Hugging Face's logo

DL-Project
/
hatespeech_ast

Audio Classification
Transformers
Safetensors
audio-spectrogram-transformer
Generated from Trainer
Inference Endpoints
Model card Files Community
Luca-Engel commited on
Commit
2ff77b9
•
1 Parent(s): 13ad7af

ast trainer push best model after 5 epochs fp16

Browse files
Files changed (2) hide show
  1. README.md +18 -13
  2. model.safetensors +1 -1
README.md CHANGED
@@ -20,11 +20,11 @@ should probably proofread and complete it, then remove this comment. -->
20
 
21
  This model is a fine-tuned version of [MIT/ast-finetuned-audioset-10-10-0.4593](https://huggingface.co/MIT/ast-finetuned-audioset-10-10-0.4593) on an unknown dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.6336
24
- - Accuracy: 0.6431
25
- - Recall: 0.7452
26
- - Precision: 0.6237
27
- - F1: 0.6790
28
 
29
  ## Model description
30
 
@@ -52,18 +52,23 @@ The following hyperparameters were used during training:
52
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
53
  - lr_scheduler_type: linear
54
  - lr_scheduler_warmup_ratio: 0.1
55
- - num_epochs: 5
56
  - mixed_precision_training: Native AMP
57
 
58
  ### Training results
59
 
60
- | Training Loss | Epoch | Step | Validation Loss | Accuracy | Recall | Precision | F1 |
61
- |:-------------:|:------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
62
- | 0.6432 | 0.9987 | 387 | 0.6686 | 0.5992 | 0.6580 | 0.5944 | 0.6245 |
63
- | 0.6414 | 2.0 | 775 | 0.6336 | 0.6431 | 0.7452 | 0.6237 | 0.6790 |
64
- | 0.6079 | 2.9987 | 1162 | 0.6505 | 0.6328 | 0.5783 | 0.6561 | 0.6148 |
65
- | 0.5088 | 4.0 | 1550 | 0.7122 | 0.6176 | 0.6624 | 0.6136 | 0.6371 |
66
- | 0.3005 | 4.9935 | 1935 | 0.9250 | 0.6099 | 0.6038 | 0.6176 | 0.6106 |
 
 
 
 
 
67
 
68
 
69
  ### Framework versions
 
20
 
21
  This model is a fine-tuned version of [MIT/ast-finetuned-audioset-10-10-0.4593](https://huggingface.co/MIT/ast-finetuned-audioset-10-10-0.4593) on an unknown dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 0.6441
24
+ - Accuracy: 0.6318
25
+ - Recall: 0.8191
26
+ - Precision: 0.6001
27
+ - F1: 0.6927
28
 
29
  ## Model description
30
 
 
52
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
53
  - lr_scheduler_type: linear
54
  - lr_scheduler_warmup_ratio: 0.1
55
+ - num_epochs: 10
56
  - mixed_precision_training: Native AMP
57
 
58
  ### Training results
59
 
60
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | Recall | Precision | F1 |
61
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
62
+ | 0.753 | 1.0 | 310 | 0.6793 | 0.5559 | 0.2258 | 0.6968 | 0.3411 |
63
+ | 0.6598 | 2.0 | 620 | 0.6447 | 0.6265 | 0.7575 | 0.6066 | 0.6737 |
64
+ | 0.6374 | 3.0 | 930 | 0.6306 | 0.6486 | 0.8368 | 0.6136 | 0.7080 |
65
+ | 0.5586 | 4.0 | 1240 | 0.7678 | 0.6091 | 0.9144 | 0.5727 | 0.7043 |
66
+ | 0.4008 | 5.0 | 1550 | 0.8134 | 0.6212 | 0.5515 | 0.6511 | 0.5972 |
67
+ | 0.2072 | 6.0 | 1860 | 1.0746 | 0.6265 | 0.7448 | 0.6088 | 0.6700 |
68
+ | 0.0904 | 7.0 | 2170 | 2.0297 | 0.6273 | 0.6878 | 0.6209 | 0.6526 |
69
+ | 0.0203 | 8.0 | 2480 | 3.0627 | 0.6236 | 0.6307 | 0.6302 | 0.6305 |
70
+ | 0.0244 | 9.0 | 2790 | 3.2017 | 0.6297 | 0.7013 | 0.6206 | 0.6585 |
71
+ | 0.0 | 10.0 | 3100 | 3.2659 | 0.6313 | 0.6331 | 0.6392 | 0.6361 |
72
 
73
 
74
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:84671667a6556b59d2977dd91ebb055b6df9cd5c3deb2f260f527c5b6cd9725e
3
  size 344790040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79ecb30118d35bc10afeb64f2e7019d1e7f71cd53d5f8d748b079db947f0160a
3
  size 344790040