Training in progress, step 100

adapter_config.json

@@ -3,7 +3,7 @@
   "alpha_pattern": {},
   "arrow_config": null,
   "auto_mapping": null,
-  "base_model_name_or_path": "bigcode/starcoderbase-3b",
+  "base_model_name_or_path": "bigcode/starcoderbase-1b",
   "bias": "none",
   "corda_config": null,
   "ensure_weight_tying": false,
@@ -23,16 +23,16 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "peft_version": "0.18.0",
+  "peft_version": "0.18.1",
   "qalora_group_size": 16,
   "r": 8,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_attn",
     "c_proj",
     "c_fc",
-    "c_attn"
+    "c_attn",
+    "q_attn"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8f0fa23724611f80e334a1429603527d15928dd1a9f8742919dca6dc79554f9
-size 45748400
+oid sha256:4acfeb4cc9cda09a3acc118e7f81ec7eaeffa9c5836edfa49f09d13bff373a38
+size 22241240

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78ee86147e50110f6d17c09ddb931a96a8767e71126cc66d08be84c5b877af8f
-size 5905
+oid sha256:4264536d71111fb254fb1bba3ec36537bfc6b612b8c2d34a93e2e2871df79690
+size 5201