Training in progress, step 10

adapter_config.json

@@ -7,14 +7,17 @@
   "init_lora_weights": true,
   "layers_pattern": null,
   "layers_to_transform": null,
-  "lora_alpha": 32,
-  "lora_dropout": 0.05,
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 16,
+  "r": 64,
   "revision": null,
   "target_modules": [
-    "query_key_value"
+    "query_key_value",
+    "dense",
+    "dense_h_to_4h",
+    "dense_4h_to_h"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15b14a293a4f53fba8df0c41b2e6b4bef81f54a53a9d5108ad6ec29a7e73cfec
-size 18898161
+oid sha256:bba8e475ad3408f6bee6be775f421555c7c138cf7f0f6c227c6fff552f2d591c
+size 522284877

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 1024,
+    "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:cd463a31be8e7c1fe29693ee0cf2a9854d9bd07fa9a16c18cf0638dd362fd7ab
+oid sha256:ef510fb627ec8a9476f1430f75d3272f1be71466b29516709831ab96f6b46538
 size 3963