Upload TFBertForMaskedLM

README.md

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: bert-base-cased
+base_model: raygx/NepaliLM-BERT
 tags:
 - generated_from_keras_callback
 model-index:
@@ -13,10 +13,10 @@ probably proofread and complete it, then remove this comment. -->
 
 # NepaliLM-BERT
 
-This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset.
+This model is a fine-tuned version of [raygx/NepaliLM-BERT](https://huggingface.co/raygx/NepaliLM-BERT) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 5.8743
-- Validation Loss: 5.8342
+- Train Loss: 5.6802
+- Validation Loss: 5.5575
 - Epoch: 1
 
 ## Model description
@@ -36,15 +36,15 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- 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': 56297, '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': 0.05}
+- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'WarmUp', 'config': {'initial_learning_rate': 2e-06, 'decay_schedule_fn': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-06, 'decay_steps': 12205, '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': 0.065}
 - training_precision: mixed_bfloat16
 
 ### Training results
 
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 6.3059     | 5.8342          | 0     |
-| 5.8743     | 5.8342          | 1     |
+| 5.6988     | 5.5615          | 0     |
+| 5.6802     | 5.5575          | 1     |
 
 
 ### Framework versions

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "bert-base-cased",
+  "_name_or_path": "raygx/NepaliLM-BERT",
   "architectures": [
     "BertForMaskedLM"
   ],

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:149cf4408a9d82fa769f8f38a84bdac6228c1fa55a0d482ada785601f6ba4fad
+oid sha256:296aa4f983116b4f393ca5acb0510c628593f4eff106b33e819dca68f8bbfff7
 size 653438360