Hugging Face's logo

Master-Rapha7
/
mobilenetv2-typecoffee-2

Image Classification
Transformers
TensorBoard
Safetensors
mobilenet_v2
vision
Generated from Trainer
Model card Files
xet
Metrics Community
Master-Rapha7 commited on
Commit
bc9e9ef
·
verified ·
1 Parent(s): dda2825

Training in progress, epoch 3

Browse files
Files changed (16) hide show
  1. README.md +111 -0
  2. all_results.json +13 -0
  3. config.json +40 -0
  4. eval_results.json +8 -0
  5. model.safetensors +3 -0
  6. preprocessor_config.json +26 -0
  7. runs/Mar06_18-14-26_12dd6e624592/events.out.tfevents.1741284871.12dd6e624592.13333.0 +3 -0
  8. runs/Mar06_18-14-26_12dd6e624592/events.out.tfevents.1741285190.12dd6e624592.13333.1 +3 -0
  9. runs/Mar06_18-45-35_12dd6e624592/events.out.tfevents.1741286739.12dd6e624592.21275.0 +3 -0
  10. runs/Mar06_18-45-35_12dd6e624592/events.out.tfevents.1741287069.12dd6e624592.21275.1 +3 -0
  11. runs/Mar06_18-56-30_12dd6e624592/events.out.tfevents.1741287393.12dd6e624592.24149.0 +3 -0
  12. runs/Mar06_18-56-30_12dd6e624592/events.out.tfevents.1741288990.12dd6e624592.24149.1 +3 -0
  13. runs/Mar06_19-31-23_12dd6e624592/events.out.tfevents.1741289487.12dd6e624592.33169.0 +3 -0
  14. train_results.json +8 -0
  15. trainer_state.json +0 -0
  16. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,111 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ base_model: google/mobilenet_v2_1.0_224
4
+ tags:
5
+ - image-classification
6
+ - vision
7
+ - generated_from_trainer
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: mobilenetv2-typecoffee
12
+ results: []
13
+ ---
14
+
15
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
+ should probably proofread and complete it, then remove this comment. -->
17
+
18
+ # mobilenetv2-typecoffee
19
+
20
+ This model is a fine-tuned version of [google/mobilenet_v2_1.0_224](https://huggingface.co/google/mobilenet_v2_1.0_224) on the Master-Rapha7/TypeCoffee_128x128 dataset.
21
+ It achieves the following results on the evaluation set:
22
+ - Loss: 0.3891
23
+ - Accuracy: 0.8705
24
+
25
+ ## Model description
26
+
27
+ More information needed
28
+
29
+ ## Intended uses & limitations
30
+
31
+ More information needed
32
+
33
+ ## Training and evaluation data
34
+
35
+ More information needed
36
+
37
+ ## Training procedure
38
+
39
+ ### Training hyperparameters
40
+
41
+ The following hyperparameters were used during training:
42
+ - learning_rate: 5e-05
43
+ - train_batch_size: 16
44
+ - eval_batch_size: 16
45
+ - seed: 42
46
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
47
+ - lr_scheduler_type: linear
48
+ - num_epochs: 50.0
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
53
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|
54
+ | 1.0566 | 1.0 | 364 | 1.3442 | 0.4711 |
55
+ | 0.7958 | 2.0 | 728 | 0.9054 | 0.6309 |
56
+ | 0.7631 | 3.0 | 1092 | 1.8326 | 0.3444 |
57
+ | 0.8108 | 4.0 | 1456 | 1.5297 | 0.5 |
58
+ | 0.9185 | 5.0 | 1820 | 2.1793 | 0.4366 |
59
+ | 0.5972 | 6.0 | 2184 | 0.7575 | 0.7383 |
60
+ | 0.5495 | 7.0 | 2548 | 1.5874 | 0.6006 |
61
+ | 0.5987 | 8.0 | 2912 | 1.1093 | 0.6680 |
62
+ | 0.4262 | 9.0 | 3276 | 0.9131 | 0.6915 |
63
+ | 0.5068 | 10.0 | 3640 | 2.0110 | 0.5937 |
64
+ | 0.4457 | 11.0 | 4004 | 0.8147 | 0.7603 |
65
+ | 0.4789 | 12.0 | 4368 | 0.4532 | 0.8512 |
66
+ | 0.5156 | 13.0 | 4732 | 0.6730 | 0.8058 |
67
+ | 0.3494 | 14.0 | 5096 | 1.2551 | 0.6584 |
68
+ | 0.5386 | 15.0 | 5460 | 1.2512 | 0.6171 |
69
+ | 0.3413 | 16.0 | 5824 | 0.8357 | 0.7383 |
70
+ | 0.4416 | 17.0 | 6188 | 1.2328 | 0.6791 |
71
+ | 0.3827 | 18.0 | 6552 | 0.6589 | 0.8044 |
72
+ | 0.3838 | 19.0 | 6916 | 1.0300 | 0.6983 |
73
+ | 0.4336 | 20.0 | 7280 | 1.1139 | 0.7011 |
74
+ | 0.3418 | 21.0 | 7644 | 0.6383 | 0.7948 |
75
+ | 0.4024 | 22.0 | 8008 | 3.2976 | 0.4421 |
76
+ | 0.4106 | 23.0 | 8372 | 0.7275 | 0.7796 |
77
+ | 0.3289 | 24.0 | 8736 | 2.0388 | 0.6088 |
78
+ | 0.5709 | 25.0 | 9100 | 2.2146 | 0.6391 |
79
+ | 0.2912 | 26.0 | 9464 | 0.9518 | 0.7410 |
80
+ | 0.433 | 27.0 | 9828 | 1.8215 | 0.6901 |
81
+ | 0.2391 | 28.0 | 10192 | 0.8574 | 0.7782 |
82
+ | 0.2589 | 29.0 | 10556 | 0.7175 | 0.7824 |
83
+ | 0.2877 | 30.0 | 10920 | 1.1670 | 0.7273 |
84
+ | 0.2391 | 31.0 | 11284 | 0.7039 | 0.7796 |
85
+ | 0.3905 | 32.0 | 11648 | 1.0528 | 0.6928 |
86
+ | 0.3362 | 33.0 | 12012 | 1.4142 | 0.7218 |
87
+ | 0.4056 | 34.0 | 12376 | 0.5757 | 0.8623 |
88
+ | 0.2026 | 35.0 | 12740 | 0.8064 | 0.7769 |
89
+ | 0.2183 | 36.0 | 13104 | 1.9640 | 0.5964 |
90
+ | 0.2996 | 37.0 | 13468 | 1.1046 | 0.7011 |
91
+ | 0.1853 | 38.0 | 13832 | 1.2391 | 0.7369 |
92
+ | 0.2278 | 39.0 | 14196 | 0.3891 | 0.8705 |
93
+ | 0.2415 | 40.0 | 14560 | 0.4691 | 0.8251 |
94
+ | 0.2394 | 41.0 | 14924 | 1.4963 | 0.6736 |
95
+ | 0.3786 | 42.0 | 15288 | 1.8459 | 0.6804 |
96
+ | 0.2873 | 43.0 | 15652 | 2.0178 | 0.5634 |
97
+ | 0.2306 | 44.0 | 16016 | 0.7742 | 0.7603 |
98
+ | 0.3525 | 45.0 | 16380 | 0.6618 | 0.8140 |
99
+ | 0.1891 | 46.0 | 16744 | 1.1009 | 0.7121 |
100
+ | 0.2664 | 47.0 | 17108 | 0.8616 | 0.7562 |
101
+ | 0.2374 | 48.0 | 17472 | 2.2997 | 0.4766 |
102
+ | 0.2761 | 49.0 | 17836 | 1.3257 | 0.7452 |
103
+ | 0.2137 | 50.0 | 18200 | 1.0285 | 0.7507 |
104
+
105
+
106
+ ### Framework versions
107
+
108
+ - Transformers 4.48.3
109
+ - Pytorch 2.5.1+cu124
110
+ - Datasets 3.3.2
111
+ - Tokenizers 0.21.0
all_results.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 50.0,
3
+ "eval_accuracy": 0.8705234159779615,
4
+ "eval_loss": 0.3891112208366394,
5
+ "eval_runtime": 1.9855,
6
+ "eval_samples_per_second": 365.644,
7
+ "eval_steps_per_second": 23.168,
8
+ "total_flos": 7.644201407152128e+17,
9
+ "train_loss": 0.40744263351618587,
10
+ "train_runtime": 1591.5969,
11
+ "train_samples_per_second": 182.553,
12
+ "train_steps_per_second": 11.435
13
+ }
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/mobilenet_v2_1.0_224",
3
+ "architectures": [
4
+ "MobileNetV2ForImageClassification"
5
+ ],
6
+ "classifier_dropout_prob": 0.2,
7
+ "depth_divisible_by": 8,
8
+ "depth_multiplier": 1.0,
9
+ "expand_ratio": 6,
10
+ "finegrained_output": true,
11
+ "finetuning_task": "image-classification",
12
+ "first_layer_is_expansion": true,
13
+ "hidden_act": "relu6",
14
+ "id2label": {
15
+ "0": "DuraRiadoRio_128x128",
16
+ "1": "Mole_128x128",
17
+ "2": "Quebrado_128x128",
18
+ "3": "RiadoRio_128x128",
19
+ "4": "RioFechado_128x128"
20
+ },
21
+ "image_size": 224,
22
+ "initializer_range": 0.02,
23
+ "label2id": {
24
+ "DuraRiadoRio_128x128": "0",
25
+ "Mole_128x128": "1",
26
+ "Quebrado_128x128": "2",
27
+ "RiadoRio_128x128": "3",
28
+ "RioFechado_128x128": "4"
29
+ },
30
+ "layer_norm_eps": 0.001,
31
+ "min_depth": 8,
32
+ "model_type": "mobilenet_v2",
33
+ "num_channels": 3,
34
+ "output_stride": 32,
35
+ "problem_type": "single_label_classification",
36
+ "semantic_loss_ignore_index": 255,
37
+ "tf_padding": true,
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.48.3"
40
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 50.0,
3
+ "eval_accuracy": 0.8705234159779615,
4
+ "eval_loss": 0.3891112208366394,
5
+ "eval_runtime": 1.9855,
6
+ "eval_samples_per_second": 365.644,
7
+ "eval_steps_per_second": 23.168
8
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:138fc2f96e9081b60b79e681802f465998cdec3835858f3977b7fa67db10c49d
3
+ size 9095588
preprocessor_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": {
3
+ "height": 224,
4
+ "width": 224
5
+ },
6
+ "do_center_crop": true,
7
+ "do_normalize": true,
8
+ "do_rescale": true,
9
+ "do_resize": true,
10
+ "image_mean": [
11
+ 0.5,
12
+ 0.5,
13
+ 0.5
14
+ ],
15
+ "image_processor_type": "MobileNetV2ImageProcessor",
16
+ "image_std": [
17
+ 0.5,
18
+ 0.5,
19
+ 0.5
20
+ ],
21
+ "resample": 2,
22
+ "rescale_factor": 0.00392156862745098,
23
+ "size": {
24
+ "shortest_edge": 256
25
+ }
26
+ }
runs/Mar06_18-14-26_12dd6e624592/events.out.tfevents.1741284871.12dd6e624592.13333.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4ba5dc39d49f1138ab235cbf3a05e8ff1e8897d0debc09ab8d652fd01ee21f7
3
+ size 85802
runs/Mar06_18-14-26_12dd6e624592/events.out.tfevents.1741285190.12dd6e624592.13333.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9250a15a59056b7bd4fdbbbefa2bba0fa4d04769b9dd82a20439b2cbb303ccb8
3
+ size 411
runs/Mar06_18-45-35_12dd6e624592/events.out.tfevents.1741286739.12dd6e624592.21275.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddd71a1f7f524493f672517a743af4477ba6bc91dca59ced585e8e2e1cd7d242
3
+ size 85802
runs/Mar06_18-45-35_12dd6e624592/events.out.tfevents.1741287069.12dd6e624592.21275.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbc4c9b605496fb54ed04499fdea21b86674f61e11ffdfbffb5d38201b7aa7ae
3
+ size 411
runs/Mar06_18-56-30_12dd6e624592/events.out.tfevents.1741287393.12dd6e624592.24149.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bdaa2f4ff3fc31f2fd0c6b7c7bd59bcb7cee08e2f093c0c1e1f457ee45907d5
3
+ size 406702
runs/Mar06_18-56-30_12dd6e624592/events.out.tfevents.1741288990.12dd6e624592.24149.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:111998636578a7542ec52dd910f70fbb87e3a26cdc98465a23fd9a1f5f9eadef
3
+ size 417
runs/Mar06_19-31-23_12dd6e624592/events.out.tfevents.1741289487.12dd6e624592.33169.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97c71567ea48554282e705e1cb22a54c3cb4bf646369bfd5b595f55c697cccbf
3
+ size 29385
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 50.0,
3
+ "total_flos": 7.644201407152128e+17,
4
+ "train_loss": 0.40744263351618587,
5
+ "train_runtime": 1591.5969,
6
+ "train_samples_per_second": 182.553,
7
+ "train_steps_per_second": 11.435
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 sha256:73ee52238a2de53d7f819601a421e555b5b79fe5eee7719c89861ebc9070525f
3
+ size 5432