Model save
Browse files
README.md
ADDED
|
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: microsoft/swinv2-tiny-patch4-window8-256
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
metrics:
|
| 8 |
+
- accuracy
|
| 9 |
+
model-index:
|
| 10 |
+
- name: swinv2-tiny-patch4-window8-256-dmae-humeda-DAV24
|
| 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 |
+
# swinv2-tiny-patch4-window8-256-dmae-humeda-DAV24
|
| 18 |
+
|
| 19 |
+
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.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.8851
|
| 22 |
+
- Accuracy: 0.7059
|
| 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: 3e-05
|
| 42 |
+
- train_batch_size: 32
|
| 43 |
+
- eval_batch_size: 32
|
| 44 |
+
- seed: 42
|
| 45 |
+
- gradient_accumulation_steps: 4
|
| 46 |
+
- total_train_batch_size: 128
|
| 47 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 48 |
+
- lr_scheduler_type: cosine
|
| 49 |
+
- lr_scheduler_warmup_ratio: 0.2
|
| 50 |
+
- num_epochs: 25
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 55 |
+
|:-------------:|:-------:|:----:|:---------------:|:--------:|
|
| 56 |
+
| 6.5614 | 1.0 | 17 | 1.6096 | 0.3176 |
|
| 57 |
+
| 6.1279 | 2.0 | 34 | 1.5651 | 0.3176 |
|
| 58 |
+
| 5.5089 | 3.0 | 51 | 1.3188 | 0.5529 |
|
| 59 |
+
| 4.453 | 4.0 | 68 | 1.0195 | 0.6353 |
|
| 60 |
+
| 3.3808 | 5.0 | 85 | 0.9741 | 0.5882 |
|
| 61 |
+
| 2.7707 | 6.0 | 102 | 0.8365 | 0.6353 |
|
| 62 |
+
| 2.3091 | 7.0 | 119 | 0.7725 | 0.6588 |
|
| 63 |
+
| 1.9831 | 8.0 | 136 | 0.8312 | 0.6588 |
|
| 64 |
+
| 1.8284 | 9.0 | 153 | 0.8473 | 0.7059 |
|
| 65 |
+
| 1.511 | 10.0 | 170 | 0.7539 | 0.7176 |
|
| 66 |
+
| 1.2827 | 11.0 | 187 | 0.8067 | 0.7176 |
|
| 67 |
+
| 1.2072 | 12.0 | 204 | 0.7927 | 0.7176 |
|
| 68 |
+
| 1.2069 | 13.0 | 221 | 0.8184 | 0.6824 |
|
| 69 |
+
| 0.9242 | 14.0 | 238 | 0.8548 | 0.7059 |
|
| 70 |
+
| 0.9772 | 15.0 | 255 | 0.8374 | 0.7294 |
|
| 71 |
+
| 0.8412 | 16.0 | 272 | 0.8340 | 0.7176 |
|
| 72 |
+
| 0.8921 | 17.0 | 289 | 0.8729 | 0.6941 |
|
| 73 |
+
| 0.7975 | 18.0 | 306 | 0.9115 | 0.7059 |
|
| 74 |
+
| 0.8107 | 19.0 | 323 | 0.8830 | 0.6941 |
|
| 75 |
+
| 0.7131 | 20.0 | 340 | 0.9049 | 0.6941 |
|
| 76 |
+
| 0.6777 | 21.0 | 357 | 0.8895 | 0.7059 |
|
| 77 |
+
| 0.6557 | 22.0 | 374 | 0.8831 | 0.7059 |
|
| 78 |
+
| 0.6555 | 23.0 | 391 | 0.8846 | 0.7059 |
|
| 79 |
+
| 0.7766 | 23.5455 | 400 | 0.8851 | 0.7059 |
|
| 80 |
+
|
| 81 |
+
|
| 82 |
+
### Framework versions
|
| 83 |
+
|
| 84 |
+
- Transformers 4.47.1
|
| 85 |
+
- Pytorch 2.5.1+cu121
|
| 86 |
+
- Datasets 3.2.0
|
| 87 |
+
- Tokenizers 0.21.0
|
runs/Jan24_00-55-50_28a7f0679e8d/events.out.tfevents.1737680173.28a7f0679e8d.4728.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a7f819e755a82eef84aab132f1104ddf1176a62c1c55412914365e135c0afc7b
|
| 3 |
+
size 20716
|