Upload TFBertForTokenClassification

README.md

@@ -12,10 +12,10 @@ probably proofread and complete it, then remove this comment. -->
 
 # bert-finetuned-ner-per-v2
 
-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 [BeardedJohn/bert-finetuned-ner-per-v2](https://huggingface.co/BeardedJohn/bert-finetuned-ner-per-v2) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.0201
-- Validation Loss: 0.0303
+- Train Loss: 0.0005
+- Validation Loss: 0.0002
 - Epoch: 2
 
 ## Model description
@@ -35,16 +35,16 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 1365, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
+- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 939, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, '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
 
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 0.2160     | 0.0385          | 0     |
-| 0.0334     | 0.0307          | 1     |
-| 0.0201     | 0.0303          | 2     |
+| 0.0202     | 0.0006          | 0     |
+| 0.0010     | 0.0002          | 1     |
+| 0.0005     | 0.0002          | 2     |
 
 
 ### Framework versions

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "bert-base-cased",
+  "_name_or_path": "BeardedJohn/bert-finetuned-ner-per-v2",
   "architectures": [
     "BertForTokenClassification"
   ],

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be42e4394c2675051b73ce44f41942853ed133f23ab2b58bbc76bdd7d9821e83
+oid sha256:1e90cb5b64104dbec414055417424157a7222885d48cdc0c61b327c2b7a3da44
 size 431179820