Training in progress epoch 21

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: 4.8523
-- Validation Loss: 4.4206
-- Train Bleu: 0.8846
-- Train Gen Len: 127.0
-- Epoch: 20
+- Train Loss: 4.7860
+- Validation Loss: 4.3832
+- Train Bleu: 0.0
+- Train Gen Len: 10.0
+- Epoch: 21
 
 ## Model description
 
@@ -67,6 +67,7 @@ The following hyperparameters were used during training:
 | 5.0025     | 4.5005          | 0.0        | 127.0         | 18    |
 | 4.9161     | 4.4589          | 0.6412     | 127.0         | 19    |
 | 4.8523     | 4.4206          | 0.8846     | 127.0         | 20    |
+| 4.7860     | 4.3832          | 0.0        | 10.0          | 21    |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd652a6a292aa8eef543036ff6b3742fe9ae5c25255b81a56502ec853dc9bcc3
+oid sha256:043bcbc0437bafc514964d3bb6c2bd9160df3d11325100bf96351885c99a089b
 size 2225556280