Training in progress, step 500

adapter_config.json

@@ -12,19 +12,21 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 64,
+  "lora_alpha": 16,
   "lora_bias": false,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 32,
+  "r": 8,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "v",
-    "q"
+    "k",
+    "q",
+    "o"
   ],
   "task_type": "SEQ_2_SEQ_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4183f3ff9cb16c4be3ba5964836fe5b115257921c5758b548ad2eaaa94df0bce
-size 14176016
+oid sha256:daed4f58aaeb134c2276109ddda78ec1a836644a8550ee5f0b062d44419900e4
+size 7117824

tokenizer_config.json

@@ -1,4 +1,5 @@
 {
+  "add_prefix_space": null,
   "added_tokens_decoder": {
     "0": {
       "content": "<pad>",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:257adc19181b44d46a14429956f6d930b2ba08cb030ef48856b822e1a4c079c4
+oid sha256:fcbfb8f8a1b2e761d439397c55cf07067038f3736cccd50d377ea739836ab149
 size 5560