Training in progress, epoch 1

adapter_config.json

@@ -9,7 +9,7 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 64,
+  "lora_alpha": 32,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
@@ -17,17 +17,17 @@
     "lm_head"
   ],
   "peft_type": "LORA",
-  "r": 8,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "k_proj",
     "gate_proj",
-    "o_proj",
     "up_proj",
-    "q_proj",
-    "v_proj",
     "down_proj",
-    "k_proj"
+    "v_proj",
+    "o_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_rslora": false

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8b71f4933ae483355e1688923428ec4427c74e5253ed82bfacff4e684f856a6
-size 1090646616
+oid sha256:491f4b0615148f4016161512d99f159f6258616f5a095dbb1e5aedd88bac34d6
+size 1132590104

runs/Apr07_09-20-07_f812a9042f10/events.out.tfevents.1712481636.f812a9042f10.947.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:011c13e2e8591435b3f8a48570acbdc09cacbc88a382dda31c41750b611341eb
+size 4954

tokenizer.json

@@ -1,11 +1,6 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 3072,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
+  "truncation": null,
   "padding": null,
   "added_tokens": [
     {

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee104c7074019e1eae3d7edeef3b8a47b4315795ac0fabdd6aa7886ec5186896
+oid sha256:087c66220d67c6cd5f570df05279bbc1f3924aafb5adc045f6cc83232166f8e3
 size 4728