Skanda Vivek commited on
Commit
d43a4ba
1 Parent(s): fab7dbb

Training in progress epoch 0

Browse files
Files changed (3) hide show
  1. README.md +6 -8
  2. config.json +1 -1
  3. tf_model.h5 +1 -1
README.md CHANGED
@@ -14,8 +14,8 @@ probably proofread and complete it, then remove this comment. -->
14
 
15
  This model is a fine-tuned version of [deepset/roberta-base-squad2](https://huggingface.co/deepset/roberta-base-squad2) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
- - Train Loss: 0.2808
18
- - Epoch: 2
19
 
20
  ## Model description
21
 
@@ -34,21 +34,19 @@ More information needed
34
  ### Training hyperparameters
35
 
36
  The following hyperparameters were used during training:
37
- - optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 759, '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}
38
  - training_precision: mixed_float16
39
 
40
  ### Training results
41
 
42
  | Train Loss | Epoch |
43
  |:----------:|:-----:|
44
- | 0.6235 | 0 |
45
- | 0.3887 | 1 |
46
- | 0.2808 | 2 |
47
 
48
 
49
  ### Framework versions
50
 
51
- - Transformers 4.21.1
52
- - TensorFlow 2.9.1
53
  - Datasets 2.4.0
54
  - Tokenizers 0.12.1
 
14
 
15
  This model is a fine-tuned version of [deepset/roberta-base-squad2](https://huggingface.co/deepset/roberta-base-squad2) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Train Loss: 0.5969
18
+ - Epoch: 0
19
 
20
  ## Model description
21
 
 
34
  ### Training hyperparameters
35
 
36
  The following hyperparameters were used during training:
37
+ - optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 3030, '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}
38
  - training_precision: mixed_float16
39
 
40
  ### Training results
41
 
42
  | Train Loss | Epoch |
43
  |:----------:|:-----:|
44
+ | 0.5969 | 0 |
 
 
45
 
46
 
47
  ### Framework versions
48
 
49
+ - Transformers 4.21.2
50
+ - TensorFlow 2.8.2
51
  - Datasets 2.4.0
52
  - Tokenizers 0.12.1
config.json CHANGED
@@ -22,7 +22,7 @@
22
  "num_hidden_layers": 12,
23
  "pad_token_id": 1,
24
  "position_embedding_type": "absolute",
25
- "transformers_version": "4.21.1",
26
  "type_vocab_size": 1,
27
  "use_cache": true,
28
  "vocab_size": 50265
 
22
  "num_hidden_layers": 12,
23
  "pad_token_id": 1,
24
  "position_embedding_type": "absolute",
25
+ "transformers_version": "4.21.2",
26
  "type_vocab_size": 1,
27
  "use_cache": true,
28
  "vocab_size": 50265
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:47419e300ed7c1892b335cc075788370630257e34427f0c96d1774fdc2904fc6
3
  size 496513360
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b19a41b53ffef3421d0a497075decaad7f80b05bcda0b0b1418d7fdfff6c002
3
  size 496513360