Edmon02 commited on
Commit
a0c0ff3
1 Parent(s): 4946031

End of training

Browse files
Files changed (2) hide show
  1. README.md +20 -22
  2. generation_config.json +1 -1
README.md CHANGED
@@ -1,15 +1,13 @@
1
  ---
2
  license: mit
3
- base_model: Edmon02/speecht5_finetuned_hy
4
  tags:
5
  - generated_from_trainer
 
 
6
  model-index:
7
  - name: speecht5_finetuned_voxpopuli_hy
8
  results: []
9
- datasets:
10
- - mozilla-foundation/common_voice_17_0
11
- language:
12
- - hy
13
  ---
14
 
15
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -17,9 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  # speecht5_finetuned_voxpopuli_hy
19
 
20
- This model is a fine-tuned version of [Edmon02/speecht5_finetuned_hy](https://huggingface.co/Edmon02/speecht5_finetuned_hy) on the None dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.6214
23
 
24
  ## Model description
25
 
@@ -38,7 +36,7 @@ More information needed
38
  ### Training hyperparameters
39
 
40
  The following hyperparameters were used during training:
41
- - learning_rate: 2e-05
42
  - train_batch_size: 4
43
  - eval_batch_size: 2
44
  - seed: 42
@@ -46,27 +44,27 @@ The following hyperparameters were used during training:
46
  - total_train_batch_size: 32
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
49
- - lr_scheduler_warmup_steps: 1000
50
  - training_steps: 4000
51
  - mixed_precision_training: Native AMP
52
 
53
  ### Training results
54
 
55
- | Training Loss | Epoch | Step | Validation Loss |
56
- |:-------------:|:-------:|:----:|:---------------:|
57
- | 0.7717 | 4.4199 | 500 | 0.7195 |
58
- | 0.7361 | 8.8398 | 1000 | 0.6810 |
59
- | 0.7088 | 13.2597 | 1500 | 0.6597 |
60
- | 0.6942 | 17.6796 | 2000 | 0.6465 |
61
- | 0.6835 | 22.0994 | 2500 | 0.6367 |
62
- | 0.6753 | 26.5193 | 3000 | 0.6309 |
63
- | 0.6734 | 30.9392 | 3500 | 0.6245 |
64
- | 0.6747 | 35.3591 | 4000 | 0.6214 |
65
 
66
 
67
  ### Framework versions
68
 
69
- - Transformers 4.43.3
70
- - Pytorch 2.4.0+cu121
71
  - Datasets 2.20.0
72
- - Tokenizers 0.19.1
 
1
  ---
2
  license: mit
3
+ base_model: Edmon02/speecht5_finetuned_voxpopuli_hy
4
  tags:
5
  - generated_from_trainer
6
+ datasets:
7
+ - common_voice_17_0
8
  model-index:
9
  - name: speecht5_finetuned_voxpopuli_hy
10
  results: []
 
 
 
 
11
  ---
12
 
13
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
15
 
16
  # speecht5_finetuned_voxpopuli_hy
17
 
18
+ This model is a fine-tuned version of [Edmon02/speecht5_finetuned_voxpopuli_hy](https://huggingface.co/Edmon02/speecht5_finetuned_voxpopuli_hy) on the common_voice_17_0 dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.5088
21
 
22
  ## Model description
23
 
 
36
  ### Training hyperparameters
37
 
38
  The following hyperparameters were used during training:
39
+ - learning_rate: 1e-05
40
  - train_batch_size: 4
41
  - eval_batch_size: 2
42
  - seed: 42
 
44
  - total_train_batch_size: 32
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
+ - lr_scheduler_warmup_steps: 250
48
  - training_steps: 4000
49
  - mixed_precision_training: Native AMP
50
 
51
  ### Training results
52
 
53
+ | Training Loss | Epoch | Step | Validation Loss |
54
+ |:-------------:|:------:|:----:|:---------------:|
55
+ | 0.5974 | 1.2114 | 500 | 0.5489 |
56
+ | 0.57 | 2.4228 | 1000 | 0.5261 |
57
+ | 0.5684 | 3.6342 | 1500 | 0.5201 |
58
+ | 0.5516 | 4.8455 | 2000 | 0.5144 |
59
+ | 0.5521 | 6.0569 | 2500 | 0.5134 |
60
+ | 0.5436 | 7.2683 | 3000 | 0.5116 |
61
+ | 0.5434 | 8.4797 | 3500 | 0.5105 |
62
+ | 0.5449 | 9.6911 | 4000 | 0.5088 |
63
 
64
 
65
  ### Framework versions
66
 
67
+ - Transformers 4.42.4
68
+ - Pytorch 2.3.1+cu121
69
  - Datasets 2.20.0
70
+ - Tokenizers 0.19.1
generation_config.json CHANGED
@@ -5,5 +5,5 @@
5
  "eos_token_id": 2,
6
  "max_length": 1876,
7
  "pad_token_id": 1,
8
- "transformers_version": "4.43.3"
9
  }
 
5
  "eos_token_id": 2,
6
  "max_length": 1876,
7
  "pad_token_id": 1,
8
+ "transformers_version": "4.42.4"
9
  }