SJChaudhuri
commited on
Commit
•
5785882
1
Parent(s):
a688c05
update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,91 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
metrics:
|
6 |
+
- accuracy
|
7 |
+
model-index:
|
8 |
+
- name: cvt-13-finetuned-IDRiD
|
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 |
+
# cvt-13-finetuned-IDRiD
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [microsoft/cvt-13](https://huggingface.co/microsoft/cvt-13) on an unknown dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 1.2520
|
20 |
+
- Accuracy: 0.4524
|
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: 32
|
41 |
+
- eval_batch_size: 32
|
42 |
+
- seed: 42
|
43 |
+
- gradient_accumulation_steps: 4
|
44 |
+
- total_train_batch_size: 128
|
45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
+
- lr_scheduler_type: linear
|
47 |
+
- lr_scheduler_warmup_ratio: 0.1
|
48 |
+
- num_epochs: 30
|
49 |
+
|
50 |
+
### Training results
|
51 |
+
|
52 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
53 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
54 |
+
| No log | 1.0 | 3 | 1.6800 | 0.1190 |
|
55 |
+
| No log | 2.0 | 6 | 1.6686 | 0.2143 |
|
56 |
+
| No log | 3.0 | 9 | 1.5528 | 0.3333 |
|
57 |
+
| 1.6061 | 4.0 | 12 | 1.4874 | 0.3333 |
|
58 |
+
| 1.6061 | 5.0 | 15 | 1.4834 | 0.3571 |
|
59 |
+
| 1.6061 | 6.0 | 18 | 1.4485 | 0.3810 |
|
60 |
+
| 1.4325 | 7.0 | 21 | 1.4295 | 0.4048 |
|
61 |
+
| 1.4325 | 8.0 | 24 | 1.4172 | 0.4286 |
|
62 |
+
| 1.4325 | 9.0 | 27 | 1.3890 | 0.4048 |
|
63 |
+
| 1.3474 | 10.0 | 30 | 1.3739 | 0.4286 |
|
64 |
+
| 1.3474 | 11.0 | 33 | 1.3571 | 0.4048 |
|
65 |
+
| 1.3474 | 12.0 | 36 | 1.3244 | 0.4048 |
|
66 |
+
| 1.3474 | 13.0 | 39 | 1.3090 | 0.4048 |
|
67 |
+
| 1.3039 | 14.0 | 42 | 1.3438 | 0.4286 |
|
68 |
+
| 1.3039 | 15.0 | 45 | 1.3617 | 0.4286 |
|
69 |
+
| 1.3039 | 16.0 | 48 | 1.3513 | 0.4286 |
|
70 |
+
| 1.2892 | 17.0 | 51 | 1.3187 | 0.4524 |
|
71 |
+
| 1.2892 | 18.0 | 54 | 1.3054 | 0.3810 |
|
72 |
+
| 1.2892 | 19.0 | 57 | 1.2862 | 0.4286 |
|
73 |
+
| 1.2489 | 20.0 | 60 | 1.2670 | 0.4524 |
|
74 |
+
| 1.2489 | 21.0 | 63 | 1.2810 | 0.4762 |
|
75 |
+
| 1.2489 | 22.0 | 66 | 1.2389 | 0.4524 |
|
76 |
+
| 1.2489 | 23.0 | 69 | 1.2312 | 0.4762 |
|
77 |
+
| 1.2378 | 24.0 | 72 | 1.2619 | 0.4524 |
|
78 |
+
| 1.2378 | 25.0 | 75 | 1.2652 | 0.4524 |
|
79 |
+
| 1.2378 | 26.0 | 78 | 1.2639 | 0.4524 |
|
80 |
+
| 1.1968 | 27.0 | 81 | 1.2517 | 0.4524 |
|
81 |
+
| 1.1968 | 28.0 | 84 | 1.2603 | 0.4286 |
|
82 |
+
| 1.1968 | 29.0 | 87 | 1.2463 | 0.4524 |
|
83 |
+
| 1.1977 | 30.0 | 90 | 1.2520 | 0.4524 |
|
84 |
+
|
85 |
+
|
86 |
+
### Framework versions
|
87 |
+
|
88 |
+
- Transformers 4.30.0
|
89 |
+
- Pytorch 2.2.1+cu121
|
90 |
+
- Datasets 2.18.0
|
91 |
+
- Tokenizers 0.13.3
|