Training in progress, epoch 1

adapter_config.json

@@ -18,19 +18,22 @@
   "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
-  "modules_to_save": null,
+  "modules_to_save": [
+    "lm_head",
+    "embed_token"
+  ],
   "peft_type": "LORA",
-  "r": 8,
+  "r": 64,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "o_proj",
     "q_proj",
     "k_proj",
-    "gate_proj",
     "down_proj",
-    "up_proj",
-    "o_proj",
-    "v_proj"
+    "v_proj",
+    "gate_proj",
+    "up_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c3157ce8a6cf1d2c4caa017e6f7d1037bb5a8abd16559c116791034c06b50fd
-size 20814808
+oid sha256:f5bf3a97ebc0ba37b5ca0d22fc407b5c26aa12c5e0c0a228556df3eaf73e391a
+size 166182928

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b9b77965c133a757ad3dd49d4501bc15d2229be24cf2457eaed84115634df0f
+oid sha256:37f46a61bfe0182c14cd7d9df91ee608838b4e278fffcc8d77fb4b0038ac8b19
 size 6904