Training in progress, epoch 0

adapter_config.json

@@ -10,23 +10,23 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 128,
+  "lora_alpha": 64,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 256,
+  "r": 64,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "down_proj",
     "v_proj",
     "o_proj",
-    "gate_proj",
+    "up_proj",
+    "down_proj",
     "k_proj",
-    "up_proj"
+    "q_proj",
+    "gate_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:ed30ef6b4d1449c02ddeec6503939b8a9b835ca90696e0ff9cfd68aff8828c33
-size 2684416208
+oid sha256:ce44a353ebd946439d499292de3068ebdc2a5a6fe0a4e66eccaf6e35d09334d0
+size 671149168

runs/Jul16_11-52-00_vwbmgpua100-sit02/events.out.tfevents.1721130751.vwbmgpua100-sit02

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e5fd4de1fcbee6d508c6e1e3aaa7a783a09b96a05875365cfacbe36795b2070
+size 7431

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddd0b6220f4cab940801f77f4203323c678337b1d7c45cc869a3108876493152
+oid sha256:eb265b4c0170203e7bc8ea563880a5db1be9245efd6a6024e8797d57c693d497
 size 5496