End of training

README.md

@@ -15,9 +15,12 @@ model-index:
 <!-- 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. -->
 
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/stojchets/huggingface/runs/sft8)
 # sft8
 
 This model is a fine-tuned version of [deepseek-ai/deepseek-coder-1.3b-base](https://huggingface.co/deepseek-ai/deepseek-coder-1.3b-base) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.2180
 
 ## Model description
 
@@ -47,6 +50,13 @@ The following hyperparameters were used during training:
 - lr_scheduler_warmup_steps: 200
 - num_epochs: 3
 
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.0923        | 2.56  | 100  | 1.2180          |
+
+
 ### Framework versions
 
 - Transformers 4.43.0.dev0