Hugging Face's logo

anton-l
/
xtreme_s_xlsr_300m_fleurs_langid

Audio Classification
Transformers
PyTorch
TensorBoard
Allar
wav2vec2
fleurs-lang_id
google/xtreme_s
generated_from_trainer
Inference Endpoints
Model card Files Metrics Community
2
anton-l HF staff commited on
Commit
3a97e0e
•
1 Parent(s): 660ff20

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +26 -27
README.md CHANGED
@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the xtreme_s dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 1.3514
22
  - Accuracy: 0.7236
 
23
 
24
  ## Model description
25
 
@@ -39,14 +39,13 @@ More information needed
39
 
40
  The following hyperparameters were used during training:
41
  - learning_rate: 0.0003
42
- - train_batch_size: 4
43
- - eval_batch_size: 1
44
  - seed: 42
45
  - distributed_type: multi-GPU
46
  - num_devices: 8
47
- - gradient_accumulation_steps: 2
48
  - total_train_batch_size: 64
49
- - total_eval_batch_size: 8
50
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
  - lr_scheduler_type: linear
52
  - lr_scheduler_warmup_steps: 2000
@@ -55,32 +54,32 @@ The following hyperparameters were used during training:
55
 
56
  ### Training results
57
 
58
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
59
- |:-------------:|:-----:|:-----:|:---------------:|:--------:|
60
- | 0.5296 | 0.26 | 1000 | 2.6633 | 0.4016 |
61
- | 0.4252 | 0.52 | 2000 | 1.8582 | 0.5751 |
62
- | 0.2989 | 0.78 | 3000 | 1.6780 | 0.6332 |
63
- | 0.3563 | 1.04 | 4000 | 1.4479 | 0.6799 |
64
- | 0.1617 | 1.3 | 5000 | 1.5066 | 0.6679 |
65
- | 0.1409 | 1.56 | 6000 | 1.4082 | 0.6992 |
66
- | 0.01 | 1.82 | 7000 | 1.2448 | 0.7071 |
67
- | 0.0018 | 2.08 | 8000 | 1.1996 | 0.7148 |
68
- | 0.0014 | 2.34 | 9000 | 1.6505 | 0.6410 |
69
- | 0.0188 | 2.6 | 10000 | 1.4050 | 0.6840 |
70
- | 0.0007 | 2.86 | 11000 | 1.5831 | 0.6621 |
71
- | 0.1038 | 3.12 | 12000 | 1.5441 | 0.6829 |
72
- | 0.0003 | 3.38 | 13000 | 1.3483 | 0.6900 |
73
- | 0.0004 | 3.64 | 14000 | 1.7070 | 0.6414 |
74
- | 0.0003 | 3.9 | 15000 | 1.3198 | 0.7075 |
75
- | 0.0002 | 4.16 | 16000 | 1.3118 | 0.7105 |
76
- | 0.0001 | 4.42 | 17000 | 1.4099 | 0.7029 |
77
- | 0.0 | 4.68 | 18000 | 1.3658 | 0.7180 |
78
- | 0.0001 | 4.93 | 19000 | 1.3514 | 0.7236 |
79
 
80
 
81
  ### Framework versions
82
 
83
  - Transformers 4.18.0.dev0
84
- - Pytorch 1.11.0+cu113
85
  - Datasets 1.18.4.dev0
86
  - Tokenizers 0.11.6
 
18
 
19
  This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the xtreme_s dataset.
20
  It achieves the following results on the evaluation set:
 
21
  - Accuracy: 0.7236
22
+ - Loss: 1.3514
23
 
24
  ## Model description
25
 
 
39
 
40
  The following hyperparameters were used during training:
41
  - learning_rate: 0.0003
42
+ - train_batch_size: 8
43
+ - eval_batch_size: 4
44
  - seed: 42
45
  - distributed_type: multi-GPU
46
  - num_devices: 8
 
47
  - total_train_batch_size: 64
48
+ - total_eval_batch_size: 32
49
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
  - lr_scheduler_type: linear
51
  - lr_scheduler_warmup_steps: 2000
 
54
 
55
  ### Training results
56
 
57
+ | Training Loss | Epoch | Step | Accuracy | Validation Loss |
58
+ |:-------------:|:-----:|:-----:|:--------:|:---------------:|
59
+ | 0.5296 | 0.26 | 1000 | 0.4016 | 2.6633 |
60
+ | 0.4252 | 0.52 | 2000 | 0.5751 | 1.8582 |
61
+ | 0.2989 | 0.78 | 3000 | 0.6332 | 1.6780 |
62
+ | 0.3563 | 1.04 | 4000 | 0.6799 | 1.4479 |
63
+ | 0.1617 | 1.3 | 5000 | 0.6679 | 1.5066 |
64
+ | 0.1409 | 1.56 | 6000 | 0.6992 | 1.4082 |
65
+ | 0.01 | 1.82 | 7000 | 0.7071 | 1.2448 |
66
+ | 0.0018 | 2.08 | 8000 | 0.7148 | 1.1996 |
67
+ | 0.0014 | 2.34 | 9000 | 0.6410 | 1.6505 |
68
+ | 0.0188 | 2.6 | 10000 | 0.6840 | 1.4050 |
69
+ | 0.0007 | 2.86 | 11000 | 0.6621 | 1.5831 |
70
+ | 0.1038 | 3.12 | 12000 | 0.6829 | 1.5441 |
71
+ | 0.0003 | 3.38 | 13000 | 0.6900 | 1.3483 |
72
+ | 0.0004 | 3.64 | 14000 | 0.6414 | 1.7070 |
73
+ | 0.0003 | 3.9 | 15000 | 0.7075 | 1.3198 |
74
+ | 0.0002 | 4.16 | 16000 | 0.7105 | 1.3118 |
75
+ | 0.0001 | 4.42 | 17000 | 0.7029 | 1.4099 |
76
+ | 0.0 | 4.68 | 18000 | 0.7180 | 1.3658 |
77
+ | 0.0001 | 4.93 | 19000 | 0.7236 | 1.3514 |
78
 
79
 
80
  ### Framework versions
81
 
82
  - Transformers 4.18.0.dev0
83
+ - Pytorch 1.10.1+cu111
84
  - Datasets 1.18.4.dev0
85
  - Tokenizers 0.11.6