Training in progress, step 100

adapter_config.json

@@ -12,24 +12,24 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 128,
+  "lora_alpha": 2,
   "lora_bias": false,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 128,
+  "r": 2,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
     "q_proj",
-    "o_proj",
-    "v_proj",
     "down_proj",
     "k_proj",
-    "gate_proj"
+    "o_proj",
+    "gate_proj",
+    "v_proj",
+    "up_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0798da613f8d60d43440befb0f4adb1e1411d2c69b07a66ee0d5801938419165
-size 2354131208
+oid sha256:de003e40675259b45cff8f262427f98d06084dafa95223d99ce84a88b04757d2
+size 1588242560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f038816579a41eec6ee93d6385ead64cd5e067636396c2db507658802ed94599
+oid sha256:0929067966f9e342e3cac8f0fd182187d5d8b2ea24e30a7186ff92102497c94b
 size 13304