Model save
Browse files- README.md +75 -0
- model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
base_model: apple/mobilevit-xx-small
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- accuracy
|
| 8 |
+
model-index:
|
| 9 |
+
- name: quickdraw-MobileViT-xxs-a
|
| 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 |
+
# quickdraw-MobileViT-xxs-a
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [apple/mobilevit-xx-small](https://huggingface.co/apple/mobilevit-xx-small) on an unknown dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 1.1512
|
| 21 |
+
- Accuracy: 0.7126
|
| 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: 0.0008
|
| 41 |
+
- train_batch_size: 512
|
| 42 |
+
- eval_batch_size: 512
|
| 43 |
+
- seed: 42
|
| 44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
+
- lr_scheduler_type: cosine
|
| 46 |
+
- lr_scheduler_warmup_steps: 5000
|
| 47 |
+
- num_epochs: 8
|
| 48 |
+
- mixed_precision_training: Native AMP
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 53 |
+
|:-------------:|:------:|:-----:|:---------------:|:--------:|
|
| 54 |
+
| 1.8007 | 0.5688 | 5000 | 1.7490 | 0.5725 |
|
| 55 |
+
| 1.5116 | 1.1377 | 10000 | 1.5185 | 0.6256 |
|
| 56 |
+
| 1.4298 | 1.7065 | 15000 | 1.4384 | 0.6438 |
|
| 57 |
+
| 1.3622 | 2.2753 | 20000 | 1.3908 | 0.6547 |
|
| 58 |
+
| 1.332 | 2.8441 | 25000 | 1.3210 | 0.6712 |
|
| 59 |
+
| 1.2903 | 3.4130 | 30000 | 1.2758 | 0.6824 |
|
| 60 |
+
| 1.2693 | 3.9818 | 35000 | 1.2592 | 0.6864 |
|
| 61 |
+
| 1.2391 | 4.5506 | 40000 | 1.2169 | 0.6965 |
|
| 62 |
+
| 1.2078 | 5.1195 | 45000 | 1.1928 | 0.7023 |
|
| 63 |
+
| 1.1959 | 5.6883 | 50000 | 1.1779 | 0.7059 |
|
| 64 |
+
| 1.1749 | 6.2571 | 55000 | 1.1669 | 0.7083 |
|
| 65 |
+
| 1.1713 | 6.8259 | 60000 | 1.1564 | 0.7110 |
|
| 66 |
+
| 1.1573 | 7.3948 | 65000 | 1.1524 | 0.7123 |
|
| 67 |
+
| 1.1555 | 7.9636 | 70000 | 1.1512 | 0.7126 |
|
| 68 |
+
|
| 69 |
+
|
| 70 |
+
### Framework versions
|
| 71 |
+
|
| 72 |
+
- Transformers 4.41.0
|
| 73 |
+
- Pytorch 2.2.1
|
| 74 |
+
- Datasets 2.19.1
|
| 75 |
+
- Tokenizers 0.19.1
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4308708
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:de4bcfa7c6264b62561f6b6c488c53b7b113755327eb9caade5da82f4b6cffff
|
| 3 |
size 4308708
|