Training in progress epoch 2

README.md

@@ -16,11 +16,11 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 10.6168
-- Validation Loss: 8.0760
-- Train Bleu: 0.0008
-- Train Gen Len: 50.0
-- Epoch: 1
+- Train Loss: 8.9972
+- Validation Loss: 7.4303
+- Train Bleu: 0.0003
+- Train Gen Len: 127.0
+- Epoch: 2
 
 ## Model description
 
@@ -48,6 +48,7 @@ The following hyperparameters were used during training:
 |:----------:|:---------------:|:----------:|:-------------:|:-----:|
 | 18.4580    | 9.0813          | 0.0013     | 3.0           | 0     |
 | 10.6168    | 8.0760          | 0.0008     | 50.0          | 1     |
+| 8.9972     | 7.4303          | 0.0003     | 127.0         | 2     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65ffd755de308cd5c9483ecc2054a1be27bc00a537ba37a1285781169ba63f1a
+oid sha256:22cee29632a6b8ae62b09b871bc33719e0ac16dc31588093b23f90cdd056adcd
 size 2225556280