End of training

adapter_config.json

@@ -10,7 +10,7 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
+  "lora_alpha": 32,
   "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
@@ -20,9 +20,9 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "o_proj",
     "down_proj",
     "qkv_proj",
-    "o_proj",
     "gate_up_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d52b79b6457d5518306ddf32a2b422f637ab184dbff3c2ddfa2e603c81b425a1
+oid sha256:0416ed9f9dd238cf7c268705028cb5a3968b03281c9b2120db29f533340b576a
 size 201361568

runs/Dec09_02-28-43_e18105abca6d/events.out.tfevents.1733711419.e18105abca6d.1193.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5768b025aea9d8b21356f367be131888b445b3f4cbdb356dab60a307572ec3e1
+size 27190

tokenizer.json

@@ -1,7 +1,19 @@
 {
   "version": "1.0",
-  "truncation": null,
-  "padding": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 2048,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
+  "padding": {
+    "strategy": "BatchLongest",
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 32000,
+    "pad_type_id": 0,
+    "pad_token": "<|endoftext|>"
+  },
   "added_tokens": [
     {
       "id": 0,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1da18c039f80a4ef12f9be02fea240ffb129e4abfe14d1c511de6bc1ad840a30
+oid sha256:c388b8e4b73914ad812fdfd2d501c63b0b0c67ec74a3d99f4376e357ddc7b861
 size 5560