felixshier commited on
Commit
ee92744
1 Parent(s): 0763707

Upload TFBertForSequenceClassification

Browse files
Files changed (2) hide show
  1. README.md +10 -11
  2. tf_model.h5 +1 -1
README.md CHANGED
@@ -15,10 +15,10 @@ probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Train Loss: 0.1644
19
- - Validation Loss: 0.7249
20
- - Train F1: 0.7388
21
- - Epoch: 5
22
 
23
  ## Model description
24
 
@@ -37,19 +37,18 @@ More information needed
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
- - 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': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 4790, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
41
  - training_precision: float32
42
 
43
  ### Training results
44
 
45
  | Train Loss | Validation Loss | Train F1 | Epoch |
46
  |:----------:|:---------------:|:--------:|:-----:|
47
- | 0.6653 | 0.5726 | 0.7255 | 0 |
48
- | 0.5481 | 0.5550 | 0.7296 | 1 |
49
- | 0.4503 | 0.5308 | 0.7469 | 2 |
50
- | 0.3473 | 0.5723 | 0.7359 | 3 |
51
- | 0.2440 | 0.6400 | 0.7355 | 4 |
52
- | 0.1644 | 0.7249 | 0.7388 | 5 |
53
 
54
 
55
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Train Loss: 0.1172
19
+ - Validation Loss: 0.5493
20
+ - Train F1: 0.8137
21
+ - Epoch: 4
22
 
23
  ## Model description
24
 
 
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
+ - 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': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 4030, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
41
  - training_precision: float32
42
 
43
  ### Training results
44
 
45
  | Train Loss | Validation Loss | Train F1 | Epoch |
46
  |:----------:|:---------------:|:--------:|:-----:|
47
+ | 0.5556 | 0.4472 | 0.7965 | 0 |
48
+ | 0.3877 | 0.4268 | 0.8107 | 1 |
49
+ | 0.2931 | 0.4459 | 0.8165 | 2 |
50
+ | 0.1734 | 0.5071 | 0.8223 | 3 |
51
+ | 0.1172 | 0.5493 | 0.8137 | 4 |
 
52
 
53
 
54
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eed93917e20886209fd54839d62281794f51957bd8943db4c462dbf81caf3163
3
  size 438223128
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e4d8e42745ffeefcc6dd8e22d74f5cd35bfc59c3b353d94d22186f54ec6abbd
3
  size 438223128