Training in progress, epoch 2

adapter_config.json

@@ -1,9 +1,12 @@
 {
+  "alora_invocation_tokens": null,
   "alpha_pattern": {},
+  "arrow_config": null,
   "auto_mapping": null,
   "base_model_name_or_path": "voidful/llm-codec",
   "bias": "none",
   "corda_config": null,
+  "ensure_weight_tying": false,
   "eva_config": null,
   "exclude_modules": null,
   "fan_in_fan_out": false,
@@ -20,20 +23,24 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
   "r": 64,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "k_proj",
     "q_proj",
-    "up_proj",
     "o_proj",
+    "k_proj",
+    "down_proj",
     "v_proj",
-    "down_proj"
+    "up_proj",
+    "gate_proj"
   ],
+  "target_parameters": null,
   "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 sha256:01f1adfb4d4f0a2f044323aa36e6c31cb24bfadfa7406d2ff26dd9deb8027ff2
+oid sha256:4af9c056765e599d2a4ce35908801edf4f9ff2ba4ba9ec7d22de8aa5e9694682
 size 528550256

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09ef793003aa3f31e0fa9d57c9998371626de0241ae516edb6c9795266860010
+oid sha256:086a4fbc7538a577fb092ba511f7e1a4d6b3867e138da19ed05f63656337f331
 size 5841