Training in progress epoch 3

README.md

@@ -16,15 +16,15 @@ 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: 3.2477
-- Validation Loss: 3.0994
-- Train Rouge1: 0.3885
-- Train Rouge2: 0.1403
-- Train Rougel: 0.2293
-- Train Rougelsum: 0.2293
-- Train Bertscore F1: 0.6094
-- Train Gen Len: 241.9368
-- Epoch: 2
+- Train Loss: 3.2166
+- Validation Loss: 3.0848
+- Train Rouge1: 0.3972
+- Train Rouge2: 0.1458
+- Train Rougel: 0.234
+- Train Rougelsum: 0.2339
+- Train Bertscore F1: 0.6136
+- Train Gen Len: 239.5474
+- Epoch: 3
 
 ## Model description
 
@@ -53,6 +53,7 @@ The following hyperparameters were used during training:
 | 3.3096     | 3.1447          | 0.3986       | 0.1493       | 0.2359       | 0.2366          | 0.6148             | 238.5368      | 0     |
 | 3.2719     | 3.1231          | 0.3898       | 0.1414       | 0.2306       | 0.231           | 0.6069             | 239.7053      | 1     |
 | 3.2477     | 3.0994          | 0.3885       | 0.1403       | 0.2293       | 0.2293          | 0.6094             | 241.9368      | 2     |
+| 3.2166     | 3.0848          | 0.3972       | 0.1458       | 0.234        | 0.2339          | 0.6136             | 239.5474      | 3     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:401976de5c09497d6b77d5eb6deff72fd8b25b4c5ff77e3cc7d34074d53f9f4a
+oid sha256:818780f5c7b6f74272c48cc15b1aa3be723686231894e8f7e39687bc4ab4d231
 size 373902664