rajakashh commited on
Commit
f8c6769
1 Parent(s): 80f9877

Training in progress epoch 0

Browse files
Files changed (2) hide show
  1. README.md +5 -27
  2. tf_model.h5 +1 -1
README.md CHANGED
@@ -14,9 +14,9 @@ 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: 5.4873
18
- - Validation Loss: 5.7961
19
- - Epoch: 22
20
 
21
  ## Model description
22
 
@@ -35,36 +35,14 @@ More information needed
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
- - 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': False, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 8, '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}
39
  - training_precision: float32
40
 
41
  ### Training results
42
 
43
  | Train Loss | Validation Loss | Epoch |
44
  |:----------:|:---------------:|:-----:|
45
- | 5.8687 | 5.8872 | 0 |
46
- | 5.7520 | 5.8630 | 1 |
47
- | 5.6948 | 5.8424 | 2 |
48
- | 5.6174 | 5.8249 | 3 |
49
- | 5.5704 | 5.8109 | 4 |
50
- | 5.5612 | 5.8011 | 5 |
51
- | 5.5110 | 5.7961 | 6 |
52
- | 5.4624 | 5.7961 | 7 |
53
- | 5.4813 | 5.7961 | 8 |
54
- | 5.5084 | 5.7961 | 9 |
55
- | 5.4843 | 5.7961 | 10 |
56
- | 5.5092 | 5.7961 | 11 |
57
- | 5.4877 | 5.7961 | 12 |
58
- | 5.4751 | 5.7961 | 13 |
59
- | 5.4973 | 5.7961 | 14 |
60
- | 5.4947 | 5.7961 | 15 |
61
- | 5.4639 | 5.7961 | 16 |
62
- | 5.5140 | 5.7961 | 17 |
63
- | 5.4980 | 5.7961 | 18 |
64
- | 5.5275 | 5.7961 | 19 |
65
- | 5.4578 | 5.7961 | 20 |
66
- | 5.4623 | 5.7961 | 21 |
67
- | 5.4873 | 5.7961 | 22 |
68
 
69
 
70
  ### 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: 5.9855
18
+ - Validation Loss: 5.8892
19
+ - Epoch: 0
20
 
21
  ## Model description
22
 
 
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
+ - 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': False, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 2, '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}
39
  - training_precision: float32
40
 
41
  ### Training results
42
 
43
  | Train Loss | Validation Loss | Epoch |
44
  |:----------:|:---------------:|:-----:|
45
+ | 5.9855 | 5.8892 | 0 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
46
 
47
 
48
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e57b01bbf7309aa61d20121460de8e7a4274461246e05bd0959d8ea4933881c4
3
  size 265583592
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54a8d263a614812945b2cfcb24d97153aad75418f5d65901702174743557b70c
3
  size 265583592