Commit
•
fe4ab47
1
Parent(s):
5e6c270
End of training
Browse files- README.md +111 -0
- model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,111 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: facebook/deit-tiny-patch16-224
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
datasets:
|
| 7 |
+
- imagefolder
|
| 8 |
+
metrics:
|
| 9 |
+
- accuracy
|
| 10 |
+
model-index:
|
| 11 |
+
- name: hushem_1x_deit_tiny_adamax_lr0001_fold3
|
| 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: test
|
| 21 |
+
args: default
|
| 22 |
+
metrics:
|
| 23 |
+
- name: Accuracy
|
| 24 |
+
type: accuracy
|
| 25 |
+
value: 0.6976744186046512
|
| 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 |
+
# hushem_1x_deit_tiny_adamax_lr0001_fold3
|
| 32 |
+
|
| 33 |
+
This model is a fine-tuned version of [facebook/deit-tiny-patch16-224](https://huggingface.co/facebook/deit-tiny-patch16-224) on the imagefolder dataset.
|
| 34 |
+
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 0.8641
|
| 36 |
+
- Accuracy: 0.6977
|
| 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: 0.0001
|
| 56 |
+
- train_batch_size: 32
|
| 57 |
+
- eval_batch_size: 32
|
| 58 |
+
- seed: 42
|
| 59 |
+
- gradient_accumulation_steps: 4
|
| 60 |
+
- total_train_batch_size: 128
|
| 61 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 62 |
+
- lr_scheduler_type: linear
|
| 63 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 64 |
+
- num_epochs: 50
|
| 65 |
+
|
| 66 |
+
### Training results
|
| 67 |
+
|
| 68 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 69 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 70 |
+
| No log | 0.67 | 1 | 1.6041 | 0.2558 |
|
| 71 |
+
| No log | 2.0 | 3 | 1.2890 | 0.3953 |
|
| 72 |
+
| No log | 2.67 | 4 | 1.2944 | 0.3023 |
|
| 73 |
+
| No log | 4.0 | 6 | 1.2013 | 0.4186 |
|
| 74 |
+
| No log | 4.67 | 7 | 1.1135 | 0.4186 |
|
| 75 |
+
| No log | 6.0 | 9 | 1.0796 | 0.5349 |
|
| 76 |
+
| 1.2559 | 6.67 | 10 | 1.0570 | 0.5581 |
|
| 77 |
+
| 1.2559 | 8.0 | 12 | 1.1038 | 0.4884 |
|
| 78 |
+
| 1.2559 | 8.67 | 13 | 1.0764 | 0.4884 |
|
| 79 |
+
| 1.2559 | 10.0 | 15 | 0.9749 | 0.5349 |
|
| 80 |
+
| 1.2559 | 10.67 | 16 | 0.9354 | 0.5581 |
|
| 81 |
+
| 1.2559 | 12.0 | 18 | 0.9274 | 0.6279 |
|
| 82 |
+
| 1.2559 | 12.67 | 19 | 0.9435 | 0.6512 |
|
| 83 |
+
| 0.4315 | 14.0 | 21 | 0.9225 | 0.6512 |
|
| 84 |
+
| 0.4315 | 14.67 | 22 | 0.9168 | 0.6279 |
|
| 85 |
+
| 0.4315 | 16.0 | 24 | 0.8830 | 0.6279 |
|
| 86 |
+
| 0.4315 | 16.67 | 25 | 0.8956 | 0.6512 |
|
| 87 |
+
| 0.4315 | 18.0 | 27 | 0.9038 | 0.6744 |
|
| 88 |
+
| 0.4315 | 18.67 | 28 | 0.8913 | 0.6744 |
|
| 89 |
+
| 0.058 | 20.0 | 30 | 0.8683 | 0.6512 |
|
| 90 |
+
| 0.058 | 20.67 | 31 | 0.8553 | 0.6744 |
|
| 91 |
+
| 0.058 | 22.0 | 33 | 0.8508 | 0.6977 |
|
| 92 |
+
| 0.058 | 22.67 | 34 | 0.8546 | 0.6977 |
|
| 93 |
+
| 0.058 | 24.0 | 36 | 0.8627 | 0.6977 |
|
| 94 |
+
| 0.058 | 24.67 | 37 | 0.8639 | 0.6977 |
|
| 95 |
+
| 0.058 | 26.0 | 39 | 0.8636 | 0.7209 |
|
| 96 |
+
| 0.0086 | 26.67 | 40 | 0.8627 | 0.7209 |
|
| 97 |
+
| 0.0086 | 28.0 | 42 | 0.8622 | 0.7209 |
|
| 98 |
+
| 0.0086 | 28.67 | 43 | 0.8622 | 0.6977 |
|
| 99 |
+
| 0.0086 | 30.0 | 45 | 0.8629 | 0.6977 |
|
| 100 |
+
| 0.0086 | 30.67 | 46 | 0.8632 | 0.6977 |
|
| 101 |
+
| 0.0086 | 32.0 | 48 | 0.8638 | 0.6977 |
|
| 102 |
+
| 0.0086 | 32.67 | 49 | 0.8640 | 0.6977 |
|
| 103 |
+
| 0.004 | 33.33 | 50 | 0.8641 | 0.6977 |
|
| 104 |
+
|
| 105 |
+
|
| 106 |
+
### Framework versions
|
| 107 |
+
|
| 108 |
+
- Transformers 4.35.0
|
| 109 |
+
- Pytorch 2.1.0+cu118
|
| 110 |
+
- Datasets 2.14.6
|
| 111 |
+
- Tokenizers 0.14.1
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 22123464
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:790b889b2732390701027e66a64cbbc3821106c3fe596352c9f2c1aa151a5d69
|
| 3 |
size 22123464
|