Training in progress, epoch 0

adapter_config.json

@@ -10,22 +10,22 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 128,
+  "lora_alpha": 16,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 256,
+  "r": 64,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "o_proj",
+    "down_proj",
     "q_proj",
     "gate_proj",
     "v_proj",
     "k_proj",
-    "down_proj",
     "up_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d125515430bf0cfd92f119a0b6ad2801e12024cc3d6b461e1f70bd12fa2db84e
-size 1342239008
+oid sha256:72695af6f18b93243aac09d2bca5b1e6428277932fd5edb5c81432f33124451c
+size 671149168

runs/Jul09_08-00-20_6c79c09bc9e5/events.out.tfevents.1720512110.6c79c09bc9e5.4868.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b55d0c25c8865e4d0ece4f18dcc5a89428fc44f60b939baf9639744c5e130111
+size 4184

runs/Jul09_08-03-22_6c79c09bc9e5/events.out.tfevents.1720512205.6c79c09bc9e5.6619.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:092d6b66f12e88f66d5598c25bace8a8f9e03df75dd62763907e7035b70cb244
+size 6221

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74a5ebc63e8473b6f2f9cfaefda1cc34bb69187ce396c7ef523921b2d2ea40ab
-size 5176
+oid sha256:316c753f9cd5f389a9570367e97ca08c2b43f65be86d9b52949cd2647cda590b
+size 5368