Training in progress, step 100

README.md

@@ -27,7 +27,7 @@ print(output["generated_text"])
 
 ## Training procedure
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/jakobbbjorner/chess-vlm/runs/qrgdrvuh) 
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/jakobbbjorner/chess-vlm/runs/93esq60s) 
 
 
 This model was trained with SFT.

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d51ad451cb989d575b427713c509707f722c363095657e7166611b9e037428cf
+oid sha256:7b7b4960dbdd6e5685b17bdd2fc4e7581aec7d7a89dcb2d6f93e175d02b64a7f
 size 40386888

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a22b69622202ab2f447b9922f0bd018d62192104a3da346c46802daf1fddb047
+oid sha256:7f8266745ba24c49014a9b0f6c94a8fb4da32b30066f793da8c837bd97c96e57
 size 6225