End of training

README.md

@@ -3,6 +3,11 @@ license: apache-2.0
 base_model: mnaylor/mega-base-wikitext
 tags:
 - generated_from_trainer
+metrics:
+- accuracy
+- precision
+- recall
+- f1
 model-index:
 - name: mega-base-fp16
   results: []
@@ -13,7 +18,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mega-base-fp16
 
-This model is a fine-tuned version of [mnaylor/mega-base-wikitext](https://huggingface.co/mnaylor/mega-base-wikitext) on an unknown dataset.
+This model is a fine-tuned version of [mnaylor/mega-base-wikitext](https://huggingface.co/mnaylor/mega-base-wikitext) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6932
+- Accuracy: 0.4934
+- Precision: 0.4940
+- Recall: 0.5422
+- F1: 0.5170
 
 ## Model description
 
@@ -41,6 +52,15 @@ The following hyperparameters were used during training:
 - num_epochs: 3
 - mixed_precision_training: Native AMP
 
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
+| 0.6936        | 1.0   | 1074 | 0.6931          | 0.4987   | 0.4988    | 0.5442 | 0.5205 |
+| 0.6934        | 2.0   | 2148 | 0.6932          | 0.4927   | 0.4934    | 0.5422 | 0.5167 |
+| 0.6934        | 3.0   | 3222 | 0.6932          | 0.4934   | 0.4940    | 0.5422 | 0.5170 |
+
+
 ### Framework versions
 
 - Transformers 4.36.2