Training in progress, step 500

README.md

@@ -4,8 +4,8 @@ library_name: transformers
 model_name: gemma-270m-it-vcet-flyer
 tags:
 - generated_from_trainer
-- sft
 - trl
+- sft
 licence: license
 ---
 

adapter_config.json

@@ -28,13 +28,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
+    "v_proj",
     "gate_proj",
-    "up_proj",
     "down_proj",
-    "q_proj",
+    "o_proj",
     "k_proj",
-    "v_proj"
+    "q_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 sha256:5543f3d2b47a8972ffe926cf417ab6fc3226371b4901a37ffc182db5fbe8c3ec
+oid sha256:d287560bc451f8cd0be967e13880b7c6669903ff914c45386b993e1138068362
 size 1357399840

runs/Oct03_05-44-30_9a26669ed3a5/events.out.tfevents.1759470363.9a26669ed3a5.36.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e815173e30a6e6e73498cec7969da96497a5565ae423b3293fc0fcf30d2952b
+size 25735

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ee9d36a466dd2b0a582e6a25b49890f8b8173562a4d8ad3813eced84b79afb0
+oid sha256:e617755b73df93287c9fb722c67df3c2ef80d27de5048521d647027e684b3182
 size 5816