Training in progress, step 500

adapter_config.json

@@ -10,23 +10,23 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 8,
-  "lora_dropout": 0.08,
+  "lora_alpha": 16,
+  "lora_dropout": 0.09,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 8,
+  "r": 32,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "down_proj",
     "up_proj",
+    "down_proj",
     "v_proj",
-    "gate_proj",
     "o_proj",
-    "q_proj"
+    "k_proj",
+    "q_proj",
+    "gate_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:d42dde5a2694a17a6dc7858ac284f52f0e25c3664738c3a797bc034bf2af127c
-size 125918320
+oid sha256:c9395df68ee74114fe5c94758eefc0cefdb248ec29918b947b185b0e8874944c
+size 503407240

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 512,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57356aa92834a903ed42dd8ed6253f3f8e00beb54d25086fde818a4e582a0603
+oid sha256:4ac1475d2dd06c092ad6d8a23f2ffbdafd0f365ca34fa280aa3b3bc0d1f8f214
 size 5368