Training in progress epoch 0

README.md

@@ -15,11 +15,11 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.3425
-- Train Accuracy: 0.9555
-- Validation Loss: 0.9625
-- Validation Accuracy: 0.7835
-- Epoch: 9
+- Train Loss: 2.8423
+- Train Accuracy: 0.2313
+- Validation Loss: 2.5340
+- Validation Accuracy: 0.3593
+- Epoch: 0
 
 ## Model description
 
@@ -38,23 +38,14 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: {'name': 'Adam', 'weight_decay': None, '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': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 4e-05, 'decay_steps': 1160, 'end_learning_rate': 4e-08, 'power': 1.0, 'cycle': False, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
+- optimizer: {'name': 'Adam', 'weight_decay': None, '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': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-05, 'decay_steps': 2320, 'end_learning_rate': 0, 'power': 1.0, 'cycle': False, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
 - training_precision: float32
 
 ### Training results
 
 | Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
 |:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
-| 2.7650     | 0.2801         | 2.4192          | 0.3463              | 0     |
-| 2.3111     | 0.3626         | 2.1394          | 0.3680              | 1     |
-| 1.8627     | 0.4777         | 1.7134          | 0.5325              | 2     |
-| 1.3526     | 0.6580         | 1.4877          | 0.5758              | 3     |
-| 1.0242     | 0.7318         | 1.3084          | 0.6623              | 4     |
-| 0.7743     | 0.8046         | 1.2363          | 0.6883              | 5     |
-| 0.5871     | 0.8784         | 1.0712          | 0.7273              | 6     |
-| 0.4679     | 0.9164         | 1.0081          | 0.7749              | 7     |
-| 0.3966     | 0.9381         | 0.9864          | 0.7706              | 8     |
-| 0.3425     | 0.9555         | 0.9625          | 0.7835              | 9     |
+| 2.8423     | 0.2313         | 2.5340          | 0.3593              | 0     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d20eb0dc581653a4361caf7747ea05ee88d5a0fadab54f62cf905b42e41a07c1
+oid sha256:0508dfb64a5307ecd322af864378a7f6aded18f00b16637bf7a3c7a8c8cb42a5
 size 711818664