casarf commited on
Commit
2254b5c
·
1 Parent(s): dc2b07f

Training in progress epoch 0

Browse files
Files changed (2) hide show
  1. README.md +6 -8
  2. tf_model.h5 +2 -2
README.md CHANGED
@@ -14,10 +14,10 @@ probably proofread and complete it, then remove this comment. -->
14
 
15
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
- - Train Loss: 0.0712
18
- - Validation Loss: 0.9693
19
- - Train Accuracy: 0.7108
20
- - Epoch: 2
21
 
22
  ## Model description
23
 
@@ -36,16 +36,14 @@ More information needed
36
  ### Training hyperparameters
37
 
38
  The following hyperparameters were used during training:
39
- - 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': 820, '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}
40
  - training_precision: float32
41
 
42
  ### Training results
43
 
44
  | Train Loss | Validation Loss | Train Accuracy | Epoch |
45
  |:----------:|:---------------:|:--------------:|:-----:|
46
- | 0.1717 | 0.7892 | 0.6627 | 0 |
47
- | 0.1141 | 0.8703 | 0.7229 | 1 |
48
- | 0.0712 | 0.9693 | 0.7108 | 2 |
49
 
50
 
51
  ### Framework versions
 
14
 
15
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Train Loss: 0.6552
18
+ - Validation Loss: 0.6188
19
+ - Train Accuracy: 0.6627
20
+ - Epoch: 0
21
 
22
  ## Model description
23
 
 
36
  ### Training hyperparameters
37
 
38
  The following hyperparameters were used during training:
39
+ - 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': 205, '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}
40
  - training_precision: float32
41
 
42
  ### Training results
43
 
44
  | Train Loss | Validation Loss | Train Accuracy | Epoch |
45
  |:----------:|:---------------:|:--------------:|:-----:|
46
+ | 0.6552 | 0.6188 | 0.6627 | 0 |
 
 
47
 
48
 
49
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4b9d5ad24176ce736800319fe87a83c65b6d2fa1c3fe443636e91049826846cd
3
- size 267951808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06510820f2d933e2ec57e456c16cbe198780d7b5b8843af1527de0f5fb4f4b2b
3
+ size 267955144