callmesan commited on
Commit
6982c4d
1 Parent(s): 4ce0aae

End of training

Browse files
Files changed (1) hide show
  1. README.md +128 -0
README.md ADDED
@@ -0,0 +1,128 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: Harveenchadha/vakyansh-wav2vec2-hindi-him-4200
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ model-index:
9
+ - name: vakyansh-wav2vec2-hindi-him-4200-audio-abuse-feature
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # vakyansh-wav2vec2-hindi-him-4200-audio-abuse-feature
17
+
18
+ This model is a fine-tuned version of [Harveenchadha/vakyansh-wav2vec2-hindi-him-4200](https://huggingface.co/Harveenchadha/vakyansh-wav2vec2-hindi-him-4200) on the None dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.6541
21
+ - Accuracy: 0.6938
22
+ - Macro F1-score: 0.6938
23
+
24
+ ## Model description
25
+
26
+ More information needed
27
+
28
+ ## Intended uses & limitations
29
+
30
+ More information needed
31
+
32
+ ## Training and evaluation data
33
+
34
+ More information needed
35
+
36
+ ## Training procedure
37
+
38
+ ### Training hyperparameters
39
+
40
+ The following hyperparameters were used during training:
41
+ - learning_rate: 2e-05
42
+ - train_batch_size: 16
43
+ - eval_batch_size: 16
44
+ - seed: 42
45
+ - gradient_accumulation_steps: 4
46
+ - total_train_batch_size: 64
47
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
+ - lr_scheduler_type: linear
49
+ - lr_scheduler_warmup_ratio: 0.1
50
+ - num_epochs: 50
51
+
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | Macro F1-score |
55
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:--------------:|
56
+ | 6.7199 | 0.77 | 10 | 6.7179 | 0.0 | 0.0 |
57
+ | 6.699 | 1.54 | 20 | 6.6606 | 0.1192 | 0.0134 |
58
+ | 6.6237 | 2.31 | 30 | 6.5410 | 0.4499 | 0.0852 |
59
+ | 6.4723 | 3.08 | 40 | 6.3277 | 0.5014 | 0.2226 |
60
+ | 6.2904 | 3.85 | 50 | 6.0526 | 0.5041 | 0.3351 |
61
+ | 6.0074 | 4.62 | 60 | 5.7219 | 0.5041 | 0.3351 |
62
+ | 5.7233 | 5.38 | 70 | 5.3914 | 0.5041 | 0.3351 |
63
+ | 5.4426 | 6.15 | 80 | 5.0902 | 0.5041 | 0.3351 |
64
+ | 5.1776 | 6.92 | 90 | 4.8584 | 0.5041 | 0.3351 |
65
+ | 5.0097 | 7.69 | 100 | 4.6328 | 0.5041 | 0.3351 |
66
+ | 4.7851 | 8.46 | 110 | 4.4098 | 0.5041 | 0.3351 |
67
+ | 4.6801 | 9.23 | 120 | 4.2064 | 0.5041 | 0.3351 |
68
+ | 4.4144 | 10.0 | 130 | 3.9980 | 0.5041 | 0.3351 |
69
+ | 4.1631 | 10.77 | 140 | 3.7914 | 0.5041 | 0.3351 |
70
+ | 4.0093 | 11.54 | 150 | 3.5793 | 0.5041 | 0.3351 |
71
+ | 3.7803 | 12.31 | 160 | 3.3708 | 0.5041 | 0.3351 |
72
+ | 3.645 | 13.08 | 170 | 3.1635 | 0.5041 | 0.3351 |
73
+ | 3.3334 | 13.85 | 180 | 2.9564 | 0.5041 | 0.3351 |
74
+ | 3.0942 | 14.62 | 190 | 2.7570 | 0.5041 | 0.3351 |
75
+ | 3.0844 | 15.38 | 200 | 2.5619 | 0.5041 | 0.3351 |
76
+ | 2.749 | 16.15 | 210 | 2.3733 | 0.5041 | 0.3351 |
77
+ | 2.5448 | 16.92 | 220 | 2.1896 | 0.5041 | 0.3351 |
78
+ | 2.3636 | 17.69 | 230 | 2.0160 | 0.5041 | 0.3351 |
79
+ | 2.1303 | 18.46 | 240 | 1.8579 | 0.5041 | 0.3351 |
80
+ | 2.1702 | 19.23 | 250 | 1.7136 | 0.5041 | 0.3351 |
81
+ | 1.8911 | 20.0 | 260 | 1.5809 | 0.5041 | 0.3351 |
82
+ | 1.7695 | 20.77 | 270 | 1.4511 | 0.5041 | 0.3351 |
83
+ | 1.5466 | 21.54 | 280 | 1.3433 | 0.5041 | 0.3351 |
84
+ | 1.4228 | 22.31 | 290 | 1.2479 | 0.5041 | 0.3351 |
85
+ | 1.4089 | 23.08 | 300 | 1.1632 | 0.5041 | 0.3351 |
86
+ | 1.2252 | 23.85 | 310 | 1.0900 | 0.5041 | 0.3351 |
87
+ | 1.2236 | 24.62 | 320 | 1.0268 | 0.5041 | 0.3351 |
88
+ | 1.0727 | 25.38 | 330 | 0.9742 | 0.5041 | 0.3351 |
89
+ | 1.0036 | 26.15 | 340 | 0.9273 | 0.5041 | 0.3351 |
90
+ | 0.95 | 26.92 | 350 | 0.8892 | 0.5041 | 0.3351 |
91
+ | 0.9304 | 27.69 | 360 | 0.8592 | 0.5041 | 0.3351 |
92
+ | 0.9426 | 28.46 | 370 | 0.8355 | 0.5041 | 0.3351 |
93
+ | 0.8967 | 29.23 | 380 | 0.8136 | 0.5041 | 0.3351 |
94
+ | 0.862 | 30.0 | 390 | 0.7942 | 0.5041 | 0.3351 |
95
+ | 0.8609 | 30.77 | 400 | 0.7799 | 0.5041 | 0.3351 |
96
+ | 0.8013 | 31.54 | 410 | 0.7667 | 0.5041 | 0.3351 |
97
+ | 0.7845 | 32.31 | 420 | 0.7572 | 0.5041 | 0.3351 |
98
+ | 0.77 | 33.08 | 430 | 0.7425 | 0.5041 | 0.3351 |
99
+ | 0.7952 | 33.85 | 440 | 0.7309 | 0.5041 | 0.3351 |
100
+ | 0.7433 | 34.62 | 450 | 0.7119 | 0.7046 | 0.7036 |
101
+ | 0.7791 | 35.38 | 460 | 0.7002 | 0.7019 | 0.6992 |
102
+ | 0.7409 | 36.15 | 470 | 0.6932 | 0.7073 | 0.7029 |
103
+ | 0.7233 | 36.92 | 480 | 0.6887 | 0.6911 | 0.6904 |
104
+ | 0.716 | 37.69 | 490 | 0.6820 | 0.6992 | 0.6986 |
105
+ | 0.6994 | 38.46 | 500 | 0.6821 | 0.6883 | 0.6881 |
106
+ | 0.6899 | 39.23 | 510 | 0.6701 | 0.6938 | 0.6930 |
107
+ | 0.7014 | 40.0 | 520 | 0.6683 | 0.6965 | 0.6965 |
108
+ | 0.7252 | 40.77 | 530 | 0.6632 | 0.7019 | 0.7011 |
109
+ | 0.6763 | 41.54 | 540 | 0.6650 | 0.6883 | 0.6882 |
110
+ | 0.7115 | 42.31 | 550 | 0.6615 | 0.6829 | 0.6829 |
111
+ | 0.6703 | 43.08 | 560 | 0.6628 | 0.6911 | 0.6908 |
112
+ | 0.6757 | 43.85 | 570 | 0.6626 | 0.6938 | 0.6935 |
113
+ | 0.6672 | 44.62 | 580 | 0.6545 | 0.7046 | 0.7043 |
114
+ | 0.6518 | 45.38 | 590 | 0.6559 | 0.6965 | 0.6965 |
115
+ | 0.6661 | 46.15 | 600 | 0.6610 | 0.6802 | 0.6800 |
116
+ | 0.679 | 46.92 | 610 | 0.6580 | 0.6856 | 0.6856 |
117
+ | 0.7079 | 47.69 | 620 | 0.6558 | 0.6911 | 0.6911 |
118
+ | 0.7103 | 48.46 | 630 | 0.6536 | 0.6992 | 0.6992 |
119
+ | 0.6613 | 49.23 | 640 | 0.6536 | 0.6965 | 0.6965 |
120
+ | 0.6326 | 50.0 | 650 | 0.6541 | 0.6938 | 0.6938 |
121
+
122
+
123
+ ### Framework versions
124
+
125
+ - Transformers 4.33.0
126
+ - Pytorch 2.0.0
127
+ - Datasets 2.1.0
128
+ - Tokenizers 0.13.3