update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
datasets:
|
| 5 |
+
- coco
|
| 6 |
+
metrics:
|
| 7 |
+
- rouge
|
| 8 |
+
- bleu
|
| 9 |
+
model-index:
|
| 10 |
+
- name: vit-swin-base-224-gpt2-image-captioning
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# vit-swin-base-224-gpt2-image-captioning
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [](https://huggingface.co/) on the coco dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.7923
|
| 22 |
+
- Rouge1: 41.8451
|
| 23 |
+
- Rouge2: 16.3493
|
| 24 |
+
- Rougel: 38.0288
|
| 25 |
+
- Rougelsum: 38.049
|
| 26 |
+
- Bleu: 10.2776
|
| 27 |
+
- Gen Len: 11.2946
|
| 28 |
+
|
| 29 |
+
## Model description
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Intended uses & limitations
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Training and evaluation data
|
| 38 |
+
|
| 39 |
+
More information needed
|
| 40 |
+
|
| 41 |
+
## Training procedure
|
| 42 |
+
|
| 43 |
+
### Training hyperparameters
|
| 44 |
+
|
| 45 |
+
The following hyperparameters were used during training:
|
| 46 |
+
- learning_rate: 5e-05
|
| 47 |
+
- train_batch_size: 64
|
| 48 |
+
- eval_batch_size: 64
|
| 49 |
+
- seed: 42
|
| 50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 51 |
+
- lr_scheduler_type: linear
|
| 52 |
+
- num_epochs: 2
|
| 53 |
+
|
| 54 |
+
### Training results
|
| 55 |
+
|
| 56 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Bleu | Gen Len |
|
| 57 |
+
|:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|:-------:|
|
| 58 |
+
| 1.0018 | 0.38 | 2000 | 0.8860 | 38.6537 | 13.8145 | 35.3932 | 35.3935 | 8.2448 | 11.2946 |
|
| 59 |
+
| 0.8827 | 0.75 | 4000 | 0.8395 | 40.0458 | 14.8829 | 36.5321 | 36.5366 | 9.1169 | 11.2946 |
|
| 60 |
+
| 0.8378 | 1.13 | 6000 | 0.8140 | 41.2736 | 15.9576 | 37.5504 | 37.5512 | 9.871 | 11.2946 |
|
| 61 |
+
| 0.7913 | 1.51 | 8000 | 0.8012 | 41.6642 | 16.1987 | 37.8786 | 37.8891 | 10.0786 | 11.2946 |
|
| 62 |
+
| 0.7794 | 1.89 | 10000 | 0.7933 | 41.9119 | 16.3738 | 38.1062 | 38.1292 | 10.288 | 11.2946 |
|
| 63 |
+
|
| 64 |
+
|
| 65 |
+
### Framework versions
|
| 66 |
+
|
| 67 |
+
- Transformers 4.26.0
|
| 68 |
+
- Pytorch 1.13.1+cu116
|
| 69 |
+
- Datasets 2.9.0
|
| 70 |
+
- Tokenizers 0.13.2
|