Training in progress, step 50

adapter_config.json

@@ -6,6 +6,9 @@
   },
   "base_model_name_or_path": "princeton-nlp/Sheared-LLaMA-1.3B",
   "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
   "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": true,
@@ -14,6 +17,7 @@
   "layers_to_transform": null,
   "loftq_config": {},
   "lora_alpha": 32,
+  "lora_bias": false,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
@@ -23,15 +27,16 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "k_proj",
     "gate_proj",
-    "o_proj",
     "down_proj",
-    "k_proj",
-    "v_proj",
+    "o_proj",
     "q_proj",
-    "up_proj"
+    "up_proj",
+    "v_proj"
   ],
   "task_type": null,
+  "trainable_token_indices": null,
   "use_dora": false,
   "use_rslora": false
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed69b1cd434a6c996e67cc5361811c9dacadead171572878f130728cf4ace0bb
+oid sha256:456d9554a7c598cb08f15be06838bba539a6ec736c0cd9b44c2cef0c2f33d0f3
 size 60008032

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14972892659a7e425ff0f1cdcfcc283577db9a86e97cb5b34f06e13bc3b6af5e
-size 5368
+oid sha256:b145f1484b7ed4f71e8e7576aa1baab4194b7d4f53883102a42a0ddd8f36a1d3
+size 5777