Model save

README.md

@@ -38,20 +38,16 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0002
-- train_batch_size: 1
+- train_batch_size: 3
 - eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 16
-- total_train_batch_size: 16
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 24
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant
 - lr_scheduler_warmup_ratio: 0.03
 - num_epochs: 3
 
-### Training results
-
-
-
 ### Framework versions
 
 - PEFT 0.12.0

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "q_proj",
+    "v_proj",
     "k_proj",
     "o_proj",
+    "up_proj",
     "gate_proj",
-    "v_proj",
-    "up_proj"
+    "q_proj",
+    "down_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:a4037af8e7cea44ee280d07d56862b8426f501ae659a05db97a2c852e3ce590d
+oid sha256:ec9a1c5fd37babfa9f861a8fd06ec2280949a4081ae2035ae933d1b03b33d2fa
 size 3443617864

runs/Feb16_16-58-13_ip-172-31-3-189/events.out.tfevents.1739725098.ip-172-31-3-189.1346.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:527c8bfe4e96bb260e480f80da2df83d5120f2591e2b4c6209c198ac6c070c9c
+size 6064

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4a0dde11ba6da27beacc711bc13b02cde59dbd8ddf04fe41d14003b57bc8142
+oid sha256:072066f806c07c82951a717e54f820f3c4ee916028033b8c73b119f8bac558d6
 size 5560