Hugging Face's logo

corranm
/
vit-base-patch16-224-in21k_16batch

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
corranm commited on
Commit
5b5d1db
·
verified ·
1 Parent(s): 1f1899b

End of training

Browse files
Files changed (13) hide show
  1. README.md +112 -0
  2. all_results.json +22 -0
  3. config.json +42 -0
  4. eval_results.json +17 -0
  5. model.safetensors +3 -0
  6. preprocessor_config.json +23 -0
  7. runs/Feb02_22-38-37_modal/events.out.tfevents.1738535918.modal.2.0 +3 -0
  8. runs/Feb02_22-38-37_modal/events.out.tfevents.1738535918.modal.2.1 +3 -0
  9. runs/Feb02_22-38-37_modal/events.out.tfevents.1738537055.modal.2.2 +3 -0
  10. runs/Feb02_22-38-37_modal/events.out.tfevents.1738537055.modal.2.3 +3 -0
  11. train_results.json +8 -0
  12. trainer_state.json +0 -0
  13. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: google/vit-base-patch16-224-in21k
5
+ tags:
6
+ - generated_from_trainer
7
+ metrics:
8
+ - accuracy
9
+ model-index:
10
+ - name: vit-base-patch16-224-in21k_16batch
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # vit-base-patch16-224-in21k_16batch
18
+
19
+ This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 1.2813
22
+ - F1 Macro: 0.4280
23
+ - F1 Micro: 0.5455
24
+ - F1 Weighted: 0.4882
25
+ - Precision Macro: 0.4004
26
+ - Precision Micro: 0.5455
27
+ - Precision Weighted: 0.4529
28
+ - Recall Macro: 0.4762
29
+ - Recall Micro: 0.5455
30
+ - Recall Weighted: 0.5455
31
+ - Accuracy: 0.5455
32
+
33
+ ## Model description
34
+
35
+ More information needed
36
+
37
+ ## Intended uses & limitations
38
+
39
+ More information needed
40
+
41
+ ## Training and evaluation data
42
+
43
+ More information needed
44
+
45
+ ## Training procedure
46
+
47
+ ### Training hyperparameters
48
+
49
+ The following hyperparameters were used during training:
50
+ - learning_rate: 1e-05
51
+ - train_batch_size: 8
52
+ - eval_batch_size: 16
53
+ - seed: 42
54
+ - gradient_accumulation_steps: 2
55
+ - total_train_batch_size: 16
56
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
57
+ - lr_scheduler_type: linear
58
+ - lr_scheduler_warmup_ratio: 0.1
59
+ - num_epochs: 40
60
+
61
+ ### Training results
62
+
63
+ | Training Loss | Epoch | Step | Validation Loss | F1 Macro | F1 Micro | F1 Weighted | Precision Macro | Precision Micro | Precision Weighted | Recall Macro | Recall Micro | Recall Weighted | Accuracy |
64
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:-----------:|:---------------:|:---------------:|:------------------:|:------------:|:------------:|:---------------:|:--------:|
65
+ | 1.9371 | 1.0 | 29 | 1.9372 | 0.0504 | 0.1212 | 0.0604 | 0.0334 | 0.1212 | 0.0403 | 0.1029 | 0.1212 | 0.1212 | 0.1212 |
66
+ | 1.9078 | 2.0 | 58 | 1.9066 | 0.0454 | 0.1818 | 0.0602 | 0.0272 | 0.1818 | 0.0361 | 0.1371 | 0.1818 | 0.1818 | 0.1818 |
67
+ | 1.9276 | 3.0 | 87 | 1.8808 | 0.0696 | 0.1818 | 0.0968 | 0.0492 | 0.1818 | 0.0682 | 0.1295 | 0.1818 | 0.1818 | 0.1818 |
68
+ | 1.8373 | 4.0 | 116 | 1.8696 | 0.0485 | 0.2045 | 0.0695 | 0.0292 | 0.2045 | 0.0418 | 0.1429 | 0.2045 | 0.2045 | 0.2045 |
69
+ | 1.8152 | 5.0 | 145 | 1.8490 | 0.1339 | 0.2576 | 0.1745 | 0.1298 | 0.2576 | 0.1640 | 0.1944 | 0.2576 | 0.2576 | 0.2576 |
70
+ | 1.8488 | 6.0 | 174 | 1.8281 | 0.1379 | 0.2727 | 0.1817 | 0.1512 | 0.2727 | 0.1891 | 0.1997 | 0.2727 | 0.2727 | 0.2727 |
71
+ | 1.7626 | 7.0 | 203 | 1.7917 | 0.2271 | 0.3333 | 0.2718 | 0.1922 | 0.3333 | 0.2298 | 0.2783 | 0.3333 | 0.3333 | 0.3333 |
72
+ | 1.7169 | 8.0 | 232 | 1.7478 | 0.2887 | 0.4242 | 0.3465 | 0.2706 | 0.4242 | 0.3154 | 0.3426 | 0.4242 | 0.4242 | 0.4242 |
73
+ | 1.5364 | 9.0 | 261 | 1.7098 | 0.2835 | 0.4091 | 0.3409 | 0.2720 | 0.4091 | 0.3245 | 0.3324 | 0.4091 | 0.4091 | 0.4091 |
74
+ | 1.7373 | 10.0 | 290 | 1.6765 | 0.2906 | 0.4167 | 0.3463 | 0.2726 | 0.4167 | 0.3157 | 0.3386 | 0.4167 | 0.4167 | 0.4167 |
75
+ | 1.5345 | 11.0 | 319 | 1.6423 | 0.2805 | 0.3939 | 0.3342 | 0.3728 | 0.3939 | 0.4258 | 0.3275 | 0.3939 | 0.3939 | 0.3939 |
76
+ | 1.6421 | 12.0 | 348 | 1.6103 | 0.3324 | 0.4697 | 0.3978 | 0.4583 | 0.4697 | 0.5178 | 0.3760 | 0.4697 | 0.4697 | 0.4697 |
77
+ | 1.5266 | 13.0 | 377 | 1.5835 | 0.3171 | 0.4621 | 0.3822 | 0.2917 | 0.4621 | 0.3483 | 0.3748 | 0.4621 | 0.4621 | 0.4621 |
78
+ | 1.5182 | 14.0 | 406 | 1.5633 | 0.3133 | 0.4242 | 0.3680 | 0.3634 | 0.4242 | 0.4009 | 0.3568 | 0.4242 | 0.4242 | 0.4242 |
79
+ | 1.5341 | 15.0 | 435 | 1.5528 | 0.3015 | 0.4167 | 0.3585 | 0.3109 | 0.4167 | 0.3638 | 0.3499 | 0.4167 | 0.4167 | 0.4167 |
80
+ | 1.3961 | 16.0 | 464 | 1.5273 | 0.3449 | 0.4545 | 0.3991 | 0.4329 | 0.4545 | 0.4704 | 0.3839 | 0.4545 | 0.4545 | 0.4545 |
81
+ | 1.3601 | 17.0 | 493 | 1.4971 | 0.3670 | 0.5 | 0.4357 | 0.5047 | 0.5 | 0.5382 | 0.4078 | 0.5 | 0.5 | 0.5 |
82
+ | 1.2535 | 18.0 | 522 | 1.5006 | 0.3511 | 0.4621 | 0.4138 | 0.4778 | 0.4621 | 0.5101 | 0.3872 | 0.4621 | 0.4621 | 0.4621 |
83
+ | 1.2375 | 19.0 | 551 | 1.4659 | 0.3655 | 0.4924 | 0.4345 | 0.4298 | 0.4924 | 0.4797 | 0.4020 | 0.4924 | 0.4924 | 0.4924 |
84
+ | 1.2141 | 20.0 | 580 | 1.4407 | 0.3914 | 0.5076 | 0.4565 | 0.4650 | 0.5076 | 0.5087 | 0.4217 | 0.5076 | 0.5076 | 0.5076 |
85
+ | 1.2831 | 21.0 | 609 | 1.4454 | 0.3965 | 0.5152 | 0.4645 | 0.4801 | 0.5152 | 0.5265 | 0.4214 | 0.5152 | 0.5152 | 0.5152 |
86
+ | 1.1543 | 22.0 | 638 | 1.4167 | 0.4285 | 0.5455 | 0.4997 | 0.4781 | 0.5455 | 0.5309 | 0.4521 | 0.5455 | 0.5455 | 0.5455 |
87
+ | 1.4079 | 23.0 | 667 | 1.4465 | 0.3675 | 0.4621 | 0.4269 | 0.4187 | 0.4621 | 0.4676 | 0.3929 | 0.4621 | 0.4621 | 0.4621 |
88
+ | 1.0619 | 24.0 | 696 | 1.4249 | 0.4092 | 0.5076 | 0.4724 | 0.4659 | 0.5076 | 0.5180 | 0.4336 | 0.5076 | 0.5076 | 0.5076 |
89
+ | 1.1059 | 25.0 | 725 | 1.3834 | 0.4356 | 0.5530 | 0.5061 | 0.5025 | 0.5530 | 0.5491 | 0.4594 | 0.5530 | 0.5530 | 0.5530 |
90
+ | 1.192 | 26.0 | 754 | 1.3784 | 0.4286 | 0.5379 | 0.4893 | 0.4566 | 0.5379 | 0.4969 | 0.4544 | 0.5379 | 0.5379 | 0.5379 |
91
+ | 1.21 | 27.0 | 783 | 1.3874 | 0.4409 | 0.5379 | 0.5060 | 0.4709 | 0.5379 | 0.5258 | 0.4616 | 0.5379 | 0.5379 | 0.5379 |
92
+ | 1.0901 | 28.0 | 812 | 1.3621 | 0.4402 | 0.5379 | 0.5074 | 0.4635 | 0.5379 | 0.5204 | 0.4557 | 0.5379 | 0.5379 | 0.5379 |
93
+ | 1.1254 | 29.0 | 841 | 1.3714 | 0.4265 | 0.5227 | 0.4873 | 0.4492 | 0.5227 | 0.4984 | 0.4449 | 0.5227 | 0.5227 | 0.5227 |
94
+ | 0.9345 | 30.0 | 870 | 1.3525 | 0.4425 | 0.5379 | 0.5074 | 0.4736 | 0.5379 | 0.5264 | 0.4557 | 0.5379 | 0.5379 | 0.5379 |
95
+ | 1.2036 | 31.0 | 899 | 1.3592 | 0.4363 | 0.5379 | 0.5020 | 0.4869 | 0.5379 | 0.5368 | 0.4533 | 0.5379 | 0.5379 | 0.5379 |
96
+ | 1.036 | 32.0 | 928 | 1.3362 | 0.4451 | 0.5455 | 0.5109 | 0.4673 | 0.5455 | 0.5226 | 0.4637 | 0.5455 | 0.5455 | 0.5455 |
97
+ | 0.9979 | 33.0 | 957 | 1.3492 | 0.4454 | 0.5455 | 0.5134 | 0.4808 | 0.5455 | 0.5358 | 0.4620 | 0.5455 | 0.5455 | 0.5455 |
98
+ | 0.8353 | 34.0 | 986 | 1.3402 | 0.4635 | 0.5606 | 0.5301 | 0.4659 | 0.5606 | 0.5268 | 0.4854 | 0.5606 | 0.5606 | 0.5606 |
99
+ | 0.9384 | 35.0 | 1015 | 1.3414 | 0.4408 | 0.5455 | 0.5088 | 0.4664 | 0.5455 | 0.5237 | 0.4602 | 0.5455 | 0.5455 | 0.5455 |
100
+ | 0.996 | 36.0 | 1044 | 1.3405 | 0.4559 | 0.5530 | 0.5235 | 0.4795 | 0.5530 | 0.5377 | 0.4715 | 0.5530 | 0.5530 | 0.5530 |
101
+ | 0.9613 | 37.0 | 1073 | 1.3357 | 0.4847 | 0.5833 | 0.5535 | 0.5011 | 0.5833 | 0.5612 | 0.5020 | 0.5833 | 0.5833 | 0.5833 |
102
+ | 0.8507 | 38.0 | 1102 | 1.3347 | 0.4760 | 0.5758 | 0.5454 | 0.4897 | 0.5758 | 0.5510 | 0.4940 | 0.5758 | 0.5758 | 0.5758 |
103
+ | 1.1563 | 39.0 | 1131 | 1.3396 | 0.4553 | 0.5530 | 0.5250 | 0.4608 | 0.5530 | 0.5234 | 0.4735 | 0.5530 | 0.5530 | 0.5530 |
104
+ | 0.9681 | 40.0 | 1160 | 1.3371 | 0.4703 | 0.5682 | 0.5396 | 0.4816 | 0.5682 | 0.5445 | 0.4887 | 0.5682 | 0.5682 | 0.5682 |
105
+
106
+
107
+ ### Framework versions
108
+
109
+ - Transformers 4.48.2
110
+ - Pytorch 2.6.0+cu124
111
+ - Datasets 3.2.0
112
+ - Tokenizers 0.21.0
all_results.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 40.0,
3
+ "eval_accuracy": 0.5454545454545454,
4
+ "eval_f1_macro": 0.42801448064605957,
5
+ "eval_f1_micro": 0.5454545454545454,
6
+ "eval_f1_weighted": 0.4881648565859092,
7
+ "eval_loss": 1.2812808752059937,
8
+ "eval_precision_macro": 0.4003968253968254,
9
+ "eval_precision_micro": 0.5454545454545454,
10
+ "eval_precision_weighted": 0.452946127946128,
11
+ "eval_recall_macro": 0.4762471655328798,
12
+ "eval_recall_micro": 0.5454545454545454,
13
+ "eval_recall_weighted": 0.5454545454545454,
14
+ "eval_runtime": 1.0813,
15
+ "eval_samples_per_second": 61.04,
16
+ "eval_steps_per_second": 4.624,
17
+ "total_flos": 1.432116143221801e+18,
18
+ "train_loss": 1.348873134933669,
19
+ "train_runtime": 1135.3077,
20
+ "train_samples_per_second": 16.278,
21
+ "train_steps_per_second": 1.022
22
+ }
config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.0,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "-",
13
+ "1": "0",
14
+ "2": "1",
15
+ "3": "2",
16
+ "4": "3",
17
+ "5": "4",
18
+ "6": "5"
19
+ },
20
+ "image_size": 224,
21
+ "initializer_range": 0.02,
22
+ "intermediate_size": 3072,
23
+ "label2id": {
24
+ "-": "0",
25
+ "0": "1",
26
+ "1": "2",
27
+ "2": "3",
28
+ "3": "4",
29
+ "4": "5",
30
+ "5": "6"
31
+ },
32
+ "layer_norm_eps": 1e-12,
33
+ "model_type": "vit",
34
+ "num_attention_heads": 12,
35
+ "num_channels": 3,
36
+ "num_hidden_layers": 12,
37
+ "patch_size": 16,
38
+ "problem_type": "single_label_classification",
39
+ "qkv_bias": true,
40
+ "torch_dtype": "float32",
41
+ "transformers_version": "4.48.2"
42
+ }
eval_results.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 40.0,
3
+ "eval_accuracy": 0.5454545454545454,
4
+ "eval_f1_macro": 0.42801448064605957,
5
+ "eval_f1_micro": 0.5454545454545454,
6
+ "eval_f1_weighted": 0.4881648565859092,
7
+ "eval_loss": 1.2812808752059937,
8
+ "eval_precision_macro": 0.4003968253968254,
9
+ "eval_precision_micro": 0.5454545454545454,
10
+ "eval_precision_weighted": 0.452946127946128,
11
+ "eval_recall_macro": 0.4762471655328798,
12
+ "eval_recall_micro": 0.5454545454545454,
13
+ "eval_recall_weighted": 0.5454545454545454,
14
+ "eval_runtime": 1.0813,
15
+ "eval_samples_per_second": 61.04,
16
+ "eval_steps_per_second": 4.624
17
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:437f5124d359048106bd9c5c0797562471700a2d670508b25062e4d8ff3877d6
3
+ size 343239356
preprocessor_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": null,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.5,
8
+ 0.5,
9
+ 0.5
10
+ ],
11
+ "image_processor_type": "ViTImageProcessorFast",
12
+ "image_std": [
13
+ 0.5,
14
+ 0.5,
15
+ 0.5
16
+ ],
17
+ "resample": 2,
18
+ "rescale_factor": 0.00392156862745098,
19
+ "size": {
20
+ "height": 224,
21
+ "width": 224
22
+ }
23
+ }
runs/Feb02_22-38-37_modal/events.out.tfevents.1738535918.modal.2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3dc48fe469c01d6a1bf3b1db6c53d36748215e631631097a9c9f93b22ba609de
3
+ size 160959
runs/Feb02_22-38-37_modal/events.out.tfevents.1738535918.modal.2.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97696eb02ff8f964db6d4c99417ac9ab2e46e8ab558a4ef24822073ca753ff38
3
+ size 160959
runs/Feb02_22-38-37_modal/events.out.tfevents.1738537055.modal.2.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:031fb2bac852cdb195e7d6ea7fd37b475c9be27247dd77d14f1ee213ef693883
3
+ size 921
runs/Feb02_22-38-37_modal/events.out.tfevents.1738537055.modal.2.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bed70d579908521c31616c1e0e6a75ad853e2b24da488b09ffa26150db917af3
3
+ size 921
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 40.0,
3
+ "total_flos": 1.432116143221801e+18,
4
+ "train_loss": 1.348873134933669,
5
+ "train_runtime": 1135.3077,
6
+ "train_samples_per_second": 16.278,
7
+ "train_steps_per_second": 1.022
8
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53d7e08099d6841f25b26efa158169c7abecfb8168d96eeb1c2981741f338975
3
+ size 5432