nonoJDWAOIDAWKDA commited on
Commit
ea30441
·
verified ·
1 Parent(s): c33b92b

End of training

Browse files
Files changed (3) hide show
  1. README.md +9 -9
  2. generation_config.json +1 -1
  3. model.safetensors +1 -1
README.md CHANGED
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.5904
20
 
21
  ## Model description
22
 
@@ -41,7 +41,7 @@ The following hyperparameters were used during training:
41
  - seed: 42
42
  - gradient_accumulation_steps: 8
43
  - total_train_batch_size: 32
44
- - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
45
  - lr_scheduler_type: linear
46
  - lr_scheduler_warmup_ratio: 0.1
47
  - lr_scheduler_warmup_steps: 100
@@ -52,16 +52,16 @@ The following hyperparameters were used during training:
52
 
53
  | Training Loss | Epoch | Step | Validation Loss |
54
  |:-------------:|:-------:|:----:|:---------------:|
55
- | 0.6158 | 16.6667 | 100 | 0.5684 |
56
- | 0.5078 | 33.3333 | 200 | 0.5707 |
57
- | 0.4824 | 50.0 | 300 | 0.5851 |
58
- | 0.4662 | 66.6667 | 400 | 0.5831 |
59
- | 0.4488 | 83.3333 | 500 | 0.5904 |
60
 
61
 
62
  ### Framework versions
63
 
64
- - Transformers 4.46.2
65
- - Pytorch 2.5.1+cu121
66
  - Datasets 3.1.0
67
  - Tokenizers 0.20.0
 
16
 
17
  This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.5493
20
 
21
  ## Model description
22
 
 
41
  - seed: 42
42
  - gradient_accumulation_steps: 8
43
  - total_train_batch_size: 32
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
  - lr_scheduler_warmup_ratio: 0.1
47
  - lr_scheduler_warmup_steps: 100
 
52
 
53
  | Training Loss | Epoch | Step | Validation Loss |
54
  |:-------------:|:-------:|:----:|:---------------:|
55
+ | 0.5984 | 16.6667 | 100 | 0.5402 |
56
+ | 0.5067 | 33.3333 | 200 | 0.5504 |
57
+ | 0.4818 | 50.0 | 300 | 0.5412 |
58
+ | 0.4621 | 66.6667 | 400 | 0.5398 |
59
+ | 0.4534 | 83.3333 | 500 | 0.5493 |
60
 
61
 
62
  ### Framework versions
63
 
64
+ - Transformers 4.45.0
65
+ - Pytorch 2.4.1+cu118
66
  - Datasets 3.1.0
67
  - Tokenizers 0.20.0
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": "4.46.2"
9
  }
 
5
  "eos_token_id": 2,
6
  "max_length": 1876,
7
  "pad_token_id": 1,
8
+ "transformers_version": "4.45.0"
9
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1464252c0ab9eddb8415fecc4ef375ce69dde20f1936a6460c8920547b3faf0d
3
  size 577789320
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79553713989ff2d1c21a5cb0044980b599feba4061f964af314dbbdbb8306ab4
3
  size 577789320