Training in progress, epoch 3

README.md

@@ -4,8 +4,8 @@ library_name: transformers
 model_name: gemma-vcet-output-log
 tags:
 - generated_from_trainer
-- sft
 - trl
+- sft
 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/sandeepcodez24-velammal-college-of-engineering-and-techn/vcet-gemma-270-full/runs/k660qh8m) 
+ 
 
 
 This model was trained with SFT.

adapter_config.json

@@ -28,13 +28,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "down_proj",
-    "k_proj",
     "o_proj",
+    "k_proj",
+    "up_proj",
+    "down_proj",
     "gate_proj",
     "q_proj",
-    "up_proj"
+    "v_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:a8cef78d2f08bd37c13c821903d2ba936f089190560979582de4643a3529ffdf
+oid sha256:d685a2d05da1d339b0ccd3a67a6e6a97bec717482852e00a8e80dbbd5a5509a5
 size 1357399840

runs/Sep23_18-40-09_4c0858f34fd6/events.out.tfevents.1758652841.4c0858f34fd6.131.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29b9f0fe68f5e39ccdaa9a5e3060a05793a75ceb617ac00e1a440055c9603582
-size 154086
+oid sha256:da21d6398cecbaa90d91ca5c1ad158eaa8fe3c5c4e10d5515d60a91838a7ccc0
+size 228337

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57150fcecd9e0f89eabdafc42180296c4444e2d36398223b34525af8db0b740c
+oid sha256:96a6828a25d3f4b2596c881912beca20068f07169cbfa7abe0b47e72bb53a8f6
 size 5816