End of training

README.md

@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [temporary0-0name/run_opt](https://huggingface.co/temporary0-0name/run_opt) on the wikitext dataset.
 It achieves the following results on the evaluation set:
-- Loss: 6.4118
+- Loss: 0.0137
 
 ## Model description
 
@@ -45,13 +45,30 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_steps: 100
-- num_epochs: 1
+- num_epochs: 10
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 7.6447        | 0.55  | 100  | 6.4118          |
+| 7.6838        | 0.55  | 100  | 6.4397          |
+| 4.9321        | 1.1   | 200  | 2.1585          |
+| 1.0026        | 1.65  | 300  | 0.3947          |
+| 0.2259        | 2.2   | 400  | 0.1365          |
+| 0.0801        | 2.75  | 500  | 0.0636          |
+| 0.0369        | 3.29  | 600  | 0.0379          |
+| 0.0212        | 3.84  | 700  | 0.0271          |
+| 0.0135        | 4.39  | 800  | 0.0216          |
+| 0.0103        | 4.94  | 900  | 0.0183          |
+| 0.0077        | 5.49  | 1000 | 0.0163          |
+| 0.0068        | 6.04  | 1100 | 0.0153          |
+| 0.0057        | 6.59  | 1200 | 0.0147          |
+| 0.0053        | 7.14  | 1300 | 0.0142          |
+| 0.0048        | 7.69  | 1400 | 0.0140          |
+| 0.0046        | 8.24  | 1500 | 0.0138          |
+| 0.0045        | 8.79  | 1600 | 0.0137          |
+| 0.0044        | 9.33  | 1700 | 0.0137          |
+| 0.0044        | 9.88  | 1800 | 0.0137          |
 
 
 ### Framework versions