Upload TFDistilBertForMaskedLM

README.md

@@ -2,14 +2,14 @@
 tags:
 - generated_from_keras_callback
 model-index:
-- name: dBERT-Nepali-Masked-LM
+- name: distilBERT-Nepali
   results: []
 ---
 
 <!-- This model card has been generated automatically according to the information Keras had access to. You should
 probably proofread and complete it, then remove this comment. -->
 
-# dBERT-Nepali-Masked-LM
+# distilBERT-Nepali
 
 This model was trained from scratch on an unknown dataset.
 It achieves the following results on the evaluation set:
@@ -32,8 +32,8 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: None
-- training_precision: float32
+- 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': 16760, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, '__passive_serialization__': True}, 'warmup_steps': 1000, 'power': 1.0, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
+- training_precision: mixed_float16
 
 ### Training results
 
@@ -41,7 +41,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- Transformers 4.28.1
-- TensorFlow 2.11.0
+- Transformers 4.30.2
+- TensorFlow 2.12.0
 - Datasets 2.1.0
 - Tokenizers 0.13.3

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/kaggle/input/distilbert-nepali-maskedlm/DistilBert-Nepali-MaskedLM",
+  "_name_or_path": "raygx/distilBERT-Nepali",
   "activation": "gelu",
   "architectures": [
     "DistilBertForMaskedLM"
@@ -20,6 +20,6 @@
   "seq_classif_dropout": 0.2,
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
-  "transformers_version": "4.28.1",
-  "vocab_size": 30000
+  "transformers_version": "4.30.2",
+  "vocab_size": 50000
 }

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c64de5cd0c33d09dfc0c912b5d18f62b6e975394a1065cad75c3330ceff88c79
-size 360214392
+oid sha256:b466f1f965142edcd99bbc4b2739fd7b6902837491970417767034ec361a9967
+size 636980224