YassineBenlaria commited on
Commit
cc99e95
1 Parent(s): 9e8a8bf

continue training (tamasheq only feature extractor)

Browse files
Files changed (2) hide show
  1. README.md +10 -10
  2. pytorch_model.bin +1 -1
README.md CHANGED
@@ -15,8 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model was trained from scratch on the None dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 1.5169
19
- - Wer: 0.8575
20
 
21
  ## Model description
22
 
@@ -36,11 +36,11 @@ More information needed
36
 
37
  The following hyperparameters were used during training:
38
  - learning_rate: 3e-05
39
- - train_batch_size: 16
40
  - eval_batch_size: 8
41
  - seed: 42
42
  - gradient_accumulation_steps: 2
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_steps: 500
@@ -50,12 +50,12 @@ The following hyperparameters were used during training:
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Wer |
52
  |:-------------:|:-----:|:----:|:---------------:|:------:|
53
- | 8.0502 | 15.79 | 300 | 3.0170 | 0.9972 |
54
- | 2.2958 | 31.58 | 600 | 1.2753 | 0.8575 |
55
- | 0.5807 | 47.37 | 900 | 1.2622 | 0.8547 |
56
- | 0.3897 | 63.16 | 1200 | 1.3396 | 0.8603 |
57
- | 0.311 | 78.95 | 1500 | 1.4590 | 0.8743 |
58
- | 0.2819 | 94.74 | 1800 | 1.5169 | 0.8575 |
59
 
60
 
61
  ### Framework versions
 
15
 
16
  This model was trained from scratch on the None dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 1.3689
19
+ - Wer: 0.8342
20
 
21
  ## Model description
22
 
 
36
 
37
  The following hyperparameters were used during training:
38
  - learning_rate: 3e-05
39
+ - train_batch_size: 8
40
  - eval_batch_size: 8
41
  - seed: 42
42
  - gradient_accumulation_steps: 2
43
+ - total_train_batch_size: 16
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
  - lr_scheduler_warmup_steps: 500
 
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Wer |
52
  |:-------------:|:-----:|:----:|:---------------:|:------:|
53
+ | 7.4856 | 5.71 | 300 | 2.9956 | 0.9974 |
54
+ | 2.3903 | 11.43 | 600 | 1.2600 | 0.8816 |
55
+ | 0.9577 | 17.14 | 900 | 1.1878 | 0.8342 |
56
+ | 0.7051 | 22.86 | 1200 | 1.1907 | 0.8053 |
57
+ | 0.5821 | 28.57 | 1500 | 1.2621 | 0.8316 |
58
+ | 0.5037 | 34.29 | 1800 | 1.3689 | 0.8342 |
59
 
60
 
61
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:28ed9fb28eea050068b246d10d18d70fdd64fa6d7d7b2fc90c061dd0e74e09b8
3
  size 1262078125
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b38d7dd7b1a594c232bef815eb7488de6a8f01d655b7c936d9b61e40f4d6f452
3
  size 1262078125