Training in progress, step 300

adapter_config.json

@@ -11,26 +11,22 @@
   "init_lora_weights": true,
   "layer_replication": null,
   "layers_pattern": null,
-  "layers_to_transform": null,
+  "layers_to_transform": [
+    20
+  ],
   "loftq_config": {},
-  "lora_alpha": 64,
+  "lora_alpha": 256,
   "lora_bias": false,
   "lora_dropout": 0.0,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 32,
+  "r": 1,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "down_proj",
-    "k_proj",
-    "v_proj",
-    "o_proj",
-    "up_proj",
-    "gate_proj"
+    "down_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 sha256:3c7c896fe5e751aef3d0f435f66b59df5f7b11f7b347fc5aae164d79bae2dd66
+oid sha256:79cc80c757cd259f6e7647791559ca3fe1a265ef0d11819779c028490976711b
 size 90400