Training in progress, step 32

adapter_config.json

@@ -16,12 +16,16 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 16,
+  "r": 64,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "up_proj",
+    "gate_proj",
+    "q_proj",
+    "down_proj",
     "v_proj",
-    "q_proj"
+    "k_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:eb73e16db500e780afa716e99339fcb2719feafafefc5a37bf33fa95f5a90d6c
-size 4373064
+oid sha256:df9f701c9249fc5b5e429b09a4d9c2b70e575d71e10ce7533647b207eb165473
+size 136753176

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88a3a6fcb80132f76da8aa40cdc3fccd7e5d8468ef15421f5b0c2715e85217d2
-size 11420538
+oid sha256:091aa7594dc2fcfbfa06b9e3c22a5f0562ac14f30375c13af7309407a0e67b8a
+size 11420371

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47cc2b715a2aa624bad152cdcfe75d961031a5b794e1d991059bf80476d9ea1d
+oid sha256:64558442d214d8534f78de779fea18cf0a73ba1c265eaa52c1bc959ac5bbedac
 size 5560