Model save
Browse files
README.md
ADDED
|
@@ -0,0 +1,95 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
datasets:
|
| 5 |
+
- imagefolder
|
| 6 |
+
metrics:
|
| 7 |
+
- accuracy
|
| 8 |
+
model-index:
|
| 9 |
+
- name: vit-pretraining-2024_03_25-classifier
|
| 10 |
+
results:
|
| 11 |
+
- task:
|
| 12 |
+
name: Image Classification
|
| 13 |
+
type: image-classification
|
| 14 |
+
dataset:
|
| 15 |
+
name: imagefolder
|
| 16 |
+
type: imagefolder
|
| 17 |
+
config: default
|
| 18 |
+
split: train
|
| 19 |
+
args: default
|
| 20 |
+
metrics:
|
| 21 |
+
- name: Accuracy
|
| 22 |
+
type: accuracy
|
| 23 |
+
value: 0.7648975791433892
|
| 24 |
+
---
|
| 25 |
+
|
| 26 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 27 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 28 |
+
|
| 29 |
+
# vit-pretraining-2024_03_25-classifier
|
| 30 |
+
|
| 31 |
+
This model was trained from scratch on the imagefolder dataset.
|
| 32 |
+
It achieves the following results on the evaluation set:
|
| 33 |
+
- Loss: 0.5083
|
| 34 |
+
- Accuracy: 0.7649
|
| 35 |
+
|
| 36 |
+
## Model description
|
| 37 |
+
|
| 38 |
+
More information needed
|
| 39 |
+
|
| 40 |
+
## Intended uses & limitations
|
| 41 |
+
|
| 42 |
+
More information needed
|
| 43 |
+
|
| 44 |
+
## Training and evaluation data
|
| 45 |
+
|
| 46 |
+
More information needed
|
| 47 |
+
|
| 48 |
+
## Training procedure
|
| 49 |
+
|
| 50 |
+
### Training hyperparameters
|
| 51 |
+
|
| 52 |
+
The following hyperparameters were used during training:
|
| 53 |
+
- learning_rate: 5e-06
|
| 54 |
+
- train_batch_size: 4
|
| 55 |
+
- eval_batch_size: 4
|
| 56 |
+
- seed: 42
|
| 57 |
+
- gradient_accumulation_steps: 4
|
| 58 |
+
- total_train_batch_size: 16
|
| 59 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 60 |
+
- lr_scheduler_type: linear
|
| 61 |
+
- lr_scheduler_warmup_ratio: 0.2
|
| 62 |
+
- num_epochs: 20
|
| 63 |
+
|
| 64 |
+
### Training results
|
| 65 |
+
|
| 66 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 67 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
| 68 |
+
| 0.6422 | 1.0 | 537 | 0.6409 | 0.6560 |
|
| 69 |
+
| 0.5509 | 2.0 | 1074 | 0.5966 | 0.6862 |
|
| 70 |
+
| 0.5123 | 3.0 | 1611 | 0.5743 | 0.7044 |
|
| 71 |
+
| 0.5237 | 4.0 | 2148 | 0.5523 | 0.7188 |
|
| 72 |
+
| 0.5589 | 5.0 | 2685 | 0.5352 | 0.7370 |
|
| 73 |
+
| 0.5671 | 6.0 | 3222 | 0.5317 | 0.7407 |
|
| 74 |
+
| 0.5247 | 7.0 | 3759 | 0.5228 | 0.7486 |
|
| 75 |
+
| 0.4855 | 8.0 | 4296 | 0.5422 | 0.7374 |
|
| 76 |
+
| 0.5122 | 9.0 | 4833 | 0.5195 | 0.7477 |
|
| 77 |
+
| 0.5381 | 10.0 | 5370 | 0.5277 | 0.7398 |
|
| 78 |
+
| 0.5465 | 11.0 | 5907 | 0.5213 | 0.7514 |
|
| 79 |
+
| 0.4552 | 12.0 | 6444 | 0.5300 | 0.7495 |
|
| 80 |
+
| 0.5188 | 13.0 | 6981 | 0.5107 | 0.7505 |
|
| 81 |
+
| 0.5056 | 14.0 | 7518 | 0.5075 | 0.7579 |
|
| 82 |
+
| 0.4759 | 15.0 | 8055 | 0.5077 | 0.7644 |
|
| 83 |
+
| 0.6042 | 16.0 | 8592 | 0.5143 | 0.7602 |
|
| 84 |
+
| 0.4002 | 17.0 | 9129 | 0.5184 | 0.7612 |
|
| 85 |
+
| 0.4664 | 18.0 | 9666 | 0.5072 | 0.7630 |
|
| 86 |
+
| 0.4653 | 19.0 | 10203 | 0.5103 | 0.7626 |
|
| 87 |
+
| 0.4096 | 20.0 | 10740 | 0.5083 | 0.7649 |
|
| 88 |
+
|
| 89 |
+
|
| 90 |
+
### Framework versions
|
| 91 |
+
|
| 92 |
+
- Transformers 4.39.0.dev0
|
| 93 |
+
- Pytorch 2.2.1+cu121
|
| 94 |
+
- Datasets 2.18.0
|
| 95 |
+
- Tokenizers 0.15.2
|