Training in progress, step 200

adapter_config.json

@@ -8,16 +8,19 @@
   "init_lora_weights": true,
   "layers_pattern": null,
   "layers_to_transform": null,
+  "loftq_config": {},
   "lora_alpha": 16,
   "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
   "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "lm_head",
-    "wte"
+    "wte",
+    "lm_head"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ae72702d86e8595631327b59d103b03b60a3b8e4a34126a9dcdf4e083752f9c
-size 6531688
+oid sha256:4b76a31ba0bbfe8ab3c58a744876eca18e84ec3104d553ac85a9d25cf397fb4c
+size 315310960

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b54e7146d4a5dc4a3337fb31a8552c8e24ec22dac2fb8150598aee2a784cb069
-size 4536
+oid sha256:60b018dc4d170d606b335547d5635a623e16b3c4e70985d20aeaeda860bed4d6
+size 4219