Training in progress, step 100

adapter_config.json

@@ -11,7 +11,7 @@
   "layers_to_transform": null,
   "loftq_config": {},
   "lora_alpha": 16,
-  "lora_dropout": 0.05,
+  "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "gate_proj",
     "k_proj",
+    "q_proj",
+    "up_proj",
     "down_proj",
-    "o_proj",
-    "gate_proj",
     "v_proj",
-    "q_proj",
-    "up_proj"
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d88be5c4bb779995176fa621cd13ee128769053c7a5cd740555bc4a516185cc
+oid sha256:84a28c8f68204626f8e38ae7bbbcfdc576f12f535ffade0f5830fd4439611dce
 size 335604696

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:547039fe2a31ba860a28cb2b9229d7c38678603f25f74fd606a198c3b3db6c18
+oid sha256:cdf3f8ff98474ef5dc2bbe6168ae75d23e5500c2bd9c54b8b33d54b66c887fe2
 size 6776