Training in progress, epoch 0

adapter_config.json

@@ -9,19 +9,22 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 64,
+  "lora_alpha": 16,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 32,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "fc2",
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "dense",
     "fc1",
-    "Wqkv"
+    "fc2"
   ],
   "task_type": "CASUAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9c78d841cea7f615bc21abedc9ad78a478dab743eacaf08282160409421e49a
-size 146825352
+oid sha256:80db286f62ce58b5ba413b651a9c434241d43704dbc9bfb41e60b29e819059ac
+size 94422368

runs/Jan18_16-04-33_04747477d0a5/events.out.tfevents.1705593884.04747477d0a5.945.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0013295590a5509597fabc20bacfbca931e747b4f35350e4818643276d05521f
+size 6932

tokenizer.json

@@ -2,7 +2,7 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 690,
+    "max_length": 1024,
     "strategy": "LongestFirst",
     "stride": 0
   },

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b56dbfd6aaec75a50b700846cdc336349b79525223611a5aa526c1086985a7f1
-size 4664
+oid sha256:d2aa8436bcc0024971ac69a2823e2fd635857afb1d5a7580ea83f8d657e27919
+size 4728