Training in progress, step 960

adapter_config.json

@@ -13,24 +13,24 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
+  "lora_alpha": 64,
   "lora_bias": false,
   "lora_dropout": 0,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 16,
+  "r": 32,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "v_proj",
     "up_proj",
-    "q_proj",
+    "gate_proj",
     "o_proj",
     "down_proj",
-    "v_proj",
-    "gate_proj",
-    "k_proj"
+    "k_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50d46a6ac208063f25f1f3e525d291856b422785040797e1e95fc606128010d5
-size 119801528
+oid sha256:ba1deb810b52c49fafe12e70e80d3fd303ce37cb56dcdd114371a79d64a998e1
+size 239536272

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:640bba4c31fd0385165c5d5986c7cba02a4d97410d82504a8e7166d7773b5d6c
+oid sha256:9671014af00191463aa5a02941564784b104e26fcae1a2c57cc3208dc86646fb
 size 6993