Model save
Browse files
README.md
ADDED
|
@@ -0,0 +1,93 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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-DAV4
|
| 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-DAV4
|
| 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: 1.3233
|
| 22 |
+
- Accuracy: 0.6538
|
| 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: 16
|
| 43 |
+
- eval_batch_size: 16
|
| 44 |
+
- seed: 42
|
| 45 |
+
- gradient_accumulation_steps: 2
|
| 46 |
+
- total_train_batch_size: 32
|
| 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: linear
|
| 49 |
+
- lr_scheduler_warmup_ratio: 0.05
|
| 50 |
+
- num_epochs: 30
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 55 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 56 |
+
| 3.1112 | 1.0 | 23 | 1.4616 | 0.4423 |
|
| 57 |
+
| 2.4301 | 2.0 | 46 | 1.3378 | 0.3846 |
|
| 58 |
+
| 1.8107 | 3.0 | 69 | 1.1497 | 0.4423 |
|
| 59 |
+
| 1.3272 | 4.0 | 92 | 1.2177 | 0.5 |
|
| 60 |
+
| 1.2039 | 5.0 | 115 | 1.1250 | 0.5577 |
|
| 61 |
+
| 1.0311 | 6.0 | 138 | 1.0660 | 0.5577 |
|
| 62 |
+
| 1.0515 | 7.0 | 161 | 1.2242 | 0.5 |
|
| 63 |
+
| 0.8709 | 8.0 | 184 | 1.0952 | 0.5962 |
|
| 64 |
+
| 0.677 | 9.0 | 207 | 1.1033 | 0.5385 |
|
| 65 |
+
| 0.6763 | 10.0 | 230 | 0.9551 | 0.7115 |
|
| 66 |
+
| 0.5749 | 11.0 | 253 | 1.0428 | 0.6346 |
|
| 67 |
+
| 0.4896 | 12.0 | 276 | 1.0981 | 0.6538 |
|
| 68 |
+
| 0.4817 | 13.0 | 299 | 1.3429 | 0.4808 |
|
| 69 |
+
| 0.4264 | 14.0 | 322 | 1.3040 | 0.6154 |
|
| 70 |
+
| 0.5637 | 15.0 | 345 | 1.2592 | 0.4808 |
|
| 71 |
+
| 0.3846 | 16.0 | 368 | 1.1849 | 0.6154 |
|
| 72 |
+
| 0.5337 | 17.0 | 391 | 1.2025 | 0.6346 |
|
| 73 |
+
| 0.34 | 18.0 | 414 | 1.0894 | 0.6346 |
|
| 74 |
+
| 0.3511 | 19.0 | 437 | 1.2145 | 0.6346 |
|
| 75 |
+
| 0.2539 | 20.0 | 460 | 1.1755 | 0.6346 |
|
| 76 |
+
| 0.2683 | 21.0 | 483 | 1.2359 | 0.6731 |
|
| 77 |
+
| 0.3144 | 22.0 | 506 | 1.2633 | 0.6538 |
|
| 78 |
+
| 0.3249 | 23.0 | 529 | 1.2980 | 0.6346 |
|
| 79 |
+
| 0.2363 | 24.0 | 552 | 1.1872 | 0.6538 |
|
| 80 |
+
| 0.2876 | 25.0 | 575 | 1.2377 | 0.6923 |
|
| 81 |
+
| 0.2694 | 26.0 | 598 | 1.2695 | 0.6538 |
|
| 82 |
+
| 0.2307 | 27.0 | 621 | 1.2481 | 0.6731 |
|
| 83 |
+
| 0.2508 | 28.0 | 644 | 1.3112 | 0.6731 |
|
| 84 |
+
| 0.3558 | 29.0 | 667 | 1.3209 | 0.6731 |
|
| 85 |
+
| 0.2418 | 30.0 | 690 | 1.3233 | 0.6538 |
|
| 86 |
+
|
| 87 |
+
|
| 88 |
+
### Framework versions
|
| 89 |
+
|
| 90 |
+
- Transformers 4.47.1
|
| 91 |
+
- Pytorch 2.5.1+cu121
|
| 92 |
+
- Datasets 3.2.0
|
| 93 |
+
- Tokenizers 0.21.0
|
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 sha256:521f8a7e828c11bb904b73cfd9256063caf887d9e5b6c5e8fbe31d8ce38c7e67
|
| 3 |
size 110359372
|
runs/Jan19_20-17-10_91b964dcb8be/events.out.tfevents.1737317909.91b964dcb8be.751.0
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:f9a8cbf80d96ff467b310a23a14280bf7efb18e81af763fb310199baacd6f9b7
|
| 3 |
+
size 30256
|