Training in progress, step 10

adapter_config.json

@@ -14,21 +14,22 @@
  "r": 64,
  "revision": null,
  "target_modules": [
+ "layers.0.wte",
  "layers.20.mixer.Wqkv",
- "layers.20.mixer.out_proj",
  "layers.21.mixer.Wqkv",
- "layers.21.mixer.out_proj",
  "layers.22.mixer.Wqkv",
- "layers.22.mixer.out_proj",
  "layers.23.mixer.Wqkv",
- "layers.23.mixer.out_proj",
  "layers.24.mixer.Wqkv",
+ "layers.20.mixer.out_proj",
+ "layers.21.mixer.out_proj",
+ "layers.22.mixer.out_proj",
+ "layers.23.mixer.out_proj",
  "layers.24.mixer.out_proj",
  "layers.11.mlp.fc1",
- "layers.11.mlp.fc2",
  "layers.17.mlp.fc1",
- "layers.17.mlp.fc2",
  "layers.24.mlp.fc1",
+ "layers.11.mlp.fc2",
+ "layers.17.mlp.fc2",
  "layers.24.mlp.fc2",
  "layers.25.linear"
  ],

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e995f7e09220fa1266a2ce95072f32779c23627d528ab0f02539a7d9116c3fb0
-size 45100375
+oid sha256:270618d72024f56bf8bcf3a161951b2399ba28a19a9536fbf9b7db1151bc6246
+size 58732573

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1e8576a6c07deb1c112e9eb1f11236358461986a5fa54c3425dbdf1d97be208
+oid sha256:b8c25623a0eac8249cc43398c125199cff741e4f26b87182b1914eb5f5112061
 size 4027