Hugging Face's logo

TTian
/
deberta-classifier-feedback-1024-pseudo

Token Classification
Transformers
PyTorch
TensorBoard
deberta-v2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
TTian commited on
Commit
540b920
•
1 Parent(s): 1a82343

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +129 -0
README.md ADDED
@@ -0,0 +1,129 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: deberta-classifier-feedback-1024-pseudo
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
+ # deberta-classifier-feedback-1024-pseudo
14
+
15
+ This model is a fine-tuned version of [TTian/deberta-classifier-feedback-1024](https://huggingface.co/TTian/deberta-classifier-feedback-1024) on an unknown dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Loss: 1.1018
18
+
19
+ ## Model description
20
+
21
+ More information needed
22
+
23
+ ## Intended uses & limitations
24
+
25
+ More information needed
26
+
27
+ ## Training and evaluation data
28
+
29
+ More information needed
30
+
31
+ ## Training procedure
32
+
33
+ ### Training hyperparameters
34
+
35
+ The following hyperparameters were used during training:
36
+ - learning_rate: 2e-05
37
+ - train_batch_size: 8
38
+ - eval_batch_size: 8
39
+ - seed: 42
40
+ - gradient_accumulation_steps: 2
41
+ - total_train_batch_size: 16
42
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
+ - lr_scheduler_type: linear
44
+ - num_epochs: 1
45
+ - mixed_precision_training: Native AMP
46
+
47
+ ### Training results
48
+
49
+ | Training Loss | Epoch | Step | Validation Loss |
50
+ |:-------------:|:-----:|:----:|:---------------:|
51
+ | 0.5566 | 0.01 | 10 | 0.8514 |
52
+ | 0.3244 | 0.03 | 20 | 0.8647 |
53
+ | 0.2631 | 0.04 | 30 | 0.6700 |
54
+ | 0.2237 | 0.06 | 40 | 0.8904 |
55
+ | 0.2103 | 0.07 | 50 | 0.7951 |
56
+ | 0.2576 | 0.08 | 60 | 0.8669 |
57
+ | 0.2519 | 0.1 | 70 | 0.9586 |
58
+ | 0.2419 | 0.11 | 80 | 0.7507 |
59
+ | 0.2088 | 0.13 | 90 | 1.1316 |
60
+ | 0.218 | 0.14 | 100 | 0.7750 |
61
+ | 0.1886 | 0.15 | 110 | 0.9505 |
62
+ | 0.1979 | 0.17 | 120 | 0.9668 |
63
+ | 0.2069 | 0.18 | 130 | 0.9559 |
64
+ | 0.2633 | 0.2 | 140 | 1.1578 |
65
+ | 0.2176 | 0.21 | 150 | 0.9224 |
66
+ | 0.2026 | 0.22 | 160 | 0.9700 |
67
+ | 0.2231 | 0.24 | 170 | 1.0094 |
68
+ | 0.2396 | 0.25 | 180 | 1.1268 |
69
+ | 0.2172 | 0.27 | 190 | 0.9728 |
70
+ | 0.2105 | 0.28 | 200 | 0.9813 |
71
+ | 0.2816 | 0.29 | 210 | 0.8179 |
72
+ | 0.1927 | 0.31 | 220 | 1.0210 |
73
+ | 0.1686 | 0.32 | 230 | 1.0608 |
74
+ | 0.1662 | 0.34 | 240 | 0.9698 |
75
+ | 0.1969 | 0.35 | 250 | 0.9445 |
76
+ | 0.2037 | 0.36 | 260 | 1.0223 |
77
+ | 0.1684 | 0.38 | 270 | 0.9921 |
78
+ | 0.1934 | 0.39 | 280 | 0.9738 |
79
+ | 0.1927 | 0.41 | 290 | 0.9370 |
80
+ | 0.1978 | 0.42 | 300 | 1.0144 |
81
+ | 0.1591 | 0.43 | 310 | 0.9222 |
82
+ | 0.1748 | 0.45 | 320 | 0.9433 |
83
+ | 0.2245 | 0.46 | 330 | 0.9773 |
84
+ | 0.2297 | 0.48 | 340 | 0.9884 |
85
+ | 0.1746 | 0.49 | 350 | 1.0024 |
86
+ | 0.152 | 0.5 | 360 | 0.9463 |
87
+ | 0.1514 | 0.52 | 370 | 1.0633 |
88
+ | 0.1898 | 0.53 | 380 | 1.1181 |
89
+ | 0.1438 | 0.55 | 390 | 1.0994 |
90
+ | 0.1426 | 0.56 | 400 | 1.0228 |
91
+ | 0.1545 | 0.58 | 410 | 1.1413 |
92
+ | 0.146 | 0.59 | 420 | 1.0416 |
93
+ | 0.1295 | 0.6 | 430 | 1.0037 |
94
+ | 0.1538 | 0.62 | 440 | 1.0532 |
95
+ | 0.1584 | 0.63 | 450 | 1.1754 |
96
+ | 0.1607 | 0.65 | 460 | 1.0540 |
97
+ | 0.1518 | 0.66 | 470 | 1.0318 |
98
+ | 0.1447 | 0.67 | 480 | 1.0777 |
99
+ | 0.1432 | 0.69 | 490 | 1.0318 |
100
+ | 0.1491 | 0.7 | 500 | 1.0717 |
101
+ | 0.1134 | 0.72 | 510 | 1.0512 |
102
+ | 0.1106 | 0.73 | 520 | 1.1904 |
103
+ | 0.1521 | 0.74 | 530 | 1.0705 |
104
+ | 0.1485 | 0.76 | 540 | 1.0390 |
105
+ | 0.1431 | 0.77 | 550 | 1.1089 |
106
+ | 0.1537 | 0.79 | 560 | 1.0316 |
107
+ | 0.1472 | 0.8 | 570 | 1.1694 |
108
+ | 0.129 | 0.81 | 580 | 1.1325 |
109
+ | 0.1286 | 0.83 | 590 | 1.0471 |
110
+ | 0.1338 | 0.84 | 600 | 1.1001 |
111
+ | 0.1285 | 0.86 | 610 | 1.0770 |
112
+ | 0.1379 | 0.87 | 620 | 1.1107 |
113
+ | 0.1299 | 0.88 | 630 | 1.0579 |
114
+ | 0.1151 | 0.9 | 640 | 1.0898 |
115
+ | 0.1119 | 0.91 | 650 | 1.1335 |
116
+ | 0.1297 | 0.93 | 660 | 1.1061 |
117
+ | 0.1218 | 0.94 | 670 | 1.1080 |
118
+ | 0.1038 | 0.95 | 680 | 1.0922 |
119
+ | 0.1286 | 0.97 | 690 | 1.1035 |
120
+ | 0.1263 | 0.98 | 700 | 1.1118 |
121
+ | 0.1182 | 1.0 | 710 | 1.1018 |
122
+
123
+
124
+ ### Framework versions
125
+
126
+ - Transformers 4.24.0
127
+ - Pytorch 1.12.1+cu113
128
+ - Datasets 2.7.1
129
+ - Tokenizers 0.13.2