Hugging Face's logo

tgrhn
/
wav2vec2-multiple-medical-2-1

PyTorch
wav2vec2
Generated from Trainer
Model card Files Community
tgrhn commited on
Commit
bbfbf73
•
1 Parent(s): eca8665

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +103 -0
README.md ADDED
@@ -0,0 +1,103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: wav2vec2-multiple-medical-2-1
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-multiple-medical-2-1
14
+
15
+ 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.
16
+ It achieves the following results on the evaluation set:
17
+ - Loss: 0.2340
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: 1e-05
37
+ - train_batch_size: 2
38
+ - eval_batch_size: 2
39
+ - seed: 42
40
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
+ - lr_scheduler_type: linear
42
+ - lr_scheduler_warmup_ratio: 0.1
43
+ - num_epochs: 30
44
+ - mixed_precision_training: Native AMP
45
+
46
+ ### Training results
47
+
48
+ | Training Loss | Epoch | Step | Validation Loss |
49
+ |:-------------:|:-----:|:-----:|:---------------:|
50
+ | 5.7848 | 0.56 | 1500 | 4.7981 |
51
+ | 3.4426 | 1.12 | 3000 | 3.3244 |
52
+ | 3.1079 | 1.68 | 4500 | 3.0999 |
53
+ | 3.0034 | 2.24 | 6000 | 2.9647 |
54
+ | 2.0403 | 2.8 | 7500 | 1.5829 |
55
+ | 1.2797 | 3.36 | 9000 | 0.9095 |
56
+ | 1.052 | 3.92 | 10500 | 0.6498 |
57
+ | 0.8326 | 4.48 | 12000 | 0.5418 |
58
+ | 0.7443 | 5.04 | 13500 | 0.4615 |
59
+ | 0.6949 | 5.6 | 15000 | 0.4191 |
60
+ | 0.6096 | 6.16 | 16500 | 0.3817 |
61
+ | 0.5699 | 6.72 | 18000 | 0.3545 |
62
+ | 0.5718 | 7.28 | 19500 | 0.3439 |
63
+ | 0.5159 | 7.84 | 21000 | 0.3243 |
64
+ | 0.4808 | 8.4 | 22500 | 0.3112 |
65
+ | 0.4979 | 8.96 | 24000 | 0.2975 |
66
+ | 0.4271 | 9.52 | 25500 | 0.2948 |
67
+ | 0.4364 | 10.08 | 27000 | 0.2818 |
68
+ | 0.4205 | 10.64 | 28500 | 0.2770 |
69
+ | 0.418 | 11.2 | 30000 | 0.2747 |
70
+ | 0.3915 | 11.76 | 31500 | 0.2695 |
71
+ | 0.4121 | 12.32 | 33000 | 0.2596 |
72
+ | 0.4057 | 12.88 | 34500 | 0.2627 |
73
+ | 0.363 | 13.44 | 36000 | 0.2617 |
74
+ | 0.3767 | 14.0 | 37500 | 0.2567 |
75
+ | 0.3804 | 14.56 | 39000 | 0.2512 |
76
+ | 0.3537 | 15.12 | 40500 | 0.2505 |
77
+ | 0.3195 | 15.68 | 42000 | 0.2508 |
78
+ | 0.311 | 16.24 | 43500 | 0.2523 |
79
+ | 0.3089 | 16.8 | 45000 | 0.2462 |
80
+ | 0.3121 | 17.36 | 46500 | 0.2463 |
81
+ | 0.3549 | 17.92 | 48000 | 0.2479 |
82
+ | 0.3111 | 18.48 | 49500 | 0.2422 |
83
+ | 0.3228 | 19.04 | 51000 | 0.2414 |
84
+ | 0.2936 | 19.6 | 52500 | 0.2415 |
85
+ | 0.28 | 20.16 | 54000 | 0.2411 |
86
+ | 0.3174 | 20.72 | 55500 | 0.2354 |
87
+ | 0.2735 | 21.28 | 57000 | 0.2335 |
88
+ | 0.3498 | 21.84 | 58500 | 0.2352 |
89
+ | 0.2958 | 22.4 | 60000 | 0.2341 |
90
+ | 0.3009 | 22.96 | 61500 | 0.2328 |
91
+ | 0.2869 | 23.52 | 63000 | 0.2352 |
92
+ | 0.2644 | 24.08 | 64500 | 0.2343 |
93
+ | 0.2692 | 24.64 | 66000 | 0.2346 |
94
+ | 0.3376 | 25.2 | 67500 | 0.2339 |
95
+ | 0.2522 | 25.76 | 69000 | 0.2340 |
96
+
97
+
98
+ ### Framework versions
99
+
100
+ - Transformers 4.26.1
101
+ - Pytorch 2.4.1+cu121
102
+ - Datasets 2.20.0
103
+ - Tokenizers 0.13.3