Training in progress, step 500

adapter_config.json

@@ -12,19 +12,19 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 64,
+  "lora_alpha": 16,
   "lora_bias": false,
   "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 32,
+  "r": 8,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
     "k_proj",
+    "q_proj",
     "o_proj",
     "v_proj"
   ],

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:408a6edb092851f30388cd935ef581521018a1c466e9d8722f26dfc33fe27a24
-size 34895152
+oid sha256:b1b2f3093149cebeefedf3a5ee1a415b660f6f3a1cc4c7681b14ba933ad8fa32
+size 8745704

tokenized_dataset/cache-6211ebc98931c431.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c6d8732b0e61aec94dec36f5c624b62f55d82fe17cede28384172483c8a9928
+size 120105536

tokenized_dataset/cache-71f8ee40ee86bdb9.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebb3213976f6a7b2cd70e4f4ba0e81761e34957d8d5cfdab0c292d2a3ca6a16c
+size 120105536

tokenized_dataset/cache-811439b4c9b54ef5.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb9777d5024d9a9cc9baac3f018572afd5ee899e2d4652e313232e65ca251eb4
+size 120105536

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89a7fd6fff523254fd035d4be817533440573ca5b9e42395c0b537d145a503c5
+oid sha256:ba807154eae7864376bdf7117097ddeb38e678537034894f828221aadcf66a6a
 size 5624