Training in progress, step 100

adapter_config.json

@@ -6,23 +6,24 @@
   "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": 32,
+  "lora_alpha": 16,
   "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 64,
+  "r": 8,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
     "k_proj",
     "o_proj",
-    "v_proj"
+    "v_proj",
+    "q_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:e47a4d72e3918c0c02d25e1697e883e203ad49669ebd7c4dc2253896fc929d59
-size 218138576
+oid sha256:d37e6cd396cb27d5f3ab91446e70499987a5025a8255abc033802360d69dddd2
+size 27297032

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a680d476ff8a3eb712f1e1e163b1243bda5bc71ec5294868266d29730e2aa4c
+oid sha256:7523d83c98241ee4c34cb76e35bf170b32d4a35ae6bc7cabbc063b9764478e8b
 size 4856