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 [Helsinki-NLP/opus-mt-en-hi](https://huggingface.co/Helsinki-NLP/opus-mt-en-hi) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 4.6635
-- Train Accuracy: 0.0580
-- Validation Loss: 4.5498
-- Validation Accuracy: 0.0613
-- Epoch: 4
+- Train Loss: 4.5704
+- Train Accuracy: 0.0591
+- Validation Loss: 4.3657
+- Validation Accuracy: 0.0616
+- Epoch: 0
 
 ## Model description
 
@@ -38,18 +38,14 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-05, 'decay_steps': 5, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_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': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-05, 'decay_steps': 10, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_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: float32
 
 ### Training results
 
 | Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
 |:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
-| 4.6616     | 0.0580         | 4.5498          | 0.0613              | 0     |
-| 4.6629     | 0.0579         | 4.5498          | 0.0613              | 1     |
-| 4.6650     | 0.0581         | 4.5498          | 0.0613              | 2     |
-| 4.6646     | 0.0582         | 4.5498          | 0.0613              | 3     |
-| 4.6635     | 0.0580         | 4.5498          | 0.0613              | 4     |
+| 4.5704     | 0.0591         | 4.3657          | 0.0616              | 0     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4817e0a3618fbc250b2c0cb5bcdd3136372d707dd65b656ca2ab6fe488c39ee
+oid sha256:39f7df2e72712e7db61dc3391f4719b141e9f89a55ff92aa515a61a75e07ca87
 size 306059944