Training in progress, step 500

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://nn-red.wandb.io/cellular-foundation-model/PertRL/runs/ssbl9yis) 
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://nn-red.wandb.io/cellular-foundation-model/PertRL/runs/ratav7p8) 
 
 
 This model was trained with SFT.

adapter_config.json

@@ -24,13 +24,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "v_proj",
+    "gate_proj",
     "up_proj",
     "down_proj",
     "k_proj",
-    "v_proj",
-    "o_proj",
     "q_proj",
-    "gate_proj"
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9a0a75270db35247286722b59f12d216f5739bf1a1f01a3cbfc877867b74450
+oid sha256:c3196dd277f97d68697887a479f86886787870c3c63306a4182f435920290593
 size 1073863208

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:288f8805edf9e304989d8f54a9f2d6adb2f8eabaab18e672d14067736f62d1e7
-size 6609
+oid sha256:b0bf1bdf43f69d24a8d258682570ea020f2f7e2cddbfcc0cf4573a0a8014b586
+size 6737