Training in progress, step 100

adapter_config.json

@@ -10,23 +10,23 @@
   "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,
   "peft_type": "LORA",
-  "r": 8,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "k_proj",
-    "v_proj",
     "q_proj",
+    "down_proj",
     "o_proj",
-    "up_proj",
-    "down_proj"
+    "k_proj",
+    "gate_proj",
+    "v_proj",
+    "up_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:c7b95deeb84e22467dfafc0746ad9bfc804aab1f995e55e3b26cf0c371a8c453
-size 19644912
+oid sha256:10644171c4f9e00108c7f5b739bba8458404e61dabf30114ec2a216371ed60f9
+size 39256960

runs/Jun10_03-34-16_48ddfe8e991f/events.out.tfevents.1717990608.48ddfe8e991f.74946.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:001ae172deddc14f2546747c49543b69426d1fbe2f6c6a6439af16b935f07aa9
+size 9956

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d889397c2e07b72245e38515ecd3382fdce1ee92051f51ad40b982f68739f507
-size 5176
+oid sha256:7635952a5ef9d0df3b73e9cad3902787d049992c2e26b42159a6d80284bebac3
+size 5304