Training in progress, step 60

adapter_config.json

@@ -20,23 +20,20 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "qalora_group_size": 16,
   "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "o_proj",
-    "k_proj",
     "down_proj",
-    "v_proj",
     "gate_proj",
-    "up_proj",
-    "q_proj"
+    "v_proj",
+    "k_proj",
+    "q_proj",
+    "up_proj"
   ],
-  "target_parameters": null,
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,
   "use_dora": false,
-  "use_qalora": false,
   "use_rslora": false
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ecc28121641b60aa2ce4ee48b6c64ff118ee5d03492e8a326f36abfd85fcbee
+oid sha256:7dd05b34e7bd696977c2471a076aca40b7e38d3acaf2700368022d2fff9e45b3
 size 167832240

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8f20cd74e313044f8e8d07a1dcdc435dc7c54ab8cb7e8286be55ad9af7f8bb4
-size 6225
+oid sha256:b88666eac0f7ee35fdcf5071ce0fe8c058b6f246ca8342fe1afad8bc7a8cece6
+size 6097