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: 0.3644
-- Train Accuracy: 0.9338
-- Validation Loss: 1.0379
-- Validation Accuracy: 0.7446
-- Epoch: 9
+- Train Loss: 2.7650
+- Train Accuracy: 0.2801
+- Validation Loss: 2.4192
+- Validation Accuracy: 0.3463
+- 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': 3e-05, 'decay_steps': 1160, 'end_learning_rate': 3e-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': 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}
 - training_precision: float32
 
 ### Training results
 
 | Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
 |:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
-| 2.8014     | 0.2649         | 2.6062          | 0.3203              | 0     |
-| 2.2623     | 0.3779         | 2.0848          | 0.4199              | 1     |
-| 1.6972     | 0.5700         | 1.6515          | 0.5411              | 2     |
-| 1.2381     | 0.7036         | 1.3295          | 0.6494              | 3     |
-| 0.9510     | 0.7752         | 1.4154          | 0.6753              | 4     |
-| 0.7616     | 0.8143         | 1.2083          | 0.7186              | 5     |
-| 0.5738     | 0.8784         | 1.1157          | 0.7359              | 6     |
-| 0.4715     | 0.9055         | 1.0284          | 0.7576              | 7     |
-| 0.4009     | 0.9240         | 1.0385          | 0.7532              | 8     |
-| 0.3644     | 0.9338         | 1.0379          | 0.7446              | 9     |
+| 2.7650     | 0.2801         | 2.4192          | 0.3463              | 0     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d82b28f0cf00076d282ea376f4465bfe2933f80ccbf8af0cd5cf3a78a2fe1848
+oid sha256:2455a01cfad5d5044ace3f31b2c0c9b91d889425917997e8a93eb069170fb7f4
 size 711818664