Commit ·
a705816
1
Parent(s): 696116e
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: bsd-3-clause
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- imagefolder
|
| 7 |
+
model-index:
|
| 8 |
+
- name: models
|
| 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 |
+
# models
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [Salesforce/blip-image-captioning-base](https://huggingface.co/Salesforce/blip-image-captioning-base) on the imagefolder dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 1.4107
|
| 20 |
+
- Wer Score: 0.5495
|
| 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: 1
|
| 41 |
+
- eval_batch_size: 1
|
| 42 |
+
- seed: 42
|
| 43 |
+
- gradient_accumulation_steps: 4
|
| 44 |
+
- total_train_batch_size: 4
|
| 45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
+
- lr_scheduler_type: linear
|
| 47 |
+
- num_epochs: 1
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer Score |
|
| 52 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|
|
| 53 |
+
| 9.4536 | 0.05 | 10 | 7.8217 | 41.7753 |
|
| 54 |
+
| 7.3267 | 0.11 | 20 | 6.6585 | 0.7753 |
|
| 55 |
+
| 6.2358 | 0.16 | 30 | 5.7758 | 0.5667 |
|
| 56 |
+
| 5.2862 | 0.22 | 40 | 4.7628 | 0.5419 |
|
| 57 |
+
| 4.3786 | 0.27 | 50 | 3.9203 | 0.6398 |
|
| 58 |
+
| 3.5554 | 0.33 | 60 | 3.1482 | 0.5613 |
|
| 59 |
+
| 2.849 | 0.38 | 70 | 2.5209 | 0.5548 |
|
| 60 |
+
| 2.3041 | 0.44 | 80 | 2.0561 | 0.5645 |
|
| 61 |
+
| 1.8999 | 0.49 | 90 | 1.7474 | 0.5645 |
|
| 62 |
+
| 1.658 | 0.55 | 100 | 1.5722 | 0.5548 |
|
| 63 |
+
| 1.5238 | 0.6 | 110 | 1.4836 | 0.5591 |
|
| 64 |
+
| 1.4726 | 0.66 | 120 | 1.4461 | 0.5538 |
|
| 65 |
+
| 1.4328 | 0.71 | 130 | 1.4285 | 0.5473 |
|
| 66 |
+
| 1.4211 | 0.77 | 140 | 1.4205 | 0.5559 |
|
| 67 |
+
| 1.4202 | 0.82 | 150 | 1.4156 | 0.5548 |
|
| 68 |
+
| 1.4098 | 0.88 | 160 | 1.4129 | 0.5505 |
|
| 69 |
+
| 1.4124 | 0.93 | 170 | 1.4113 | 0.5548 |
|
| 70 |
+
| 1.4075 | 0.99 | 180 | 1.4107 | 0.5495 |
|
| 71 |
+
|
| 72 |
+
|
| 73 |
+
### Framework versions
|
| 74 |
+
|
| 75 |
+
- Transformers 4.30.2
|
| 76 |
+
- Pytorch 2.0.1+cpu
|
| 77 |
+
- Datasets 2.13.1
|
| 78 |
+
- Tokenizers 0.13.3
|