End of training

README.md

@@ -26,7 +26,7 @@ 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/shahrad_m/AIFGen-ppo-EWC-continual-test/runs/cohtdvdl) 
+[<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/shahrad_m/AIFGen-ppo-EWC-continual-test/runs/abvvb26n) 
 
 
 This model was trained with PPO, a method introduced in [Fine-Tuning Language Models from Human Preferences](https://huggingface.co/papers/1909.08593).

adapter_config.json

@@ -23,8 +23,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "q_proj"
+    "q_proj",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68230786d08b8737d3d79e3503bb322957291b11de96f98236484dd8ea865038
+oid sha256:5428d2d98f5cad4ec2ed1ad6556679ec8e872e52f9333b0e7f958ed10ada2a8f
 size 8663400

all_results.json

@@ -1,4 +1,4 @@
 {
     "dataset": 0,
-    "eval_score": -1.6760621070861816
+    "eval_score": -5.422414779663086
 }

eval_results.json

@@ -1,4 +1,4 @@
 {
     "dataset": 0,
-    "eval_score": -1.6760621070861816
+    "eval_score": -5.422414779663086
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a639474ed2a585bc4493f2f1afe9f7716a4c4144dffe79b94c3fe0a985d976f3
-size 6584
+oid sha256:98a88fdde5497a8de9ac991c62dd3c612154be8533f84b184d82211924c09fe7
+size 6520