Training in progress, step 500

adapter_config.json

@@ -9,18 +9,18 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
+  "lora_alpha": 20,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 8,
+  "r": 10,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "q_proj"
+    "q_proj",
+    "v_proj"
   ],
   "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 sha256:8fb6abaf2d38d5695cd3c80b1932e860e3602a2cf9bf9cdb1dc31348a6e8fcdb
-size 1779432
+oid sha256:93cbda98cfcb716422d64ae66d6bdde98f0cc48f14caf1a286a01958e8948ae8
+size 2221888

runs/Mar04_07-46-12_ad3495d78288/events.out.tfevents.1709538391.ad3495d78288.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af8b594e58f4d2c733ff75b7f7296e85ebff2ffcdea8f9a5c63e781dbdc881d1
+size 5876

runs/Mar04_07-46-53_ad3495d78288/events.out.tfevents.1709538422.ad3495d78288.34.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d70f10c1392f921ed51c792e7af0f4fdb27710776fd527fd1a80228fa1dbdfd5
+size 6826

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 600,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a2f9a0eb104ffd994e65cfdd2a7ab7e441afb1483ae16a8fb409078d384e870
+oid sha256:c1423dd304ace557156c35f22cbd08e70a654a1648c4d6d95b5f44ddcdd53932
 size 5112