Jlonge4/outputs

README.md

@@ -36,11 +36,11 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0005
-- train_batch_size: 1
+- train_batch_size: 2
 - eval_batch_size: 8
 - seed: 42
 - gradient_accumulation_steps: 4
-- total_train_batch_size: 4
+- total_train_batch_size: 8
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 10

adapter_config.json

@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
     "q_proj",
-    "o_proj",
-    "v_proj"
+    "k_proj",
+    "v_proj",
+    "o_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:da429f9889be81d27f4e206c1dbedd2f4a04256a9eb992327945856b1b9c1b23
+oid sha256:21419fe8c8e63bf7a15abda6a5bef359d46b75562a16aa0872ec619be56a4849
 size 25174424

runs/Jun11_23-38-07_c34ae01b46c7/events.out.tfevents.1718149088.c34ae01b46c7.1196.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45e0577a3364b12f5cdc62a6084c9c1808aa7b67e87c16a8bc4b4905c1d686d4
+size 26677

runs/Jun11_23-41-52_c34ae01b46c7/events.out.tfevents.1718149313.c34ae01b46c7.1196.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f12e16c66e063063214db27d8a2b613a6b388c1907eec620158f184828556ce3
+size 26677

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c99b0f2d819640cbcc07771cd69fa2bcdcc7fc03ed9267e4b4ccbf0cfce2404
+oid sha256:dbf33f1600bd5f7bdcbbaad49cffcc4f87535dc7ef8e6b3374e84ee225ed8a6d
 size 5112