Model save

README.md

@@ -33,12 +33,14 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 2
-- eval_batch_size: 4
+- train_batch_size: 4
+- eval_batch_size: 8
 - seed: 42
 - distributed_type: multi-GPU
+- num_devices: 2
 - gradient_accumulation_steps: 128
-- total_train_batch_size: 256
+- total_train_batch_size: 1024
+- total_eval_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - num_epochs: 1

adapter_config.json

@@ -16,10 +16,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
     "v_proj",
+    "o_proj",
     "k_proj",
-    "o_proj"
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

runs/Jan17_02-14-44_r2d2-devbox-llwcj/events.out.tfevents.1737080153.r2d2-devbox-llwcj.44228.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77672f7c41e93f1d7d98c1fa5408c2bf19a64323dcd4a22a0ed1a5676f3cc947
+size 4265

step_0/README.md

@@ -211,4 +211,11 @@ 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

@@ -16,10 +16,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
     "v_proj",
+    "o_proj",
     "k_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:a40e3e8fb80d18201db606db2052b6816b01c9421b9ba063219d796e10d1a604
+oid sha256:35b68deefef1292e85c11dc4c2e55d35de8ea1fdc0bfba5f2425fb2c7dc7243d
 size 5560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a40e3e8fb80d18201db606db2052b6816b01c9421b9ba063219d796e10d1a604
+oid sha256:35b68deefef1292e85c11dc4c2e55d35de8ea1fdc0bfba5f2425fb2c7dc7243d
 size 5560