Model save
Browse files
README.md
ADDED
|
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: microsoft/swinv2-base-patch4-window12to16-192to256-22kto1k-ft
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- accuracy
|
| 8 |
+
model-index:
|
| 9 |
+
- name: 1_M_cards-swinv2-base-patch4-window12to16-192to256-22kto1k-ft-finetuned-v3
|
| 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 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/vjti_ai/huggingface/runs/11oybdf9)
|
| 17 |
+
# 1_M_cards-swinv2-base-patch4-window12to16-192to256-22kto1k-ft-finetuned-v3
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [microsoft/swinv2-base-patch4-window12to16-192to256-22kto1k-ft](https://huggingface.co/microsoft/swinv2-base-patch4-window12to16-192to256-22kto1k-ft) on an unknown dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 1.1701
|
| 22 |
+
- Accuracy: 0.5118
|
| 23 |
+
|
| 24 |
+
## Model description
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Intended uses & limitations
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training and evaluation data
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training procedure
|
| 37 |
+
|
| 38 |
+
### Training hyperparameters
|
| 39 |
+
|
| 40 |
+
The following hyperparameters were used during training:
|
| 41 |
+
- learning_rate: 5e-05
|
| 42 |
+
- train_batch_size: 128
|
| 43 |
+
- eval_batch_size: 128
|
| 44 |
+
- seed: 42
|
| 45 |
+
- gradient_accumulation_steps: 4
|
| 46 |
+
- total_train_batch_size: 512
|
| 47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
+
- lr_scheduler_type: linear
|
| 49 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 50 |
+
- num_epochs: 10
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 55 |
+
|:-------------:|:------:|:-----:|:---------------:|:--------:|
|
| 56 |
+
| 1.3156 | 0.9995 | 1633 | 1.2976 | 0.4477 |
|
| 57 |
+
| 1.2943 | 1.9997 | 3267 | 1.2443 | 0.4668 |
|
| 58 |
+
| 1.2411 | 2.9998 | 4901 | 1.2229 | 0.4787 |
|
| 59 |
+
| 1.2368 | 4.0 | 6535 | 1.1967 | 0.4901 |
|
| 60 |
+
| 1.1973 | 4.9995 | 8168 | 1.1910 | 0.4927 |
|
| 61 |
+
| 1.2124 | 5.9997 | 9802 | 1.1811 | 0.4989 |
|
| 62 |
+
| 1.1753 | 6.9998 | 11436 | 1.1685 | 0.5062 |
|
| 63 |
+
| 1.1554 | 8.0 | 13070 | 1.1681 | 0.5080 |
|
| 64 |
+
| 1.1279 | 8.9995 | 14703 | 1.1685 | 0.5100 |
|
| 65 |
+
| 1.1121 | 9.9954 | 16330 | 1.1701 | 0.5118 |
|
| 66 |
+
|
| 67 |
+
|
| 68 |
+
### Framework versions
|
| 69 |
+
|
| 70 |
+
- Transformers 4.41.0
|
| 71 |
+
- Pytorch 2.0.1+cu117
|
| 72 |
+
- Datasets 2.19.1
|
| 73 |
+
- Tokenizers 0.19.1
|