Imene commited on
Commit
cf0cc23
·
1 Parent(s): 997f479

Training in progress epoch 0

Browse files
README.md CHANGED
@@ -14,13 +14,13 @@ probably proofread and complete it, then remove this comment. -->
14
 
15
  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.
16
  It achieves the following results on the evaluation set:
17
- - Train Loss: 0.1732
18
- - Train Accuracy: 0.9937
19
- - Train Top-3-accuracy: 0.9989
20
- - Validation Loss: 3.0706
21
- - Validation Accuracy: 0.2574
22
- - Validation Top-3-accuracy: 0.4676
23
- - Epoch: 9
24
 
25
  ## Model description
26
 
@@ -39,23 +39,14 @@ More information needed
39
  ### Training hyperparameters
40
 
41
  The following hyperparameters were used during training:
42
- - optimizer: {'inner_optimizer': {'class_name': 'AdamWeightDecay', 'config': {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 0.0003, 'decay_steps': 2100, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.001}}, 'dynamic': True, 'initial_scale': 32768.0, 'dynamic_growth_steps': 2000}
43
  - training_precision: mixed_float16
44
 
45
  ### Training results
46
 
47
  | Train Loss | Train Accuracy | Train Top-3-accuracy | Validation Loss | Validation Accuracy | Validation Top-3-accuracy | Epoch |
48
  |:----------:|:--------------:|:--------------------:|:---------------:|:-------------------:|:-------------------------:|:-----:|
49
- | 4.5039 | 0.0202 | 0.0553 | 4.2793 | 0.0338 | 0.0915 | 0 |
50
- | 4.1594 | 0.0358 | 0.1021 | 4.0697 | 0.0468 | 0.1475 | 1 |
51
- | 3.8935 | 0.0713 | 0.1752 | 3.8171 | 0.0915 | 0.2106 | 2 |
52
- | 3.4793 | 0.1286 | 0.2882 | 3.3657 | 0.1429 | 0.3109 | 3 |
53
- | 2.9441 | 0.2044 | 0.4216 | 3.0881 | 0.1805 | 0.3845 | 4 |
54
- | 2.4544 | 0.3106 | 0.5588 | 2.9695 | 0.2206 | 0.4350 | 5 |
55
- | 1.8994 | 0.4614 | 0.7073 | 2.9141 | 0.2311 | 0.4450 | 6 |
56
- | 1.2352 | 0.6731 | 0.8710 | 2.9199 | 0.2545 | 0.4697 | 7 |
57
- | 0.5456 | 0.8977 | 0.9799 | 2.9824 | 0.2628 | 0.4768 | 8 |
58
- | 0.1732 | 0.9937 | 0.9989 | 3.0706 | 0.2574 | 0.4676 | 9 |
59
 
60
 
61
  ### Framework versions
 
14
 
15
  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.
16
  It achieves the following results on the evaluation set:
17
+ - Train Loss: 4.6733
18
+ - Train Accuracy: 0.0106
19
+ - Train Top-3-accuracy: 0.0335
20
+ - Validation Loss: 4.5751
21
+ - Validation Accuracy: 0.0196
22
+ - Validation Top-3-accuracy: 0.0464
23
+ - Epoch: 0
24
 
25
  ## Model description
26
 
 
39
  ### Training hyperparameters
40
 
41
  The following hyperparameters were used during training:
42
+ - optimizer: {'inner_optimizer': {'class_name': 'AdamWeightDecay', 'config': {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 0.003, 'decay_steps': 1400, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}}, 'dynamic': True, 'initial_scale': 32768.0, 'dynamic_growth_steps': 2000}
43
  - training_precision: mixed_float16
44
 
45
  ### Training results
46
 
47
  | Train Loss | Train Accuracy | Train Top-3-accuracy | Validation Loss | Validation Accuracy | Validation Top-3-accuracy | Epoch |
48
  |:----------:|:--------------:|:--------------------:|:---------------:|:-------------------:|:-------------------------:|:-----:|
49
+ | 4.6733 | 0.0106 | 0.0335 | 4.5751 | 0.0196 | 0.0464 | 0 |
 
 
 
 
 
 
 
 
 
50
 
51
 
52
  ### Framework versions
logs/train/events.out.tfevents.1662824115.c6cc2fa81cae.76.2.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:760c667767caf976ce251204bc2825c3c1aef68442a88bb1d45187739e8f6028
3
+ size 3303671
logs/validation/events.out.tfevents.1662825279.c6cc2fa81cae.76.3.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14ea45891e4fee1414b218959a9e9ddd6011c68d050968792e54ecc319ae853b
3
+ size 530
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1988ac1c326096187f386b5898b6dc7cffba59988aaadcba9bf945550c9e40d9
3
- size 343770912
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6782cc809ed0b584fcb4862c30fa794909b9047be3d1d822b4cadb0ab1453a68
3
+ size 343787296