Master-Rapha7 commited on
Commit
96bfbc6
·
verified ·
1 Parent(s): 164959c

End of training

Browse files
README.md CHANGED
@@ -3,6 +3,8 @@ library_name: transformers
3
  license: other
4
  base_model: google/mobilenet_v2_1.0_224
5
  tags:
 
 
6
  - generated_from_trainer
7
  metrics:
8
  - accuracy
@@ -19,28 +21,28 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  # mobilenetv2-typecoffee-3
21
 
22
- This model is a fine-tuned version of [google/mobilenet_v2_1.0_224](https://huggingface.co/google/mobilenet_v2_1.0_224) on an unknown dataset.
23
  It achieves the following results on the evaluation set:
24
- - Loss: 1.7110
25
- - Accuracy: 0.7369
26
- - Precision: 0.8185
27
- - Recall: 0.7359
28
- - F1: 0.7259
29
- - Precision Durariadorio 64x64: 0.98
30
- - Recall Durariadorio 64x64: 0.3403
31
- - F1 Durariadorio 64x64: 0.5052
32
- - Precision Mole 64x64: 0.9663
33
- - Recall Mole 64x64: 0.5972
34
- - F1 Mole 64x64: 0.7382
35
- - Precision Quebrado 64x64: 0.7901
36
- - Recall Quebrado 64x64: 0.9931
37
- - F1 Quebrado 64x64: 0.88
38
- - Precision Riadorio 64x64: 0.5116
39
- - Recall Riadorio 64x64: 0.8684
40
- - F1 Riadorio 64x64: 0.6439
41
- - Precision Riofechado 64x64: 0.8446
42
- - Recall Riofechado 64x64: 0.8803
43
- - F1 Riofechado 64x64: 0.8621
44
 
45
  ## Model description
46
 
 
3
  license: other
4
  base_model: google/mobilenet_v2_1.0_224
5
  tags:
6
+ - image-classification
7
+ - vision
8
  - generated_from_trainer
9
  metrics:
10
  - accuracy
 
21
 
22
  # mobilenetv2-typecoffee-3
23
 
24
+ 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_64x64 dataset.
25
  It achieves the following results on the evaluation set:
26
+ - Loss: 0.4428
27
+ - Accuracy: 0.8733
28
+ - Precision: 0.8809
29
+ - Recall: 0.8742
30
+ - F1: 0.8751
31
+ - Precision Durariadorio 64x64: 0.9512
32
+ - Recall Durariadorio 64x64: 0.8125
33
+ - F1 Durariadorio 64x64: 0.8764
34
+ - Precision Mole 64x64: 0.9357
35
+ - Recall Mole 64x64: 0.9097
36
+ - F1 Mole 64x64: 0.9225
37
+ - Precision Quebrado 64x64: 0.8059
38
+ - Recall Quebrado 64x64: 0.9514
39
+ - F1 Quebrado 64x64: 0.8726
40
+ - Precision Riadorio 64x64: 0.7707
41
+ - Recall Riadorio 64x64: 0.7961
42
+ - F1 Riadorio 64x64: 0.7832
43
+ - Precision Riofechado 64x64: 0.9412
44
+ - Recall Riofechado 64x64: 0.9014
45
+ - F1 Riofechado 64x64: 0.9209
46
 
47
  ## Model description
48
 
all_results.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 100.0,
3
+ "eval_accuracy": 0.8732782369146006,
4
+ "eval_f1": 0.8751172002011796,
5
+ "eval_f1_DuraRiadoRio_64x64": 0.8764044943820225,
6
+ "eval_f1_Mole_64x64": 0.9225352112676056,
7
+ "eval_f1_Quebrado_64x64": 0.8726114649681529,
8
+ "eval_f1_RiadoRio_64x64": 0.7831715210355987,
9
+ "eval_f1_RioFechado_64x64": 0.920863309352518,
10
+ "eval_loss": 0.442775160074234,
11
+ "eval_precision": 0.8809386516762989,
12
+ "eval_precision_DuraRiadoRio_64x64": 0.9512195121951219,
13
+ "eval_precision_Mole_64x64": 0.9357142857142857,
14
+ "eval_precision_Quebrado_64x64": 0.8058823529411765,
15
+ "eval_precision_RiadoRio_64x64": 0.7707006369426752,
16
+ "eval_precision_RioFechado_64x64": 0.9411764705882353,
17
+ "eval_recall": 0.8742144386788567,
18
+ "eval_recall_DuraRiadoRio_64x64": 0.8125,
19
+ "eval_recall_Mole_64x64": 0.9097222222222222,
20
+ "eval_recall_Quebrado_64x64": 0.9513888888888888,
21
+ "eval_recall_RiadoRio_64x64": 0.7960526315789473,
22
+ "eval_recall_RioFechado_64x64": 0.9014084507042254,
23
+ "eval_runtime": 1.7704,
24
+ "eval_samples_per_second": 410.066,
25
+ "eval_steps_per_second": 25.982,
26
+ "total_flos": 1.5288402814304256e+18,
27
+ "train_loss": 0.34031273227807385,
28
+ "train_runtime": 2805.7892,
29
+ "train_samples_per_second": 207.108,
30
+ "train_steps_per_second": 12.973
31
+ }
eval_results.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 100.0,
3
+ "eval_accuracy": 0.8732782369146006,
4
+ "eval_f1": 0.8751172002011796,
5
+ "eval_f1_DuraRiadoRio_64x64": 0.8764044943820225,
6
+ "eval_f1_Mole_64x64": 0.9225352112676056,
7
+ "eval_f1_Quebrado_64x64": 0.8726114649681529,
8
+ "eval_f1_RiadoRio_64x64": 0.7831715210355987,
9
+ "eval_f1_RioFechado_64x64": 0.920863309352518,
10
+ "eval_loss": 0.442775160074234,
11
+ "eval_precision": 0.8809386516762989,
12
+ "eval_precision_DuraRiadoRio_64x64": 0.9512195121951219,
13
+ "eval_precision_Mole_64x64": 0.9357142857142857,
14
+ "eval_precision_Quebrado_64x64": 0.8058823529411765,
15
+ "eval_precision_RiadoRio_64x64": 0.7707006369426752,
16
+ "eval_precision_RioFechado_64x64": 0.9411764705882353,
17
+ "eval_recall": 0.8742144386788567,
18
+ "eval_recall_DuraRiadoRio_64x64": 0.8125,
19
+ "eval_recall_Mole_64x64": 0.9097222222222222,
20
+ "eval_recall_Quebrado_64x64": 0.9513888888888888,
21
+ "eval_recall_RiadoRio_64x64": 0.7960526315789473,
22
+ "eval_recall_RioFechado_64x64": 0.9014084507042254,
23
+ "eval_runtime": 1.7704,
24
+ "eval_samples_per_second": 410.066,
25
+ "eval_steps_per_second": 25.982
26
+ }
runs/Mar07_01-27-36_58c153bfa619/events.out.tfevents.1741313683.58c153bfa619.7111.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c221681991bde6bfed0a13be4d71d63830221947c615fc0702fc2958431bfa32
3
+ size 1560
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 100.0,
3
+ "total_flos": 1.5288402814304256e+18,
4
+ "train_loss": 0.34031273227807385,
5
+ "train_runtime": 2805.7892,
6
+ "train_samples_per_second": 207.108,
7
+ "train_steps_per_second": 12.973
8
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff