Upload TFDistilBertForSequenceClassification
Browse files- README.md +1 -1
- config.json +6 -6
- 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':
|
| 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': 3681, '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': 0.6}
|
| 37 |
- training_precision: float32
|
| 38 |
|
| 39 |
### Training results
|
config.json
CHANGED
|
@@ -4,9 +4,9 @@
|
|
| 4 |
"architectures": [
|
| 5 |
"DistilBertForSequenceClassification"
|
| 6 |
],
|
| 7 |
-
"attention_dropout": 0.
|
| 8 |
"dim": 768,
|
| 9 |
-
"dropout": 0.
|
| 10 |
"hidden_dim": 3072,
|
| 11 |
"id2label": {
|
| 12 |
"0": "NEGATIVE",
|
|
@@ -20,13 +20,13 @@
|
|
| 20 |
"max_position_embeddings": 512,
|
| 21 |
"model_type": "distilbert",
|
| 22 |
"n_heads": 12,
|
| 23 |
-
"n_layers":
|
| 24 |
"output_past": true,
|
| 25 |
"pad_token_id": 0,
|
| 26 |
"qa_dropout": 0.1,
|
| 27 |
-
"seq_classif_dropout": 0.
|
| 28 |
-
"sinusoidal_pos_embds":
|
| 29 |
"tie_weights_": true,
|
| 30 |
"transformers_version": "4.30.2",
|
| 31 |
-
"vocab_size":
|
| 32 |
}
|
|
|
|
| 4 |
"architectures": [
|
| 5 |
"DistilBertForSequenceClassification"
|
| 6 |
],
|
| 7 |
+
"attention_dropout": 0.25,
|
| 8 |
"dim": 768,
|
| 9 |
+
"dropout": 0.35,
|
| 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": 13,
|
| 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",
|
| 31 |
+
"vocab_size": 119548
|
| 32 |
}
|
tf_model.h5
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:95dd04ec29c7970f97762bd6639436b51c65740edc188cae53f7ba4fa64e0c0f
|
| 3 |
+
size 1107292752
|