Training in progress, epoch 1

adapter_config.json

@@ -19,19 +19,19 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 128,
+  "r": 256,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "gate_proj",
-    "k_proj",
+    "down_proj",
     "up_proj",
+    "q_proj",
+    "lm_head",
     "v_proj",
-    "down_proj",
-    "o_proj",
+    "k_proj",
     "embed_tokens",
-    "lm_head"
+    "o_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 sha256:8b65f14bc8c5fe9a0267002af3d87f57d15c6c99320bc1cc357d6c6209c9d77d
-size 3604943664
+oid sha256:19f36ce7d03391cdec3b6e5f67b416def3c2bd477ddf48384b01b00f283951f5
+size 4720497456

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0c26e125c025d8a486b7a7df4f43cd01635126542528ff83d4edaffa999e741
-size 11421995
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c4769e9a1238f023b766fcb81da370fdca2d2df66ab5fb209503a3dc5c9de95
+oid sha256:411851d375270341a17f8fe9d24c8afb93933497823944e6ccbe1e7d7dcf1aa7
 size 5777