polejowska
commited on
Commit
•
adbe741
1
Parent(s):
425a064
update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
model-index:
|
6 |
+
- name: detr-resnet50-cd45rb-subdataset
|
7 |
+
results: []
|
8 |
+
---
|
9 |
+
|
10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
11 |
+
should probably proofread and complete it, then remove this comment. -->
|
12 |
+
|
13 |
+
# detr-resnet50-cd45rb-subdataset
|
14 |
+
|
15 |
+
This model is a fine-tuned version of [facebook/detr-resnet-50](https://huggingface.co/facebook/detr-resnet-50) on the None dataset.
|
16 |
+
It achieves the following results on the evaluation set:
|
17 |
+
- Loss: 2.7267
|
18 |
+
|
19 |
+
## Model description
|
20 |
+
|
21 |
+
More information needed
|
22 |
+
|
23 |
+
## Intended uses & limitations
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Training and evaluation data
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training procedure
|
32 |
+
|
33 |
+
### Training hyperparameters
|
34 |
+
|
35 |
+
The following hyperparameters were used during training:
|
36 |
+
- learning_rate: 0.0001
|
37 |
+
- train_batch_size: 4
|
38 |
+
- eval_batch_size: 8
|
39 |
+
- seed: 42
|
40 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
41 |
+
- lr_scheduler_type: linear
|
42 |
+
- num_epochs: 10
|
43 |
+
|
44 |
+
### Training results
|
45 |
+
|
46 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
47 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
48 |
+
| 3.774 | 1.0 | 242 | 2.9629 |
|
49 |
+
| 3.6768 | 2.0 | 484 | 2.8229 |
|
50 |
+
| 3.6554 | 3.0 | 726 | 2.8255 |
|
51 |
+
| 3.5964 | 4.0 | 968 | 2.8284 |
|
52 |
+
| 3.5668 | 5.0 | 1210 | 2.7503 |
|
53 |
+
| 3.5733 | 6.0 | 1452 | 2.7553 |
|
54 |
+
| 3.5197 | 7.0 | 1694 | 2.7467 |
|
55 |
+
| 3.5313 | 8.0 | 1936 | 2.7521 |
|
56 |
+
| 3.4862 | 9.0 | 2178 | 2.7275 |
|
57 |
+
| 3.503 | 10.0 | 2420 | 2.7267 |
|
58 |
+
|
59 |
+
|
60 |
+
### Framework versions
|
61 |
+
|
62 |
+
- Transformers 4.28.1
|
63 |
+
- Pytorch 2.0.0
|
64 |
+
- Datasets 2.10.0
|
65 |
+
- Tokenizers 0.13.2
|