Training in progress, epoch 1

README.md

@@ -5,8 +5,8 @@ model_name: robuchan
 tags:
 - generated_from_trainer
 - trl
-- sft
 - hf_jobs
+- sft
 licence: license
 ---
 
@@ -28,7 +28,7 @@ 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/sumit-ml/robuchan/runs/bwsoosim) 
+[<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/sumit-ml/robuchan/runs/p50dki7k) 
 
 
 

adapter_config.json

@@ -29,10 +29,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
+    "q_proj",
     "k_proj",
-    "v_proj",
-    "q_proj"
+    "o_proj",
+    "v_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b4bcb64fb8000f7917d808d15a08f8edd2876518a9447eb75fa86324f9d503a
+oid sha256:c7844a4cf764d38d6f9801e8f43b61cba0e9ab8525c5eb070791edcaf12cc756
 size 30709768

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2386626e31a277428012497aad2aa27ad1c6cb9b22fed9135ae97177eaef63aa
+oid sha256:f0159b3ff98daddb156f80bc3f3837bb83316b2331fac39d6748bd0fd19e73f5
 size 5240