TheRamsay commited on
Commit
aae9cb2
·
verified ·
1 Parent(s): 856bfe3

End of training

Browse files
Files changed (1) hide show
  1. README.md +9 -8
README.md CHANGED
@@ -15,8 +15,6 @@ should probably proofread and complete it, then remove this comment. -->
15
  # results
16
 
17
  This model is a fine-tuned version of [](https://huggingface.co/) on the common_voice_17_0 dataset.
18
- It achieves the following results on the evaluation set:
19
- - Loss: 0.7078
20
 
21
  ## Model description
22
 
@@ -35,20 +33,23 @@ More information needed
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
- - learning_rate: 5e-05
39
- - train_batch_size: 8
40
- - eval_batch_size: 8
41
  - seed: 42
 
 
42
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
  - lr_scheduler_type: linear
44
- - num_epochs: 2
 
 
45
 
46
  ### Training results
47
 
48
  | Training Loss | Epoch | Step | Validation Loss |
49
  |:-------------:|:-----:|:----:|:---------------:|
50
- | No log | 1.0 | 4 | 0.8053 |
51
- | No log | 2.0 | 8 | 0.7078 |
52
 
53
 
54
  ### Framework versions
 
15
  # results
16
 
17
  This model is a fine-tuned version of [](https://huggingface.co/) on the common_voice_17_0 dataset.
 
 
18
 
19
  ## Model description
20
 
 
33
  ### Training hyperparameters
34
 
35
  The following hyperparameters were used during training:
36
+ - learning_rate: 0.0005
37
+ - train_batch_size: 32
38
+ - eval_batch_size: 32
39
  - seed: 42
40
+ - gradient_accumulation_steps: 2
41
+ - total_train_batch_size: 64
42
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
  - lr_scheduler_type: linear
44
+ - lr_scheduler_warmup_ratio: 0.08
45
+ - num_epochs: 1
46
+ - mixed_precision_training: Native AMP
47
 
48
  ### Training results
49
 
50
  | Training Loss | Epoch | Step | Validation Loss |
51
  |:-------------:|:-----:|:----:|:---------------:|
52
+ | No log | 1.0 | 1 | 10.9618 |
 
53
 
54
 
55
  ### Framework versions