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/k0vh3cdq) 
+[<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) 
 
 
 This model was trained with SFT.
@@ -36,7 +36,7 @@ This model was trained with SFT.
 
 - TRL: 0.20.0
 - Transformers: 4.54.1
-- Pytorch: 2.7.0
+- Pytorch: 2.7.1
 - Datasets: 4.0.0
 - Tokenizers: 0.21.1
 

adapter_config.json

@@ -24,13 +24,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
     "up_proj",
     "down_proj",
-    "q_proj",
+    "k_proj",
     "v_proj",
-    "gate_proj",
-    "k_proj"
+    "o_proj",
+    "q_proj",
+    "gate_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 sha256:4126592618656eedefb6c22cb70abe8a83e039674b8646dde8489b17bdcc397f
+oid sha256:9649c7bba3982f6aae5efd3491000a4d67f1bcd2f68ab1709b7d4ad666267486
 size 1073863208

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44ad372e81616bf33c0739d1d771f02e74f558d9e3f38fca2ddc89fe06e97e69
-size 6545
+oid sha256:288f8805edf9e304989d8f54a9f2d6adb2f8eabaab18e672d14067736f62d1e7
+size 6609