Hugging Face's logo

sagir567
/
wav2vec2transformerEMR4

Audio Classification
Transformers
Safetensors
wav2vec2
Generated from Trainer
Model card Files
xet
Community
sagir567 commited on
Commit
66d8adf
·
verified ·
1 Parent(s): 27a05e9

End of training

Browse files
Files changed (4) hide show
  1. README.md +35 -20
  2. config.json +1 -1
  3. model.safetensors +2 -2
  4. training_args.bin +1 -1
README.md CHANGED
@@ -21,11 +21,11 @@ should probably proofread and complete it, then remove this comment. -->
21
 
22
  This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on an unknown dataset.
23
  It achieves the following results on the evaluation set:
24
- - Loss: 0.6386
25
- - Accuracy: 0.8076
26
- - Precision: 0.8080
27
- - Recall: 0.8076
28
- - F1: 0.8066
29
 
30
  ## Model description
31
 
@@ -45,30 +45,45 @@ More information needed
45
 
46
  The following hyperparameters were used during training:
47
  - learning_rate: 1e-05
48
- - train_batch_size: 16
49
- - eval_batch_size: 16
50
  - seed: 42
51
  - gradient_accumulation_steps: 2
52
- - total_train_batch_size: 32
53
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
54
  - lr_scheduler_type: linear
55
  - lr_scheduler_warmup_steps: 500
56
- - num_epochs: 15
57
  - mixed_precision_training: Native AMP
58
 
59
  ### Training results
60
 
61
- | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
62
- |:-------------:|:-------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
63
- | 1.4985 | 1.6420 | 500 | 1.3740 | 0.5643 | 0.5544 | 0.5643 | 0.5373 |
64
- | 0.9889 | 3.2841 | 1000 | 0.9292 | 0.7312 | 0.7468 | 0.7312 | 0.7263 |
65
- | 0.783 | 4.9261 | 1500 | 0.8380 | 0.7349 | 0.7484 | 0.7349 | 0.7274 |
66
- | 0.5992 | 6.5681 | 2000 | 0.6920 | 0.7826 | 0.7829 | 0.7826 | 0.7812 |
67
- | 0.5158 | 8.2102 | 2500 | 0.6813 | 0.7842 | 0.7857 | 0.7842 | 0.7813 |
68
- | 0.4349 | 9.8522 | 3000 | 0.6448 | 0.7928 | 0.7942 | 0.7928 | 0.7921 |
69
- | 0.3765 | 11.4943 | 3500 | 0.6531 | 0.7953 | 0.7951 | 0.7953 | 0.7934 |
70
- | 0.3511 | 13.1363 | 4000 | 0.6386 | 0.8076 | 0.8080 | 0.8076 | 0.8066 |
71
- | 0.3283 | 14.7783 | 4500 | 0.6371 | 0.8076 | 0.8077 | 0.8076 | 0.8065 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
72
 
73
 
74
  ### Framework versions
 
21
 
22
  This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on an unknown dataset.
23
  It achieves the following results on the evaluation set:
24
+ - Loss: 1.3565
25
+ - Accuracy: 0.4562
26
+ - Precision: 0.5012
27
+ - Recall: 0.4562
28
+ - F1: 0.4643
29
 
30
  ## Model description
31
 
 
45
 
46
  The following hyperparameters were used during training:
47
  - learning_rate: 1e-05
48
+ - train_batch_size: 8
49
+ - eval_batch_size: 8
50
  - seed: 42
51
  - gradient_accumulation_steps: 2
52
+ - total_train_batch_size: 16
53
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
54
  - lr_scheduler_type: linear
55
  - lr_scheduler_warmup_steps: 500
56
+ - num_epochs: 10
57
  - mixed_precision_training: Native AMP
58
 
59
  ### Training results
60
 
61
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
62
+ |:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
63
+ | 1.9245 | 0.4108 | 250 | 1.9090 | 0.1981 | 0.1953 | 0.1981 | 0.1794 |
64
+ | 1.8806 | 0.8217 | 500 | 1.8641 | 0.2289 | 0.2390 | 0.2289 | 0.1796 |
65
+ | 1.8357 | 1.2325 | 750 | 1.8233 | 0.2417 | 0.2369 | 0.2417 | 0.2167 |
66
+ | 1.7745 | 1.6434 | 1000 | 1.7732 | 0.2713 | 0.2984 | 0.2713 | 0.2736 |
67
+ | 1.7518 | 2.0542 | 1250 | 1.7497 | 0.2741 | 0.2975 | 0.2741 | 0.2529 |
68
+ | 1.7009 | 2.4651 | 1500 | 1.6719 | 0.3321 | 0.3849 | 0.3321 | 0.3177 |
69
+ | 1.6498 | 2.8759 | 1750 | 1.6159 | 0.3646 | 0.4064 | 0.3646 | 0.3554 |
70
+ | 1.597 | 3.2868 | 2000 | 1.5689 | 0.4065 | 0.4511 | 0.4065 | 0.3915 |
71
+ | 1.5607 | 3.6976 | 2250 | 1.5324 | 0.4040 | 0.4374 | 0.4040 | 0.3919 |
72
+ | 1.5268 | 4.1085 | 2500 | 1.4833 | 0.4287 | 0.4760 | 0.4287 | 0.4339 |
73
+ | 1.4696 | 4.5193 | 2750 | 1.4981 | 0.4254 | 0.4939 | 0.4254 | 0.4137 |
74
+ | 1.455 | 4.9302 | 3000 | 1.4694 | 0.4332 | 0.4876 | 0.4332 | 0.4242 |
75
+ | 1.4473 | 5.3410 | 3250 | 1.4505 | 0.4254 | 0.4688 | 0.4254 | 0.4128 |
76
+ | 1.4134 | 5.7518 | 3500 | 1.4207 | 0.4406 | 0.5431 | 0.4406 | 0.4514 |
77
+ | 1.3963 | 6.1627 | 3750 | 1.4242 | 0.4427 | 0.4593 | 0.4427 | 0.4440 |
78
+ | 1.3909 | 6.5735 | 4000 | 1.3723 | 0.4632 | 0.5042 | 0.4632 | 0.4707 |
79
+ | 1.3539 | 6.9844 | 4250 | 1.3810 | 0.4513 | 0.4797 | 0.4513 | 0.4531 |
80
+ | 1.3561 | 7.3952 | 4500 | 1.3852 | 0.4595 | 0.4977 | 0.4595 | 0.4609 |
81
+ | 1.373 | 7.8061 | 4750 | 1.3906 | 0.4505 | 0.5019 | 0.4505 | 0.4540 |
82
+ | 1.3812 | 8.2169 | 5000 | 1.3636 | 0.4731 | 0.4975 | 0.4731 | 0.4715 |
83
+ | 1.3208 | 8.6278 | 5250 | 1.3825 | 0.4538 | 0.5153 | 0.4538 | 0.4574 |
84
+ | 1.3025 | 9.0386 | 5500 | 1.3696 | 0.4649 | 0.4963 | 0.4649 | 0.4683 |
85
+ | 1.3109 | 9.4495 | 5750 | 1.3573 | 0.4681 | 0.5135 | 0.4681 | 0.4746 |
86
+ | 1.3264 | 9.8603 | 6000 | 1.3491 | 0.4686 | 0.5117 | 0.4686 | 0.4741 |
87
 
88
 
89
  ### Framework versions
config.json CHANGED
@@ -7,7 +7,7 @@
7
  "add_adapter": false,
8
  "apply_spec_augment": true,
9
  "architectures": [
10
- "Wav2Vec2Model"
11
  ],
12
  "attention_dropout": 0.1,
13
  "bos_token_id": 1,
 
7
  "add_adapter": false,
8
  "apply_spec_augment": true,
9
  "architectures": [
10
+ "Wav2Vec2ForSequenceClassification"
11
  ],
12
  "attention_dropout": 0.1,
13
  "bos_token_id": 1,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:09b113e7a37a87c6f7a52059007889bd83ebf3a136d4cafc74e231fe9d45ef22
3
- size 377510632
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b043391c49334498d1e2027bb0440e32f46522cb86fc37ac4ca2fe6493056c2
3
+ size 378307508
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4b638ee06625a3021b2ba89b0a8fff4a89a90489d9b73b298cefad03acd32971
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:908f6d0228e57e43e4b95a2e8602e1f64f3c04a4cb7fa8b8c450bb80548e34fa
3
  size 5240