oluwagbotty commited on
Commit
59b8f03
·
verified ·
1 Parent(s): 53aa11e

End of training

Browse files
Files changed (3) hide show
  1. README.md +96 -0
  2. adapter.eng_yor.safetensors +3 -0
  3. training_args.bin +2 -2
README.md ADDED
@@ -0,0 +1,96 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ base_model: oluwagbotty/CS_mms_eng_yor
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - wer
8
+ model-index:
9
+ - name: CS_mms_eng_yor
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # CS_mms_eng_yor
17
+
18
+ This model is a fine-tuned version of [oluwagbotty/CS_mms_eng_yor](https://huggingface.co/oluwagbotty/CS_mms_eng_yor) on the None dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.3397
21
+ - Wer: 0.3218
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 0.0005705665024630542
41
+ - train_batch_size: 16
42
+ - eval_batch_size: 8
43
+ - seed: 42
44
+ - gradient_accumulation_steps: 2
45
+ - total_train_batch_size: 32
46
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
47
+ - lr_scheduler_type: linear
48
+ - num_epochs: 1
49
+ - mixed_precision_training: Native AMP
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
54
+ |:-------------:|:------:|:----:|:---------------:|:------:|
55
+ | 2.3476 | 0.2436 | 100 | 0.4135 | 0.3730 |
56
+ | 0.4631 | 0.4872 | 200 | 0.3958 | 0.3640 |
57
+ | 0.4441 | 0.7308 | 300 | 0.3826 | 0.3493 |
58
+ | 0.4367 | 0.9744 | 400 | 0.3784 | 0.3522 |
59
+ | 0.424 | 1.2168 | 500 | 0.3734 | 0.3468 |
60
+ | 0.4256 | 1.4604 | 600 | 0.3760 | 0.3516 |
61
+ | 0.4189 | 1.7040 | 700 | 0.3739 | 0.3474 |
62
+ | 0.4293 | 1.9476 | 800 | 0.3678 | 0.3448 |
63
+ | 0.4105 | 2.1900 | 900 | 0.3663 | 0.3466 |
64
+ | 0.3981 | 2.4336 | 1000 | 0.3736 | 0.3441 |
65
+ | 0.4161 | 2.6772 | 1100 | 0.3725 | 0.3487 |
66
+ | 0.4188 | 2.9208 | 1200 | 0.3628 | 0.3434 |
67
+ | 0.3984 | 3.1632 | 1300 | 0.3671 | 0.3426 |
68
+ | 0.4108 | 3.4068 | 1400 | 0.3674 | 0.3410 |
69
+ | 0.3905 | 3.6504 | 1500 | 0.3593 | 0.3388 |
70
+ | 0.3977 | 3.8940 | 1600 | 0.3626 | 0.3387 |
71
+ | 0.3961 | 4.1364 | 1700 | 0.3610 | 0.3322 |
72
+ | 0.3844 | 4.3800 | 1800 | 0.3644 | 0.3423 |
73
+ | 0.3938 | 4.6236 | 1900 | 0.3554 | 0.3355 |
74
+ | 0.3808 | 4.8672 | 2000 | 0.3579 | 0.3349 |
75
+ | 0.3822 | 5.1096 | 2100 | 0.3562 | 0.3330 |
76
+ | 0.3755 | 5.3532 | 2200 | 0.3556 | 0.3307 |
77
+ | 0.3789 | 5.5968 | 2300 | 0.3514 | 0.3303 |
78
+ | 0.3742 | 5.8404 | 2400 | 0.3472 | 0.3328 |
79
+ | 0.3608 | 6.0828 | 2500 | 0.3470 | 0.3276 |
80
+ | 0.3647 | 6.3264 | 2600 | 0.3468 | 0.3295 |
81
+ | 0.3719 | 6.5700 | 2700 | 0.3457 | 0.3260 |
82
+ | 0.3678 | 6.8136 | 2800 | 0.3423 | 0.3179 |
83
+ | 0.3575 | 7.0560 | 2900 | 0.3422 | 0.3201 |
84
+ | 0.3427 | 7.2996 | 3000 | 0.3516 | 0.3232 |
85
+ | 0.3661 | 7.5432 | 3100 | 0.3420 | 0.3216 |
86
+ | 0.3502 | 7.7868 | 3200 | 0.3430 | 0.3238 |
87
+ | 0.3681 | 8.0292 | 3300 | 0.3388 | 0.3201 |
88
+ | 0.3454 | 8.2728 | 3400 | 0.3397 | 0.3218 |
89
+
90
+
91
+ ### Framework versions
92
+
93
+ - Transformers 4.52.0.dev0
94
+ - Pytorch 2.6.0+cu124
95
+ - Datasets 3.6.0
96
+ - Tokenizers 0.21.1
adapter.eng_yor.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88dedc0ba93ddcd2ff977e13a109114adf00c2cd3a1865f068d7b2b41b3cc55e
3
+ size 8988136
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2014236a29c7f3c0cda56f7ec8cef5d485b6734b02b72c85745b804087a3127d
3
- size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85fff907b969389dcda74abbf2255d1c6cef3551f7891de56193d503b6209a58
3
+ size 5304