mikhail-panzo commited on
Commit
474a146
1 Parent(s): a084b69

End of training

Browse files
README.md ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: microsoft/speecht5_tts
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: ceb_b64_le4_s8000
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # ceb_b64_le4_s8000
15
+
16
+ This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on an unknown dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 0.4050
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 0.0001
38
+ - train_batch_size: 16
39
+ - eval_batch_size: 8
40
+ - seed: 42
41
+ - gradient_accumulation_steps: 4
42
+ - total_train_batch_size: 64
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: linear
45
+ - lr_scheduler_warmup_steps: 2000
46
+ - training_steps: 8000
47
+ - mixed_precision_training: Native AMP
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss |
52
+ |:-------------:|:--------:|:----:|:---------------:|
53
+ | 0.4561 | 19.8020 | 500 | 0.4151 |
54
+ | 0.4179 | 39.6040 | 1000 | 0.3994 |
55
+ | 0.4075 | 59.4059 | 1500 | 0.4018 |
56
+ | 0.3981 | 79.2079 | 2000 | 0.4029 |
57
+ | 0.3862 | 99.0099 | 2500 | 0.3978 |
58
+ | 0.3726 | 118.8119 | 3000 | 0.3978 |
59
+ | 0.365 | 138.6139 | 3500 | 0.3960 |
60
+ | 0.3525 | 158.4158 | 4000 | 0.3969 |
61
+ | 0.3545 | 178.2178 | 4500 | 0.3982 |
62
+ | 0.3473 | 198.0198 | 5000 | 0.4039 |
63
+ | 0.3439 | 217.8218 | 5500 | 0.4020 |
64
+ | 0.3371 | 237.6238 | 6000 | 0.4044 |
65
+ | 0.3362 | 257.4257 | 6500 | 0.4041 |
66
+ | 0.3311 | 277.2277 | 7000 | 0.4022 |
67
+ | 0.3345 | 297.0297 | 7500 | 0.4051 |
68
+ | 0.3348 | 316.8317 | 8000 | 0.4050 |
69
+
70
+
71
+ ### Framework versions
72
+
73
+ - Transformers 4.41.0.dev0
74
+ - Pytorch 2.2.1+cu121
75
+ - Datasets 2.19.0
76
+ - Tokenizers 0.19.1
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "decoder_start_token_id": 2,
5
+ "eos_token_id": 2,
6
+ "max_length": 1876,
7
+ "pad_token_id": 1,
8
+ "transformers_version": "4.41.0.dev0"
9
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f49478b3558087de3ef1a10558e5e95232e5021f5554b1a3c06b2ca1a4c1837
3
  size 577789320
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e88bcddd088e858a9bb66970598a4a31f3a99fa875613237e38373a495920782
3
  size 577789320
runs/May03_02-42-40_f1ee6ff06047/events.out.tfevents.1714704161.f1ee6ff06047.2167.1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:18709329e9ad7e78dc9146903a83b816df0ea462932c859bd34e602e49c54e31
3
- size 44573
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:189e911434be90ba09ec276ec05a9d991cdea0089f29342e7d680223d62d4b16
3
+ size 44927