1576000 | 3.6302 |
247
+ | 3.4406 | 32.45 | 1584000 | 3.6053 |
248
+ | 3.4406 | 32.62 | 1592000 | 3.5934 |
249
+ | 3.4392 | 32.78 | 1600000 | 3.5942 |
250
+ | 3.4392 | 32.94 | 1608000 | 3.6013 |
251
+ | 3.4514 | 33.11 | 1616000 | 3.6506 |
252
+ | 3.4514 | 33.27 | 1624000 | 3.6049 |
253
+ | 3.4406 | 33.44 | 1632000 | 3.6285 |
254
+ | 3.4406 | 33.6 | 1640000 | 3.6107 |
255
+ | 3.4522 | 33.76 | 1648000 | 3.6081 |
256
+ | 3.4522 | 33.93 | 1656000 | 3.6121 |
257
+ | 3.4592 | 34.09 | 1664000 | 3.6396 |
258
+ | 3.4592 | 34.26 | 1672000 | 3.6284 |
259
+ | 3.4587 | 34.42 | 1680000 | 3.6195 |
260
+ | 3.4587 | 34.58 | 1688000 | 3.6168 |
261
+ | 3.4589 | 34.75 | 1696000 | 3.6315 |
262
+ | 3.4589 | 34.91 | 1704000 | 3.6045 |
263
+ | 3.4703 | 35.08 | 1712000 | 3.6251 |
264
+ | 3.4703 | 35.24 | 1720000 | 3.6252 |
265
+ | 3.4565 | 35.4 | 1728000 | 3.6254 |
266
+ | 3.4565 | 35.57 | 1736000 | 3.6544 |
267
+ | 3.4634 | 35.73 | 1744000 | 3.6290 |
268
+ | 3.4634 | 35.9 | 1752000 | 3.6124 |
269
+ | 3.4625 | 36.06 | 1760000 | 3.6262 |
270
+ | 3.4625 | 36.22 | 1768000 | 3.6318 |
271
+ | 3.457 | 36.39 | 1776000 | 3.6408 |
272
+ | 3.457 | 36.55 | 1784000 | 3.6433 |
273
+ | 3.4618 | 36.71 | 1792000 | 3.6276 |
274
+ | 3.4618 | 36.88 | 1800000 | 3.6314 |
275
+ | 3.4611 | 37.04 | 1808000 | 3.6416 |
276
+ | 3.4611 | 37.21 | 1816000 | 3.6658 |
277
+ | 3.4651 | 37.37 | 1824000 | 3.6382 |
278
+ | 3.4651 | 37.53 | 1832000 | 3.6562 |
279
+ | 3.4625 | 37.7 | 1840000 | 3.6376 |
280
+ | 3.4625 | 37.86 | 1848000 | 3.6520 |
281
+ | 3.4561 | 38.03 | 1856000 | 3.6301 |
282
+ | 3.4561 | 38.19 | 1864000 | 3.6195 |
283
+ | 3.4655 | 38.35 | 1872000 | 3.6279 |
284
+ | 3.4655 | 38.52 | 1880000 | 3.6365 |
285
+ | 3.4637 | 38.68 | 1888000 | 3.6386 |
286
+ | 3.4637 | 38.85 | 1896000 | 3.6434 |
287
+ | 3.458 | 39.01 | 1904000 | 3.6519 |
288
+ | 3.458 | 39.17 | 1912000 | 3.6438 |
289
+ | 3.4523 | 39.34 | 1920000 | 3.6408 |
290
+ | 3.4523 | 39.5 | 1928000 | 3.6513 |
291
+ | 3.4743 | 39.66 | 1936000 | 3.6178 |
292
+ | 3.4743 | 39.83 | 1944000 | 3.6399 |
293
+ | 3.4626 | 39.99 | 1952000 | 3.6243 |
294
+ | 3.4626 | 40.16 | 1960000 | 3.6326 |
295
+ | 3.4692 | 40.32 | 1968000 | 3.6723 |
296
+ | 3.4692 | 40.48 | 1976000 | 3.6456 |
297
+ | 3.4765 | 40.65 | 1984000 | 3.6437 |
298
+ | 3.4765 | 40.81 | 1992000 | 3.6477 |
299
+ | 3.4747 | 40.98 | 2000000 | 3.6384 |
300
+ | 3.4747 | 41.14 | 2008000 | 3.6370 |
301
+ | 3.4683 | 41.3 | 2016000 | 3.6625 |
302
+ | 3.4683 | 41.47 | 2024000 | 3.6453 |
303
+ | 3.4599 | 41.63 | 2032000 | 3.6489 |
304
+ | 3.4599 | 41.8 | 2040000 | 3.6311 |
305
+ | 3.4713 | 41.96 | 2048000 | 3.6192 |
306
+ | 3.4713 | 42.12 | 2056000 | 3.6511 |
307
+ | 3.4677 | 42.29 | 2064000 | 3.6426 |
308
+ | 3.4677 | 42.45 | 2072000 | 3.6363 |
309
+ | 3.4689 | 42.62 | 2080000 | 3.6378 |
310
+ | 3.4689 | 42.78 | 2088000 | 3.6450 |
311
+ | 3.4598 | 42.94 | 2096000 | 3.6481 |
312
+ | 3.4598 | 43.11 | 2104000 | 3.6675 |
313
+ | 3.4487 | 43.27 | 2112000 | 3.6558 |
314
+ | 3.4487 | 43.43 | 2120000 | 3.6451 |
315
+ | 3.4555 | 43.6 | 2128000 | 3.6431 |
316
+ | 3.4555 | 43.76 | 2136000 | 3.6470 |
317
+ | 3.4727 | 43.93 | 2144000 | 3.6265 |
318
+ | 3.4727 | 44.09 | 2152000 | 3.6335 |
319
+ | 3.4626 | 44.25 | 2160000 | 3.6396 |
320
+ | 3.4626 | 44.42 | 2168000 | 3.6537 |
321
+ | 3.4724 | 44.58 | 2176000 | 3.6168 |
322
+ | 3.4724 | 44.75 | 2184000 | 3.6444 |
323
+ | 3.4545 | 44.91 | 2192000 | 3.6440 |
324
+ | 3.4545 | 45.07 | 2200000 | 3.6327 |
325
+ | 3.461 | 45.24 | 2208000 | 3.6363 |
326
+ | 3.461 | 45.4 | 2216000 | 3.6537 |
327
+ | 3.4702 | 45.57 | 2224000 | 3.6123 |
328
+ | 3.4702 | 45.73 | 2232000 | 3.6554 |
329
+ | 3.4565 | 45.89 | 2240000 | 3.6523 |
330
+ | 3.4565 | 46.06 | 2248000 | 3.6340 |
331
+ | 3.4517 | 46.22 | 2256000 | 3.6459 |
332
+ | 3.4517 | 46.38 | 2264000 | 3.6561 |
333
+ | 3.4631 | 46.55 | 2272000 | 3.6548 |
334
+ | 3.4631 | 46.71 | 2280000 | 3.6229 |
335
+ | 3.4518 | 46.88 | 2288000 | 3.6350 |
336
+ | 3.4518 | 47.04 | 2296000 | 3.6483 |
337
+ | 3.4592 | 47.2 | 2304000 | 3.6263 |
338
+ | 3.4592 | 47.37 | 2312000 | 3.6339 |
339
+ | 3.4569 | 47.53 | 2320000 | 3.6594 |
340
+ | 3.4569 | 47.7 | 2328000 | 3.6385 |
341
+ | 3.4524 | 47.86 | 2336000 | 3.6434 |
342
+ | 3.4524 | 48.02 | 2344000 | 3.6502 |
343
+ | 3.4644 | 48.19 | 2352000 | 3.6176 |
344
+ | 3.4644 | 48.35 | 2360000 | 3.6293 |
345
+ | 3.4586 | 48.52 | 2368000 | 3.6304 |
346
+ | 3.4586 | 48.68 | 2376000 | 3.6343 |
347
+ | 3.4439 | 48.84 | 2384000 | 3.6090 |
348
+ | 3.4439 | 49.01 | 2392000 | 3.6414 |
349
+ | 3.4474 | 49.17 | 2400000 | 3.6208 |
350
+
351
+
352
+ ### Framework versions
353
+
354
+ - Transformers 4.35.0.dev0
355
+ - Pytorch 2.0.1+cu117
356
+ - Datasets 2.14.5
357
+ - Tokenizers 0.14.0
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fd2eaab42c19d7cde38678fb0d66338ddf67fb1de20009ee269531847b6de704
3
  size 498859189
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd50ad67b3827b1dc9c44f02691c10192ff933d2ac0fe54f49d2c8557e2d5d9d
3
  size 498859189