Training in progress, step 500

adapter_config.json

@@ -16,24 +16,24 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 4,
+  "lora_alpha": 8,
   "lora_bias": false,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 1,
+  "r": 2,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "k_proj",
+    "fc2",
+    "fc1",
     "out_proj",
     "v_proj",
-    "language_projection",
-    "fc1",
-    "k_proj",
     "q_proj",
-    "fc2"
+    "language_projection"
   ],
   "task_type": null,
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90a7635018b362d38acb038264996f19c609c19a3293ed17f11716fabd0be40c
-size 8347336
+oid sha256:36b40e6c554966b1cfa7f51fbcbda62a528ca305ff1af7e982f444e6f9cceba4
+size 16615616

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da8b7bf666b89316ca6326e97b994388596d3eb95ad8e19e6d52c4b4779aa49d
+oid sha256:424d4ff5a00257c914a5db96c3bc0106e39f95d05a17e99e1ea79eb465b2a65b
 size 5368