Training in progress, step 200

adapter_config.json

@@ -9,23 +9,23 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
+  "lora_alpha": 128,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 16,
+  "r": 128,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
+    "up_proj",
     "v_proj",
-    "o_proj",
+    "q_proj",
     "gate_proj",
     "down_proj",
-    "q_proj",
-    "up_proj"
+    "o_proj",
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cb5c6fc7d4bdfeb0a0cf7462bf351aef0423bfa34b4b3b3c04ea9d593fe5fa3
-size 83945744
+oid sha256:112c34f8b3357a99160d97016c03590ef6825bbf2cde3805901445b16c905f9f
+size 671150064

tokenizer_config.json

@@ -1,4 +1,6 @@
 {
+  "add_bos_token": true,
+  "add_eos_token": false,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbc4e5dcb3ef08d7a371088bc04ccc10240a32b15ead5755a987f922ecc1b4b9
-size 4856
+oid sha256:89ae9269821a7a76bfccee733cea8c3af1d1b7b751ef31fb40915f4d080f4944
+size 4920