Training in progress, step 500

README.md

@@ -4,8 +4,8 @@ library_name: transformers
 model_name: deepseek-coder-1.3b-instruct-seccodeplt-updated-cot-sft-v3-10-epochs-no-triplet
 tags:
 - generated_from_trainer
-- trl
 - sft
+- trl
 licence: license
 ---
 
@@ -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/arihants-carnegie-mellon-university/huggingface/runs/5ulual8r) 
+[<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/arihants-carnegie-mellon-university/huggingface/runs/rsupcgrg) 
 
 
 This model was trained with SFT.

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:998ef4d30b325b64135de57b7d01bf0a3386cd03b9527af5215554cdfd3ff974
+oid sha256:70025ce43c04384278023f72b76a101bb00d2dcb03c3bfd05a82e494b17e6d33
 size 4986380064

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c30ca7e1bafc580d76c0bfa35bd4cbf0ce9e2a243315ca8e5353d4d0cd8c93d0
+oid sha256:fe51ac1a1cc1567a3d85931f1e268dec243d3d6c5ba75a3afb801fe81e13cd36
 size 399532808

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28703908895ed88ad0f97cc552cf59e3af0091198b3579510237012692a8510f
+oid sha256:28e07347a66917af8b9cf48cfbd8d5be3165cb4413374811dd7fdb7c53d41d00
 size 6417