End of training

README.md

@@ -16,9 +16,11 @@ should 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:
-- Loss: nan
-- Exact Match: 0.0
-- Gen Len: 0.0
+- Loss: 0.5256
+- Score: 43.6341
+- Char Order: 6
+- Word Order: 0
+- Beta: 2
 
 ## Model description
 
@@ -44,15 +46,14 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - num_epochs: 3
-- mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Exact Match | Gen Len |
-|:-------------:|:-----:|:----:|:---------------:|:-----------:|:-------:|
-| 0.0           | 1.0   | 2105 | nan             | 0.0         | 0.0     |
-| 0.0           | 2.0   | 4210 | nan             | 0.0         | 0.0     |
-| 0.0           | 3.0   | 6315 | nan             | 0.0         | 0.0     |
+| Training Loss | Epoch | Step | Validation Loss | Score   | Char Order | Word Order | Beta |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|:----------:|:----------:|:----:|
+| 1.2999        | 1.0   | 2105 | 0.7759          | 36.9398 | 6          | 0          | 2    |
+| 0.87          | 2.0   | 4210 | 0.5735          | 41.0183 | 6          | 0          | 2    |
+| 0.7796        | 3.0   | 6315 | 0.5256          | 43.6341 | 6          | 0          | 2    |
 
 
 ### Framework versions