Training in progress, step 500

adapter_config.json

@@ -9,20 +9,20 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
-  "lora_dropout": 0.1,
+  "lora_alpha": 32,
+  "lora_dropout": 0.01,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": [
     "lm_head"
   ],
   "peft_type": "LORA",
-  "r": 16,
+  "r": 8,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v",
-    "q"
+    "q",
+    "v"
   ],
   "task_type": "SEQ_2_SEQ_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb88a0308ecd30b0b3cbcc7f91ca8332df55a27e9c23cc7f410d70e4c13a2691
-size 150511720
+oid sha256:2b9aaa95f7c66083a5d57b1885feabfb2f40ba0a10790b5fb1bea6e9a889585b
+size 141073944

tokenizer.json

@@ -1,21 +1,7 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 30,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
-  "padding": {
-    "strategy": {
-      "Fixed": 30
-    },
-    "direction": "Right",
-    "pad_to_multiple_of": null,
-    "pad_id": 0,
-    "pad_type_id": 0,
-    "pad_token": "<pad>"
-  },
+  "truncation": null,
+  "padding": null,
   "added_tokens": [
     {
       "id": 0,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:147b2df6f46d9de7cfda46969ce87d4b9c259fda1d673ca46ec0b77d19af9aa2
+oid sha256:fbe9e7dbb0a8f131bcf38b0e26110ab4d2ef08b14bacd2d0de11344e3650bac0
 size 4856