Jlonge4/outputs

README.md

@@ -35,16 +35,16 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
-- train_batch_size: 2
+- learning_rate: 0.0005
+- train_batch_size: 1
 - eval_batch_size: 8
 - seed: 42
 - gradient_accumulation_steps: 4
-- total_train_batch_size: 8
+- total_train_batch_size: 4
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 10
-- training_steps: 180
+- training_steps: 100
 - mixed_precision_training: Native AMP
 
 ### Training results

adapter_config.json

@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
+    "k_proj",
     "q_proj",
-    "v_proj",
-    "k_proj"
+    "o_proj",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c54d37547a591fd867f1b0860f17044d4f49c3bc6776f6a31997fff21226b3b
+oid sha256:da429f9889be81d27f4e206c1dbedd2f4a04256a9eb992327945856b1b9c1b23
 size 25174424

runs/Jun11_01-48-07_4ae7e20f059c/events.out.tfevents.1718070488.4ae7e20f059c.2615.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5538df376430f9aa05689a193d5b0a8f07d966adb4818413936826869c4e4ac1
+size 23610

runs/Jun11_01-52-10_4ae7e20f059c/events.out.tfevents.1718070731.4ae7e20f059c.2615.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d1b9ab4210f9959b147a6e0f6db3c2ddd4ed37b126c258cb9e7dc0d980b1ee0
+size 26650

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5578193f2f7446f0ac442896d1c5392202dafad8950e0c56cef7a7ff0368d0e
+oid sha256:6c99b0f2d819640cbcc07771cd69fa2bcdcc7fc03ed9267e4b4ccbf0cfce2404
 size 5112