YassineBenlaria commited on
Commit
3015079
1 Parent(s): b1ce7ad

End of training

Browse files
Files changed (1) hide show
  1. README.md +66 -0
README.md ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ metrics:
5
+ - wer
6
+ model-index:
7
+ - name: testing_pretrained_tamasheq_only
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
+ # testing_pretrained_tamasheq_only
15
+
16
+ This model was trained from scratch on the None dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 1.5616
19
+ - Wer: 0.8593
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
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
47
+ - num_epochs: 250
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
52
+ |:-------------:|:------:|:----:|:---------------:|:------:|
53
+ | 6.486 | 35.29 | 300 | 2.9498 | 1.0 |
54
+ | 2.859 | 70.59 | 600 | 2.7420 | 1.0 |
55
+ | 2.7652 | 105.88 | 900 | 2.7188 | 1.0 |
56
+ | 2.6354 | 141.18 | 1200 | 2.2511 | 1.0 |
57
+ | 1.9486 | 176.47 | 1500 | 1.5854 | 0.9111 |
58
+ | 1.3512 | 211.76 | 1800 | 1.5616 | 0.8593 |
59
+
60
+
61
+ ### Framework versions
62
+
63
+ - Transformers 4.33.2
64
+ - Pytorch 2.0.1+cu118
65
+ - Datasets 2.14.5
66
+ - Tokenizers 0.13.3