bernardocecchetto commited on
Commit
a2b62f3
1 Parent(s): 2e8253c

Upload TFDistilBertForSequenceClassification

Browse files
Files changed (3) hide show
  1. README.md +1 -1
  2. config.json +4 -4
  3. tf_model.h5 +2 -2
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': 2e-05, 'decay_schedule_fn': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-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': 0.2}
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': 1e-05, 'decay_schedule_fn': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 1e-05, 'decay_steps': 3402, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, '__passive_serialization__': True}, 'warmup_steps': 3, 'power': 1.0, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.2}
37
  - training_precision: float32
38
 
39
  ### Training results
config.json CHANGED
@@ -4,9 +4,9 @@
4
  "architectures": [
5
  "DistilBertForSequenceClassification"
6
  ],
7
- "attention_dropout": 0.2,
8
  "dim": 768,
9
- "dropout": 0.2,
10
  "hidden_dim": 3072,
11
  "id2label": {
12
  "0": "NEGATIVE",
@@ -20,11 +20,11 @@
20
  "max_position_embeddings": 512,
21
  "model_type": "distilbert",
22
  "n_heads": 12,
23
- "n_layers": 8,
24
  "output_past": true,
25
  "pad_token_id": 0,
26
  "qa_dropout": 0.1,
27
- "seq_classif_dropout": 0.6,
28
  "sinusoidal_pos_embds": true,
29
  "tie_weights_": true,
30
  "transformers_version": "4.30.2",
 
4
  "architectures": [
5
  "DistilBertForSequenceClassification"
6
  ],
7
+ "attention_dropout": 0.6,
8
  "dim": 768,
9
+ "dropout": 0.4,
10
  "hidden_dim": 3072,
11
  "id2label": {
12
  "0": "NEGATIVE",
 
20
  "max_position_embeddings": 512,
21
  "model_type": "distilbert",
22
  "n_heads": 12,
23
+ "n_layers": 10,
24
  "output_past": true,
25
  "pad_token_id": 0,
26
  "qa_dropout": 0.1,
27
+ "seq_classif_dropout": 0.4,
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:a939d167a84a4de9bcf584fca81d6c58052cc5ed2f3bba6118890e431b20b851
3
- size 598179808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c7d1a3e2170a3f98a4596d19666effe7062169a2b5c62c4910b74470137d7ea
3
+ size 654915400