Hugging Face's logo

Mattis0525
/
bert-base-chinese-finetuned-tcfd

Fill-Mask
Transformers
TensorFlow
bert
generated_from_keras_callback
Inference Endpoints
Model card Files Community
Mattis0525 commited on
Commit
73e0b2d
•
1 Parent(s): eccd8d2

Training in progress epoch 0

Browse files
Files changed (2) hide show
  1. README.md +9 -14
  2. tf_model.h5 +1 -1
README.md CHANGED
@@ -14,9 +14,11 @@ probably proofread and complete it, then remove this comment. -->
14
 
15
  This model is a fine-tuned version of [bert-base-chinese](https://huggingface.co/bert-base-chinese) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
- - Train Loss: 0.6470
18
- - Validation Loss: 0.6767
19
- - Epoch: 7
 
 
20
 
21
  ## Model description
22
 
@@ -36,20 +38,13 @@ More information needed
36
 
37
  The following hyperparameters were used during training:
38
  - optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'transformers.optimization_tf', 'class_name': 'WarmUp', 'config': {'initial_learning_rate': 2e-05, 'decay_schedule_fn': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': -800, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'warmup_steps': 1000, 'power': 1.0, 'name': None}, 'registered_name': 'WarmUp'}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
39
- - training_precision: mixed_float16
40
 
41
  ### Training results
42
 
43
- | Train Loss | Validation Loss | Epoch |
44
- |:----------:|:---------------:|:-----:|
45
- | 0.9382 | 0.8242 | 0 |
46
- | 0.8509 | 0.7021 | 1 |
47
- | 0.7672 | 0.7041 | 2 |
48
- | 0.7263 | 0.6545 | 3 |
49
- | 0.6599 | 0.6147 | 4 |
50
- | 0.6491 | 0.6207 | 5 |
51
- | 0.6481 | 0.6252 | 6 |
52
- | 0.6470 | 0.6767 | 7 |
53
 
54
 
55
  ### Framework versions
 
14
 
15
  This model is a fine-tuned version of [bert-base-chinese](https://huggingface.co/bert-base-chinese) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Train Loss: 0.9480
18
+ - Train Accuracy: 0.0555
19
+ - Validation Loss: 0.8742
20
+ - Validation Accuracy: 0.0566
21
+ - Epoch: 0
22
 
23
  ## Model description
24
 
 
38
 
39
  The following hyperparameters were used during training:
40
  - optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'transformers.optimization_tf', 'class_name': 'WarmUp', 'config': {'initial_learning_rate': 2e-05, 'decay_schedule_fn': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': -800, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'warmup_steps': 1000, 'power': 1.0, 'name': None}, 'registered_name': 'WarmUp'}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
41
+ - training_precision: float32
42
 
43
  ### Training results
44
 
45
+ | Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
46
+ |:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
47
+ | 0.9480 | 0.0555 | 0.8742 | 0.0566 | 0 |
 
 
 
 
 
 
 
48
 
49
 
50
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:164d5a48caeaa48c9ced3f7110917e5b1c707885f35556c1efef056628277b3e
3
  size 475933304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fb154761b1a7f38c07247e2b79700f30e07514e994d82e654b99f6bb5166edb
3
  size 475933304