LexiconShiftInnovations/Gemma_Dental_it_07

README.md

@@ -35,7 +35,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0002
+- learning_rate: 2e-05
 - train_batch_size: 1
 - eval_batch_size: 8
 - seed: 42
@@ -45,6 +45,10 @@ The following hyperparameters were used during training:
 - training_steps: 1000
 - mixed_precision_training: Native AMP
 
+### Training results
+
+
+
 ### Framework versions
 
 - PEFT 0.8.2

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c7972b9c31dd4bc101fa384d48d60bf8ade8ffc913e7a05cee851bad1707704
+oid sha256:46b743668d305602ebd9e9286d35697f86b7d18e1ad288c05c8b3d5e3e17b89f
 size 39256456

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb7e592b7314175501c7fc56b904d581de569169ac90e5aa2ec11a860c2cbbaa
-size 17477652
+oid sha256:d0d908b4f9326e0998815690e325b6abbd378978553e10627924dd825db7e243
+size 17477553

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e692e3c8c54e278d94129a1fc90da995221393d62d024d86256ac8ca066daa4
+oid sha256:22a8b3761e8146cfa039785518bfa8f54c4202e492c2e39d03f0d3cb4dbd82ab
 size 4920