Commit
•
17098f7
1
Parent(s):
2817683
Model save
Browse files- README.md +102 -0
- model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,102 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: microsoft/swinv2-tiny-patch4-window8-256
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- accuracy
|
| 8 |
+
model-index:
|
| 9 |
+
- name: swinv2-tiny-patch4-window8-256-dmae-humeda-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 |
+
# swinv2-tiny-patch4-window8-256-dmae-humeda-2
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [microsoft/swinv2-tiny-patch4-window8-256](https://huggingface.co/microsoft/swinv2-tiny-patch4-window8-256) on an unknown dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.7356
|
| 21 |
+
- Accuracy: 0.6923
|
| 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: 32
|
| 42 |
+
- eval_batch_size: 32
|
| 43 |
+
- seed: 42
|
| 44 |
+
- gradient_accumulation_steps: 4
|
| 45 |
+
- total_train_batch_size: 128
|
| 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: 40
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 54 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 55 |
+
| No log | 1.0 | 2 | 1.3469 | 0.5 |
|
| 56 |
+
| No log | 2.0 | 4 | 1.3200 | 0.4808 |
|
| 57 |
+
| No log | 3.0 | 6 | 1.3124 | 0.4808 |
|
| 58 |
+
| No log | 4.0 | 8 | 1.2178 | 0.5 |
|
| 59 |
+
| 1.1551 | 5.0 | 10 | 1.0957 | 0.5769 |
|
| 60 |
+
| 1.1551 | 6.0 | 12 | 1.0359 | 0.5769 |
|
| 61 |
+
| 1.1551 | 7.0 | 14 | 1.0103 | 0.5962 |
|
| 62 |
+
| 1.1551 | 8.0 | 16 | 0.9382 | 0.6538 |
|
| 63 |
+
| 1.1551 | 9.0 | 18 | 0.8748 | 0.6346 |
|
| 64 |
+
| 0.9827 | 10.0 | 20 | 0.8836 | 0.6154 |
|
| 65 |
+
| 0.9827 | 11.0 | 22 | 0.8574 | 0.6154 |
|
| 66 |
+
| 0.9827 | 12.0 | 24 | 0.8494 | 0.5962 |
|
| 67 |
+
| 0.9827 | 13.0 | 26 | 0.8226 | 0.6154 |
|
| 68 |
+
| 0.9827 | 14.0 | 28 | 0.8242 | 0.6346 |
|
| 69 |
+
| 0.8007 | 15.0 | 30 | 0.8304 | 0.6154 |
|
| 70 |
+
| 0.8007 | 16.0 | 32 | 0.8447 | 0.6538 |
|
| 71 |
+
| 0.8007 | 17.0 | 34 | 0.8228 | 0.6923 |
|
| 72 |
+
| 0.8007 | 18.0 | 36 | 0.7928 | 0.7115 |
|
| 73 |
+
| 0.8007 | 19.0 | 38 | 0.7822 | 0.6731 |
|
| 74 |
+
| 0.6882 | 20.0 | 40 | 0.7750 | 0.6538 |
|
| 75 |
+
| 0.6882 | 21.0 | 42 | 0.7726 | 0.6538 |
|
| 76 |
+
| 0.6882 | 22.0 | 44 | 0.7898 | 0.6731 |
|
| 77 |
+
| 0.6882 | 23.0 | 46 | 0.8021 | 0.6731 |
|
| 78 |
+
| 0.6882 | 24.0 | 48 | 0.7834 | 0.6923 |
|
| 79 |
+
| 0.6154 | 25.0 | 50 | 0.7634 | 0.6731 |
|
| 80 |
+
| 0.6154 | 26.0 | 52 | 0.7584 | 0.6923 |
|
| 81 |
+
| 0.6154 | 27.0 | 54 | 0.7773 | 0.6538 |
|
| 82 |
+
| 0.6154 | 28.0 | 56 | 0.7830 | 0.6538 |
|
| 83 |
+
| 0.6154 | 29.0 | 58 | 0.7719 | 0.6538 |
|
| 84 |
+
| 0.541 | 30.0 | 60 | 0.7603 | 0.6538 |
|
| 85 |
+
| 0.541 | 31.0 | 62 | 0.7497 | 0.6731 |
|
| 86 |
+
| 0.541 | 32.0 | 64 | 0.7381 | 0.7115 |
|
| 87 |
+
| 0.541 | 33.0 | 66 | 0.7275 | 0.6923 |
|
| 88 |
+
| 0.541 | 34.0 | 68 | 0.7277 | 0.6923 |
|
| 89 |
+
| 0.5163 | 35.0 | 70 | 0.7271 | 0.6923 |
|
| 90 |
+
| 0.5163 | 36.0 | 72 | 0.7274 | 0.6923 |
|
| 91 |
+
| 0.5163 | 37.0 | 74 | 0.7304 | 0.6923 |
|
| 92 |
+
| 0.5163 | 38.0 | 76 | 0.7329 | 0.6923 |
|
| 93 |
+
| 0.5163 | 39.0 | 78 | 0.7351 | 0.6923 |
|
| 94 |
+
| 0.5183 | 40.0 | 80 | 0.7356 | 0.6923 |
|
| 95 |
+
|
| 96 |
+
|
| 97 |
+
### Framework versions
|
| 98 |
+
|
| 99 |
+
- Transformers 4.41.2
|
| 100 |
+
- Pytorch 2.3.0+cu121
|
| 101 |
+
- Datasets 2.20.0
|
| 102 |
+
- 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 110359372
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:752f35bff339635d1d8c89133d5a37aba25f956c9d783ec5534b6fdb517f35c8
|
| 3 |
size 110359372
|