bernardocecchetto commited on
Commit
a4fa104
·
verified ·
1 Parent(s): 2d7ac5d

Upload TFDistilBertForSequenceClassification

Browse files
Files changed (3) hide show
  1. README.md +1 -1
  2. config.json +2 -2
  3. tf_model.h5 +1 -1
README.md CHANGED
@@ -33,7 +33,7 @@ More information needed
33
  ### Training hyperparameters
34
 
35
  The following hyperparameters were used during training:
36
- - optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'WarmUp', 'config': {'initial_learning_rate': 3.0000000000000004e-05, 'decay_schedule_fn': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3.0000000000000004e-05, 'decay_steps': 3400, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, '__passive_serialization__': True}, 'warmup_steps': 5, 'power': 1.0, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.4}
37
  - training_precision: float32
38
 
39
  ### Training results
 
33
  ### Training hyperparameters
34
 
35
  The following hyperparameters were used during training:
36
+ - optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'WarmUp', 'config': {'initial_learning_rate': 3.0000000000000004e-05, 'decay_schedule_fn': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3.0000000000000004e-05, 'decay_steps': 3401, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, '__passive_serialization__': True}, 'warmup_steps': 4, 'power': 1.0, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.4}
37
  - training_precision: float32
38
 
39
  ### Training results
config.json CHANGED
@@ -4,7 +4,7 @@
4
  "architectures": [
5
  "DistilBertForSequenceClassification"
6
  ],
7
- "attention_dropout": 0.1,
8
  "dim": 768,
9
  "dropout": 0.2,
10
  "hidden_dim": 3072,
@@ -24,7 +24,7 @@
24
  "output_past": true,
25
  "pad_token_id": 0,
26
  "qa_dropout": 0.1,
27
- "seq_classif_dropout": 0.5,
28
  "sinusoidal_pos_embds": true,
29
  "tie_weights_": true,
30
  "transformers_version": "4.30.2",
 
4
  "architectures": [
5
  "DistilBertForSequenceClassification"
6
  ],
7
+ "attention_dropout": 0.2,
8
  "dim": 768,
9
  "dropout": 0.2,
10
  "hidden_dim": 3072,
 
24
  "output_past": true,
25
  "pad_token_id": 0,
26
  "qa_dropout": 0.1,
27
+ "seq_classif_dropout": 0.30000000000000004,
28
  "sinusoidal_pos_embds": true,
29
  "tie_weights_": true,
30
  "transformers_version": "4.30.2",
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f3d8b21b5bb60e807f1a15b6c14d2929a71dc36079f1a4276fb7beff183abf6e
3
  size 711666800
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8d2f3774ce6006b5606f646326f3fbd469abfcb21cd586de84223e2a08e7cfd
3
  size 711666800