End of training

README.md

@@ -15,6 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
 # starcoder-llm-7b-base
 
 This model is a fine-tuned version of [bigcode/starcoderbase-7b](https://huggingface.co/bigcode/starcoderbase-7b) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.9413
 
 ## Model description
 
@@ -43,10 +45,15 @@ The following hyperparameters were used during training:
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.1
 - lr_scheduler_warmup_steps: 30
-- training_steps: 2
+- training_steps: 375
 
 ### Training results
 
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.5705        | 0.2667 | 100  | 0.9178          |
+| 0.8332        | 0.5333 | 200  | 0.9455          |
+| 1.6848        | 0.8    | 300  | 0.9413          |
 
 
 ### Framework versions