llamantino7b_2_2_syntetic-question-answering

README.md

@@ -42,7 +42,7 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.03
-- num_epochs: 2
+- num_epochs: 3
 
 ### Training results
 

adapter_config.json

@@ -19,13 +19,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "down_proj",
+    "up_proj",
+    "q_proj",
+    "v_proj",
     "k_proj",
     "o_proj",
-    "q_proj",
-    "up_proj",
-    "v_proj"
+    "down_proj",
+    "gate_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_rslora": false

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04a240d7b26be23b1810b6315b9fc0fe08cbe5e46b9eccd91284cdf505dab4b9
+oid sha256:a9e091b11a047bc51d4d5608cde70f9359235138295222d4baa7b9a388dcd572
 size 639691872

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fcab6936f2b02d715e388fcca1a5f1f66396e4ea6e8b22d1df81fc3ac6e62b5
+oid sha256:ca2d84401ff09ae7196e4302d101b091763affdff18a759d3d22d09d7b087f3e
 size 4411