vnktrmnb commited on
Commit
f3da78d
1 Parent(s): 4b2278a

Training in progress epoch 0

Browse files
README.md CHANGED
@@ -15,13 +15,13 @@ probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Train Loss: 0.8674
19
- - Train End Logits Accuracy: 0.7836
20
- - Train Start Logits Accuracy: 0.8129
21
- - Validation Loss: 0.4738
22
- - Validation End Logits Accuracy: 0.8582
23
- - Validation Start Logits Accuracy: 0.8982
24
- - Epoch: 1
25
 
26
  ## Model description
27
 
@@ -40,15 +40,14 @@ More information needed
40
  ### Training hyperparameters
41
 
42
  The following hyperparameters were used during training:
43
- - optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 1608, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
44
  - training_precision: float32
45
 
46
  ### Training results
47
 
48
  | Train Loss | Train End Logits Accuracy | Train Start Logits Accuracy | Validation Loss | Validation End Logits Accuracy | Validation Start Logits Accuracy | Epoch |
49
  |:----------:|:-------------------------:|:---------------------------:|:---------------:|:------------------------------:|:--------------------------------:|:-----:|
50
- | 1.5118 | 0.6474 | 0.6732 | 0.5099 | 0.8325 | 0.8943 | 0 |
51
- | 0.8674 | 0.7836 | 0.8129 | 0.4738 | 0.8582 | 0.8982 | 1 |
52
 
53
 
54
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Train Loss: 1.5040
19
+ - Train End Logits Accuracy: 0.6478
20
+ - Train Start Logits Accuracy: 0.6786
21
+ - Validation Loss: 0.5486
22
+ - Validation End Logits Accuracy: 0.8299
23
+ - Validation Start Logits Accuracy: 0.8840
24
+ - Epoch: 0
25
 
26
  ## Model description
27
 
 
40
  ### Training hyperparameters
41
 
42
  The following hyperparameters were used during training:
43
+ - optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 2412, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
44
  - training_precision: float32
45
 
46
  ### Training results
47
 
48
  | Train Loss | Train End Logits Accuracy | Train Start Logits Accuracy | Validation Loss | Validation End Logits Accuracy | Validation Start Logits Accuracy | Epoch |
49
  |:----------:|:-------------------------:|:---------------------------:|:---------------:|:------------------------------:|:--------------------------------:|:-----:|
50
+ | 1.5040 | 0.6478 | 0.6786 | 0.5486 | 0.8299 | 0.8840 | 0 |
 
51
 
52
 
53
  ### Framework versions
logs/train/events.out.tfevents.1691917378.e7c9a2504c08.255.0.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e9744bff04299bce84370343111f04b6ddb04de9f96976fb8ae463a4858cb7c
3
+ size 2645337
logs/validation/events.out.tfevents.1691918449.e7c9a2504c08.255.1.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54cc501cb55e0ffefebf369fbb0550469a0c13fbee2860aaed0448d45cfd097d
3
+ size 604
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cd961436f71bb5844ac0f6678ee406328f480286183066b1f98450868f13906d
3
  size 709326800
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1aa3da7a86739959d562ec3cb50f33848c19fe6c2ed81691da956be9934a71cc
3
  size 709326800