Training in progress, step 20

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,
@@ -16,7 +16,7 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 128,
+  "lora_alpha": 32,
   "lora_bias": false,
   "lora_dropout": 0.0,
   "megatron_config": null,
@@ -25,13 +25,13 @@
   "peft_type": "LORA",
   "peft_version": "0.18.1",
   "qalora_group_size": 16,
-  "r": 64,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "c_fc",
     "c_attn",
-    "c_proj"
+    "c_proj",
+    "c_fc"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a01d341d02b1e66ff640c619cc217c41bbb0a77d5dbad17275de4faab75e7dc
-size 365728752
+oid sha256:fadcd475ad239d9ffdec03952ea78d463220d2b32e40d6032b5fc07b4ab12d5f
+size 44458224