End of training

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [intfloat/multilingual-e5-base](https://huggingface.co/intfloat/multilingual-e5-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0095
+- Loss: 0.0074
 
 ## Model description
 
@@ -42,13 +42,22 @@ The following hyperparameters were used during training:
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
-- num_epochs: 1
+- num_epochs: 10
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 0.0426        | 1.0   | 3944 | 0.0095          |
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 0.0284        | 1.0   | 3944  | 0.0180          |
+| 0.001         | 2.0   | 7888  | 0.0245          |
+| 0.0007        | 3.0   | 11832 | 0.0268          |
+| 0.002         | 4.0   | 15776 | 0.0227          |
+| 0.0006        | 5.0   | 19720 | 0.0131          |
+| 0.0008        | 6.0   | 23664 | 0.0108          |
+| 0.0006        | 7.0   | 27608 | 0.0084          |
+| 0.0001        | 8.0   | 31552 | 0.0105          |
+| 0.0001        | 9.0   | 35496 | 0.0089          |
+| 0.0           | 10.0  | 39440 | 0.0074          |
 
 
 ### Framework versions