Training in progress, step 500

adapter_config.json

@@ -10,23 +10,23 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 4,
+  "lora_alpha": 8,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 4,
+  "r": 8,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "q_proj",
+    "down_proj",
     "gate_proj",
+    "v_proj",
     "o_proj",
-    "up_proj",
-    "down_proj",
     "k_proj",
-    "v_proj"
+    "up_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:159923ef13e2912ce7eb4db834a9b603db22abb5cdf4669b3bdd02e672be6c0c
-size 11301296
+oid sha256:432622e3909ad4aad2b4472f906cf00f2eda3620d13e105e478148d4a87132ea
+size 22573704

tokenizer.json

@@ -2,13 +2,13 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 3072,
+    "max_length": 2048,
     "strategy": "LongestFirst",
     "stride": 0
   },
   "padding": {
     "strategy": {
-      "Fixed": 3072
+      "Fixed": 2048
     },
     "direction": "Right",
     "pad_to_multiple_of": null,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37cdbe9793ba7a4337dedeb39e13fd29338572727aacf834bb2bc04de4644c7e
+oid sha256:747a1f2aef8a24fa516ef7cf77cde8caacc9991b4e096eee03111844c6dd72a7
 size 5496