Commit
•
080c1e8
1
Parent(s):
56bcd8a
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,344 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: cc0-1.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: wav2vec2-large-voxrex-npsc-nst
|
| 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-large-voxrex-npsc-nst
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [KBLab/wav2vec2-large-voxrex](https://huggingface.co/KBLab/wav2vec2-large-voxrex) on the None dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 0.0475
|
| 18 |
+
- Wer: 0.0514
|
| 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: 0.0001
|
| 38 |
+
- train_batch_size: 16
|
| 39 |
+
- eval_batch_size: 16
|
| 40 |
+
- seed: 42
|
| 41 |
+
- gradient_accumulation_steps: 2
|
| 42 |
+
- total_train_batch_size: 32
|
| 43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
+
- lr_scheduler_type: linear
|
| 45 |
+
- lr_scheduler_warmup_steps: 2000
|
| 46 |
+
- num_epochs: 15.0
|
| 47 |
+
- mixed_precision_training: Native AMP
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 52 |
+
|:-------------:|:-----:|:------:|:---------------:|:------:|
|
| 53 |
+
| 3.3888 | 0.05 | 500 | 3.2558 | 1.0 |
|
| 54 |
+
| 2.7683 | 0.11 | 1000 | 2.4163 | 1.0000 |
|
| 55 |
+
| 0.6279 | 0.16 | 1500 | 0.3610 | 0.3608 |
|
| 56 |
+
| 0.5093 | 0.21 | 2000 | 0.2610 | 0.2776 |
|
| 57 |
+
| 0.4024 | 0.26 | 2500 | 0.2219 | 0.2303 |
|
| 58 |
+
| 0.3705 | 0.32 | 3000 | 0.1940 | 0.2043 |
|
| 59 |
+
| 0.3588 | 0.37 | 3500 | 0.1806 | 0.1822 |
|
| 60 |
+
| 0.3312 | 0.42 | 4000 | 0.1611 | 0.1736 |
|
| 61 |
+
| 0.3062 | 0.47 | 4500 | 0.1571 | 0.1619 |
|
| 62 |
+
| 0.2838 | 0.53 | 5000 | 0.1482 | 0.1552 |
|
| 63 |
+
| 0.2896 | 0.58 | 5500 | 0.1406 | 0.1482 |
|
| 64 |
+
| 0.2704 | 0.63 | 6000 | 0.1311 | 0.1467 |
|
| 65 |
+
| 0.263 | 0.69 | 6500 | 0.1258 | 0.1406 |
|
| 66 |
+
| 0.2574 | 0.74 | 7000 | 0.1252 | 0.1343 |
|
| 67 |
+
| 0.252 | 0.79 | 7500 | 0.1162 | 0.1279 |
|
| 68 |
+
| 0.2355 | 0.84 | 8000 | 0.1161 | 0.1275 |
|
| 69 |
+
| 0.2381 | 0.9 | 8500 | 0.1095 | 0.1247 |
|
| 70 |
+
| 0.2354 | 0.95 | 9000 | 0.1106 | 0.1250 |
|
| 71 |
+
| 0.234 | 1.0 | 9500 | 0.1044 | 0.1186 |
|
| 72 |
+
| 0.2094 | 1.05 | 10000 | 0.1052 | 0.1157 |
|
| 73 |
+
| 0.2088 | 1.11 | 10500 | 0.1026 | 0.1158 |
|
| 74 |
+
| 0.2123 | 1.16 | 11000 | 0.0998 | 0.1120 |
|
| 75 |
+
| 0.3087 | 1.21 | 11500 | 0.0971 | 0.1108 |
|
| 76 |
+
| 0.1995 | 1.26 | 12000 | 0.0973 | 0.1085 |
|
| 77 |
+
| 0.1989 | 1.32 | 12500 | 0.0928 | 0.1063 |
|
| 78 |
+
| 0.1993 | 1.37 | 13000 | 0.0920 | 0.1064 |
|
| 79 |
+
| 0.1996 | 1.42 | 13500 | 0.0904 | 0.1050 |
|
| 80 |
+
| 0.1917 | 1.48 | 14000 | 0.0895 | 0.1051 |
|
| 81 |
+
| 0.1857 | 1.53 | 14500 | 0.0889 | 0.1038 |
|
| 82 |
+
| 0.1871 | 1.58 | 15000 | 0.0867 | 0.1054 |
|
| 83 |
+
| 0.2047 | 1.63 | 15500 | 0.0866 | 0.1017 |
|
| 84 |
+
| 0.1845 | 1.69 | 16000 | 0.0865 | 0.1007 |
|
| 85 |
+
| 0.178 | 1.74 | 16500 | 0.0835 | 0.0999 |
|
| 86 |
+
| 0.1741 | 1.79 | 17000 | 0.0838 | 0.0985 |
|
| 87 |
+
| 0.1737 | 1.84 | 17500 | 0.0833 | 0.0966 |
|
| 88 |
+
| 0.1713 | 1.9 | 18000 | 0.0799 | 0.0963 |
|
| 89 |
+
| 0.1703 | 1.95 | 18500 | 0.0802 | 0.0950 |
|
| 90 |
+
| 0.1735 | 2.0 | 19000 | 0.0785 | 0.0926 |
|
| 91 |
+
| 0.1619 | 2.06 | 19500 | 0.0785 | 0.0930 |
|
| 92 |
+
| 0.1707 | 2.11 | 20000 | 0.0787 | 0.0928 |
|
| 93 |
+
| 0.17 | 2.16 | 20500 | 0.0765 | 0.0902 |
|
| 94 |
+
| 0.1604 | 2.21 | 21000 | 0.0772 | 0.0918 |
|
| 95 |
+
| 0.1576 | 2.27 | 21500 | 0.0745 | 0.0912 |
|
| 96 |
+
| 0.1529 | 2.32 | 22000 | 0.0741 | 0.0906 |
|
| 97 |
+
| 0.1435 | 2.37 | 22500 | 0.0751 | 0.0888 |
|
| 98 |
+
| 0.1526 | 2.42 | 23000 | 0.0734 | 0.0892 |
|
| 99 |
+
| 0.1471 | 2.48 | 23500 | 0.0746 | 0.0886 |
|
| 100 |
+
| 0.1553 | 2.53 | 24000 | 0.0727 | 0.0872 |
|
| 101 |
+
| 0.1641 | 2.58 | 24500 | 0.0720 | 0.0862 |
|
| 102 |
+
| 0.1495 | 2.64 | 25000 | 0.0707 | 0.0868 |
|
| 103 |
+
| 0.1498 | 2.69 | 25500 | 0.0719 | 0.0864 |
|
| 104 |
+
| 0.1438 | 2.74 | 26000 | 0.0703 | 0.0853 |
|
| 105 |
+
| 0.1532 | 2.79 | 26500 | 0.0710 | 0.0854 |
|
| 106 |
+
| 0.1435 | 2.85 | 27000 | 0.0690 | 0.0847 |
|
| 107 |
+
| 0.1486 | 2.9 | 27500 | 0.0683 | 0.0882 |
|
| 108 |
+
| 0.1359 | 2.95 | 28000 | 0.0673 | 0.0839 |
|
| 109 |
+
| 0.1309 | 3.0 | 28500 | 0.0687 | 0.0843 |
|
| 110 |
+
| 0.1312 | 3.06 | 29000 | 0.0696 | 0.0865 |
|
| 111 |
+
| 0.1387 | 3.11 | 29500 | 0.0667 | 0.0857 |
|
| 112 |
+
| 0.1327 | 3.16 | 30000 | 0.0667 | 0.0845 |
|
| 113 |
+
| 0.1251 | 3.21 | 30500 | 0.0662 | 0.0820 |
|
| 114 |
+
| 0.1415 | 3.27 | 31000 | 0.0652 | 0.0831 |
|
| 115 |
+
| 0.1221 | 3.32 | 31500 | 0.0660 | 0.0822 |
|
| 116 |
+
| 0.1337 | 3.37 | 32000 | 0.0658 | 0.0799 |
|
| 117 |
+
| 0.1342 | 3.43 | 32500 | 0.0650 | 0.0808 |
|
| 118 |
+
| 0.1391 | 3.48 | 33000 | 0.0658 | 0.0791 |
|
| 119 |
+
| 0.1351 | 3.53 | 33500 | 0.0654 | 0.0794 |
|
| 120 |
+
| 0.1309 | 3.58 | 34000 | 0.0650 | 0.0781 |
|
| 121 |
+
| 0.1317 | 3.64 | 34500 | 0.0629 | 0.0783 |
|
| 122 |
+
| 0.1326 | 3.69 | 35000 | 0.0637 | 0.0795 |
|
| 123 |
+
| 0.1296 | 3.74 | 35500 | 0.0624 | 0.0773 |
|
| 124 |
+
| 0.1156 | 3.79 | 36000 | 0.0613 | 0.0759 |
|
| 125 |
+
| 0.1242 | 3.85 | 36500 | 0.0627 | 0.0761 |
|
| 126 |
+
| 0.1251 | 3.9 | 37000 | 0.0638 | 0.0758 |
|
| 127 |
+
| 0.1335 | 3.95 | 37500 | 0.0620 | 0.0756 |
|
| 128 |
+
| 0.1374 | 4.01 | 38000 | 0.0628 | 0.0756 |
|
| 129 |
+
| 0.1227 | 4.06 | 38500 | 0.0637 | 0.0770 |
|
| 130 |
+
| 0.1144 | 4.11 | 39000 | 0.0637 | 0.0775 |
|
| 131 |
+
| 0.1222 | 4.16 | 39500 | 0.0630 | 0.0738 |
|
| 132 |
+
| 0.1207 | 4.22 | 40000 | 0.0607 | 0.0720 |
|
| 133 |
+
| 0.1181 | 4.27 | 40500 | 0.0608 | 0.0724 |
|
| 134 |
+
| 0.1259 | 4.32 | 41000 | 0.0608 | 0.0734 |
|
| 135 |
+
| 0.1137 | 4.37 | 41500 | 0.0623 | 0.0718 |
|
| 136 |
+
| 0.1275 | 4.43 | 42000 | 0.0620 | 0.0721 |
|
| 137 |
+
| 0.1218 | 4.48 | 42500 | 0.0599 | 0.0703 |
|
| 138 |
+
| 0.1212 | 4.53 | 43000 | 0.0612 | 0.0708 |
|
| 139 |
+
| 0.1144 | 4.59 | 43500 | 0.0589 | 0.0702 |
|
| 140 |
+
| 0.1199 | 4.64 | 44000 | 0.0589 | 0.0695 |
|
| 141 |
+
| 0.1113 | 4.69 | 44500 | 0.0601 | 0.0698 |
|
| 142 |
+
| 0.1108 | 4.74 | 45000 | 0.0584 | 0.0695 |
|
| 143 |
+
| 0.1196 | 4.8 | 45500 | 0.0596 | 0.0694 |
|
| 144 |
+
| 0.1216 | 4.85 | 46000 | 0.0578 | 0.0703 |
|
| 145 |
+
| 0.1188 | 4.9 | 46500 | 0.0596 | 0.0684 |
|
| 146 |
+
| 0.1122 | 4.95 | 47000 | 0.0584 | 0.0671 |
|
| 147 |
+
| 0.1115 | 5.01 | 47500 | 0.0594 | 0.0682 |
|
| 148 |
+
| 0.1777 | 5.06 | 48000 | 0.0597 | 0.0682 |
|
| 149 |
+
| 0.108 | 5.11 | 48500 | 0.0573 | 0.0691 |
|
| 150 |
+
| 0.1132 | 5.16 | 49000 | 0.0583 | 0.0666 |
|
| 151 |
+
| 0.1091 | 5.22 | 49500 | 0.0582 | 0.0672 |
|
| 152 |
+
| 0.1056 | 5.27 | 50000 | 0.0578 | 0.0674 |
|
| 153 |
+
| 0.1027 | 5.32 | 50500 | 0.0574 | 0.0671 |
|
| 154 |
+
| 0.1112 | 5.38 | 51000 | 0.0569 | 0.0659 |
|
| 155 |
+
| 0.1096 | 5.43 | 51500 | 0.0582 | 0.0662 |
|
| 156 |
+
| 0.1098 | 5.48 | 52000 | 0.0576 | 0.0667 |
|
| 157 |
+
| 0.1088 | 5.53 | 52500 | 0.0560 | 0.0679 |
|
| 158 |
+
| 0.1076 | 5.59 | 53000 | 0.0579 | 0.0664 |
|
| 159 |
+
| 0.1037 | 5.64 | 53500 | 0.0556 | 0.0661 |
|
| 160 |
+
| 0.1039 | 5.69 | 54000 | 0.0572 | 0.0675 |
|
| 161 |
+
| 0.108 | 5.74 | 54500 | 0.0562 | 0.0662 |
|
| 162 |
+
| 0.1069 | 5.8 | 55000 | 0.0576 | 0.0663 |
|
| 163 |
+
| 0.1066 | 5.85 | 55500 | 0.0564 | 0.0651 |
|
| 164 |
+
| 0.0939 | 5.9 | 56000 | 0.0566 | 0.0644 |
|
| 165 |
+
| 0.1118 | 5.96 | 56500 | 0.0570 | 0.0650 |
|
| 166 |
+
| 0.1111 | 6.01 | 57000 | 0.0563 | 0.0668 |
|
| 167 |
+
| 0.1014 | 6.06 | 57500 | 0.0557 | 0.0660 |
|
| 168 |
+
| 0.0971 | 6.11 | 58000 | 0.0567 | 0.0667 |
|
| 169 |
+
| 0.0932 | 6.17 | 58500 | 0.0559 | 0.0664 |
|
| 170 |
+
| 0.1002 | 6.22 | 59000 | 0.0551 | 0.0640 |
|
| 171 |
+
| 0.1028 | 6.27 | 59500 | 0.0560 | 0.0629 |
|
| 172 |
+
| 0.0992 | 6.32 | 60000 | 0.0547 | 0.0641 |
|
| 173 |
+
| 0.0975 | 6.38 | 60500 | 0.0556 | 0.0630 |
|
| 174 |
+
| 0.0957 | 6.43 | 61000 | 0.0555 | 0.0632 |
|
| 175 |
+
| 0.0931 | 6.48 | 61500 | 0.0546 | 0.0641 |
|
| 176 |
+
| 0.0999 | 6.54 | 62000 | 0.0556 | 0.0633 |
|
| 177 |
+
| 0.0998 | 6.59 | 62500 | 0.0539 | 0.0628 |
|
| 178 |
+
| 0.0991 | 6.64 | 63000 | 0.0559 | 0.0630 |
|
| 179 |
+
| 0.1027 | 6.69 | 63500 | 0.0549 | 0.0628 |
|
| 180 |
+
| 0.097 | 6.75 | 64000 | 0.0547 | 0.0628 |
|
| 181 |
+
| 0.0933 | 6.8 | 64500 | 0.0544 | 0.0633 |
|
| 182 |
+
| 0.0919 | 6.85 | 65000 | 0.0535 | 0.0640 |
|
| 183 |
+
| 0.0973 | 6.9 | 65500 | 0.0543 | 0.0619 |
|
| 184 |
+
| 0.0979 | 6.96 | 66000 | 0.0525 | 0.0620 |
|
| 185 |
+
| 0.1076 | 7.01 | 66500 | 0.0529 | 0.0615 |
|
| 186 |
+
| 0.0888 | 7.06 | 67000 | 0.0546 | 0.0617 |
|
| 187 |
+
| 0.0926 | 7.11 | 67500 | 0.0530 | 0.0636 |
|
| 188 |
+
| 0.0902 | 7.17 | 68000 | 0.0540 | 0.0631 |
|
| 189 |
+
| 0.1004 | 7.22 | 68500 | 0.0529 | 0.0624 |
|
| 190 |
+
| 0.0963 | 7.27 | 69000 | 0.0534 | 0.0631 |
|
| 191 |
+
| 0.0946 | 7.33 | 69500 | 0.0534 | 0.0601 |
|
| 192 |
+
| 0.0897 | 7.38 | 70000 | 0.0525 | 0.0607 |
|
| 193 |
+
| 0.0925 | 7.43 | 70500 | 0.0535 | 0.0599 |
|
| 194 |
+
| 0.0883 | 7.48 | 71000 | 0.0518 | 0.0605 |
|
| 195 |
+
| 0.0942 | 7.54 | 71500 | 0.0522 | 0.0587 |
|
| 196 |
+
| 0.0863 | 7.59 | 72000 | 0.0533 | 0.0593 |
|
| 197 |
+
| 0.0894 | 7.64 | 72500 | 0.0529 | 0.0587 |
|
| 198 |
+
| 0.0908 | 7.69 | 73000 | 0.0519 | 0.0596 |
|
| 199 |
+
| 0.0878 | 7.75 | 73500 | 0.0521 | 0.0585 |
|
| 200 |
+
| 0.0949 | 7.8 | 74000 | 0.0524 | 0.0588 |
|
| 201 |
+
| 0.0962 | 7.85 | 74500 | 0.0521 | 0.0581 |
|
| 202 |
+
| 0.0918 | 7.91 | 75000 | 0.0513 | 0.0579 |
|
| 203 |
+
| 0.0933 | 7.96 | 75500 | 0.0522 | 0.0582 |
|
| 204 |
+
| 0.0839 | 8.01 | 76000 | 0.0536 | 0.0579 |
|
| 205 |
+
| 0.0868 | 8.06 | 76500 | 0.0526 | 0.0577 |
|
| 206 |
+
| 0.086 | 8.12 | 77000 | 0.0525 | 0.0590 |
|
| 207 |
+
| 0.0801 | 8.17 | 77500 | 0.0533 | 0.0586 |
|
| 208 |
+
| 0.0845 | 8.22 | 78000 | 0.0516 | 0.0578 |
|
| 209 |
+
| 0.0895 | 8.27 | 78500 | 0.0530 | 0.0583 |
|
| 210 |
+
| 0.0841 | 8.33 | 79000 | 0.0515 | 0.0584 |
|
| 211 |
+
| 0.0921 | 8.38 | 79500 | 0.0518 | 0.0573 |
|
| 212 |
+
| 0.0897 | 8.43 | 80000 | 0.0514 | 0.0583 |
|
| 213 |
+
| 0.0889 | 8.49 | 80500 | 0.0508 | 0.0582 |
|
| 214 |
+
| 0.1783 | 8.54 | 81000 | 0.0507 | 0.0574 |
|
| 215 |
+
| 0.0854 | 8.59 | 81500 | 0.0505 | 0.0580 |
|
| 216 |
+
| 0.0855 | 8.64 | 82000 | 0.0513 | 0.0577 |
|
| 217 |
+
| 0.0843 | 8.7 | 82500 | 0.0508 | 0.0580 |
|
| 218 |
+
| 0.0858 | 8.75 | 83000 | 0.0501 | 0.0578 |
|
| 219 |
+
| 0.0814 | 8.8 | 83500 | 0.0509 | 0.0580 |
|
| 220 |
+
| 0.0823 | 8.85 | 84000 | 0.0509 | 0.0575 |
|
| 221 |
+
| 0.0857 | 8.91 | 84500 | 0.0499 | 0.0599 |
|
| 222 |
+
| 0.0787 | 8.96 | 85000 | 0.0505 | 0.0598 |
|
| 223 |
+
| 0.0805 | 9.01 | 85500 | 0.0510 | 0.0606 |
|
| 224 |
+
| 0.0798 | 9.07 | 86000 | 0.0515 | 0.0603 |
|
| 225 |
+
| 0.0812 | 9.12 | 86500 | 0.0507 | 0.0586 |
|
| 226 |
+
| 0.0781 | 9.17 | 87000 | 0.0511 | 0.0612 |
|
| 227 |
+
| 0.0814 | 9.22 | 87500 | 0.0508 | 0.0589 |
|
| 228 |
+
| 0.0821 | 9.28 | 88000 | 0.0507 | 0.0588 |
|
| 229 |
+
| 0.0808 | 9.33 | 88500 | 0.0498 | 0.0571 |
|
| 230 |
+
| 0.0793 | 9.38 | 89000 | 0.0502 | 0.0574 |
|
| 231 |
+
| 0.0791 | 9.43 | 89500 | 0.0498 | 0.0568 |
|
| 232 |
+
| 0.0779 | 9.49 | 90000 | 0.0507 | 0.0570 |
|
| 233 |
+
| 0.0777 | 9.54 | 90500 | 0.0508 | 0.0573 |
|
| 234 |
+
| 0.0816 | 9.59 | 91000 | 0.0493 | 0.0573 |
|
| 235 |
+
| 0.0835 | 9.64 | 91500 | 0.0496 | 0.0563 |
|
| 236 |
+
| 0.0827 | 9.7 | 92000 | 0.0493 | 0.0559 |
|
| 237 |
+
| 0.0904 | 9.75 | 92500 | 0.0492 | 0.0564 |
|
| 238 |
+
| 0.0753 | 9.8 | 93000 | 0.0503 | 0.0557 |
|
| 239 |
+
| 0.0748 | 9.86 | 93500 | 0.0493 | 0.0554 |
|
| 240 |
+
| 0.0759 | 9.91 | 94000 | 0.0499 | 0.0557 |
|
| 241 |
+
| 0.0825 | 9.96 | 94500 | 0.0498 | 0.0566 |
|
| 242 |
+
| 0.0787 | 10.01 | 95000 | 0.0499 | 0.0561 |
|
| 243 |
+
| 0.0804 | 10.07 | 95500 | 0.0499 | 0.0562 |
|
| 244 |
+
| 0.0784 | 10.12 | 96000 | 0.0500 | 0.0555 |
|
| 245 |
+
| 0.0747 | 10.17 | 96500 | 0.0497 | 0.0548 |
|
| 246 |
+
| 0.0748 | 10.22 | 97000 | 0.0492 | 0.0565 |
|
| 247 |
+
| 0.0732 | 10.28 | 97500 | 0.0493 | 0.0547 |
|
| 248 |
+
| 0.0766 | 10.33 | 98000 | 0.0490 | 0.0552 |
|
| 249 |
+
| 0.0762 | 10.38 | 98500 | 0.0504 | 0.0551 |
|
| 250 |
+
| 0.0744 | 10.44 | 99000 | 0.0496 | 0.0553 |
|
| 251 |
+
| 0.0702 | 10.49 | 99500 | 0.0496 | 0.0548 |
|
| 252 |
+
| 0.0802 | 10.54 | 100000 | 0.0499 | 0.0545 |
|
| 253 |
+
| 0.1605 | 10.59 | 100500 | 0.0477 | 0.0543 |
|
| 254 |
+
| 0.0768 | 10.65 | 101000 | 0.0487 | 0.0552 |
|
| 255 |
+
| 0.0833 | 10.7 | 101500 | 0.0495 | 0.0550 |
|
| 256 |
+
| 0.0782 | 10.75 | 102000 | 0.0479 | 0.0553 |
|
| 257 |
+
| 0.0813 | 10.8 | 102500 | 0.0490 | 0.0542 |
|
| 258 |
+
| 0.0712 | 10.86 | 103000 | 0.0485 | 0.0541 |
|
| 259 |
+
| 0.0703 | 10.91 | 103500 | 0.0486 | 0.0544 |
|
| 260 |
+
| 0.0765 | 10.96 | 104000 | 0.0480 | 0.0538 |
|
| 261 |
+
| 0.0796 | 11.02 | 104500 | 0.0486 | 0.0535 |
|
| 262 |
+
| 0.0778 | 11.07 | 105000 | 0.0492 | 0.0535 |
|
| 263 |
+
| 0.0735 | 11.12 | 105500 | 0.0494 | 0.0533 |
|
| 264 |
+
| 0.068 | 11.17 | 106000 | 0.0485 | 0.0528 |
|
| 265 |
+
| 0.0687 | 11.23 | 106500 | 0.0498 | 0.0534 |
|
| 266 |
+
| 0.0641 | 11.28 | 107000 | 0.0493 | 0.0534 |
|
| 267 |
+
| 0.0712 | 11.33 | 107500 | 0.0485 | 0.0526 |
|
| 268 |
+
| 0.0827 | 11.38 | 108000 | 0.0484 | 0.0530 |
|
| 269 |
+
| 0.0715 | 11.44 | 108500 | 0.0480 | 0.0533 |
|
| 270 |
+
| 0.0733 | 11.49 | 109000 | 0.0482 | 0.0532 |
|
| 271 |
+
| 0.0754 | 11.54 | 109500 | 0.0481 | 0.0537 |
|
| 272 |
+
| 0.0719 | 11.59 | 110000 | 0.0475 | 0.0533 |
|
| 273 |
+
| 0.0707 | 11.65 | 110500 | 0.0479 | 0.0536 |
|
| 274 |
+
| 0.0687 | 11.7 | 111000 | 0.0483 | 0.0535 |
|
| 275 |
+
| 0.0713 | 11.75 | 111500 | 0.0485 | 0.0535 |
|
| 276 |
+
| 0.0674 | 11.81 | 112000 | 0.0482 | 0.0537 |
|
| 277 |
+
| 0.0704 | 11.86 | 112500 | 0.0487 | 0.0537 |
|
| 278 |
+
| 0.0691 | 11.91 | 113000 | 0.0484 | 0.0541 |
|
| 279 |
+
| 0.0708 | 11.96 | 113500 | 0.0485 | 0.0548 |
|
| 280 |
+
| 0.0683 | 12.02 | 114000 | 0.0487 | 0.0541 |
|
| 281 |
+
| 0.0691 | 12.07 | 114500 | 0.0492 | 0.0540 |
|
| 282 |
+
| 0.0679 | 12.12 | 115000 | 0.0486 | 0.0540 |
|
| 283 |
+
| 0.073 | 12.17 | 115500 | 0.0479 | 0.0545 |
|
| 284 |
+
| 0.0647 | 12.23 | 116000 | 0.0484 | 0.0534 |
|
| 285 |
+
| 0.0663 | 12.28 | 116500 | 0.0484 | 0.0532 |
|
| 286 |
+
| 0.0687 | 12.33 | 117000 | 0.0483 | 0.0532 |
|
| 287 |
+
| 0.0696 | 12.39 | 117500 | 0.0482 | 0.0541 |
|
| 288 |
+
| 0.068 | 12.44 | 118000 | 0.0487 | 0.0531 |
|
| 289 |
+
| 0.0681 | 12.49 | 118500 | 0.0483 | 0.0530 |
|
| 290 |
+
| 0.0774 | 12.54 | 119000 | 0.0481 | 0.0533 |
|
| 291 |
+
| 0.0656 | 12.6 | 119500 | 0.0484 | 0.0529 |
|
| 292 |
+
| 0.0628 | 12.65 | 120000 | 0.0479 | 0.0533 |
|
| 293 |
+
| 0.0657 | 12.7 | 120500 | 0.0490 | 0.0538 |
|
| 294 |
+
| 0.0668 | 12.75 | 121000 | 0.0485 | 0.0533 |
|
| 295 |
+
| 0.0656 | 12.81 | 121500 | 0.0484 | 0.0531 |
|
| 296 |
+
| 0.0745 | 12.86 | 122000 | 0.0474 | 0.0526 |
|
| 297 |
+
| 0.0654 | 12.91 | 122500 | 0.0485 | 0.0528 |
|
| 298 |
+
| 0.0764 | 12.97 | 123000 | 0.0482 | 0.0529 |
|
| 299 |
+
| 0.0673 | 13.02 | 123500 | 0.0491 | 0.0526 |
|
| 300 |
+
| 0.0649 | 13.07 | 124000 | 0.0489 | 0.0527 |
|
| 301 |
+
| 0.0655 | 13.12 | 124500 | 0.0485 | 0.0520 |
|
| 302 |
+
| 0.0688 | 13.18 | 125000 | 0.0476 | 0.0524 |
|
| 303 |
+
| 0.0683 | 13.23 | 125500 | 0.0475 | 0.0523 |
|
| 304 |
+
| 0.0632 | 13.28 | 126000 | 0.0480 | 0.0528 |
|
| 305 |
+
| 0.063 | 13.33 | 126500 | 0.0483 | 0.0528 |
|
| 306 |
+
| 0.1418 | 13.39 | 127000 | 0.0464 | 0.0531 |
|
| 307 |
+
| 0.0693 | 13.44 | 127500 | 0.0473 | 0.0525 |
|
| 308 |
+
| 0.0696 | 13.49 | 128000 | 0.0477 | 0.0519 |
|
| 309 |
+
| 0.0644 | 13.54 | 128500 | 0.0477 | 0.0520 |
|
| 310 |
+
| 0.0625 | 13.6 | 129000 | 0.0480 | 0.0518 |
|
| 311 |
+
| 0.0682 | 13.65 | 129500 | 0.0471 | 0.0517 |
|
| 312 |
+
| 0.0698 | 13.7 | 130000 | 0.0480 | 0.0521 |
|
| 313 |
+
| 0.0643 | 13.76 | 130500 | 0.0482 | 0.0522 |
|
| 314 |
+
| 0.065 | 13.81 | 131000 | 0.0478 | 0.0521 |
|
| 315 |
+
| 0.0648 | 13.86 | 131500 | 0.0482 | 0.0519 |
|
| 316 |
+
| 0.0689 | 13.91 | 132000 | 0.0476 | 0.0520 |
|
| 317 |
+
| 0.0721 | 13.97 | 132500 | 0.0473 | 0.0523 |
|
| 318 |
+
| 0.0652 | 14.02 | 133000 | 0.0474 | 0.0519 |
|
| 319 |
+
| 0.0651 | 14.07 | 133500 | 0.0479 | 0.0519 |
|
| 320 |
+
| 0.0638 | 14.12 | 134000 | 0.0478 | 0.0520 |
|
| 321 |
+
| 0.0626 | 14.18 | 134500 | 0.0482 | 0.0519 |
|
| 322 |
+
| 0.0656 | 14.23 | 135000 | 0.0479 | 0.0521 |
|
| 323 |
+
| 0.0633 | 14.28 | 135500 | 0.0478 | 0.0519 |
|
| 324 |
+
| 0.0665 | 14.34 | 136000 | 0.0480 | 0.0519 |
|
| 325 |
+
| 0.0638 | 14.39 | 136500 | 0.0478 | 0.0517 |
|
| 326 |
+
| 0.0691 | 14.44 | 137000 | 0.0474 | 0.0515 |
|
| 327 |
+
| 0.0642 | 14.49 | 137500 | 0.0476 | 0.0514 |
|
| 328 |
+
| 0.0696 | 14.55 | 138000 | 0.0475 | 0.0515 |
|
| 329 |
+
| 0.0601 | 14.6 | 138500 | 0.0478 | 0.0515 |
|
| 330 |
+
| 0.0616 | 14.65 | 139000 | 0.0476 | 0.0515 |
|
| 331 |
+
| 0.0648 | 14.7 | 139500 | 0.0477 | 0.0516 |
|
| 332 |
+
| 0.0682 | 14.76 | 140000 | 0.0477 | 0.0515 |
|
| 333 |
+
| 0.0641 | 14.81 | 140500 | 0.0474 | 0.0515 |
|
| 334 |
+
| 0.0579 | 14.86 | 141000 | 0.0475 | 0.0514 |
|
| 335 |
+
| 0.0613 | 14.92 | 141500 | 0.0475 | 0.0514 |
|
| 336 |
+
| 0.0624 | 14.97 | 142000 | 0.0475 | 0.0514 |
|
| 337 |
+
|
| 338 |
+
|
| 339 |
+
### Framework versions
|
| 340 |
+
|
| 341 |
+
- Transformers 4.18.0
|
| 342 |
+
- Pytorch 1.11.0+cu113
|
| 343 |
+
- Datasets 2.1.0
|
| 344 |
+
- Tokenizers 0.12.1
|