Training in progress, epoch 1

adapter_config.json

@@ -10,20 +10,20 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
+  "lora_alpha": 32,
   "lora_dropout": 0.28,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 8,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_up_proj",
-    "qkv_proj",
+    "o_proj",
     "down_proj",
-    "o_proj"
+    "qkv_proj",
+    "gate_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:b34c67672d3c38eee51c239399e2dd6cfefda2e3699eacd342ad8800aad3cd0e
-size 837118104
+oid sha256:4ad958f8c59c808668c7d40c04164879968c56bc538eeaf2828cc9b6837cc0af
+size 887450008

runs/Jun23_13-22-17_VMGPU1/events.out.tfevents.1719141745.VMGPU1.9592.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49e197c8c854fc4070bc53886b92faad10dadd2e4dfb96a49f4bbb6d921d1cb2
+size 176325

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4196c1a5e8d129f3ee0206fa8782ce9f66cf18fb5fe2a1ff83fe14a6a66b61d3
+oid sha256:3f4869b70df0cf448d47721b1ceb20bf83225f5bd1bdc05e9d9bfe4e51f5e60d
 size 5432