Training in progress epoch 0

README.md

@@ -13,9 +13,9 @@ probably proofread and complete it, then remove this comment. -->
 
 This model was trained from scratch on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.0310
+- Train Loss: 0.0534
 - Validation Loss: 0.0
-- Epoch: 14
+- Epoch: 0
 
 ## Model description
 
@@ -34,28 +34,14 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: {'inner_optimizer': {'module': 'transformers.optimization_tf', 'class_name': 'AdamWeightDecay', 'config': {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 1380, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.8999999761581421, 'beta_2': 0.9990000128746033, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.001}, 'registered_name': 'AdamWeightDecay'}, 'dynamic': True, 'initial_scale': 32768.0, 'dynamic_growth_steps': 2000}
+- optimizer: {'inner_optimizer': {'module': 'transformers.optimization_tf', 'class_name': 'AdamWeightDecay', 'config': {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 1e-05, 'decay_steps': 1380, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.8999999761581421, 'beta_2': 0.9990000128746033, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.001}, 'registered_name': 'AdamWeightDecay'}, 'dynamic': True, 'initial_scale': 32768.0, 'dynamic_growth_steps': 2000}
 - training_precision: mixed_float16
 
 ### Training results
 
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 0.2033     | 0.0             | 0     |
-| 0.1906     | 0.0             | 1     |
-| 0.1407     | 0.0             | 2     |
-| 0.1096     | 0.0             | 3     |
-| 0.0862     | 0.0             | 4     |
-| 0.0765     | 0.0             | 5     |
-| 0.0632     | 0.0             | 6     |
-| 0.0478     | 0.0             | 7     |
-| 0.0623     | 0.0             | 8     |
-| 0.0441     | 0.0             | 9     |
-| 0.0369     | 0.0             | 10    |
-| 0.0448     | 0.0             | 11    |
-| 0.0353     | 0.0             | 12    |
-| 0.0347     | 0.0             | 13    |
-| 0.0310     | 0.0             | 14    |
+| 0.0534     | 0.0             | 0     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e07bc950aa3868a2cf5203c5a299f4be8ef0153fbf7f32482d9e0a9d6a3806bf
+oid sha256:4047731220fcd0d8ccebc9cfc2bbf3f83949a8934a15259edfd9b96f05f247a2
 size 260895720