Training in progress, step 78

adapter_config.json

@@ -1,6 +1,9 @@
 {
   "alpha_pattern": {},
-  "auto_mapping": null,
+  "auto_mapping": {
+    "base_model_class": "LlamaForCausalLM",
+    "parent_library": "transformers.models.llama.modeling_llama"
+  },
   "base_model_name_or_path": "deepseek-ai/deepseek-coder-1.3b-base",
   "bias": "none",
   "fan_in_fan_out": false,
@@ -20,15 +23,15 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "o_proj",
     "down_proj",
-    "up_proj",
-    "gate_proj",
     "v_proj",
-    "k_proj"
+    "gate_proj",
+    "o_proj",
+    "up_proj",
+    "k_proj",
+    "q_proj"
   ],
-  "task_type": "CAUSAL_LM",
+  "task_type": null,
   "use_dora": false,
   "use_rslora": false
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bac7505ae4c200439b42e5036f583dc97a14bc994221080c7eb0971c8f9d2be
+oid sha256:36aaeb1a6ceeae6afacda6ee59f73c236de879f7a52f5237a459ca9bc2eb0e78
 size 119975992

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07c7166841260233c321d8c9a7518a514e4ec28c37d6ada774dc56b6b7ece2c8
+oid sha256:1fe7b2738bbcd1d5700eb0acd19db2e854b724ab42277643ea3497d17839bf56
 size 5560