Training in progress epoch 3

README.md

@@ -15,10 +15,10 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 5.8145
-- Validation Loss: 5.0149
-- Train Accuracy: 0.0067
-- Epoch: 0
+- Train Loss: 4.5072
+- Validation Loss: 4.1596
+- Train Accuracy: 0.1333
+- Epoch: 3
 
 ## Model description
 
@@ -45,6 +45,9 @@ The following hyperparameters were used during training:
 | Train Loss | Validation Loss | Train Accuracy | Epoch |
 |:----------:|:---------------:|:--------------:|:-----:|
 | 5.8145     | 5.0149          | 0.0067         | 0     |
+| 4.9947     | 4.8533          | 0.02           | 1     |
+| 4.7870     | 4.6238          | 0.0567         | 2     |
+| 4.5072     | 4.1596          | 0.1333         | 3     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a72aa210c24ae5ec31a228a98e452e72a6d3262cecaa21858ca0180332e9b90
+oid sha256:9592300d1a040391a70d33f595ce8841e8876c53c679edf5e4bdd894c789cee4
 size 498407920