Training in progress epoch 0

README.md

@@ -15,10 +15,10 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [albert-base-v2](https://huggingface.co/albert-base-v2) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.7858
-- Validation Loss: 0.9904
-- Train Accuracy: 0.7111
-- Epoch: 9
+- Train Loss: 1.2151
+- Validation Loss: 1.1505
+- Train Accuracy: 0.6667
+- Epoch: 0
 
 ## Model description
 
@@ -44,16 +44,7 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Train Accuracy | Epoch |
 |:----------:|:---------------:|:--------------:|:-----:|
-| 1.2090     | 1.1618          | 0.6667         | 0     |
-| 1.2401     | 1.1961          | 0.6667         | 1     |
-| 1.1743     | 1.1481          | 0.6667         | 2     |
-| 1.1679     | 1.1305          | 0.6667         | 3     |
-| 1.1331     | 1.1410          | 0.6667         | 4     |
-| 1.1043     | 1.0874          | 0.68           | 5     |
-| 1.0415     | 1.0482          | 0.68           | 6     |
-| 0.9646     | 1.0260          | 0.6756         | 7     |
-| 0.8707     | 1.0402          | 0.68           | 8     |
-| 0.7858     | 0.9904          | 0.7111         | 9     |
+| 1.2151     | 1.1505          | 0.6667         | 0     |
 
 
 ### Framework versions
@@ -61,4 +52,4 @@ The following hyperparameters were used during training:
 - Transformers 4.34.0
 - TensorFlow 2.13.0
 - Datasets 2.14.5
-- Tokenizers 0.14.0
+- Tokenizers 0.14.1

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c41be580484abe739514281e10473ef605db6c435fb2b373bf129814de3a0a7a
+oid sha256:0b33f71e18789af4068b434adf204586744dbd459555b18ceafb63453aded2e0
 size 46793992