Model save
Browse files- README.md +116 -0
- model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,116 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
base_model: MBZUAI/swiftformer-xs
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
datasets:
|
| 7 |
+
- imagefolder
|
| 8 |
+
metrics:
|
| 9 |
+
- accuracy
|
| 10 |
+
model-index:
|
| 11 |
+
- name: swiftformer-xs-RD-da-colab
|
| 12 |
+
results:
|
| 13 |
+
- task:
|
| 14 |
+
name: Image Classification
|
| 15 |
+
type: image-classification
|
| 16 |
+
dataset:
|
| 17 |
+
name: imagefolder
|
| 18 |
+
type: imagefolder
|
| 19 |
+
config: default
|
| 20 |
+
split: validation
|
| 21 |
+
args: default
|
| 22 |
+
metrics:
|
| 23 |
+
- name: Accuracy
|
| 24 |
+
type: accuracy
|
| 25 |
+
value: 0.5018181818181818
|
| 26 |
+
---
|
| 27 |
+
|
| 28 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 29 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 30 |
+
|
| 31 |
+
# swiftformer-xs-RD-da-colab
|
| 32 |
+
|
| 33 |
+
This model is a fine-tuned version of [MBZUAI/swiftformer-xs](https://huggingface.co/MBZUAI/swiftformer-xs) on the imagefolder dataset.
|
| 34 |
+
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 5.5780
|
| 36 |
+
- Accuracy: 0.5018
|
| 37 |
+
|
| 38 |
+
## Model description
|
| 39 |
+
|
| 40 |
+
More information needed
|
| 41 |
+
|
| 42 |
+
## Intended uses & limitations
|
| 43 |
+
|
| 44 |
+
More information needed
|
| 45 |
+
|
| 46 |
+
## Training and evaluation data
|
| 47 |
+
|
| 48 |
+
More information needed
|
| 49 |
+
|
| 50 |
+
## Training procedure
|
| 51 |
+
|
| 52 |
+
### Training hyperparameters
|
| 53 |
+
|
| 54 |
+
The following hyperparameters were used during training:
|
| 55 |
+
- learning_rate: 0.0003
|
| 56 |
+
- train_batch_size: 16
|
| 57 |
+
- eval_batch_size: 16
|
| 58 |
+
- seed: 42
|
| 59 |
+
- gradient_accumulation_steps: 4
|
| 60 |
+
- total_train_batch_size: 64
|
| 61 |
+
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 62 |
+
- lr_scheduler_type: linear
|
| 63 |
+
- num_epochs: 40
|
| 64 |
+
|
| 65 |
+
### Training results
|
| 66 |
+
|
| 67 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 68 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 69 |
+
| 0.5414 | 1.0 | 96 | 9.3183 | 0.4945 |
|
| 70 |
+
| 0.533 | 2.0 | 192 | 7.8263 | 0.5 |
|
| 71 |
+
| 0.3449 | 3.0 | 288 | 8.6048 | 0.4945 |
|
| 72 |
+
| 0.3157 | 4.0 | 384 | 8.4227 | 0.4945 |
|
| 73 |
+
| 0.2686 | 5.0 | 480 | 4.3190 | 0.5473 |
|
| 74 |
+
| 0.2987 | 6.0 | 576 | 5.0817 | 0.5164 |
|
| 75 |
+
| 0.3415 | 7.0 | 672 | 5.2399 | 0.5127 |
|
| 76 |
+
| 0.2396 | 8.0 | 768 | 6.7857 | 0.5018 |
|
| 77 |
+
| 0.2618 | 9.0 | 864 | 6.5777 | 0.5055 |
|
| 78 |
+
| 0.297 | 10.0 | 960 | 6.6086 | 0.5036 |
|
| 79 |
+
| 0.2413 | 11.0 | 1056 | 3.6891 | 0.5236 |
|
| 80 |
+
| 0.2074 | 12.0 | 1152 | 6.8991 | 0.5 |
|
| 81 |
+
| 0.2029 | 13.0 | 1248 | 5.8597 | 0.5018 |
|
| 82 |
+
| 0.2353 | 14.0 | 1344 | 7.3848 | 0.5036 |
|
| 83 |
+
| 0.1748 | 15.0 | 1440 | 4.9503 | 0.5109 |
|
| 84 |
+
| 0.1885 | 16.0 | 1536 | 7.2151 | 0.4982 |
|
| 85 |
+
| 0.1967 | 17.0 | 1632 | 7.9847 | 0.4982 |
|
| 86 |
+
| 0.1881 | 18.0 | 1728 | 4.5008 | 0.5109 |
|
| 87 |
+
| 0.172 | 19.0 | 1824 | 4.7565 | 0.5273 |
|
| 88 |
+
| 0.2222 | 20.0 | 1920 | 6.2814 | 0.4964 |
|
| 89 |
+
| 0.1673 | 21.0 | 2016 | 8.1814 | 0.4964 |
|
| 90 |
+
| 0.1831 | 22.0 | 2112 | 4.4184 | 0.5164 |
|
| 91 |
+
| 0.1121 | 23.0 | 2208 | 6.0737 | 0.4982 |
|
| 92 |
+
| 0.1464 | 24.0 | 2304 | 5.3006 | 0.5018 |
|
| 93 |
+
| 0.1343 | 25.0 | 2400 | 5.6166 | 0.5036 |
|
| 94 |
+
| 0.1385 | 26.0 | 2496 | 6.1437 | 0.5018 |
|
| 95 |
+
| 0.1153 | 27.0 | 2592 | 6.3232 | 0.5018 |
|
| 96 |
+
| 0.1175 | 28.0 | 2688 | 6.2047 | 0.5036 |
|
| 97 |
+
| 0.1107 | 29.0 | 2784 | 7.5461 | 0.4982 |
|
| 98 |
+
| 0.0914 | 30.0 | 2880 | 7.4573 | 0.4982 |
|
| 99 |
+
| 0.1123 | 31.0 | 2976 | 6.2770 | 0.4982 |
|
| 100 |
+
| 0.1268 | 32.0 | 3072 | 5.1979 | 0.5073 |
|
| 101 |
+
| 0.1074 | 33.0 | 3168 | 4.9253 | 0.5036 |
|
| 102 |
+
| 0.0712 | 34.0 | 3264 | 5.0555 | 0.5018 |
|
| 103 |
+
| 0.0792 | 35.0 | 3360 | 6.1480 | 0.4982 |
|
| 104 |
+
| 0.1097 | 36.0 | 3456 | 6.5916 | 0.4982 |
|
| 105 |
+
| 0.1035 | 37.0 | 3552 | 7.4887 | 0.4982 |
|
| 106 |
+
| 0.1066 | 38.0 | 3648 | 6.1041 | 0.5 |
|
| 107 |
+
| 0.0887 | 39.0 | 3744 | 6.7739 | 0.4982 |
|
| 108 |
+
| 0.0889 | 40.0 | 3840 | 5.5780 | 0.5018 |
|
| 109 |
+
|
| 110 |
+
|
| 111 |
+
### Framework versions
|
| 112 |
+
|
| 113 |
+
- Transformers 4.46.3
|
| 114 |
+
- Pytorch 2.5.1+cu121
|
| 115 |
+
- Datasets 3.1.0
|
| 116 |
+
- Tokenizers 0.20.3
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 12205416
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e551c45c65d03cf55678f466f754399e913fa904cf5dfecabdb4d4c02a31a2b
|
| 3 |
size 12205416
|