Model save

README.md

@@ -39,8 +39,8 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
-- lr_scheduler_warmup_steps: 3
-- training_steps: 10
+- lr_scheduler_warmup_steps: 5
+- training_steps: 20
 
 ### Training results
 

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12a75c773dd6a010ef0fc639f1079d1130cb901a5db54a115df35f1add1d11b8
+oid sha256:91f272cf9fe0943c09bd94b05b3e9516bf591e69ed5fc56b1a00283d5d0df7e2
 size 2365304

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d234b06cfa98f610a74a18ecd05fc939059aec01bb1f459dff686b394a542323
+oid sha256:79c175fb73fe6ced26b82f8aaad0a5998320d8fbe263df423b87478db363781d
 size 5112