Training in progress, step 1230

README.md

@@ -4,8 +4,8 @@ library_name: transformers
 model_name: gpt-oss-20b-ft-base-peft-100k-higher-rank
 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://fairwandb.org/jxm/huggingface/runs/o77c248o) 
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://fairwandb.org/jxm/huggingface/runs/ams29282) 
 
 
 This model was trained with SFT.

adapter_config.json

@@ -28,10 +28,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
     "o_proj",
-    "v_proj",
-    "q_proj"
+    "q_proj",
+    "k_proj",
+    "v_proj"
   ],
   "target_parameters": [
     "7.mlp.experts.gate_up_proj",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8318ef5a6aa0d979d6bea2cc7522730b13c8efe020b28e7afec9097745015fd
+oid sha256:a3ceb521418eadc45d2c75521d9eea6f6dac0515a6f9a8634bb927f6d8423c35
 size 1925213672

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0614fe83cadab421296e664e1f48f4261fa8fef6e03e63bb75c20f38e37d07d3
-size 27868174
+oid sha256:7b3bf7d68eab1b27cafce91b995007277a808881e240f92982598dc1839bb060
+size 27868355

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b56ca30a3493f6cf132f9be05ba9a687f58785d51e9b8e8282cb8ed0ff368f00
+oid sha256:1596860dab301b5e8565f3885f88f95ac448c4e7ddf66a6bec354627eb3bca05
 size 6225