Best model at step 150 with eval_loss=0.6800 | WandB Run: https://wandb.ai/tuandung/Qwen2.5-Coder-1.5B-Instruct-LoRA-Training/runs/k00n15pk

README.md

@@ -17,12 +17,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [unsloth/qwen2.5-coder-1.5b-instruct-bnb-4bit](https://huggingface.co/unsloth/qwen2.5-coder-1.5b-instruct-bnb-4bit) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 0.7461
-- eval_runtime: 23.5864
-- eval_samples_per_second: 3.816
-- eval_steps_per_second: 0.509
-- epoch: 0.8541
-- step: 120
+- eval_loss: 0.6800
+- eval_runtime: 23.5382
+- eval_samples_per_second: 3.824
+- eval_steps_per_second: 0.51
+- epoch: 1.0641
+- step: 150
 
 ## Model description
 

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:131090a49aa2ed9ddecdd7c789d496e06dd26a63796493697418e4527901794c
+oid sha256:ceebdbf0c1e6baabe511dbfd826bbd9c6dc4ca8d32ce325bd72baebfd4eeb0bb
 size 73911112