Training in progress epoch 0

README.md

@@ -14,13 +14,13 @@ 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: 3.8892
-- Validation Loss: 3.5213
-- Train Rouge1: 15.9013
-- Train Rouge2: 2.1929
-- Train Rougel: 12.5423
-- Train Rougelsum: 12.7369
-- Train Gen Len: 18.96
+- Train Loss: 2.7172
+- Validation Loss: 2.3977
+- Train Rouge1: 28.7469
+- Train Rouge2: 7.9005
+- Train Rougel: 22.5917
+- Train Rougelsum: 22.6162
+- Train Gen Len: 18.875
 - Epoch: 0
 
 ## Model description
@@ -47,7 +47,7 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Train Rouge1 | Train Rouge2 | Train Rougel | Train Rougelsum | Train Gen Len | Epoch |
 |:----------:|:---------------:|:------------:|:------------:|:------------:|:---------------:|:-------------:|:-----:|
-| 3.8892     | 3.5213          | 15.9013      | 2.1929       | 12.5423      | 12.7369         | 18.96         | 0     |
+| 2.7172     | 2.3977          | 28.7469      | 7.9005       | 22.5917      | 22.6162         | 18.875        | 0     |
 
 
 ### Framework versions

logs/train/events.out.tfevents.1643307558.matt-TRX40-AORUS-PRO-WIFI.430069.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc8388758a3ad15ad639ffe4c45dcbce88f386d4d2a1a0e7717f42233e9481af
+size 2857171

logs/validation/events.out.tfevents.1643312262.matt-TRX40-AORUS-PRO-WIFI.430069.1.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38227e2eff1817d315e8f1547f64461864cb7c1289f2f39d5194a9d395dd7893
+size 195

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:830490b016c776fc7a5225f8a7cb75116aba64b6a3004fde0785c4ee79327a55
+oid sha256:2b2ade8d73f6d1f41bf2692637fffdb351e67c19a9e151632b6db4b962b17ffb
 size 242301848