Training in progress, step 100

adapter_config.json

@@ -10,23 +10,23 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
+  "lora_alpha": 32,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 8,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj",
+    "gate_proj",
     "up_proj",
+    "v_proj",
     "down_proj",
-    "o_proj",
+    "q_proj",
     "k_proj",
-    "gate_proj"
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29c4b9695e07bfc8793431250e0d50f697c4f2a08946ed1aa0105002b6673179
-size 19644912
+oid sha256:be0b9722ce7daea9270ec4ddb03e45ef0a2f0e0d8b30c9bac8ab268039ed8f40
+size 39256960

runs/Jun10_01-58-39_48ddfe8e991f/events.out.tfevents.1717984740.48ddfe8e991f.6850.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:083779b833b3aed992010c32bc62795554bd32a28730e56089a53a6aefca0928
+size 10750

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c657f2917e59b92984f4725a0e7750712dbf01d89f6a4041a2cb327bf1b61880
-size 5176
+oid sha256:d03f4d69141483dec647971897c50625c2bc09eeed8369f1f9e7ea0125e0e729
+size 5304