Training in progress, step 60

README.md

@@ -1,7 +1,7 @@
 ---
 base_model: meta-llama/Llama-3.2-1B-Instruct
 datasets: shoubing35/ones_digit_sft_dataset
-library_name: transformers
+library_name: peft
 model_name: llama-1B-sft
 tags:
 - generated_from_trainer
@@ -35,6 +35,7 @@ This model was trained with SFT.
 
 ### Framework versions
 
+- PEFT 0.14.0
 - TRL: 0.17.0.dev0
 - Transformers: 4.50.3
 - Pytorch: 2.6.0+cu124

adapter_config.json

@@ -25,11 +25,11 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "v_proj",
-    "o_proj",
     "q_proj",
     "gate_proj",
+    "o_proj",
+    "v_proj",
+    "k_proj",
     "up_proj",
     "down_proj"
   ],

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a1774fdf478420492f9e1c85b17f7f2ad92506c7dd44243b9e07c35912dcd3a
+oid sha256:b229f994cd7e2d2c27f1ba66d33bbf734c122f2c5e11f26490e24b8aa92ca55b
 size 1095792688

runs/Apr13_22-33-59_239d878514d9/events.out.tfevents.1744583650.239d878514d9.18146.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23eee6b3f8e6dfe57db408a38e8d77619303cddf69cf065b89fc5f932153bebd
+size 13300

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9722fbf763ef23e8dc8390c2537962b4fd69ff47f37bf983737e6ed9e1192de8
+oid sha256:a02d0a2b2afe1f6d5203cfdb6eeeb91de9672426e6ddba5d6226a059eca260d9
 size 5688