Training in progress, step 500

adapter_config.json

@@ -10,13 +10,13 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
-  "lora_dropout": 0.05,
+  "lora_alpha": 32,
+  "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 8,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:467acf39bde1b33bed2ec5bbc72b7c6f7d6490ce3807ed69e58cbe43e5cce778
-size 1189560
+oid sha256:53a83d113c0ae535ba47fa2336733ab81096e20858ba93fccebb2f7842b5f879
+size 2369344

runs/May24_04-04-34_e047ed28558e/events.out.tfevents.1716523475.e047ed28558e.480.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65e9c6380fbd977eb208ab03d9497bdd9b2d8baa19ec79c3107d7c56ebf83a6e
+size 5843

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecc55530a1c6e1bc4a13af91003c3e595b3bbea252181a7477ca35a508aa3cd9
+oid sha256:558b81e643642554350f209ef08a652de29ac3d69f294a891c8a38c1e2e87600
 size 5176