LexiconShiftInnovations/Gemma_Dental_it_06

README.md

@@ -42,13 +42,9 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 2
-- training_steps: 5000
+- training_steps: 1000
 - mixed_precision_training: Native AMP
 
-### Training results
-
-
-
 ### Framework versions
 
 - PEFT 0.8.2

adapter_config.json

@@ -20,12 +20,12 @@
   "revision": null,
   "target_modules": [
     "q_proj",
+    "k_proj",
+    "up_proj",
     "v_proj",
     "o_proj",
     "down_proj",
-    "k_proj",
-    "gate_proj",
-    "up_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:e3ff190e2a9cfffc9546b5ec1450a6273b92c2fab75be264786a3a3ba7375f10
+oid sha256:5c7972b9c31dd4bc101fa384d48d60bf8ade8ffc913e7a05cee851bad1707704
 size 39256456

tokenizer.json

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

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f27ed7b267c37a1fff159262bee35ea9949762c1e79897c208af276da1b2ffb
-size 4856
+oid sha256:2e692e3c8c54e278d94129a1fc90da995221393d62d024d86256ac8ca066daa4
+size 4920