Commit
•
22d19f9
1
Parent(s):
23a3d87
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: bsd-3-clause
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: blip-image-captioning-base-blip-dummy-temp-1
|
| 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 |
+
# blip-image-captioning-base-blip-dummy-temp-1
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [Salesforce/blip-image-captioning-base](https://huggingface.co/Salesforce/blip-image-captioning-base) on an unknown dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 1.7117
|
| 18 |
+
- Wer Score: 0.4618
|
| 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: 5e-05
|
| 38 |
+
- train_batch_size: 8
|
| 39 |
+
- eval_batch_size: 8
|
| 40 |
+
- seed: 42
|
| 41 |
+
- gradient_accumulation_steps: 4
|
| 42 |
+
- total_train_batch_size: 32
|
| 43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
+
- lr_scheduler_type: linear
|
| 45 |
+
- num_epochs: 50
|
| 46 |
+
|
| 47 |
+
### Training results
|
| 48 |
+
|
| 49 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer Score |
|
| 50 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|
|
| 51 |
+
| 7.1762 | 3.23 | 50 | 4.4355 | 0.8626 |
|
| 52 |
+
| 2.7292 | 6.45 | 100 | 1.8212 | 0.7393 |
|
| 53 |
+
| 1.6499 | 9.68 | 150 | 1.7030 | 0.5773 |
|
| 54 |
+
| 1.4923 | 12.9 | 200 | 1.6767 | 0.5157 |
|
| 55 |
+
| 1.4285 | 16.13 | 250 | 1.6746 | 0.4752 |
|
| 56 |
+
| 1.3994 | 19.35 | 300 | 1.6786 | 0.4720 |
|
| 57 |
+
| 1.3862 | 22.58 | 350 | 1.6862 | 0.4611 |
|
| 58 |
+
| 1.3801 | 25.81 | 400 | 1.6925 | 0.4572 |
|
| 59 |
+
| 1.3764 | 29.03 | 450 | 1.6972 | 0.4590 |
|
| 60 |
+
| 1.3742 | 32.26 | 500 | 1.7026 | 0.4583 |
|
| 61 |
+
| 1.3727 | 35.48 | 550 | 1.7066 | 0.4604 |
|
| 62 |
+
| 1.3718 | 38.71 | 600 | 1.7087 | 0.4600 |
|
| 63 |
+
| 1.3712 | 41.94 | 650 | 1.7102 | 0.4597 |
|
| 64 |
+
| 1.3708 | 45.16 | 700 | 1.7113 | 0.4614 |
|
| 65 |
+
| 1.3707 | 48.39 | 750 | 1.7117 | 0.4618 |
|
| 66 |
+
|
| 67 |
+
|
| 68 |
+
### Framework versions
|
| 69 |
+
|
| 70 |
+
- Transformers 4.30.2
|
| 71 |
+
- Pytorch 2.0.1+cu118
|
| 72 |
+
- Datasets 2.14.3
|
| 73 |
+
- Tokenizers 0.13.3
|