MuhammadIqbalBazmi commited on
Commit
fc6b38b
1 Parent(s): 97104f3

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +106 -0
README.md ADDED
@@ -0,0 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - accuracy
7
+ model-index:
8
+ - name: wav2vec2-xls-r-300m-intent-classification-ori
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # wav2vec2-xls-r-300m-intent-classification-ori
16
+
17
+ This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the None dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 1.3107
20
+ - Accuracy: 0.625
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 3e-05
40
+ - train_batch_size: 2
41
+ - eval_batch_size: 2
42
+ - seed: 42
43
+ - gradient_accumulation_steps: 4
44
+ - total_train_batch_size: 8
45
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
+ - lr_scheduler_type: linear
47
+ - lr_scheduler_warmup_ratio: 0.1
48
+ - num_epochs: 45
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
53
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
54
+ | 2.1982 | 1.0 | 14 | 2.1951 | 0.0625 |
55
+ | 2.2021 | 2.0 | 28 | 2.1847 | 0.1458 |
56
+ | 2.1819 | 3.0 | 42 | 2.1661 | 0.3333 |
57
+ | 2.1789 | 4.0 | 56 | 2.1413 | 0.3333 |
58
+ | 2.164 | 5.0 | 70 | 2.1183 | 0.3333 |
59
+ | 2.1484 | 6.0 | 84 | 2.0974 | 0.3333 |
60
+ | 2.1199 | 7.0 | 98 | 2.0939 | 0.3333 |
61
+ | 2.1343 | 8.0 | 112 | 2.0829 | 0.3333 |
62
+ | 2.1397 | 9.0 | 126 | 2.0654 | 0.3333 |
63
+ | 2.1045 | 10.0 | 140 | 2.0553 | 0.3333 |
64
+ | 2.1083 | 11.0 | 154 | 2.0255 | 0.3333 |
65
+ | 2.0914 | 12.0 | 168 | 2.0065 | 0.3333 |
66
+ | 2.0434 | 13.0 | 182 | 1.9696 | 0.3333 |
67
+ | 2.0687 | 14.0 | 196 | 1.9231 | 0.4167 |
68
+ | 2.0237 | 15.0 | 210 | 1.8679 | 0.4167 |
69
+ | 1.9562 | 16.0 | 224 | 1.8184 | 0.4167 |
70
+ | 2.0361 | 17.0 | 238 | 1.8803 | 0.3958 |
71
+ | 1.888 | 18.0 | 252 | 1.7802 | 0.4167 |
72
+ | 1.899 | 19.0 | 266 | 1.7662 | 0.4167 |
73
+ | 1.8959 | 20.0 | 280 | 1.7076 | 0.4167 |
74
+ | 1.8368 | 21.0 | 294 | 1.6566 | 0.4375 |
75
+ | 1.7358 | 22.0 | 308 | 1.6283 | 0.5 |
76
+ | 1.7877 | 23.0 | 322 | 1.6411 | 0.4583 |
77
+ | 1.7311 | 24.0 | 336 | 1.5525 | 0.5208 |
78
+ | 1.7079 | 25.0 | 350 | 1.5163 | 0.5 |
79
+ | 1.6496 | 26.0 | 364 | 1.5458 | 0.5 |
80
+ | 1.6374 | 27.0 | 378 | 1.5211 | 0.5 |
81
+ | 1.6048 | 28.0 | 392 | 1.4533 | 0.5417 |
82
+ | 1.5927 | 29.0 | 406 | 1.4319 | 0.5 |
83
+ | 1.4987 | 30.0 | 420 | 1.4579 | 0.5208 |
84
+ | 1.5745 | 31.0 | 434 | 1.4167 | 0.6042 |
85
+ | 1.4632 | 32.0 | 448 | 1.4471 | 0.5417 |
86
+ | 1.4686 | 33.0 | 462 | 1.4116 | 0.5625 |
87
+ | 1.5368 | 34.0 | 476 | 1.3872 | 0.6042 |
88
+ | 1.4327 | 35.0 | 490 | 1.3491 | 0.5833 |
89
+ | 1.3978 | 36.0 | 504 | 1.3325 | 0.5833 |
90
+ | 1.4509 | 37.0 | 518 | 1.3236 | 0.6042 |
91
+ | 1.3881 | 38.0 | 532 | 1.3426 | 0.5833 |
92
+ | 1.39 | 39.0 | 546 | 1.3137 | 0.6042 |
93
+ | 1.4153 | 40.0 | 560 | 1.3123 | 0.625 |
94
+ | 1.3635 | 41.0 | 574 | 1.3224 | 0.6042 |
95
+ | 1.403 | 42.0 | 588 | 1.3111 | 0.6042 |
96
+ | 1.3763 | 43.0 | 602 | 1.3197 | 0.5833 |
97
+ | 1.3539 | 44.0 | 616 | 1.3077 | 0.6042 |
98
+ | 1.306 | 45.0 | 630 | 1.3107 | 0.625 |
99
+
100
+
101
+ ### Framework versions
102
+
103
+ - Transformers 4.20.1
104
+ - Pytorch 1.11.0
105
+ - Datasets 2.1.0
106
+ - Tokenizers 0.12.1