tszocinski commited on
Commit
dc6b747
1 Parent(s): 5d03344

Training in progress epoch 0

Browse files
Files changed (3) hide show
  1. README.md +5 -5
  2. config.json +1 -1
  3. tf_model.h5 +1 -1
README.md CHANGED
@@ -12,10 +12,10 @@ probably proofread and complete it, then remove this comment. -->
12
 
13
  # tszocinski/bart-base-squad-question-generation
14
 
15
- This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
- - Train Loss: 2.2901
18
- - Validation Loss: 1.8757
19
  - Epoch: 0
20
 
21
  ## Model description
@@ -35,14 +35,14 @@ More information needed
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
- - optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5.6e-05, 'decay_steps': 125, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, '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
- | 2.2901 | 1.8757 | 0 |
46
 
47
 
48
  ### Framework versions
 
12
 
13
  # tszocinski/bart-base-squad-question-generation
14
 
15
+ This model is a fine-tuned version of [tszocinski/bart-base-squad-question-generation](https://huggingface.co/tszocinski/bart-base-squad-question-generation) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Train Loss: 6.5656
18
+ - Validation Loss: 11.1958
19
  - Epoch: 0
20
 
21
  ## Model description
 
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
+ - optimizer: {'inner_optimizer': {'class_name': 'RMSprop', 'config': {'name': 'RMSprop', 'learning_rate': 0.001, 'decay': 0.0, 'rho': 0.9, 'momentum': 0.0, 'epsilon': 1e-07, 'centered': False}}, 'dynamic': True, 'initial_scale': 32768.0, 'dynamic_growth_steps': 2000}
39
  - training_precision: mixed_float16
40
 
41
  ### Training results
42
 
43
  | Train Loss | Validation Loss | Epoch |
44
  |:----------:|:---------------:|:-----:|
45
+ | 6.5656 | 11.1958 | 0 |
46
 
47
 
48
  ### Framework versions
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "facebook/bart-base",
3
  "activation_dropout": 0.1,
4
  "activation_function": "gelu",
5
  "add_bias_logits": false,
 
1
  {
2
+ "_name_or_path": "tszocinski/bart-base-squad-question-generation",
3
  "activation_dropout": 0.1,
4
  "activation_function": "gelu",
5
  "add_bias_logits": false,
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7818d72998db69bb2519ade2786d7066303ed4516bab66c7437dd9e44ea14799
3
  size 558374928
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3e71e2ee64c4de93fa6c8ccf71477ae87ecef9e4fcb2ee944e70bd2dd8daa34
3
  size 558374928