Model save
Browse files
README.md
ADDED
|
@@ -0,0 +1,105 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
datasets:
|
| 5 |
+
- imagefolder
|
| 6 |
+
metrics:
|
| 7 |
+
- accuracy
|
| 8 |
+
model-index:
|
| 9 |
+
- name: 2024_08_16_swinv2-base-patch4-window8-256
|
| 10 |
+
results:
|
| 11 |
+
- task:
|
| 12 |
+
name: Image Classification
|
| 13 |
+
type: image-classification
|
| 14 |
+
dataset:
|
| 15 |
+
name: imagefolder
|
| 16 |
+
type: imagefolder
|
| 17 |
+
config: default
|
| 18 |
+
split: train
|
| 19 |
+
args: default
|
| 20 |
+
metrics:
|
| 21 |
+
- name: Accuracy
|
| 22 |
+
type: accuracy
|
| 23 |
+
value: 0.8068181818181818
|
| 24 |
+
---
|
| 25 |
+
|
| 26 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 27 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 28 |
+
|
| 29 |
+
# 2024_08_16_swinv2-base-patch4-window8-256
|
| 30 |
+
|
| 31 |
+
This model was trained from scratch on the imagefolder dataset.
|
| 32 |
+
It achieves the following results on the evaluation set:
|
| 33 |
+
- Loss: 0.5152
|
| 34 |
+
- Accuracy: 0.8068
|
| 35 |
+
|
| 36 |
+
## Model description
|
| 37 |
+
|
| 38 |
+
More information needed
|
| 39 |
+
|
| 40 |
+
## Intended uses & limitations
|
| 41 |
+
|
| 42 |
+
More information needed
|
| 43 |
+
|
| 44 |
+
## Training and evaluation data
|
| 45 |
+
|
| 46 |
+
More information needed
|
| 47 |
+
|
| 48 |
+
## Training procedure
|
| 49 |
+
|
| 50 |
+
### Training hyperparameters
|
| 51 |
+
|
| 52 |
+
The following hyperparameters were used during training:
|
| 53 |
+
- learning_rate: 1e-05
|
| 54 |
+
- train_batch_size: 1
|
| 55 |
+
- eval_batch_size: 1
|
| 56 |
+
- seed: 42
|
| 57 |
+
- gradient_accumulation_steps: 4
|
| 58 |
+
- total_train_batch_size: 4
|
| 59 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 60 |
+
- lr_scheduler_type: linear
|
| 61 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 62 |
+
- num_epochs: 30
|
| 63 |
+
|
| 64 |
+
### Training results
|
| 65 |
+
|
| 66 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 67 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 68 |
+
| 0.6942 | 1.0 | 87 | 0.6796 | 0.6818 |
|
| 69 |
+
| 0.6661 | 2.0 | 174 | 0.5973 | 0.7045 |
|
| 70 |
+
| 0.5666 | 3.0 | 261 | 0.5844 | 0.7045 |
|
| 71 |
+
| 0.6134 | 4.0 | 348 | 0.5798 | 0.7045 |
|
| 72 |
+
| 0.5207 | 5.0 | 435 | 0.5817 | 0.6932 |
|
| 73 |
+
| 0.75 | 6.0 | 522 | 0.5488 | 0.7159 |
|
| 74 |
+
| 0.4155 | 7.0 | 609 | 0.5373 | 0.7045 |
|
| 75 |
+
| 0.5122 | 8.0 | 696 | 0.5057 | 0.7386 |
|
| 76 |
+
| 0.722 | 9.0 | 783 | 0.4951 | 0.7045 |
|
| 77 |
+
| 0.5301 | 10.0 | 870 | 0.5349 | 0.7727 |
|
| 78 |
+
| 0.5881 | 11.0 | 957 | 0.4795 | 0.7955 |
|
| 79 |
+
| 0.5295 | 12.0 | 1044 | 0.4843 | 0.7955 |
|
| 80 |
+
| 0.6252 | 13.0 | 1131 | 0.4529 | 0.8068 |
|
| 81 |
+
| 0.9347 | 14.0 | 1218 | 0.4670 | 0.7955 |
|
| 82 |
+
| 0.5375 | 15.0 | 1305 | 0.4468 | 0.8068 |
|
| 83 |
+
| 0.4811 | 16.0 | 1392 | 0.4912 | 0.7841 |
|
| 84 |
+
| 0.5728 | 17.0 | 1479 | 0.4636 | 0.8068 |
|
| 85 |
+
| 0.7997 | 18.0 | 1566 | 0.4631 | 0.8068 |
|
| 86 |
+
| 0.4473 | 19.0 | 1653 | 0.4785 | 0.8068 |
|
| 87 |
+
| 0.4999 | 20.0 | 1740 | 0.5162 | 0.8068 |
|
| 88 |
+
| 0.4572 | 21.0 | 1827 | 0.5742 | 0.7955 |
|
| 89 |
+
| 0.2571 | 22.0 | 1914 | 0.5181 | 0.7955 |
|
| 90 |
+
| 0.5085 | 23.0 | 2001 | 0.4937 | 0.7955 |
|
| 91 |
+
| 0.7698 | 24.0 | 2088 | 0.4764 | 0.7955 |
|
| 92 |
+
| 0.558 | 25.0 | 2175 | 0.4742 | 0.8068 |
|
| 93 |
+
| 0.5462 | 26.0 | 2262 | 0.5320 | 0.7841 |
|
| 94 |
+
| 0.5218 | 27.0 | 2349 | 0.5298 | 0.7841 |
|
| 95 |
+
| 0.5228 | 28.0 | 2436 | 0.5182 | 0.7955 |
|
| 96 |
+
| 0.5787 | 29.0 | 2523 | 0.5104 | 0.8068 |
|
| 97 |
+
| 0.7511 | 30.0 | 2610 | 0.5152 | 0.8068 |
|
| 98 |
+
|
| 99 |
+
|
| 100 |
+
### Framework versions
|
| 101 |
+
|
| 102 |
+
- Transformers 4.42.3
|
| 103 |
+
- Pytorch 2.3.1+cu118
|
| 104 |
+
- Datasets 2.20.0
|
| 105 |
+
- 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 347645480
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3616d533f893e4ac4cbd4ebfb1860a4ba4d6cd0ee6687e654dc94abc1ce5d029
|
| 3 |
size 347645480
|
runs/Aug16_17-40-26_EMIMDGXA100GPU1/events.out.tfevents.1723844430.EMIMDGXA100GPU1.425328.0
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:fed2110f0669872787ceb0307cb74e5b231e03e4a20d3167d3c4c1a79d11e83d
|
| 3 |
+
size 70390
|