Training in progress, step 232

adapter_config.json

@@ -10,18 +10,26 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
+  "lora_alpha": 32,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
-  "modules_to_save": null,
+  "modules_to_save": [
+    "lm_head",
+    "embed_tokens"
+  ],
   "peft_type": "LORA",
-  "r": 32,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "v_proj",
+    "up_proj",
     "q_proj",
-    "v_proj"
+    "o_proj",
+    "down_proj",
+    "gate_proj",
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b187778d4e97f3f4c1de774189f8b79f302ded8d3a85526b697132112999ec53
-size 54543184
+oid sha256:73d4e04edf4897a78be9fadddfeb7d7edd81ad878e64d6bee165e69652346380
+size 4370526560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c02244dd29614b45cb0b475c86ad9509b1dd1d7410f9e62e94ac91fca2d5c78
+oid sha256:936fc30b03faa2c3184a90cdcd2ab667d5d98c7ba74c0c7781e5632b2080552d
 size 5688