Commit
•
2ca2601
1
Parent(s):
a16eb88
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
datasets:
|
| 5 |
+
- cd45rb_nan_xywh
|
| 6 |
+
model-index:
|
| 7 |
+
- name: detr-r101-cd45rb-8ah-6l-256d-4096ffn-correcetd
|
| 8 |
+
results: []
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
# detr-r101-cd45rb-8ah-6l-256d-4096ffn-correcetd
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [](https://huggingface.co/) on the cd45rb_nan_xywh dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 1.5943
|
| 19 |
+
|
| 20 |
+
## Model description
|
| 21 |
+
|
| 22 |
+
More information needed
|
| 23 |
+
|
| 24 |
+
## Intended uses & limitations
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Training and evaluation data
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training procedure
|
| 33 |
+
|
| 34 |
+
### Training hyperparameters
|
| 35 |
+
|
| 36 |
+
The following hyperparameters were used during training:
|
| 37 |
+
- learning_rate: 1e-05
|
| 38 |
+
- train_batch_size: 4
|
| 39 |
+
- eval_batch_size: 8
|
| 40 |
+
- seed: 42
|
| 41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
+
- lr_scheduler_type: linear
|
| 43 |
+
- num_epochs: 20
|
| 44 |
+
- mixed_precision_training: Native AMP
|
| 45 |
+
|
| 46 |
+
### Training results
|
| 47 |
+
|
| 48 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 49 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
| 50 |
+
| 2.3194 | 1.0 | 4606 | 1.7874 |
|
| 51 |
+
| 2.3461 | 2.0 | 9212 | 1.8376 |
|
| 52 |
+
| 2.3028 | 3.0 | 13818 | 1.9087 |
|
| 53 |
+
| 2.2979 | 4.0 | 18424 | 1.9066 |
|
| 54 |
+
| 2.273 | 5.0 | 23030 | 1.7689 |
|
| 55 |
+
| 2.2372 | 6.0 | 27636 | 1.8501 |
|
| 56 |
+
| 2.2429 | 7.0 | 32242 | 1.7625 |
|
| 57 |
+
| 2.2066 | 8.0 | 36848 | 1.7588 |
|
| 58 |
+
| 2.1914 | 9.0 | 41454 | 1.7062 |
|
| 59 |
+
| 2.1553 | 10.0 | 46060 | 1.7069 |
|
| 60 |
+
| 2.1302 | 11.0 | 50666 | 1.6863 |
|
| 61 |
+
| 2.1321 | 12.0 | 55272 | 1.7722 |
|
| 62 |
+
| 2.1227 | 13.0 | 59878 | 1.6639 |
|
| 63 |
+
| 2.087 | 14.0 | 64484 | 1.6486 |
|
| 64 |
+
| 2.0676 | 15.0 | 69090 | 1.6632 |
|
| 65 |
+
| 2.0604 | 16.0 | 73696 | 1.6429 |
|
| 66 |
+
| 2.0435 | 17.0 | 78302 | 1.6224 |
|
| 67 |
+
| 2.0241 | 18.0 | 82908 | 1.6321 |
|
| 68 |
+
| 2.0041 | 19.0 | 87514 | 1.5970 |
|
| 69 |
+
| 1.9966 | 20.0 | 92120 | 1.5943 |
|
| 70 |
+
|
| 71 |
+
|
| 72 |
+
### Framework versions
|
| 73 |
+
|
| 74 |
+
- Transformers 4.28.0
|
| 75 |
+
- Pytorch 2.0.1
|
| 76 |
+
- Datasets 2.12.0
|
| 77 |
+
- Tokenizers 0.13.3
|