End of training
Browse files- README.md +47 -0
- config.json +27 -0
- model.safetensors +3 -0
- preprocessor_config.json +22 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- masked-auto-encoding
|
4 |
+
- generated_from_trainer
|
5 |
+
model-index:
|
6 |
+
- name: pretrainingmedd
|
7 |
+
results: []
|
8 |
+
---
|
9 |
+
|
10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
11 |
+
should probably proofread and complete it, then remove this comment. -->
|
12 |
+
|
13 |
+
# pretrainingmedd
|
14 |
+
|
15 |
+
This model is a fine-tuned version of [](https://huggingface.co/) on the cifar10 dataset.
|
16 |
+
|
17 |
+
## Model description
|
18 |
+
|
19 |
+
More information needed
|
20 |
+
|
21 |
+
## Intended uses & limitations
|
22 |
+
|
23 |
+
More information needed
|
24 |
+
|
25 |
+
## Training and evaluation data
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Training procedure
|
30 |
+
|
31 |
+
### Training hyperparameters
|
32 |
+
|
33 |
+
The following hyperparameters were used during training:
|
34 |
+
- learning_rate: 3.125e-05
|
35 |
+
- train_batch_size: 8
|
36 |
+
- eval_batch_size: 8
|
37 |
+
- seed: 42
|
38 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
39 |
+
- lr_scheduler_type: linear
|
40 |
+
- num_epochs: 3.0
|
41 |
+
|
42 |
+
### Framework versions
|
43 |
+
|
44 |
+
- Transformers 4.38.0.dev0
|
45 |
+
- Pytorch 2.1.0+cu121
|
46 |
+
- Datasets 2.17.0
|
47 |
+
- Tokenizers 0.15.2
|
config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"ViTMAEForPreTraining"
|
4 |
+
],
|
5 |
+
"attention_probs_dropout_prob": 0.0,
|
6 |
+
"decoder_hidden_size": 512,
|
7 |
+
"decoder_intermediate_size": 2048,
|
8 |
+
"decoder_num_attention_heads": 16,
|
9 |
+
"decoder_num_hidden_layers": 8,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.0,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"image_size": 224,
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"intermediate_size": 3072,
|
16 |
+
"layer_norm_eps": 1e-12,
|
17 |
+
"mask_ratio": 0.75,
|
18 |
+
"model_type": "vit_mae",
|
19 |
+
"norm_pix_loss": true,
|
20 |
+
"num_attention_heads": 12,
|
21 |
+
"num_channels": 3,
|
22 |
+
"num_hidden_layers": 12,
|
23 |
+
"patch_size": 16,
|
24 |
+
"qkv_bias": true,
|
25 |
+
"torch_dtype": "float32",
|
26 |
+
"transformers_version": "4.38.0.dev0"
|
27 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4f6be0ccffa7c2092464cbf059636ef105c6dcba914d06f60cddf7ea76711653
|
3 |
+
size 447670680
|
preprocessor_config.json
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_normalize": true,
|
3 |
+
"do_rescale": true,
|
4 |
+
"do_resize": true,
|
5 |
+
"image_mean": [
|
6 |
+
0.5,
|
7 |
+
0.5,
|
8 |
+
0.5
|
9 |
+
],
|
10 |
+
"image_processor_type": "ViTImageProcessor",
|
11 |
+
"image_std": [
|
12 |
+
0.5,
|
13 |
+
0.5,
|
14 |
+
0.5
|
15 |
+
],
|
16 |
+
"resample": 2,
|
17 |
+
"rescale_factor": 0.00392156862745098,
|
18 |
+
"size": {
|
19 |
+
"height": 224,
|
20 |
+
"width": 224
|
21 |
+
}
|
22 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d607404501f0d010366a346b5289157009e5868c5a6c94264edbfb8d8c134004
|
3 |
+
size 4920
|