Training in progress, step 15

adapter_config.json

@@ -12,24 +12,24 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 128,
+  "lora_alpha": 16,
   "lora_bias": false,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 128,
+  "r": 2,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "down_proj",
-    "k_proj",
-    "up_proj",
     "o_proj",
+    "down_proj",
     "gate_proj",
-    "v_proj"
+    "v_proj",
+    "up_proj",
+    "q_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:c67a4204c1fe77f9603354d332c1167ab71774c38109be501c48fc1c9f04fdab
-size 778096664
+oid sha256:e4f16b69bde08fd8b7084cc92e8ceb14df43d15a344284407a88e9ca8c9ed377
+size 12208024

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f13f3eccdf615ba64d4211bbd78c2374357884aca8e7de45d3629e88522c5594
-size 17210466
+oid sha256:6c0b04a3a8af80ab201e3c146591cbf297d37125c1ca9550e25fe6c1d3c0e105
+size 17210301

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a543d608cb0d0724311e678a58f6f55e2460c7804c464b1cc1241979883b527
-size 14264
+oid sha256:aefa3e1a30c72dbd80242c08fd1701ac8b188c52e82a15c7b0ad0513ee6ff592
+size 14904