End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: google/vit-base-patch16-224-in21k
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
metrics:
|
| 8 |
+
- accuracy
|
| 9 |
+
model-index:
|
| 10 |
+
- name: food_classifier_2025_01_31_00_04
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# food_classifier_2025_01_31_00_04
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.4920
|
| 22 |
+
- Accuracy: 0.8763
|
| 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: 0.0005
|
| 42 |
+
- train_batch_size: 128
|
| 43 |
+
- eval_batch_size: 128
|
| 44 |
+
- seed: 42
|
| 45 |
+
- distributed_type: multi-GPU
|
| 46 |
+
- num_devices: 4
|
| 47 |
+
- gradient_accumulation_steps: 4
|
| 48 |
+
- total_train_batch_size: 2048
|
| 49 |
+
- total_eval_batch_size: 512
|
| 50 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 51 |
+
- lr_scheduler_type: linear
|
| 52 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 53 |
+
- num_epochs: 15
|
| 54 |
+
|
| 55 |
+
### Training results
|
| 56 |
+
|
| 57 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 58 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 59 |
+
| 3.9401 | 1.0 | 37 | 3.1519 | 0.7044 |
|
| 60 |
+
| 1.5951 | 2.0 | 74 | 1.1581 | 0.7973 |
|
| 61 |
+
| 0.916 | 3.0 | 111 | 0.7583 | 0.8228 |
|
| 62 |
+
| 0.7189 | 4.0 | 148 | 0.6624 | 0.8371 |
|
| 63 |
+
| 0.5926 | 5.0 | 185 | 0.6070 | 0.8476 |
|
| 64 |
+
| 0.5456 | 6.0 | 222 | 0.5709 | 0.8553 |
|
| 65 |
+
| 0.4675 | 7.0 | 259 | 0.5564 | 0.8572 |
|
| 66 |
+
| 0.4246 | 8.0 | 296 | 0.5465 | 0.8602 |
|
| 67 |
+
| 0.3732 | 9.0 | 333 | 0.5401 | 0.8627 |
|
| 68 |
+
| 0.333 | 10.0 | 370 | 0.5197 | 0.8671 |
|
| 69 |
+
| 0.3067 | 11.0 | 407 | 0.5077 | 0.8712 |
|
| 70 |
+
| 0.2872 | 12.0 | 444 | 0.5090 | 0.8702 |
|
| 71 |
+
| 0.2537 | 13.0 | 481 | 0.5066 | 0.8761 |
|
| 72 |
+
| 0.2496 | 14.0 | 518 | 0.5004 | 0.8750 |
|
| 73 |
+
| 0.2282 | 15.0 | 555 | 0.4920 | 0.8763 |
|
| 74 |
+
|
| 75 |
+
|
| 76 |
+
### Framework versions
|
| 77 |
+
|
| 78 |
+
- Transformers 4.48.1
|
| 79 |
+
- Pytorch 2.5.1
|
| 80 |
+
- Datasets 2.19.1
|
| 81 |
+
- Tokenizers 0.21.0
|