Model save

README.md

@@ -34,14 +34,14 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 8
-- eval_batch_size: 16
+- train_batch_size: 1
+- eval_batch_size: 2
 - seed: 42
 - distributed_type: multi-GPU
 - num_devices: 4
 - gradient_accumulation_steps: 4
-- total_train_batch_size: 128
-- total_eval_batch_size: 64
+- total_train_batch_size: 16
+- total_eval_batch_size: 8
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - num_epochs: 1

adapter_config.json

@@ -18,8 +18,8 @@
   "target_modules": [
     "k_proj",
     "v_proj",
-    "q_proj",
-    "o_proj"
+    "o_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

runs/Feb01_23-57-24_r2d2-devbox-lcd4w/events.out.tfevents.1738454259.r2d2-devbox-lcd4w.1995.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a5101edd71a3fa05cef579be49d8963081f1308df40daf0a015e2fa36b1cf8a
+size 4618

step_0/README.md

@@ -203,4 +203,11 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 ### Framework versions
 
 
+- PEFT 0.6.1
+## Training procedure
+
+
+### Framework versions
+
+
 - PEFT 0.6.1

step_0/adapter_config.json

@@ -18,8 +18,8 @@
   "target_modules": [
     "k_proj",
     "v_proj",
-    "q_proj",
-    "o_proj"
+    "o_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

step_0/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3475e0f2e68ba04602c72e3234d42f97918aa20e3608d82b33595979ce095a23
+oid sha256:51ced1b716fea5a78a34109a2f40008e7a193c7727a344ca03f9d133b8efdc76
 size 5816

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3475e0f2e68ba04602c72e3234d42f97918aa20e3608d82b33595979ce095a23
+oid sha256:51ced1b716fea5a78a34109a2f40008e7a193c7727a344ca03f9d133b8efdc76
 size 5816