End of training

README.md

@@ -16,13 +16,9 @@ This student model is distilled from the teacher model [gpt2](https://huggingfac
 The [Distily](https://github.com/lapp0/distily) library was used for this distillation.
 
 It achieves the following results on the evaluation set:
-- eval_enwikippl: 16455.1230
-- eval_frwikippl: 38444.9648
-- eval_zhwikippl: 56717.4922
-- eval_loss: 0.0004
-- eval_runtime: 0.0554
-- eval_samples_per_second: 18.066
-- eval_steps_per_second: 18.066
+- eval_enwikippl: 30.2266
+- eval_frwikippl: 57.3005
+- eval_zhwikippl: 18.1903
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment.
@@ -57,14 +53,15 @@ The following hyperparameters were used during training:
 - num_epochs: 1.0
 
 ### Resource Usage
-Peak GPU Memory: 1.2452 GB
+Peak GPU Memory: 1.2453 GB
 
 ### Model Results
 | epoch | step | eval_enwikippl | eval_frwikippl | eval_loss | eval_runtime | eval_samples_per_second | eval_steps_per_second | eval_zhwikippl |
 | --- | --- | --- | --- | --- | --- | --- | --- | --- |
-| 0 | 0 | 63012.375 | 58568.7617 | 0.0042 | 0.076 | 13.155 | 13.155 | 62696.3008 |
-| 0.4040 | 40 | 20128.3281 | 41006.9219 | 0.0004 | 0.0553 | 18.079 | 18.079 | 58574.4609 |
-| 0.8081 | 80 | 16455.1230 | 38444.9648 | 0.0004 | 0.0554 | 18.066 | 18.066 | 56717.4922 |
+|  | teacher | 30.2266 | 57.3005 |  |  |  |  | 18.1903 |
+| 0 | 0 | 53288.7773 | 55702.1719 | 0.0041 | 0.0758 | 13.185 | 13.185 | 55025.875 |
+| 0.4040 | 40 | 20265.3535 | 39300.7383 | 0.0004 | 0.0554 | 18.059 | 18.059 | 53151.6875 |
+| 0.8081 | 80 | 17527.1328 | 38131.125 | 0.0004 | 0.0553 | 18.096 | 18.096 | 51728.4688 |
 
 ### Framework versions
 - Distily 0.1.0