Training in progress, epoch 0

adapter_config.json

@@ -11,22 +11,22 @@
   "layers_to_transform": null,
   "loftq_config": {},
   "lora_alpha": 64,
-  "lora_dropout": 0.1,
+  "lora_dropout": 0.2,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 16,
+  "r": 32,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "q_proj",
-    "k_proj",
+    "v_proj",
     "down_proj",
+    "gate_proj",
     "o_proj",
-    "v_proj",
     "up_proj",
-    "gate_proj"
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ced55d07bbe1717989ac6eed4c8bb63afa000f39b42d88d4977f55439931363
-size 167832240
+oid sha256:5d721ede47684c9abc657f6fedef87014566ca68c17c259d692d0418e1118b22
+size 335604696

runs/Jul11_06-11-08_ebac200b0d3f/events.out.tfevents.1720678351.ebac200b0d3f.1249.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5bd1fecd7df32993ba62622eba1ade4802786f5526ae504c928eb32209c901b
+size 4184

tokenizer.json

@@ -2,7 +2,7 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 4096,
+    "max_length": 9192,
     "strategy": "LongestFirst",
     "stride": 0
   },

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4f0b5dc2ca750a218fc1aadae315602ea07f1e974ae08376fa53da677c38eca
+oid sha256:216198139adf47830a6226d45da71cd249599bcb6b420b4d71412a19e7b57a4e
 size 5496