Training in progress, step 15

adapter_config.json

@@ -3,6 +3,7 @@
   "auto_mapping": null,
   "base_model_name_or_path": "ExplosionNuclear/Llama-2.3-3B-Instruct-special",
   "bias": "lora_only",
+  "corda_config": null,
   "eva_config": null,
   "exclude_modules": null,
   "fan_in_fan_out": false,
@@ -19,19 +20,22 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
+  "qalora_group_size": 16,
   "r": 2,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
-    "gate_proj",
+    "v_proj",
     "k_proj",
-    "q_proj",
+    "up_proj",
     "down_proj",
-    "v_proj",
-    "o_proj"
+    "o_proj",
+    "q_proj",
+    "gate_proj"
   ],
   "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
   "use_dora": false,
+  "use_qalora": false,
   "use_rslora": false
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4cfbb0089d517da40780eb23cd7808367caec52a32abea45ef1d64188ad43d1
+oid sha256:7f9088699c7de898863be4a0ac3afce54378ef66fa50e665fbd3a4337d19daec
 size 12208024

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52875e0129bf15d5b032cccddd43fa6cb5aa82ec745c71c601ad139a9b471bca
-size 14776
+oid sha256:c5ea7cd63307494abcbf6ce5ffe37692631cd23cfa2dc6e50c08f465d3115335
+size 14520