Training in progress, step 500

adapter_config.json

@@ -8,18 +8,18 @@
   "init_lora_weights": true,
   "layers_pattern": null,
   "layers_to_transform": null,
-  "lora_alpha": 32,
-  "lora_dropout": 0.05,
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 16,
+  "r": 64,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "o_proj",
     "k_proj",
-    "q_proj"
+    "q_proj",
+    "o_proj",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4067ee277ea49356f2e88a2457d2fcab69a2cdf217a7b5e178d8008490bb894f
+size 54618762

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:536db3fc719f4c85b44d08d718813950054a871955c92870658a2480c307bddc
-size 54560368
+oid sha256:f5560923ab034e3ec71d599e2f6d4798265ce3277416f05cea26b4aaf22f0697
+size 218138576

runs/Nov18_04-50-43_7a59b30c842e/events.out.tfevents.1700283049.7a59b30c842e.54271.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ad018de6c9f53597548da4393e80576812d1783b7ca5ec96c52e8ca9223259c
+size 14972

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef091abff04e499d3cc53095af484677738d5a7f8cb57daf0a3da0e27614f20e
+oid sha256:f01231f953caf52809552663f90a4cfedb9b5fb08c672c9a34ce629fa20a423f
 size 4600