Training in progress, step 1

adapter_config.json

@@ -19,17 +19,17 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 8,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "q_proj",
-    "v_proj",
+    "gate_proj",
     "down_proj",
-    "up_proj",
     "o_proj",
-    "gate_proj"
+    "q_proj",
+    "up_proj",
+    "v_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:fed357f27c231016b96ed1db8c2ef847d1338f93224795fe4a7dcf77fc25d71e
-size 83945296
+oid sha256:1969cac1b6c71b1b86df0cd92ab327717d7c189a3e86766d1eee4dd47c2c9caa
+size 167832240

tokenizer_config.json

@@ -2061,5 +2061,5 @@
   "model_max_length": 8192,
   "pad_token": "<|reserved_special_token_250|>",
   "padding_side": "right",
-  "tokenizer_class": "PreTrainedTokenizerFast"
+  "tokenizer_class": "PreTrainedTokenizer"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd494f25c414c879ae51da2ee897028f7df0749fb8b839f73fdc0ffbcf60a1a0
+oid sha256:42be50fff6be37c3856bff58f0f8ac79f7d7dd2d9b9b711dfa344bed5439feff
 size 5624