Commit
•
50782a5
1
Parent(s):
d23af88
End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: ansilmbabl/vit-base-patch16-224-in21k-cards-june-07-cropping-filtered-preprocess-change-test
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- accuracy
|
| 8 |
+
model-index:
|
| 9 |
+
- name: vit-base-patch16-224-in21k-cards-june-08-cropping-filtered-preprocess-change-test-2
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# vit-base-patch16-224-in21k-cards-june-08-cropping-filtered-preprocess-change-test-2
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [ansilmbabl/vit-base-patch16-224-in21k-cards-june-07-cropping-filtered-preprocess-change-test](https://huggingface.co/ansilmbabl/vit-base-patch16-224-in21k-cards-june-07-cropping-filtered-preprocess-change-test) on the None dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 2.5958
|
| 21 |
+
- Accuracy: 0.5147
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 5e-05
|
| 41 |
+
- train_batch_size: 64
|
| 42 |
+
- eval_batch_size: 64
|
| 43 |
+
- seed: 42
|
| 44 |
+
- gradient_accumulation_steps: 8
|
| 45 |
+
- total_train_batch_size: 512
|
| 46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
+
- lr_scheduler_type: linear
|
| 48 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 49 |
+
- num_epochs: 10
|
| 50 |
+
- mixed_precision_training: Native AMP
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Accuracy | Validation Loss |
|
| 55 |
+
|:-------------:|:------:|:-----:|:--------:|:---------------:|
|
| 56 |
+
| 1.0182 | 0.9998 | 1298 | 0.4287 | 1.5280 |
|
| 57 |
+
| 0.9583 | 1.9996 | 2596 | 0.4475 | 1.4878 |
|
| 58 |
+
| 0.8452 | 2.9998 | 3894 | 1.4847 | 0.4716 |
|
| 59 |
+
| 0.6887 | 3.9996 | 5192 | 1.5848 | 0.4736 |
|
| 60 |
+
| 0.5269 | 4.9994 | 6490 | 1.6689 | 0.493 |
|
| 61 |
+
| 0.4018 | 6.0 | 7789 | 1.8483 | 0.4986 |
|
| 62 |
+
| 0.2909 | 6.9998 | 9087 | 2.0319 | 0.5079 |
|
| 63 |
+
| 0.1823 | 7.9996 | 10385 | 2.2540 | 0.5127 |
|
| 64 |
+
| 0.1056 | 8.9994 | 11683 | 2.4652 | 0.511 |
|
| 65 |
+
| 0.0767 | 9.9985 | 12980 | 2.5958 | 0.5147 |
|
| 66 |
+
|
| 67 |
+
|
| 68 |
+
### Framework versions
|
| 69 |
+
|
| 70 |
+
- Transformers 4.41.2
|
| 71 |
+
- Pytorch 2.0.1+cu117
|
| 72 |
+
- Datasets 2.19.2
|
| 73 |
+
- Tokenizers 0.19.1
|