Petualang/adapter-Phi3doctor

README.md

@@ -36,11 +36,11 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0001
-- train_batch_size: 8
-- eval_batch_size: 8
+- train_batch_size: 4
+- eval_batch_size: 4
 - seed: 42
 - gradient_accumulation_steps: 4
-- total_train_batch_size: 32
+- total_train_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "down_proj",
+    "up_proj",
     "k_proj",
     "q_proj",
-    "up_proj",
+    "v_proj",
+    "down_proj",
     "o_proj",
-    "v_proj"
+    "gate_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:caef3bda5bc4d1e551dce572a32f5936502da8fa79b1bbfb273ef1edb3216c9a
+oid sha256:1c33f3a32a7b60081418de31548bd77308f7a84021fd01faa862673bff8d23f4
 size 35668592

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d8db170c33d8fcdaed9048d43f24193f99a8ce3597d9aec929c6f596c7c2bba
+oid sha256:481e5d6a6bec5d2347fd6988fe8fd7599318a85b737b1549bcaba9018aee34f1
 size 5432