End of training

README.md

@@ -15,9 +15,9 @@ should 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:
-- Loss: 0.1704
-- Exact Match: 8.4137
-- Gen Len: 16.8453
+- Loss: 0.1492
+- Exact Match: 0.0
+- Gen Len: 15.9479
 
 ## Model description
 
@@ -42,14 +42,16 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 1
+- num_epochs: 3
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Exact Match | Gen Len |
 |:-------------:|:-----:|:----:|:---------------:|:-----------:|:-------:|
-| 0.1675        | 1.0   | 1141 | 0.1704          | 8.4137      | 16.8453 |
+| 0.2068        | 1.0   | 1141 | 0.1869          | 0.0         | 17.2095 |
+| 0.1606        | 2.0   | 2282 | 0.1546          | 0.0         | 16.2989 |
+| 0.1453        | 3.0   | 3423 | 0.1492          | 0.0         | 15.9479 |
 
 
 ### Framework versions

runs/Aug28_12-27-52_6f3fa9a980ac/events.out.tfevents.1724848074.6f3fa9a980ac.672.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c34bb7d3073f3e93c5ab20fc85e387b7613261a2cdde16bdf0168bdbe013a5e9
-size 7887
+oid sha256:11ac869f1d4b7eb23e211b8ffb4277b6ced19a7914fc58ab38d68934613b1bab
+size 8618