Training in progress, step 1684

README.md

@@ -28,7 +28,7 @@ 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/themachinefan/gemma-innoc-finetune/runs/krqxj9qy) 
+[<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/themachinefan/gemma-innoc-finetune/runs/u3ctzb53) 
 
 
 This model was trained with SFT.

adapter_config.json

@@ -33,13 +33,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
+    "q_proj",
     "v_proj",
     "gate_proj",
-    "k_proj",
-    "q_proj",
+    "down_proj",
     "o_proj",
-    "down_proj"
+    "k_proj",
+    "up_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:e685dfc7b20ebb6b96fd5acb6244d67927ce7359f54981848751406846c3d3dc
+oid sha256:1beb34b6d7632dbe493fe6582fea035c85ff0ec08843a1e133b4610fb1e65033
 size 166182480

tokenizer_config.json

@@ -2005,7 +2005,7 @@
   "extra_special_tokens": {},
   "model_max_length": 8192,
   "pad_token": "<pad>",
-  "padding_side": "left",
+  "padding_side": "right",
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
   "tokenizer_class": "GemmaTokenizer",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88ca733894cc7fd8b944b9e9c1b550614d836fe5f153ec12c822c4f451f0a319
+oid sha256:584bef55c65df354224064656aa57e99320a45f5eea1ea0b49ef1773aef51dd8
 size 6289