Hugging Face's logo

corranm
/
square_run_with_16_batch_size

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Model card Files
xet
Metrics Community
corranm commited on
Commit
cb29e1f
·
verified ·
1 Parent(s): 328c2b8

End of training

Browse files
Files changed (13) hide show
  1. README.md +107 -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/Feb03_14-03-00_modal/events.out.tfevents.1738591380.modal.2.0 +3 -0
  8. runs/Feb03_14-03-00_modal/events.out.tfevents.1738591380.modal.2.1 +3 -0
  9. runs/Feb03_14-03-00_modal/events.out.tfevents.1738592374.modal.2.2 +3 -0
  10. runs/Feb03_14-03-00_modal/events.out.tfevents.1738592374.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 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: google/vit-base-patch16-224
5
+ tags:
6
+ - generated_from_trainer
7
+ metrics:
8
+ - accuracy
9
+ model-index:
10
+ - name: square_run_with_16_batch_size
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
+ # square_run_with_16_batch_size
18
+
19
+ This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on an unknown dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 1.4457
22
+ - F1 Macro: 0.4685
23
+ - F1 Micro: 0.5455
24
+ - F1 Weighted: 0.5242
25
+ - Precision Macro: 0.5341
26
+ - Precision Micro: 0.5455
27
+ - Precision Weighted: 0.5870
28
+ - Recall Macro: 0.4829
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: 0.0001
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: 35
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
+ | 1.9976 | 1.0 | 29 | 1.9107 | 0.0915 | 0.2045 | 0.1209 | 0.0793 | 0.2045 | 0.1019 | 0.1535 | 0.2045 | 0.2045 | 0.2045 |
66
+ | 1.7575 | 2.0 | 58 | 1.8877 | 0.1474 | 0.2348 | 0.1805 | 0.1704 | 0.2348 | 0.2163 | 0.1989 | 0.2348 | 0.2348 | 0.2348 |
67
+ | 1.8336 | 3.0 | 87 | 1.7319 | 0.1659 | 0.3182 | 0.2117 | 0.1611 | 0.3182 | 0.2133 | 0.2586 | 0.3182 | 0.3182 | 0.3182 |
68
+ | 1.452 | 4.0 | 116 | 1.5316 | 0.3336 | 0.4167 | 0.3752 | 0.3518 | 0.4167 | 0.3903 | 0.3682 | 0.4167 | 0.4167 | 0.4167 |
69
+ | 1.2545 | 5.0 | 145 | 1.4192 | 0.3999 | 0.4848 | 0.4447 | 0.4601 | 0.4848 | 0.5021 | 0.4318 | 0.4848 | 0.4848 | 0.4848 |
70
+ | 1.6479 | 6.0 | 174 | 1.3642 | 0.4649 | 0.5455 | 0.5265 | 0.5072 | 0.5455 | 0.5559 | 0.4750 | 0.5455 | 0.5455 | 0.5455 |
71
+ | 1.301 | 7.0 | 203 | 1.3015 | 0.4178 | 0.5303 | 0.4735 | 0.4090 | 0.5303 | 0.4503 | 0.4535 | 0.5303 | 0.5303 | 0.5303 |
72
+ | 0.9006 | 8.0 | 232 | 1.4861 | 0.4234 | 0.4924 | 0.4699 | 0.4586 | 0.4924 | 0.5286 | 0.4621 | 0.4924 | 0.4924 | 0.4924 |
73
+ | 0.4134 | 9.0 | 261 | 1.2101 | 0.4852 | 0.5833 | 0.5545 | 0.5427 | 0.5833 | 0.5894 | 0.5010 | 0.5833 | 0.5833 | 0.5833 |
74
+ | 0.9532 | 10.0 | 290 | 1.3783 | 0.4577 | 0.5682 | 0.5204 | 0.4557 | 0.5682 | 0.5160 | 0.4972 | 0.5682 | 0.5682 | 0.5682 |
75
+ | 0.4521 | 11.0 | 319 | 1.3602 | 0.5266 | 0.6136 | 0.5923 | 0.5296 | 0.6136 | 0.5907 | 0.5403 | 0.6136 | 0.6136 | 0.6136 |
76
+ | 0.633 | 12.0 | 348 | 1.4293 | 0.5032 | 0.5833 | 0.5727 | 0.4969 | 0.5833 | 0.5674 | 0.5140 | 0.5833 | 0.5833 | 0.5833 |
77
+ | 0.4268 | 13.0 | 377 | 1.4388 | 0.5031 | 0.5833 | 0.5676 | 0.5543 | 0.5833 | 0.6189 | 0.5124 | 0.5833 | 0.5833 | 0.5833 |
78
+ | 0.2857 | 14.0 | 406 | 1.6012 | 0.5071 | 0.5833 | 0.5676 | 0.5209 | 0.5833 | 0.5879 | 0.5211 | 0.5833 | 0.5833 | 0.5833 |
79
+ | 0.2606 | 15.0 | 435 | 1.5817 | 0.5579 | 0.6136 | 0.6109 | 0.5657 | 0.6136 | 0.6178 | 0.5590 | 0.6136 | 0.6136 | 0.6136 |
80
+ | 0.2028 | 16.0 | 464 | 1.8048 | 0.4526 | 0.5227 | 0.5112 | 0.4703 | 0.5227 | 0.5378 | 0.4668 | 0.5227 | 0.5227 | 0.5227 |
81
+ | 0.3251 | 17.0 | 493 | 1.6340 | 0.4942 | 0.5833 | 0.5625 | 0.5049 | 0.5833 | 0.5631 | 0.5031 | 0.5833 | 0.5833 | 0.5833 |
82
+ | 0.0369 | 18.0 | 522 | 1.5847 | 0.5860 | 0.6439 | 0.6349 | 0.6267 | 0.6439 | 0.6476 | 0.5824 | 0.6439 | 0.6439 | 0.6439 |
83
+ | 0.1133 | 19.0 | 551 | 1.5825 | 0.5457 | 0.6288 | 0.6157 | 0.5377 | 0.6288 | 0.6111 | 0.5615 | 0.6288 | 0.6288 | 0.6288 |
84
+ | 0.0457 | 20.0 | 580 | 1.7253 | 0.5258 | 0.6136 | 0.5938 | 0.5229 | 0.6136 | 0.5854 | 0.5391 | 0.6136 | 0.6136 | 0.6136 |
85
+ | 0.1109 | 21.0 | 609 | 1.7898 | 0.5708 | 0.6212 | 0.6154 | 0.6150 | 0.6212 | 0.6283 | 0.5613 | 0.6212 | 0.6212 | 0.6212 |
86
+ | 0.046 | 22.0 | 638 | 1.7368 | 0.5656 | 0.6136 | 0.6029 | 0.6021 | 0.6136 | 0.6103 | 0.5615 | 0.6136 | 0.6136 | 0.6136 |
87
+ | 0.0553 | 23.0 | 667 | 2.2478 | 0.4822 | 0.5682 | 0.5430 | 0.4851 | 0.5682 | 0.5380 | 0.4975 | 0.5682 | 0.5682 | 0.5682 |
88
+ | 0.0047 | 24.0 | 696 | 2.1705 | 0.5133 | 0.5909 | 0.5750 | 0.5158 | 0.5909 | 0.5716 | 0.5220 | 0.5909 | 0.5909 | 0.5909 |
89
+ | 0.0104 | 25.0 | 725 | 2.2669 | 0.4950 | 0.5833 | 0.5622 | 0.5035 | 0.5833 | 0.5609 | 0.5038 | 0.5833 | 0.5833 | 0.5833 |
90
+ | 0.0287 | 26.0 | 754 | 2.0390 | 0.5267 | 0.6061 | 0.5935 | 0.5265 | 0.6061 | 0.5898 | 0.5346 | 0.6061 | 0.6061 | 0.6061 |
91
+ | 0.0212 | 27.0 | 783 | 2.1345 | 0.5344 | 0.6136 | 0.6005 | 0.5308 | 0.6136 | 0.5946 | 0.5449 | 0.6136 | 0.6136 | 0.6136 |
92
+ | 0.0221 | 28.0 | 812 | 2.1555 | 0.5607 | 0.6136 | 0.6035 | 0.5953 | 0.6136 | 0.6107 | 0.5583 | 0.6136 | 0.6136 | 0.6136 |
93
+ | 0.001 | 29.0 | 841 | 2.1102 | 0.5833 | 0.6364 | 0.6289 | 0.6172 | 0.6364 | 0.6353 | 0.5789 | 0.6364 | 0.6364 | 0.6364 |
94
+ | 0.0045 | 30.0 | 870 | 2.0669 | 0.5862 | 0.6364 | 0.6290 | 0.6164 | 0.6364 | 0.6326 | 0.5831 | 0.6364 | 0.6364 | 0.6364 |
95
+ | 0.0021 | 31.0 | 899 | 2.1442 | 0.5833 | 0.6364 | 0.6282 | 0.6165 | 0.6364 | 0.6330 | 0.5789 | 0.6364 | 0.6364 | 0.6364 |
96
+ | 0.0014 | 32.0 | 928 | 2.1435 | 0.5616 | 0.6136 | 0.6049 | 0.5957 | 0.6136 | 0.6099 | 0.5569 | 0.6136 | 0.6136 | 0.6136 |
97
+ | 0.0016 | 33.0 | 957 | 2.1279 | 0.5621 | 0.6136 | 0.6047 | 0.5966 | 0.6136 | 0.6093 | 0.5569 | 0.6136 | 0.6136 | 0.6136 |
98
+ | 0.0008 | 34.0 | 986 | 2.1310 | 0.5691 | 0.6212 | 0.6127 | 0.6030 | 0.6212 | 0.6170 | 0.5641 | 0.6212 | 0.6212 | 0.6212 |
99
+ | 0.0006 | 35.0 | 1015 | 2.1338 | 0.5690 | 0.6212 | 0.6130 | 0.6026 | 0.6212 | 0.6176 | 0.5641 | 0.6212 | 0.6212 | 0.6212 |
100
+
101
+
102
+ ### Framework versions
103
+
104
+ - Transformers 4.48.2
105
+ - Pytorch 2.6.0+cu124
106
+ - Datasets 3.2.0
107
+ - Tokenizers 0.21.0
all_results.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 35.0,
3
+ "eval_accuracy": 0.5454545454545454,
4
+ "eval_f1_macro": 0.4685356936296786,
5
+ "eval_f1_micro": 0.5454545454545454,
6
+ "eval_f1_weighted": 0.5242137248716197,
7
+ "eval_loss": 1.4457396268844604,
8
+ "eval_precision_macro": 0.5341269841269841,
9
+ "eval_precision_micro": 0.5454545454545454,
10
+ "eval_precision_weighted": 0.587037037037037,
11
+ "eval_recall_macro": 0.48293650793650794,
12
+ "eval_recall_micro": 0.5454545454545454,
13
+ "eval_recall_weighted": 0.5454545454545454,
14
+ "eval_runtime": 1.1758,
15
+ "eval_samples_per_second": 56.132,
16
+ "eval_steps_per_second": 4.252,
17
+ "total_flos": 1.2531016253190758e+18,
18
+ "train_loss": 0.4932562636703556,
19
+ "train_runtime": 992.6691,
20
+ "train_samples_per_second": 16.289,
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",
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": 35.0,
3
+ "eval_accuracy": 0.5454545454545454,
4
+ "eval_f1_macro": 0.4685356936296786,
5
+ "eval_f1_micro": 0.5454545454545454,
6
+ "eval_f1_weighted": 0.5242137248716197,
7
+ "eval_loss": 1.4457396268844604,
8
+ "eval_precision_macro": 0.5341269841269841,
9
+ "eval_precision_micro": 0.5454545454545454,
10
+ "eval_precision_weighted": 0.587037037037037,
11
+ "eval_recall_macro": 0.48293650793650794,
12
+ "eval_recall_micro": 0.5454545454545454,
13
+ "eval_recall_weighted": 0.5454545454545454,
14
+ "eval_runtime": 1.1758,
15
+ "eval_samples_per_second": 56.132,
16
+ "eval_steps_per_second": 4.252
17
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3d1c9505767f5135e4e023488e310dfe44e0e3b5d5042d867b12f6bbc4d26b5
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/Feb03_14-03-00_modal/events.out.tfevents.1738591380.modal.2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:627ee756ab0f12f8cb7eb79835bc287f1502646783ed1fe8b3aa2cc0caf8efe1
3
+ size 141367
runs/Feb03_14-03-00_modal/events.out.tfevents.1738591380.modal.2.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e9a50c887ebf1a30657d0304e51d49d81229784b476afc461e4401c154ddf8c
3
+ size 141367
runs/Feb03_14-03-00_modal/events.out.tfevents.1738592374.modal.2.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1429499802ff9a70c13c172481aad21ce5083b29b5d7c2f9f0679602f93f699
3
+ size 921
runs/Feb03_14-03-00_modal/events.out.tfevents.1738592374.modal.2.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ad2906e699e2fe82955e3e88b911113a51d0355c95c4be0d9562533580e8209
3
+ size 921
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 35.0,
3
+ "total_flos": 1.2531016253190758e+18,
4
+ "train_loss": 0.4932562636703556,
5
+ "train_runtime": 992.6691,
6
+ "train_samples_per_second": 16.289,
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 sha256:086dbc48340ba4023d99ab3451619b11d727470c84beb0093c8859d5aea2c202
3
+ size 5368