update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,108 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
datasets:
|
6 |
+
- imagefolder
|
7 |
+
model-index:
|
8 |
+
- name: git-base-pokemon
|
9 |
+
results: []
|
10 |
+
---
|
11 |
+
|
12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
13 |
+
should probably proofread and complete it, then remove this comment. -->
|
14 |
+
|
15 |
+
# git-base-pokemon
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [microsoft/git-base](https://huggingface.co/microsoft/git-base) on the imagefolder dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 0.0396
|
20 |
+
- Wer Score: 6.0488
|
21 |
+
|
22 |
+
## Model description
|
23 |
+
|
24 |
+
More information needed
|
25 |
+
|
26 |
+
## Intended uses & limitations
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Training and evaluation data
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Training procedure
|
35 |
+
|
36 |
+
### Training hyperparameters
|
37 |
+
|
38 |
+
The following hyperparameters were used during training:
|
39 |
+
- learning_rate: 5e-05
|
40 |
+
- train_batch_size: 8
|
41 |
+
- eval_batch_size: 8
|
42 |
+
- seed: 42
|
43 |
+
- gradient_accumulation_steps: 2
|
44 |
+
- total_train_batch_size: 16
|
45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
+
- lr_scheduler_type: linear
|
47 |
+
- num_epochs: 50
|
48 |
+
- mixed_precision_training: Native AMP
|
49 |
+
|
50 |
+
### Training results
|
51 |
+
|
52 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer Score |
|
53 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|
|
54 |
+
| 7.3484 | 1.06 | 50 | 4.4320 | 10.6547 |
|
55 |
+
| 2.1536 | 2.13 | 100 | 0.2910 | 1.8947 |
|
56 |
+
| 0.0909 | 3.19 | 150 | 0.0322 | 0.3684 |
|
57 |
+
| 0.0278 | 4.26 | 200 | 0.0275 | 0.3659 |
|
58 |
+
| 0.0211 | 5.32 | 250 | 0.0271 | 0.8858 |
|
59 |
+
| 0.0185 | 6.38 | 300 | 0.0267 | 0.6778 |
|
60 |
+
| 0.0155 | 7.45 | 350 | 0.0272 | 7.8190 |
|
61 |
+
| 0.0129 | 8.51 | 400 | 0.0279 | 3.2452 |
|
62 |
+
| 0.0108 | 9.57 | 450 | 0.0280 | 15.0462 |
|
63 |
+
| 0.0082 | 10.64 | 500 | 0.0291 | 10.0372 |
|
64 |
+
| 0.0069 | 11.7 | 550 | 0.0303 | 15.1592 |
|
65 |
+
| 0.0048 | 12.77 | 600 | 0.0321 | 15.4493 |
|
66 |
+
| 0.0033 | 13.83 | 650 | 0.0322 | 16.2439 |
|
67 |
+
| 0.0022 | 14.89 | 700 | 0.0350 | 17.7125 |
|
68 |
+
| 0.0017 | 15.96 | 750 | 0.0340 | 16.8357 |
|
69 |
+
| 0.0011 | 17.02 | 800 | 0.0354 | 16.8780 |
|
70 |
+
| 0.0009 | 18.09 | 850 | 0.0351 | 17.3273 |
|
71 |
+
| 0.0006 | 19.15 | 900 | 0.0364 | 16.4788 |
|
72 |
+
| 0.0005 | 20.21 | 950 | 0.0368 | 15.4442 |
|
73 |
+
| 0.0004 | 21.28 | 1000 | 0.0368 | 16.2336 |
|
74 |
+
| 0.0004 | 22.34 | 1050 | 0.0375 | 14.1168 |
|
75 |
+
| 0.0004 | 23.4 | 1100 | 0.0375 | 14.4365 |
|
76 |
+
| 0.0004 | 24.47 | 1150 | 0.0373 | 12.3890 |
|
77 |
+
| 0.0004 | 25.53 | 1200 | 0.0379 | 8.7843 |
|
78 |
+
| 0.0004 | 26.6 | 1250 | 0.0382 | 9.2298 |
|
79 |
+
| 0.0003 | 27.66 | 1300 | 0.0383 | 8.8562 |
|
80 |
+
| 0.0003 | 28.72 | 1350 | 0.0384 | 9.5777 |
|
81 |
+
| 0.0003 | 29.79 | 1400 | 0.0383 | 8.6021 |
|
82 |
+
| 0.0003 | 30.85 | 1450 | 0.0387 | 7.9782 |
|
83 |
+
| 0.0003 | 31.91 | 1500 | 0.0387 | 7.7394 |
|
84 |
+
| 0.0003 | 32.98 | 1550 | 0.0388 | 7.6431 |
|
85 |
+
| 0.0003 | 34.04 | 1600 | 0.0389 | 6.9037 |
|
86 |
+
| 0.0003 | 35.11 | 1650 | 0.0391 | 6.8665 |
|
87 |
+
| 0.0003 | 36.17 | 1700 | 0.0392 | 6.0526 |
|
88 |
+
| 0.0003 | 37.23 | 1750 | 0.0394 | 5.6996 |
|
89 |
+
| 0.0003 | 38.3 | 1800 | 0.0393 | 6.1361 |
|
90 |
+
| 0.0003 | 39.36 | 1850 | 0.0394 | 5.9127 |
|
91 |
+
| 0.0003 | 40.43 | 1900 | 0.0394 | 5.6816 |
|
92 |
+
| 0.0003 | 41.49 | 1950 | 0.0394 | 5.3723 |
|
93 |
+
| 0.0003 | 42.55 | 2000 | 0.0395 | 4.8806 |
|
94 |
+
| 0.0002 | 43.62 | 2050 | 0.0395 | 6.9178 |
|
95 |
+
| 0.0002 | 44.68 | 2100 | 0.0395 | 6.2953 |
|
96 |
+
| 0.0002 | 45.74 | 2150 | 0.0395 | 6.1142 |
|
97 |
+
| 0.0002 | 46.81 | 2200 | 0.0396 | 6.0642 |
|
98 |
+
| 0.0002 | 47.87 | 2250 | 0.0396 | 6.0077 |
|
99 |
+
| 0.0002 | 48.94 | 2300 | 0.0396 | 6.0026 |
|
100 |
+
| 0.0002 | 50.0 | 2350 | 0.0396 | 6.0488 |
|
101 |
+
|
102 |
+
|
103 |
+
### Framework versions
|
104 |
+
|
105 |
+
- Transformers 4.29.2
|
106 |
+
- Pytorch 2.0.1+cu117
|
107 |
+
- Datasets 2.12.0
|
108 |
+
- Tokenizers 0.13.3
|