Training in progress, step 1000

adapter_config.json

@@ -13,20 +13,20 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 128,
+  "lora_alpha": 64,
   "lora_bias": false,
-  "lora_dropout": 0.1,
+  "lora_dropout": 0.0,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
   "qalora_group_size": 16,
-  "r": 64,
+  "r": 32,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "Wo",
-    "Wqkv"
+    "Wqkv",
+    "Wo"
   ],
   "target_parameters": null,
   "task_type": "FEATURE_EXTRACTION",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea6fa2cb394a5f34052164c01d3f18f394fb0d8f0f5d46001c34e1d0b410ddfd
-size 36781392
+oid sha256:e95f3eb6603f945ba47be09956748189e7b24154090153c4eb08b29ad7639e43
+size 9207032

eval/binary_classification_evaluation_test_results.csv

@@ -355,3 +355,4 @@ epoch,steps,cosine_accuracy,cosine_accuracy_threshold,cosine_f1,cosine_precision
 52.38095238095238,198000,0.7667725447832185,0.7553963798277031,0.6663251366120219,0.8719553072625699,0.777431193404544,0.5385298107291973
 0.26455026455026454,1000,0.7117589203656826,0.7177313432835821,0.5988542963885429,0.8954934823091247,0.660905056042479,0.4537581257418676
 0.26455026455026454,1000,0.7117589203656826,0.7177313432835821,0.5988542963885429,0.8954934823091247,0.6609050528483301,0.4537581257418676
+0.26455026455026454,1000,0.7243353057835249,0.7326133128473947,0.6150694286364671,0.9056983240223464,0.6722293510542969,0.4874972730253775

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a662726dfec4a4b38ffda72e74bde622d087344ac18c4624dc7db591f33f2cf6
+oid sha256:f917f50bd68beeb1a55d57934be66e908cd7af902e9c7cbc4330a1b901a78897
 size 6225