ankush-003 commited on
Commit
1170cd9
1 Parent(s): c846b2c

Training in progress epoch 0

Browse files
Files changed (2) hide show
  1. README.md +4 -4
  2. tf_model.h5 +1 -1
README.md CHANGED
@@ -15,9 +15,9 @@ probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Train Loss: 0.0277
19
  - Train Accuracy: 1.0
20
- - Validation Loss: 0.0002
21
  - Validation Accuracy: 1.0
22
  - Epoch: 0
23
 
@@ -38,14 +38,14 @@ More information needed
38
  ### Training hyperparameters
39
 
40
  The following hyperparameters were used during training:
41
- - 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': 25000, '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}
42
  - training_precision: float32
43
 
44
  ### Training results
45
 
46
  | Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
47
  |:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
48
- | 0.0277 | 1.0 | 0.0002 | 1.0 | 0 |
49
 
50
 
51
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Train Loss: 0.0257
19
  - Train Accuracy: 1.0
20
+ - Validation Loss: 0.0001
21
  - Validation Accuracy: 1.0
22
  - Epoch: 0
23
 
 
38
  ### Training hyperparameters
39
 
40
  The following hyperparameters were used during training:
41
+ - 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': 112500, '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}
42
  - training_precision: float32
43
 
44
  ### Training results
45
 
46
  | Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
47
  |:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
48
+ | 0.0257 | 1.0 | 0.0001 | 1.0 | 0 |
49
 
50
 
51
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8b70918d231ec3600a147776316e5c9fe422bb997a10a910e75c54b676af6dbd
3
  size 267951808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d662e45feb074e8769374042243c49b2e9c3bfe36ae6bdbdc540acd7b2cae2b
3
  size 267951808