Training in progress, step 50

adapter_config.json

@@ -10,7 +10,7 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 8,
+  "lora_alpha": 32,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
     "o_proj",
-    "q_proj",
+    "up_proj",
+    "v_proj",
     "gate_proj",
+    "k_proj",
     "down_proj",
-    "up_proj",
-    "v_proj"
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c34726792d36e94ef7947692dec5d4bb0113d89451ce1eda08b7e5a700115cb
+oid sha256:41f62c76c06eaa6bbcdd916a35bb4a65ed4380fcfb1715c9afd2b868bfb58e3b
 size 3611357976

runs/Apr05_01-22-12_f35651a1a25c/events.out.tfevents.1712280142.f35651a1a25c.4583.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d5b2e8c94afbbe152d7f5e103a184256b17211343d2941edea70111711f0f5e
+size 5410

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce176e5dfe3d42e67c031fb5df98cf1004e81fc2615720db9b436d2585f0e4ba
+oid sha256:403626742f6efe5f62eac6bcb5e8ca4ed2b74f8fadca2dab1b48be04a27ca074
 size 4984