Hugging Face's logo

Hemg
/
deeepfake-audio-RecognitionIRri

Audio Classification
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
Hemg commited on
Commit
f10bc5a
•
1 Parent(s): 8c08026

Model save

Browse files
Files changed (3) hide show
  1. README.md +11 -11
  2. model.safetensors +1 -1
  3. runs/Mar29_11-15-13_069fb75880fd/events.out.tfevents.1711710914.069fb75880fd.2317.7 +2 -2
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.4716981132075472
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
32
 
33
  This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the audiofolder dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.6654
36
- - Accuracy: 0.4717
37
 
38
  ## Model description
39
 
@@ -53,24 +53,24 @@ More information needed
53
 
54
  The following hyperparameters were used during training:
55
  - learning_rate: 0.0003
56
- - train_batch_size: 64
57
- - eval_batch_size: 64
58
  - seed: 42
59
  - gradient_accumulation_steps: 4
60
- - total_train_batch_size: 256
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
- - lr_scheduler_warmup_ratio: 0.5
64
  - num_epochs: 4
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
- | 0.6982 | 1.0 | 1 | 0.6990 | 0.3962 |
71
- | 0.6948 | 2.0 | 2 | 0.6934 | 0.4151 |
72
- | 0.6404 | 3.0 | 3 | 0.7042 | 0.4151 |
73
- | 0.5805 | 4.0 | 4 | 0.6654 | 0.4717 |
74
 
75
 
76
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.41509433962264153
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
32
 
33
  This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the audiofolder dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.7172
36
+ - Accuracy: 0.4151
37
 
38
  ## Model description
39
 
 
53
 
54
  The following hyperparameters were used during training:
55
  - learning_rate: 0.0003
56
+ - train_batch_size: 8
57
+ - eval_batch_size: 8
58
  - seed: 42
59
  - gradient_accumulation_steps: 4
60
+ - total_train_batch_size: 32
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
+ - lr_scheduler_warmup_ratio: 0.1
64
  - num_epochs: 4
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | 0.7449 | 0.92 | 6 | 0.8324 | 0.4151 |
71
+ | 0.6335 | 2.0 | 13 | 0.7126 | 0.4151 |
72
+ | 0.7457 | 2.92 | 19 | 0.6974 | 0.4151 |
73
+ | 0.6197 | 3.69 | 24 | 0.7172 | 0.4151 |
74
 
75
 
76
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8fbcf1cb14fe31a090fe54d990a3f8a0183ffcd210f0a3f6c9b1216c6a707035
3
  size 378302360
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94059bc6dcd5c0484315a12a32a1529b6035b9f6147ed87508470a3bdc915eb4
3
  size 378302360
runs/Mar29_11-15-13_069fb75880fd/events.out.tfevents.1711710914.069fb75880fd.2317.7 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e03715655b2d799146c6ac597a0968869f29033ace8b7aba32c024e29b071964
3
- size 8040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b259f1c150ce39d0486cc2b6e137ee5a5e31cd8c5f5bdba8a83d0d3fab578b3c
3
+ size 8912