Training in progress, step 50

adapter_config.json

@@ -10,23 +10,23 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 8,
+  "lora_alpha": 128,
   "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 4,
+  "r": 64,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "k_proj",
     "v_proj",
     "q_proj",
-    "o_proj",
     "up_proj",
-    "gate_proj",
-    "down_proj"
+    "o_proj",
+    "down_proj",
+    "gate_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:b85235b9fd06fc2b7556026c9d400735ea1cf6ceb01413094a4e13a4f220409c
-size 40036040
+oid sha256:fda53b2dbb64ee3df1572930d050a53fd43af43308677011be467155149e9da9
+size 639691872

config.json

@@ -19,7 +19,7 @@
   "quantization_config": {
     "_load_in_4bit": true,
     "_load_in_8bit": false,
-    "bnb_4bit_compute_dtype": "float16",
+    "bnb_4bit_compute_dtype": "bfloat16",
     "bnb_4bit_quant_storage": "bfloat16",
     "bnb_4bit_quant_type": "nf4",
     "bnb_4bit_use_double_quant": true,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8572afd05393422d8959a963fd5560752865fdb6ad5191112e1b0b4f625b9672
+oid sha256:467127371b2d4da2f03dc3723fc2daad3034ada0f638fbfcb2df74368b95df56
 size 6776