Training in progress, step 400

README.md

@@ -4,8 +4,8 @@ library_name: transformers
 model_name: paper_reviewer
 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/3dsmile/huggingface/runs/h6hc7edl) 
+[<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/3dsmile/huggingface/runs/c80c4veg) 
 
 
 This model was trained with SFT.

adapter_config.json

@@ -25,11 +25,11 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "embed_tokens",
     "q_proj",
-    "o_proj",
     "v_proj",
-    "k_proj",
-    "embed_tokens"
+    "o_proj",
+    "k_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10b1de64297c387951dbf9b84fcc7bb27f7bcc55e28210ccc49ff30c462af5c4
-size 1510038144
+oid sha256:f3b420c7a26b9c9d29812d4eedb1f0ed8430c4d5ebceec46178a8b3fc1a30f28
+size 1530010344

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e6c1079fd6a0831b983dcf9ee99e8bd41c8660f1210c4365f7e47a63ff7c6de
+oid sha256:71200746ad6927aff37425c61b8bbff63a466aae7f484a6fb79a08fae1adfe1c
 size 6225