Model save

README.md

@@ -38,9 +38,8 @@ The following hyperparameters were used during training:
 - eval_batch_size: 16
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: cosine
-- lr_scheduler_warmup_steps: 5
-- training_steps: 30
+- lr_scheduler_type: linear
+- training_steps: 10
 
 ### Training results
 

adapter_config.json

@@ -20,30 +20,30 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "transformer.h.2.attn.c_proj",
-    "transformer.h.0.attn.c_proj",
-    "transformer.h.0.mlp.c_proj",
-    "transformer.h.1.attn.c_attn",
-    "transformer.h.4.mlp.c_fc",
-    "transformer.h.5.mlp.c_fc",
-    "transformer.h.3.attn.c_attn",
-    "transformer.h.2.attn.c_attn",
-    "transformer.h.1.mlp.c_proj",
-    "transformer.h.2.mlp.c_fc",
     "transformer.h.3.attn.c_proj",
-    "transformer.h.4.attn.c_proj",
-    "transformer.h.5.attn.c_proj",
-    "transformer.h.0.mlp.c_fc",
-    "transformer.h.1.attn.c_proj",
-    "transformer.h.1.mlp.c_fc",
-    "transformer.h.0.attn.c_attn",
-    "transformer.h.5.attn.c_attn",
     "transformer.h.3.mlp.c_fc",
+    "transformer.h.5.mlp.c_fc",
+    "transformer.h.4.mlp.c_fc",
+    "transformer.h.2.mlp.c_proj",
+    "transformer.h.0.mlp.c_proj",
+    "transformer.h.4.attn.c_proj",
     "transformer.h.3.mlp.c_proj",
     "transformer.h.4.attn.c_attn",
-    "transformer.h.2.mlp.c_proj",
+    "transformer.h.4.mlp.c_proj",
+    "transformer.h.3.attn.c_attn",
+    "transformer.h.1.attn.c_attn",
+    "transformer.h.0.attn.c_attn",
+    "transformer.h.1.attn.c_proj",
+    "transformer.h.1.mlp.c_proj",
     "transformer.h.5.mlp.c_proj",
-    "transformer.h.4.mlp.c_proj"
+    "transformer.h.2.attn.c_proj",
+    "transformer.h.5.attn.c_attn",
+    "transformer.h.0.mlp.c_fc",
+    "transformer.h.0.attn.c_proj",
+    "transformer.h.2.mlp.c_fc",
+    "transformer.h.2.attn.c_attn",
+    "transformer.h.5.attn.c_proj",
+    "transformer.h.1.mlp.c_fc"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:313174a13db3decbfdb8cc89ca7bf90b3b0a449053671b790cd0670f6c2fa00b
+oid sha256:dab480c28c6f49f08beaad63095a709a6e07e5da50d4d81b846a9a45f479a4b8
 size 2365304

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58c2d8043c93feda75c4844001deaf3b934b34158ab14a6bcf4e66560335330a
+oid sha256:905022d7425bfab0d74e1dc861298969f9c63ef170520ac60873a866360e5cff
 size 5112