End of training
Browse files
README.md
ADDED
@@ -0,0 +1,128 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: Akashpb13/Swahili_xlsr
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- ml-superb-subset
|
8 |
+
metrics:
|
9 |
+
- wer
|
10 |
+
model-index:
|
11 |
+
- name: xty_finetune
|
12 |
+
results:
|
13 |
+
- task:
|
14 |
+
name: Automatic Speech Recognition
|
15 |
+
type: automatic-speech-recognition
|
16 |
+
dataset:
|
17 |
+
name: ml-superb-subset
|
18 |
+
type: ml-superb-subset
|
19 |
+
config: xty
|
20 |
+
split: test
|
21 |
+
args: xty
|
22 |
+
metrics:
|
23 |
+
- name: Wer
|
24 |
+
type: wer
|
25 |
+
value: 89.12633563796355
|
26 |
+
---
|
27 |
+
|
28 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
29 |
+
should probably proofread and complete it, then remove this comment. -->
|
30 |
+
|
31 |
+
# xty_finetune
|
32 |
+
|
33 |
+
This model is a fine-tuned version of [Akashpb13/Swahili_xlsr](https://huggingface.co/Akashpb13/Swahili_xlsr) on the ml-superb-subset dataset.
|
34 |
+
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 2.0874
|
36 |
+
- Wer: 89.1263
|
37 |
+
|
38 |
+
## Model description
|
39 |
+
|
40 |
+
More information needed
|
41 |
+
|
42 |
+
## Intended uses & limitations
|
43 |
+
|
44 |
+
More information needed
|
45 |
+
|
46 |
+
## Training and evaluation data
|
47 |
+
|
48 |
+
More information needed
|
49 |
+
|
50 |
+
## Training procedure
|
51 |
+
|
52 |
+
### Training hyperparameters
|
53 |
+
|
54 |
+
The following hyperparameters were used during training:
|
55 |
+
- learning_rate: 9.6e-05
|
56 |
+
- train_batch_size: 32
|
57 |
+
- eval_batch_size: 8
|
58 |
+
- seed: 42
|
59 |
+
- gradient_accumulation_steps: 2
|
60 |
+
- total_train_batch_size: 64
|
61 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
62 |
+
- lr_scheduler_type: cosine
|
63 |
+
- lr_scheduler_warmup_steps: 25
|
64 |
+
- training_steps: 500
|
65 |
+
- mixed_precision_training: Native AMP
|
66 |
+
|
67 |
+
### Training results
|
68 |
+
|
69 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
70 |
+
|:-------------:|:-------:|:----:|:---------------:|:--------:|
|
71 |
+
| 8.5823 | 1.0526 | 10 | 7.7265 | 100.0629 |
|
72 |
+
| 5.0617 | 2.1053 | 20 | 4.2231 | 100.0 |
|
73 |
+
| 3.6512 | 3.1579 | 30 | 3.5631 | 100.0 |
|
74 |
+
| 3.3211 | 4.2105 | 40 | 3.3414 | 100.0 |
|
75 |
+
| 3.2144 | 5.2632 | 50 | 3.2086 | 100.0 |
|
76 |
+
| 3.128 | 6.3158 | 60 | 3.1724 | 100.0 |
|
77 |
+
| 3.0999 | 7.3684 | 70 | 3.1261 | 100.0 |
|
78 |
+
| 3.0585 | 8.4211 | 80 | 3.1200 | 100.0 |
|
79 |
+
| 3.0318 | 9.4737 | 90 | 3.1001 | 100.0 |
|
80 |
+
| 3.0166 | 10.5263 | 100 | 3.0985 | 100.0 |
|
81 |
+
| 3.0147 | 11.5789 | 110 | 3.0971 | 100.0 |
|
82 |
+
| 3.0028 | 12.6316 | 120 | 3.0775 | 100.0 |
|
83 |
+
| 2.991 | 13.6842 | 130 | 3.0619 | 100.0 |
|
84 |
+
| 2.9692 | 14.7368 | 140 | 3.0477 | 100.0 |
|
85 |
+
| 2.9355 | 15.7895 | 150 | 3.0081 | 100.0 |
|
86 |
+
| 2.8754 | 16.8421 | 160 | 2.9190 | 100.0 |
|
87 |
+
| 2.7087 | 17.8947 | 170 | 2.7367 | 100.0 |
|
88 |
+
| 2.4346 | 18.9474 | 180 | 2.5043 | 108.5481 |
|
89 |
+
| 2.3184 | 20.0 | 190 | 2.3709 | 103.8969 |
|
90 |
+
| 2.0887 | 21.0526 | 200 | 2.2196 | 103.3941 |
|
91 |
+
| 1.9198 | 22.1053 | 210 | 2.1078 | 104.7140 |
|
92 |
+
| 1.6995 | 23.1579 | 220 | 2.0556 | 98.4287 |
|
93 |
+
| 1.6576 | 24.2105 | 230 | 2.0081 | 100.6914 |
|
94 |
+
| 1.4855 | 25.2632 | 240 | 1.9958 | 98.0515 |
|
95 |
+
| 1.3788 | 26.3158 | 250 | 1.9729 | 94.8460 |
|
96 |
+
| 1.3202 | 27.3684 | 260 | 1.9618 | 98.6172 |
|
97 |
+
| 1.2237 | 28.4211 | 270 | 1.9662 | 93.6518 |
|
98 |
+
| 1.1389 | 29.4737 | 280 | 1.9882 | 92.7090 |
|
99 |
+
| 1.0597 | 30.5263 | 290 | 1.9655 | 92.3947 |
|
100 |
+
| 1.0203 | 31.5789 | 300 | 1.9616 | 90.1948 |
|
101 |
+
| 0.9778 | 32.6316 | 310 | 1.9585 | 90.8234 |
|
102 |
+
| 0.9553 | 33.6842 | 320 | 1.9875 | 90.5091 |
|
103 |
+
| 0.895 | 34.7368 | 330 | 1.9913 | 91.3891 |
|
104 |
+
| 0.9021 | 35.7895 | 340 | 1.9906 | 90.2577 |
|
105 |
+
| 0.8105 | 36.8421 | 350 | 2.0182 | 89.4406 |
|
106 |
+
| 0.8052 | 37.8947 | 360 | 2.0227 | 89.5663 |
|
107 |
+
| 0.7484 | 38.9474 | 370 | 2.0539 | 89.0006 |
|
108 |
+
| 0.7886 | 40.0 | 380 | 2.0616 | 90.6977 |
|
109 |
+
| 0.7348 | 41.0526 | 390 | 2.0590 | 89.1892 |
|
110 |
+
| 0.7079 | 42.1053 | 400 | 2.0790 | 89.8806 |
|
111 |
+
| 0.7215 | 43.1579 | 410 | 2.0701 | 89.3149 |
|
112 |
+
| 0.6997 | 44.2105 | 420 | 2.0832 | 89.3777 |
|
113 |
+
| 0.721 | 45.2632 | 430 | 2.0798 | 89.3149 |
|
114 |
+
| 0.6609 | 46.3158 | 440 | 2.0834 | 88.4349 |
|
115 |
+
| 0.6562 | 47.3684 | 450 | 2.0892 | 89.0006 |
|
116 |
+
| 0.6418 | 48.4211 | 460 | 2.0878 | 89.3777 |
|
117 |
+
| 0.677 | 49.4737 | 470 | 2.0874 | 89.2520 |
|
118 |
+
| 0.6821 | 50.5263 | 480 | 2.0874 | 89.1263 |
|
119 |
+
| 0.6798 | 51.5789 | 490 | 2.0875 | 89.0635 |
|
120 |
+
| 0.7188 | 52.6316 | 500 | 2.0874 | 89.1263 |
|
121 |
+
|
122 |
+
|
123 |
+
### Framework versions
|
124 |
+
|
125 |
+
- Transformers 4.41.1
|
126 |
+
- Pytorch 2.3.0+cu121
|
127 |
+
- Datasets 2.19.1
|
128 |
+
- Tokenizers 0.19.1
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1262012480
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5cb014878703bda3fad3368b42e2a1f3c1a9b64a323951649e70d1cb7f9c2d43
|
3 |
size 1262012480
|
runs/May22_23-01-53_358fd2b9d7ca/events.out.tfevents.1716419579.358fd2b9d7ca.799.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a65a036cb81f0ad2e31194baa76f38d6b8a79907e2d36579a328ed94aec90b7c
|
3 |
+
size 43384
|