Taeham commited on
Commit
08e8139
1 Parent(s): bd438f6

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +358 -0
README.md ADDED
@@ -0,0 +1,358 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: wav2vec2-ksponspeech-dataset
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ # wav2vec2-ksponspeech-dataset
14
+
15
+ This model is a fine-tuned version of [Taeham/wav2vec2-ksponspeech](https://huggingface.co/Taeham/wav2vec2-ksponspeech) on the None dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Loss: 0.7077
18
+ - Wer: 0.4589
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: 0.0003
38
+ - train_batch_size: 4
39
+ - eval_batch_size: 4
40
+ - seed: 42
41
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
+ - lr_scheduler_type: linear
43
+ - lr_scheduler_warmup_steps: 500
44
+ - num_epochs: 30
45
+ - mixed_precision_training: Native AMP
46
+
47
+ ### Training results
48
+
49
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
50
+ |:-------------:|:-----:|:------:|:---------------:|:------:|
51
+ | 0.4061 | 0.1 | 500 | 0.3114 | 0.4887 |
52
+ | 0.6089 | 0.2 | 1000 | 0.3867 | 0.5276 |
53
+ | 0.6572 | 0.3 | 1500 | 0.4261 | 0.5537 |
54
+ | 0.6719 | 0.4 | 2000 | 0.4659 | 0.5592 |
55
+ | 0.6944 | 0.5 | 2500 | 0.5391 | 0.5827 |
56
+ | 0.7135 | 0.6 | 3000 | 0.5214 | 0.5818 |
57
+ | 0.7115 | 0.7 | 3500 | 0.4810 | 0.5646 |
58
+ | 0.7067 | 0.8 | 4000 | 0.5233 | 0.5863 |
59
+ | 0.6979 | 0.9 | 4500 | 0.4805 | 0.5619 |
60
+ | 0.7069 | 1.0 | 5000 | 0.5082 | 0.5682 |
61
+ | 0.6271 | 1.1 | 5500 | 0.4900 | 0.5619 |
62
+ | 0.6492 | 1.2 | 6000 | 0.5120 | 0.5818 |
63
+ | 0.6569 | 1.3 | 6500 | 0.5047 | 0.5908 |
64
+ | 0.6363 | 1.4 | 7000 | 0.5631 | 0.5664 |
65
+ | 0.649 | 1.5 | 7500 | 0.5169 | 0.5935 |
66
+ | 0.6644 | 1.6 | 8000 | 0.5603 | 0.5926 |
67
+ | 0.6552 | 1.7 | 8500 | 0.5221 | 0.5537 |
68
+ | 0.6645 | 1.8 | 9000 | 0.4719 | 0.5736 |
69
+ | 0.6672 | 1.9 | 9500 | 0.4826 | 0.5519 |
70
+ | 0.6595 | 2.0 | 10000 | 0.4955 | 0.5655 |
71
+ | 0.5548 | 2.1 | 10500 | 0.4773 | 0.5438 |
72
+ | 0.5659 | 2.2 | 11000 | 0.4921 | 0.5474 |
73
+ | 0.5895 | 2.3 | 11500 | 0.4935 | 0.5565 |
74
+ | 0.5822 | 2.4 | 12000 | 0.4767 | 0.5673 |
75
+ | 0.5688 | 2.5 | 12500 | 0.4837 | 0.5655 |
76
+ | 0.6139 | 2.6 | 13000 | 0.5139 | 0.5854 |
77
+ | 0.6089 | 2.7 | 13500 | 0.4922 | 0.5610 |
78
+ | 0.5935 | 2.8 | 14000 | 0.5057 | 0.5619 |
79
+ | 0.5909 | 2.9 | 14500 | 0.4779 | 0.5565 |
80
+ | 0.5899 | 3.0 | 15000 | 0.4848 | 0.5547 |
81
+ | 0.5035 | 3.1 | 15500 | 0.4610 | 0.5537 |
82
+ | 0.5101 | 3.2 | 16000 | 0.4901 | 0.5601 |
83
+ | 0.5286 | 3.3 | 16500 | 0.4678 | 0.5303 |
84
+ | 0.5096 | 3.4 | 17000 | 0.4523 | 0.5257 |
85
+ | 0.5535 | 3.5 | 17500 | 0.4734 | 0.5294 |
86
+ | 0.5386 | 3.6 | 18000 | 0.4956 | 0.5565 |
87
+ | 0.5624 | 3.7 | 18500 | 0.4742 | 0.5303 |
88
+ | 0.5593 | 3.8 | 19000 | 0.4508 | 0.5294 |
89
+ | 0.5487 | 3.9 | 19500 | 0.4558 | 0.5583 |
90
+ | 0.5392 | 4.0 | 20000 | 0.4595 | 0.5312 |
91
+ | 0.457 | 4.1 | 20500 | 0.4711 | 0.5059 |
92
+ | 0.4607 | 4.2 | 21000 | 0.4967 | 0.5212 |
93
+ | 0.4806 | 4.3 | 21500 | 0.5484 | 0.5330 |
94
+ | 0.4843 | 4.4 | 22000 | 0.4620 | 0.5266 |
95
+ | 0.4838 | 4.5 | 22500 | 0.5160 | 0.5339 |
96
+ | 0.4794 | 4.6 | 23000 | 0.5139 | 0.5194 |
97
+ | 0.4993 | 4.7 | 23500 | 0.4831 | 0.5438 |
98
+ | 0.4889 | 4.8 | 24000 | 0.4954 | 0.5276 |
99
+ | 0.5097 | 4.9 | 24500 | 0.4780 | 0.5294 |
100
+ | 0.4827 | 5.0 | 25000 | 0.4302 | 0.5176 |
101
+ | 0.4178 | 5.1 | 25500 | 0.4893 | 0.5294 |
102
+ | 0.4283 | 5.2 | 26000 | 0.4531 | 0.5429 |
103
+ | 0.4363 | 5.3 | 26500 | 0.5028 | 0.5176 |
104
+ | 0.4374 | 5.4 | 27000 | 0.4749 | 0.5375 |
105
+ | 0.4422 | 5.5 | 27500 | 0.5086 | 0.5474 |
106
+ | 0.4381 | 5.6 | 28000 | 0.4526 | 0.5221 |
107
+ | 0.4389 | 5.7 | 28500 | 0.4978 | 0.5321 |
108
+ | 0.4412 | 5.8 | 29000 | 0.4806 | 0.5402 |
109
+ | 0.4545 | 5.9 | 29500 | 0.4719 | 0.5095 |
110
+ | 0.4609 | 6.0 | 30000 | 0.4690 | 0.5041 |
111
+ | 0.3845 | 6.1 | 30500 | 0.5101 | 0.5149 |
112
+ | 0.3854 | 6.2 | 31000 | 0.4763 | 0.5312 |
113
+ | 0.3857 | 6.3 | 31500 | 0.4684 | 0.5158 |
114
+ | 0.3926 | 6.4 | 32000 | 0.5209 | 0.5330 |
115
+ | 0.4103 | 6.5 | 32500 | 0.4667 | 0.4761 |
116
+ | 0.3915 | 6.6 | 33000 | 0.4619 | 0.4905 |
117
+ | 0.3996 | 6.7 | 33500 | 0.5279 | 0.5158 |
118
+ | 0.3951 | 6.8 | 34000 | 0.4484 | 0.4914 |
119
+ | 0.388 | 6.9 | 34500 | 0.4517 | 0.4950 |
120
+ | 0.3873 | 7.0 | 35000 | 0.4675 | 0.4950 |
121
+ | 0.3368 | 7.1 | 35500 | 0.4793 | 0.5005 |
122
+ | 0.3617 | 7.2 | 36000 | 0.4747 | 0.4995 |
123
+ | 0.3457 | 7.3 | 36500 | 0.4941 | 0.5276 |
124
+ | 0.351 | 7.4 | 37000 | 0.4703 | 0.5077 |
125
+ | 0.376 | 7.5 | 37500 | 0.4746 | 0.5113 |
126
+ | 0.3709 | 7.6 | 38000 | 0.4739 | 0.5104 |
127
+ | 0.3747 | 7.7 | 38500 | 0.4344 | 0.4986 |
128
+ | 0.3775 | 7.8 | 39000 | 0.4661 | 0.5221 |
129
+ | 0.358 | 7.9 | 39500 | 0.4956 | 0.5339 |
130
+ | 0.3779 | 8.0 | 40000 | 0.4772 | 0.5095 |
131
+ | 0.3129 | 8.1 | 40500 | 0.5251 | 0.5149 |
132
+ | 0.328 | 8.2 | 41000 | 0.4823 | 0.5059 |
133
+ | 0.3173 | 8.3 | 41500 | 0.4826 | 0.5158 |
134
+ | 0.32 | 8.4 | 42000 | 0.5244 | 0.5131 |
135
+ | 0.3388 | 8.5 | 42500 | 0.4882 | 0.5140 |
136
+ | 0.3197 | 8.6 | 43000 | 0.5209 | 0.5086 |
137
+ | 0.3441 | 8.7 | 43500 | 0.5055 | 0.4950 |
138
+ | 0.3421 | 8.8 | 44000 | 0.4645 | 0.4851 |
139
+ | 0.3397 | 8.9 | 44500 | 0.4910 | 0.4869 |
140
+ | 0.3517 | 9.0 | 45000 | 0.4782 | 0.4878 |
141
+ | 0.3016 | 9.1 | 45500 | 0.4921 | 0.4896 |
142
+ | 0.302 | 9.2 | 46000 | 0.5573 | 0.5050 |
143
+ | 0.3061 | 9.3 | 46500 | 0.5083 | 0.5041 |
144
+ | 0.2974 | 9.4 | 47000 | 0.5100 | 0.4932 |
145
+ | 0.3172 | 9.5 | 47500 | 0.5385 | 0.5005 |
146
+ | 0.2977 | 9.6 | 48000 | 0.4716 | 0.4842 |
147
+ | 0.3064 | 9.7 | 48500 | 0.5117 | 0.5149 |
148
+ | 0.3215 | 9.8 | 49000 | 0.5030 | 0.5005 |
149
+ | 0.3018 | 9.9 | 49500 | 0.5205 | 0.5005 |
150
+ | 0.3141 | 10.0 | 50000 | 0.5180 | 0.5005 |
151
+ | 0.2527 | 10.1 | 50500 | 0.5569 | 0.5149 |
152
+ | 0.2708 | 10.2 | 51000 | 0.4962 | 0.4959 |
153
+ | 0.277 | 10.3 | 51500 | 0.5347 | 0.5023 |
154
+ | 0.2704 | 10.4 | 52000 | 0.5466 | 0.5068 |
155
+ | 0.2787 | 10.5 | 52500 | 0.5486 | 0.4932 |
156
+ | 0.278 | 10.6 | 53000 | 0.5623 | 0.4833 |
157
+ | 0.2806 | 10.7 | 53500 | 0.5272 | 0.4977 |
158
+ | 0.2836 | 10.8 | 54000 | 0.5667 | 0.5023 |
159
+ | 0.2872 | 10.9 | 54500 | 0.5089 | 0.4968 |
160
+ | 0.2919 | 11.0 | 55000 | 0.5243 | 0.4968 |
161
+ | 0.2349 | 11.1 | 55500 | 0.5277 | 0.4914 |
162
+ | 0.2514 | 11.2 | 56000 | 0.5913 | 0.5131 |
163
+ | 0.2602 | 11.3 | 56500 | 0.5492 | 0.5068 |
164
+ | 0.244 | 11.4 | 57000 | 0.5259 | 0.4950 |
165
+ | 0.2595 | 11.5 | 57500 | 0.5845 | 0.5095 |
166
+ | 0.2614 | 11.6 | 58000 | 0.5560 | 0.5230 |
167
+ | 0.2739 | 11.7 | 58500 | 0.5421 | 0.5041 |
168
+ | 0.2616 | 11.8 | 59000 | 0.5756 | 0.5149 |
169
+ | 0.2694 | 11.9 | 59500 | 0.5471 | 0.5167 |
170
+ | 0.2785 | 12.0 | 60000 | 0.5479 | 0.5050 |
171
+ | 0.2326 | 12.1 | 60500 | 0.5498 | 0.5059 |
172
+ | 0.2344 | 12.2 | 61000 | 0.5255 | 0.5077 |
173
+ | 0.2444 | 12.3 | 61500 | 0.5599 | 0.4986 |
174
+ | 0.2442 | 12.4 | 62000 | 0.5598 | 0.5050 |
175
+ | 0.2378 | 12.5 | 62500 | 0.5267 | 0.5005 |
176
+ | 0.2301 | 12.6 | 63000 | 0.5680 | 0.4986 |
177
+ | 0.2339 | 12.7 | 63500 | 0.5215 | 0.4986 |
178
+ | 0.2477 | 12.8 | 64000 | 0.5197 | 0.4923 |
179
+ | 0.2411 | 12.9 | 64500 | 0.5308 | 0.4923 |
180
+ | 0.2455 | 13.0 | 65000 | 0.5353 | 0.5014 |
181
+ | 0.2134 | 13.1 | 65500 | 0.5459 | 0.4806 |
182
+ | 0.2184 | 13.2 | 66000 | 0.6418 | 0.5023 |
183
+ | 0.2249 | 13.3 | 66500 | 0.5579 | 0.5059 |
184
+ | 0.2228 | 13.4 | 67000 | 0.5723 | 0.4986 |
185
+ | 0.2235 | 13.5 | 67500 | 0.5755 | 0.4923 |
186
+ | 0.2159 | 13.6 | 68000 | 0.5707 | 0.4833 |
187
+ | 0.2196 | 13.7 | 68500 | 0.5495 | 0.4860 |
188
+ | 0.2206 | 13.8 | 69000 | 0.5559 | 0.4715 |
189
+ | 0.2139 | 13.9 | 69500 | 0.5740 | 0.4941 |
190
+ | 0.2239 | 14.0 | 70000 | 0.5586 | 0.5059 |
191
+ | 0.1947 | 14.1 | 70500 | 0.5917 | 0.4959 |
192
+ | 0.1981 | 14.2 | 71000 | 0.6393 | 0.4860 |
193
+ | 0.2028 | 14.3 | 71500 | 0.6271 | 0.4986 |
194
+ | 0.2131 | 14.4 | 72000 | 0.5941 | 0.4932 |
195
+ | 0.2063 | 14.5 | 72500 | 0.5717 | 0.5059 |
196
+ | 0.2035 | 14.6 | 73000 | 0.6181 | 0.4806 |
197
+ | 0.2123 | 14.7 | 73500 | 0.6152 | 0.4896 |
198
+ | 0.1989 | 14.8 | 74000 | 0.5843 | 0.4878 |
199
+ | 0.2129 | 14.9 | 74500 | 0.5663 | 0.4688 |
200
+ | 0.2072 | 15.0 | 75000 | 0.6004 | 0.4734 |
201
+ | 0.1994 | 15.1 | 75500 | 0.6253 | 0.4923 |
202
+ | 0.1916 | 15.2 | 76000 | 0.5930 | 0.4887 |
203
+ | 0.209 | 15.3 | 76500 | 0.6189 | 0.4697 |
204
+ | 0.1942 | 15.4 | 77000 | 0.5974 | 0.4715 |
205
+ | 0.207 | 15.5 | 77500 | 0.6112 | 0.4842 |
206
+ | 0.1911 | 15.6 | 78000 | 0.6335 | 0.4878 |
207
+ | 0.1933 | 15.7 | 78500 | 0.6045 | 0.4932 |
208
+ | 0.1945 | 15.8 | 79000 | 0.6365 | 0.4851 |
209
+ | 0.1873 | 15.9 | 79500 | 0.6257 | 0.4842 |
210
+ | 0.1929 | 16.0 | 80000 | 0.6037 | 0.4779 |
211
+ | 0.1734 | 16.1 | 80500 | 0.6649 | 0.4869 |
212
+ | 0.1728 | 16.2 | 81000 | 0.6260 | 0.4634 |
213
+ | 0.1875 | 16.3 | 81500 | 0.6320 | 0.4724 |
214
+ | 0.1697 | 16.4 | 82000 | 0.6285 | 0.4734 |
215
+ | 0.1736 | 16.5 | 82500 | 0.6348 | 0.4743 |
216
+ | 0.1816 | 16.6 | 83000 | 0.6109 | 0.4878 |
217
+ | 0.1751 | 16.7 | 83500 | 0.6045 | 0.4797 |
218
+ | 0.1645 | 16.8 | 84000 | 0.5893 | 0.4824 |
219
+ | 0.1869 | 16.9 | 84500 | 0.5717 | 0.4833 |
220
+ | 0.1792 | 17.0 | 85000 | 0.5416 | 0.4914 |
221
+ | 0.178 | 17.1 | 85500 | 0.6184 | 0.4851 |
222
+ | 0.1652 | 17.2 | 86000 | 0.6139 | 0.4670 |
223
+ | 0.1658 | 17.3 | 86500 | 0.6055 | 0.4806 |
224
+ | 0.1899 | 17.4 | 87000 | 0.6243 | 0.4743 |
225
+ | 0.1715 | 17.5 | 87500 | 0.6521 | 0.4770 |
226
+ | 0.1622 | 17.6 | 88000 | 0.6003 | 0.4553 |
227
+ | 0.1722 | 17.7 | 88500 | 0.6221 | 0.4643 |
228
+ | 0.1762 | 17.8 | 89000 | 0.6031 | 0.4598 |
229
+ | 0.1567 | 17.9 | 89500 | 0.6585 | 0.4706 |
230
+ | 0.1536 | 18.0 | 90000 | 0.6632 | 0.4734 |
231
+ | 0.1459 | 18.1 | 90500 | 0.6663 | 0.4833 |
232
+ | 0.1555 | 18.2 | 91000 | 0.6163 | 0.4752 |
233
+ | 0.1558 | 18.3 | 91500 | 0.6267 | 0.4625 |
234
+ | 0.1662 | 18.4 | 92000 | 0.6019 | 0.4806 |
235
+ | 0.1496 | 18.5 | 92500 | 0.6495 | 0.4770 |
236
+ | 0.155 | 18.6 | 93000 | 0.5986 | 0.4860 |
237
+ | 0.1588 | 18.7 | 93500 | 0.6290 | 0.4860 |
238
+ | 0.1554 | 18.8 | 94000 | 0.6206 | 0.4661 |
239
+ | 0.1576 | 18.9 | 94500 | 0.6155 | 0.4715 |
240
+ | 0.1473 | 19.0 | 95000 | 0.6422 | 0.4661 |
241
+ | 0.1385 | 19.1 | 95500 | 0.6118 | 0.4679 |
242
+ | 0.1434 | 19.2 | 96000 | 0.6379 | 0.4652 |
243
+ | 0.1458 | 19.3 | 96500 | 0.6117 | 0.4625 |
244
+ | 0.1515 | 19.4 | 97000 | 0.5792 | 0.4697 |
245
+ | 0.1404 | 19.5 | 97500 | 0.6063 | 0.4697 |
246
+ | 0.1481 | 19.6 | 98000 | 0.6330 | 0.4643 |
247
+ | 0.1547 | 19.7 | 98500 | 0.6755 | 0.4815 |
248
+ | 0.1509 | 19.8 | 99000 | 0.6377 | 0.4887 |
249
+ | 0.145 | 19.9 | 99500 | 0.6011 | 0.4743 |
250
+ | 0.142 | 20.0 | 100000 | 0.5901 | 0.4914 |
251
+ | 0.1307 | 20.1 | 100500 | 0.6371 | 0.4815 |
252
+ | 0.137 | 20.2 | 101000 | 0.6539 | 0.4752 |
253
+ | 0.1427 | 20.3 | 101500 | 0.6443 | 0.4797 |
254
+ | 0.1363 | 20.4 | 102000 | 0.6750 | 0.4724 |
255
+ | 0.1349 | 20.5 | 102500 | 0.6614 | 0.4706 |
256
+ | 0.1352 | 20.6 | 103000 | 0.6520 | 0.4887 |
257
+ | 0.1376 | 20.7 | 103500 | 0.6448 | 0.5041 |
258
+ | 0.1401 | 20.8 | 104000 | 0.6240 | 0.4788 |
259
+ | 0.1244 | 20.9 | 104500 | 0.6442 | 0.4779 |
260
+ | 0.1328 | 21.0 | 105000 | 0.6642 | 0.4779 |
261
+ | 0.1375 | 21.1 | 105500 | 0.6823 | 0.4679 |
262
+ | 0.1312 | 21.2 | 106000 | 0.7251 | 0.4833 |
263
+ | 0.1302 | 21.3 | 106500 | 0.7144 | 0.4878 |
264
+ | 0.1477 | 21.4 | 107000 | 0.7017 | 0.4752 |
265
+ | 0.1195 | 21.5 | 107500 | 0.6747 | 0.4734 |
266
+ | 0.1212 | 21.6 | 108000 | 0.7303 | 0.4788 |
267
+ | 0.1203 | 21.7 | 108500 | 0.6792 | 0.4752 |
268
+ | 0.1302 | 21.8 | 109000 | 0.6635 | 0.4643 |
269
+ | 0.1308 | 21.9 | 109500 | 0.6453 | 0.4607 |
270
+ | 0.1297 | 22.0 | 110000 | 0.6521 | 0.4743 |
271
+ | 0.114 | 22.1 | 110500 | 0.6856 | 0.4679 |
272
+ | 0.1146 | 22.2 | 111000 | 0.6743 | 0.4661 |
273
+ | 0.1163 | 22.3 | 111500 | 0.6925 | 0.4715 |
274
+ | 0.1164 | 22.4 | 112000 | 0.6740 | 0.4688 |
275
+ | 0.1186 | 22.5 | 112500 | 0.6684 | 0.4670 |
276
+ | 0.1191 | 22.6 | 113000 | 0.6944 | 0.4752 |
277
+ | 0.1322 | 22.7 | 113500 | 0.6641 | 0.4571 |
278
+ | 0.1213 | 22.8 | 114000 | 0.6536 | 0.4706 |
279
+ | 0.1218 | 22.9 | 114500 | 0.6695 | 0.4724 |
280
+ | 0.12 | 23.0 | 115000 | 0.6867 | 0.4743 |
281
+ | 0.1229 | 23.1 | 115500 | 0.6998 | 0.4715 |
282
+ | 0.1072 | 23.2 | 116000 | 0.7036 | 0.4706 |
283
+ | 0.1152 | 23.3 | 116500 | 0.7637 | 0.4652 |
284
+ | 0.1045 | 23.4 | 117000 | 0.7213 | 0.4770 |
285
+ | 0.1066 | 23.5 | 117500 | 0.7134 | 0.4724 |
286
+ | 0.11 | 23.6 | 118000 | 0.6946 | 0.4670 |
287
+ | 0.103 | 23.7 | 118500 | 0.6868 | 0.4616 |
288
+ | 0.1043 | 23.8 | 119000 | 0.6887 | 0.4580 |
289
+ | 0.1076 | 23.9 | 119500 | 0.6531 | 0.4607 |
290
+ | 0.12 | 24.0 | 120000 | 0.6901 | 0.4706 |
291
+ | 0.1008 | 24.1 | 120500 | 0.6913 | 0.4661 |
292
+ | 0.0962 | 24.2 | 121000 | 0.6979 | 0.4715 |
293
+ | 0.1017 | 24.3 | 121500 | 0.7073 | 0.4815 |
294
+ | 0.1104 | 24.4 | 122000 | 0.7019 | 0.4724 |
295
+ | 0.0937 | 24.5 | 122500 | 0.7031 | 0.4806 |
296
+ | 0.1013 | 24.6 | 123000 | 0.6592 | 0.4770 |
297
+ | 0.0963 | 24.7 | 123500 | 0.6681 | 0.4706 |
298
+ | 0.1103 | 24.8 | 124000 | 0.6658 | 0.4598 |
299
+ | 0.1055 | 24.9 | 124500 | 0.6905 | 0.4706 |
300
+ | 0.1 | 25.0 | 125000 | 0.6904 | 0.4743 |
301
+ | 0.0866 | 25.1 | 125500 | 0.7020 | 0.4679 |
302
+ | 0.096 | 25.2 | 126000 | 0.7143 | 0.4679 |
303
+ | 0.0965 | 25.3 | 126500 | 0.6888 | 0.4553 |
304
+ | 0.1014 | 25.4 | 127000 | 0.6801 | 0.4499 |
305
+ | 0.095 | 25.5 | 127500 | 0.6610 | 0.4625 |
306
+ | 0.0968 | 25.6 | 128000 | 0.6971 | 0.4508 |
307
+ | 0.0903 | 25.7 | 128500 | 0.7054 | 0.4616 |
308
+ | 0.1007 | 25.8 | 129000 | 0.7010 | 0.4607 |
309
+ | 0.0857 | 25.9 | 129500 | 0.7039 | 0.4517 |
310
+ | 0.0915 | 26.0 | 130000 | 0.6864 | 0.4526 |
311
+ | 0.0884 | 26.1 | 130500 | 0.6973 | 0.4562 |
312
+ | 0.0883 | 26.2 | 131000 | 0.6978 | 0.4598 |
313
+ | 0.0897 | 26.3 | 131500 | 0.6601 | 0.4616 |
314
+ | 0.0906 | 26.4 | 132000 | 0.6796 | 0.4589 |
315
+ | 0.0857 | 26.5 | 132500 | 0.6934 | 0.4535 |
316
+ | 0.0861 | 26.6 | 133000 | 0.7189 | 0.4625 |
317
+ | 0.095 | 26.7 | 133500 | 0.7002 | 0.4598 |
318
+ | 0.0839 | 26.8 | 134000 | 0.6908 | 0.4670 |
319
+ | 0.0938 | 26.9 | 134500 | 0.6731 | 0.4589 |
320
+ | 0.0883 | 27.0 | 135000 | 0.6830 | 0.4571 |
321
+ | 0.0833 | 27.1 | 135500 | 0.6880 | 0.4580 |
322
+ | 0.0901 | 27.2 | 136000 | 0.7150 | 0.4571 |
323
+ | 0.0852 | 27.3 | 136500 | 0.7234 | 0.4580 |
324
+ | 0.0776 | 27.4 | 137000 | 0.7231 | 0.4616 |
325
+ | 0.0857 | 27.5 | 137500 | 0.7015 | 0.4625 |
326
+ | 0.0837 | 27.6 | 138000 | 0.7031 | 0.4553 |
327
+ | 0.0871 | 27.7 | 138500 | 0.7023 | 0.4544 |
328
+ | 0.0787 | 27.8 | 139000 | 0.7140 | 0.4571 |
329
+ | 0.0809 | 27.9 | 139500 | 0.7130 | 0.4625 |
330
+ | 0.0866 | 28.0 | 140000 | 0.6984 | 0.4508 |
331
+ | 0.0754 | 28.1 | 140500 | 0.7109 | 0.4652 |
332
+ | 0.0719 | 28.2 | 141000 | 0.7271 | 0.4544 |
333
+ | 0.0808 | 28.3 | 141500 | 0.7243 | 0.4553 |
334
+ | 0.0789 | 28.4 | 142000 | 0.7008 | 0.4598 |
335
+ | 0.0838 | 28.5 | 142500 | 0.7143 | 0.4598 |
336
+ | 0.0709 | 28.6 | 143000 | 0.7022 | 0.4562 |
337
+ | 0.0753 | 28.7 | 143500 | 0.6958 | 0.4526 |
338
+ | 0.0744 | 28.8 | 144000 | 0.7072 | 0.4544 |
339
+ | 0.0784 | 28.9 | 144500 | 0.7033 | 0.4526 |
340
+ | 0.0773 | 29.0 | 145000 | 0.7086 | 0.4562 |
341
+ | 0.0727 | 29.1 | 145500 | 0.7092 | 0.4544 |
342
+ | 0.0805 | 29.2 | 146000 | 0.7078 | 0.4571 |
343
+ | 0.0769 | 29.3 | 146500 | 0.7071 | 0.4544 |
344
+ | 0.0756 | 29.4 | 147000 | 0.7034 | 0.4544 |
345
+ | 0.0751 | 29.5 | 147500 | 0.7071 | 0.4535 |
346
+ | 0.069 | 29.6 | 148000 | 0.7072 | 0.4553 |
347
+ | 0.0746 | 29.7 | 148500 | 0.7077 | 0.4553 |
348
+ | 0.0743 | 29.8 | 149000 | 0.7091 | 0.4580 |
349
+ | 0.0763 | 29.9 | 149500 | 0.7085 | 0.4589 |
350
+ | 0.0688 | 30.0 | 150000 | 0.7077 | 0.4589 |
351
+
352
+
353
+ ### Framework versions
354
+
355
+ - Transformers 4.19.4
356
+ - Pytorch 1.11.0
357
+ - Datasets 2.2.2
358
+ - Tokenizers 0.12.1