eldad-akhaumere
commited on
End of training
Browse files- README.md +76 -0
- adapter_model.safetensors +1 -1
README.md
ADDED
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
language:
|
4 |
+
- ha
|
5 |
+
license: apache-2.0
|
6 |
+
base_model: openai/whisper-small
|
7 |
+
tags:
|
8 |
+
- generated_from_trainer
|
9 |
+
datasets:
|
10 |
+
- eldad-akhaumere/common_voice_16_0_
|
11 |
+
model-index:
|
12 |
+
- name: Whisper Small_LoRA Ha - Eldad Akhaumere
|
13 |
+
results: []
|
14 |
+
---
|
15 |
+
|
16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
17 |
+
should probably proofread and complete it, then remove this comment. -->
|
18 |
+
|
19 |
+
# Whisper Small_LoRA Ha - Eldad Akhaumere
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 16.0_ dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 2.0708
|
24 |
+
|
25 |
+
## Model description
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Intended uses & limitations
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training and evaluation data
|
34 |
+
|
35 |
+
More information needed
|
36 |
+
|
37 |
+
## Training procedure
|
38 |
+
|
39 |
+
### Training hyperparameters
|
40 |
+
|
41 |
+
The following hyperparameters were used during training:
|
42 |
+
- learning_rate: 3e-05
|
43 |
+
- train_batch_size: 16
|
44 |
+
- eval_batch_size: 8
|
45 |
+
- seed: 42
|
46 |
+
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
47 |
+
- lr_scheduler_type: constant_with_warmup
|
48 |
+
- lr_scheduler_warmup_steps: 50
|
49 |
+
- num_epochs: 20.0
|
50 |
+
- mixed_precision_training: Native AMP
|
51 |
+
|
52 |
+
### Training results
|
53 |
+
|
54 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
55 |
+
|:-------------:|:-------:|:----:|:---------------:|
|
56 |
+
| 3.0616 | 1.5924 | 250 | 2.9990 |
|
57 |
+
| 2.1053 | 3.1847 | 500 | 2.1317 |
|
58 |
+
| 2.0123 | 4.7771 | 750 | 2.0903 |
|
59 |
+
| 1.9218 | 6.3694 | 1000 | 2.0661 |
|
60 |
+
| 1.894 | 7.9618 | 1250 | 2.0513 |
|
61 |
+
| 1.7961 | 9.5541 | 1500 | 2.0348 |
|
62 |
+
| 1.764 | 11.1465 | 1750 | 2.0300 |
|
63 |
+
| 1.748 | 12.7389 | 2000 | 2.0210 |
|
64 |
+
| 1.6554 | 14.3312 | 2250 | 2.0353 |
|
65 |
+
| 1.6556 | 15.9236 | 2500 | 2.0369 |
|
66 |
+
| 1.6059 | 17.5159 | 2750 | 2.0441 |
|
67 |
+
| 1.5215 | 19.1083 | 3000 | 2.0708 |
|
68 |
+
|
69 |
+
|
70 |
+
### Framework versions
|
71 |
+
|
72 |
+
- PEFT 0.14.1.dev0
|
73 |
+
- Transformers 4.48.0.dev0
|
74 |
+
- Pytorch 2.5.1+cu121
|
75 |
+
- Datasets 3.2.0
|
76 |
+
- Tokenizers 0.21.0
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14176064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e2340c1569e1516c5a5e1d83f7291cd25214f2bb1799750ba03234f633167f41
|
3 |
size 14176064
|