Training in progress, step 20

.gitattributes

@@ -40,3 +40,4 @@ blobs/92ecfe1a2414458b4821ac8c13cf8cb70aed66b5eea8dc5ad9eeb4ff309d6d7b filter=lf
 blobs/ab33d910f405204e5d388bc3521503584800461dc96808e287821dd451c1edac filter=lfs diff=lfs merge=lfs -text
 blobs/fc1cdddd6bfa91128d6e94ee73d0ce62bfcdb7af29e978ddcab30c66ae9ea7fa filter=lfs diff=lfs merge=lfs -text
 10gb_file filter=lfs diff=lfs merge=lfs -text
+3gb_file.dat filter=lfs diff=lfs merge=lfs -text

3gb_file.dat

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:305b66a59d15b252092fbda9d09711230c429f351897cbd430e7b55a35fd3b97
+size 3221225472

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "google/gemma-3-1b-it",
+  "base_model_name_or_path": "google/gemma-3-12b-it",
   "bias": "none",
   "corda_config": null,
   "eva_config": null,
@@ -24,13 +24,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
     "k_proj",
-    "down_proj",
-    "q_proj",
-    "up_proj",
+    "gate_proj",
     "o_proj",
-    "v_proj"
+    "up_proj",
+    "q_proj",
+    "v_proj",
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc06231c0b574e80595166ba1124daa5e2d69cc9f1849fcf0e65b42fe215b3e4
-size 13093568
+oid sha256:01b3a4e877bcb19b715fd3f1d4e585df71f43b5c4fc7215e4f96af1325a84bc5
+size 65559952

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52a3cbeb94edfa5e0e2c4725cd2902239f8ce8a1f41b2a8d1a1f00bfec69edae
+oid sha256:a66f4fbd00f38938ea400e6f0a235a237700bcfc410525497f47de295ae2752c
 size 6904