KaraKaraWitch commited on
Commit
2a70f66
1 Parent(s): 568f229
README.md CHANGED
@@ -1,3 +1,73 @@
1
  ---
2
- license: wtfpl
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ license: apache-2.0
3
+ tags:
4
+ - image-classification
5
+ - vision
6
+ - generated_from_trainer
7
+ datasets:
8
+ - imagefolder
9
+ metrics:
10
+ - accuracy
11
+ model-index:
12
+ - name: outputs
13
+ results:
14
+ - task:
15
+ name: Image Classification
16
+ type: image-classification
17
+ dataset:
18
+ name: imagefolder
19
+ type: imagefolder
20
+ config: default
21
+ split: train
22
+ args: default
23
+ metrics:
24
+ - name: Accuracy
25
+ type: accuracy
26
+ value: 0.8571428571428571
27
  ---
28
+
29
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
30
+ should probably proofread and complete it, then remove this comment. -->
31
+
32
+ # Cowboy Hat emoji 🤠 (Western)
33
+
34
+ This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
35
+ It achieves the following results on the evaluation set:
36
+ - Loss: 0.5372
37
+ - Accuracy: 0.8571
38
+
39
+ ## Model description
40
+
41
+ When you want to know if an art is 🤠 or not 🤠.
42
+
43
+ ## Intended uses & limitations
44
+
45
+ filter gelbooru data on 🤠 or not 🤠
46
+
47
+ ## Training and evaluation data
48
+
49
+ Selected 72 images of 🤠 and not 🤠.
50
+
51
+ ## Training procedure
52
+
53
+ ### Training hyperparameters
54
+
55
+ The following hyperparameters were used during training:
56
+ - learning_rate: 5e-05
57
+ - train_batch_size: 8
58
+ - eval_batch_size: 8
59
+ - seed: 42
60
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
+ - lr_scheduler_type: linear
62
+ - num_epochs: 3.0
63
+
64
+ ### Training results
65
+
66
+ Works OK. Needs more finetuning.
67
+
68
+ ### Framework versions
69
+
70
+ - Transformers 4.30.0.dev0
71
+ - Pytorch 1.13.1+cu117
72
+ - Datasets 2.12.0
73
+ - Tokenizers 0.13.3
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_accuracy": 0.8571428571428571,
4
+ "eval_loss": 0.537242591381073,
5
+ "eval_runtime": 1.4402,
6
+ "eval_samples_per_second": 14.582,
7
+ "eval_steps_per_second": 2.083,
8
+ "train_loss": 0.5724380493164063,
9
+ "train_runtime": 25.85,
10
+ "train_samples_per_second": 13.81,
11
+ "train_steps_per_second": 1.741
12
+ }
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/vit-base-patch16-224-in21k",
3
+ "architectures": [
4
+ "ViTForImageClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "encoder_stride": 16,
8
+ "finetuning_task": "image-classification",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.0,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "not_western",
14
+ "1": "western"
15
+ },
16
+ "image_size": 224,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "not_western": "0",
21
+ "western": "1"
22
+ },
23
+ "layer_norm_eps": 1e-12,
24
+ "model_type": "vit",
25
+ "num_attention_heads": 12,
26
+ "num_channels": 3,
27
+ "num_hidden_layers": 12,
28
+ "patch_size": 16,
29
+ "problem_type": "single_label_classification",
30
+ "qkv_bias": true,
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.30.0.dev0"
33
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_accuracy": 0.8571428571428571,
4
+ "eval_loss": 0.537242591381073,
5
+ "eval_runtime": 1.4402,
6
+ "eval_samples_per_second": 14.582,
7
+ "eval_steps_per_second": 2.083
8
+ }
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
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f820f1f2576997b6a31a625789757927367756647cb988e7a143be3eb6411c5f
3
+ size 343268717
train_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "train_loss": 0.5724380493164063,
4
+ "train_runtime": 25.85,
5
+ "train_samples_per_second": 13.81,
6
+ "train_steps_per_second": 1.741
7
+ }
trainer_state.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "global_step": 45,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 3.0,
12
+ "step": 45,
13
+ "total_flos": 2.7664640292409344e+16,
14
+ "train_loss": 0.5724380493164063,
15
+ "train_runtime": 25.85,
16
+ "train_samples_per_second": 13.81,
17
+ "train_steps_per_second": 1.741
18
+ }
19
+ ],
20
+ "max_steps": 45,
21
+ "num_train_epochs": 3,
22
+ "total_flos": 2.7664640292409344e+16,
23
+ "trial_name": null,
24
+ "trial_params": null
25
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17eb5b0411fa90a36e2a5ef3742fb9c9089bfe617f2b308d17876d66bfad9ba6
3
+ size 3899