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 sha256:9c6902bf40cf91bace0aa5eafc98e7e1a858464ac4f09ef545a7b3e0b234305f
-size 1744865936
+oid sha256:a9b8ce878de712011d6a67625bf1dd5b05c48ef5999c5911b560df58ba7ab5df
+size 109086416

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad0dff352f4accf431b49cb2a06557e66caf4639260963210b13cc567c4f7715
-size 4920
+oid sha256:c081deb3e849ed3ead5d967fff441ca7eeeb10277aab1629b07e41895afe3e57
+size 4984