Upload TFBertForTokenClassification

README.md

@@ -14,9 +14,9 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.0030
-- Validation Loss: 0.0052
-- Epoch: 4
+- Train Loss: 0.0011
+- Validation Loss: 0.0065
+- Epoch: 6
 
 ## Model description
 
@@ -35,23 +35,25 @@ 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': 2140, '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': 8550, '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 |
 |:----------:|:---------------:|:-----:|
-| 0.0641     | 0.0078          | 0     |
-| 0.0052     | 0.0062          | 1     |
-| 0.0032     | 0.0052          | 2     |
-| 0.0029     | 0.0052          | 3     |
-| 0.0030     | 0.0052          | 4     |
+| 0.0661     | 0.0177          | 0     |
+| 0.0105     | 0.0123          | 1     |
+| 0.0062     | 0.0094          | 2     |
+| 0.0038     | 0.0090          | 3     |
+| 0.0023     | 0.0069          | 4     |
+| 0.0015     | 0.0073          | 5     |
+| 0.0011     | 0.0065          | 6     |
 
 
 ### Framework versions
 
-- Transformers 4.22.1
+- Transformers 4.22.2
 - TensorFlow 2.8.2
 - Datasets 2.5.1
 - Tokenizers 0.12.1

config.json

@@ -52,7 +52,7 @@
   "num_hidden_layers": 12,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
-  "transformers_version": "4.22.1",
+  "transformers_version": "4.22.2",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 28996

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0820bd4f377ae8fbb5024f1e97ce05d3b479572f13952290758a7329d5dff2d9
+oid sha256:f0c7596f39986de749e76b65aea39b8d0858ad8e17d1f5c74ec9d18cf1b6e28b
 size 431198276