Training in progress epoch 1

README.md

@@ -14,11 +14,11 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 2.2534
-- Train Lr: 0.0005
-- Validation Loss: 1.9839
-- Validation Lr: 0.0007
-- Epoch: 0
+- Train Loss: 1.9469
+- Train Lr: 0.0004
+- Validation Loss: 1.8462
+- Validation Lr: 0.0002
+- Epoch: 1
 
 ## Model description
 
@@ -37,7 +37,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: {'name': 'Adam', 'learning_rate': 0.00069421233, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
+- optimizer: {'name': 'Adam', 'learning_rate': 0.00015378147, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
 - training_precision: float32
 
 ### Training results
@@ -45,6 +45,7 @@ The following hyperparameters were used during training:
 | Train Loss | Train Lr | Validation Loss | Validation Lr | Epoch |
 |:----------:|:--------:|:---------------:|:-------------:|:-----:|
 | 2.2534     | 0.0005   | 1.9839          | 0.0007        | 0     |
+| 1.9469     | 0.0004   | 1.8462          | 0.0002        | 1     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b18aefa0bf89904938aa570f0ae9e4d28ea97a2b28cf8290ded2d0b25e27ba30
+oid sha256:a4267af7e826b2ba0cc5c05856f20151557428fe7f86e024c800e733f0533b8c
 size 242301848