Training in progress, epoch 1

adapter_config.json

@@ -9,10 +9,11 @@
   "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": true,
+  "layer_replication": null,
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 1024,
+  "lora_alpha": 64,
   "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
@@ -20,14 +21,14 @@
     "ln_f"
   ],
   "peft_type": "LORA",
-  "r": 512,
+  "r": 32,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
     "q_proj",
+    "v_proj",
     "k_proj",
-    "v_proj"
+    "o_proj"
   ],
   "task_type": null,
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce1c2b7549bce6b74d058223b341b8f7c59f66f3415bfe505a3dea81e29a03b0
-size 1744865936
+oid sha256:cc579edd5948ce448dd07e7ca014134b9312b15c79d9dd48850750ef7471eeef
+size 109086416

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb227571cc0a69930eea4ea12190186ea47822d663a33df6b93be4671cafee35
-size 4920
+oid sha256:664c80353e44bc5612138259e4972e42ece3c3780b3f8374747468c9636d7359
+size 4984