Training in progress, step 100

adapter_config.json

@@ -10,23 +10,23 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
+  "lora_alpha": 64,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 16,
+  "r": 32,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
-    "down_proj",
-    "v_proj",
+    "k_proj",
     "o_proj",
+    "v_proj",
     "gate_proj",
-    "k_proj",
-    "q_proj"
+    "q_proj",
+    "up_proj",
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dca6d6d9623c3d7304229fea1c56ee1985ee12e924d7112f285ef89dd8368d3
-size 39256960
+oid sha256:1661605a81a28cadd36692c9ba0b77de523429015ca7a76177e82658d627c0b3
+size 78480320

runs/Jun10_15-41-34_user-HP-Z8-Fury-G5-Workstation-Desktop-PC/events.out.tfevents.1718001709.user-HP-Z8-Fury-G5-Workstation-Desktop-PC.10374.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:746fc9725f4e27dcf80909c1fe930b1daa7cf69b7b058ec479b8b043e1e56e74
+size 9976

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1919820ff1eea3497b9cef09bc0165d7782e10f33e350766cb2dce6b401a9f19
+oid sha256:f3a64e4546344d34bfda60e22470f6d8d22980d58ee9b10059327203c9a0c23e
 size 5368