Training in progress epoch 4

README.md

@@ -15,11 +15,11 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilbert-base-cased](https://huggingface.co/distilbert-base-cased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.5718
-- Train Accuracy: 0.8100
-- Validation Loss: 0.7981
-- Validation Accuracy: 0.7571
-- Epoch: 3
+- Train Loss: 0.4216
+- Train Accuracy: 0.8541
+- Validation Loss: 0.8042
+- Validation Accuracy: 0.7628
+- Epoch: 4
 
 ## Model description
 
@@ -38,7 +38,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: {'name': 'Adam', 'weight_decay': 0.01, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': 4e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
+- optimizer: {'name': 'Adam', 'weight_decay': 0.01, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': 1e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
 - training_precision: float32
 
 ### Training results
@@ -49,6 +49,7 @@ The following hyperparameters were used during training:
 | 0.8272     | 0.7506         | 0.8106          | 0.7534              | 1     |
 | 0.6786     | 0.7826         | 0.7871          | 0.7587              | 2     |
 | 0.5718     | 0.8100         | 0.7981          | 0.7571              | 3     |
+| 0.4216     | 0.8541         | 0.8042          | 0.7628              | 4     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1218a414ab835cc3b2e4663115435b6879bde5fd3443c2fdabbc536b26cb46fd
+oid sha256:a1f3c065403820a82d67e698b24cd12708782afb6cee417148816baaf061e19a
 size 264025792