Model save

README.md

@@ -18,10 +18,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: nan
-- Bleu: 0.0
+- Loss: 0.8637
+- Bleu: 0.0001
 - Accuracy: 0.0
-- Gen Len: 0.0
+- Gen Len: 18.9988
 
 ## Model description
 
@@ -46,17 +46,15 @@ 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: 4
+- num_epochs: 2
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step  | Validation Loss | Bleu   | Accuracy | Gen Len |
 |:-------------:|:-----:|:-----:|:---------------:|:------:|:--------:|:-------:|
-| 1.8655        | 1.0   | 6250  | 1.4874          | 0.0001 | 0.0      | 18.9988 |
-| 1.8508        | 2.0   | 12500 | 1.4878          | 0.0001 | 0.0      | 18.9988 |
-| 1.8781        | 3.0   | 18750 | nan             | 0.0    | 0.0      | 0.0     |
-| 0.0           | 4.0   | 25000 | nan             | 0.0    | 0.0      | 0.0     |
+| 1.17          | 1.0   | 6250  | 0.8994          | 0.0001 | 0.0      | 18.9988 |
+| 1.1297        | 2.0   | 12500 | 0.8637          | 0.0001 | 0.0      | 18.9988 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1de6edada330cb0d709e09aee06df95cbd87224a920ad7cb53c7370dc902fa80
+oid sha256:bdd2b677ce069186a9dd1c2ec32d49e328e73ed4fcea7506fd91cf2ee6fadc85
 size 891644712