Upload TFDistilBertForSequenceClassification

README.md

@@ -33,7 +33,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'WarmUp', 'config': {'initial_learning_rate': 5e-05, 'decay_schedule_fn': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-05, 'decay_steps': 3450, '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': 0.6}
+- 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': 3448, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, '__passive_serialization__': True}, 'warmup_steps': 7, 'power': 1.0, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.5}
 - training_precision: float32
 
 ### Training results

config.json

@@ -6,7 +6,7 @@
   ],
   "attention_dropout": 0.4,
   "dim": 768,
-  "dropout": 0.30000000000000004,
+  "dropout": 0.1,
   "hidden_dim": 3072,
   "id2label": {
     "0": "NEGATIVE",
@@ -20,12 +20,12 @@
   "max_position_embeddings": 512,
   "model_type": "distilbert",
   "n_heads": 12,
-  "n_layers": 13,
+  "n_layers": 6,
   "output_past": true,
   "pad_token_id": 0,
   "qa_dropout": 0.1,
-  "seq_classif_dropout": 0.6,
-  "sinusoidal_pos_embds": false,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": true,
   "tie_weights_": true,
   "transformers_version": "4.30.2",
   "vocab_size": 119547

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:463af644afdec9d419f39d12b3df0601df34212cd1448861d8bfe53a097073d3
-size 740034320
+oid sha256:c15647adae1713bea27532ea9f837d910918fd6672d34b35af1e923a40b28ba2
+size 541436608