Training in progress, epoch 1

adapter_config.json

@@ -10,21 +10,23 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
-  "lora_dropout": 0.1,
+  "lora_alpha": 128,
+  "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 64,
+  "r": 256,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
     "gate_proj",
     "o_proj",
     "k_proj",
-    "v_proj"
+    "q_proj",
+    "v_proj",
+    "up_proj",
+    "down_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:e197622f2624e183d7145b0a0a5d997d1e82a9a552370b30c79adde1cf6269c6
-size 369142184
+oid sha256:ad6a8a59af278affcfe391cf32f2211dc5701a160375d2c97c80b3eb0a890164
+size 1342239008

runs/Jun12_13-38-04_ab6f5b8f37ef/events.out.tfevents.1718199498.ab6f5b8f37ef.4299.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:431f236e64d6ccd0e12fd9ef19f1eca0f41e664047f01938cdd5a29dfac5d4f8
+size 5432

runs/Jun12_19-56-46_b8dff662b5a0/events.out.tfevents.1718222221.b8dff662b5a0.3019.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63bc1796d44796f8918c2872f2e78599f9723d5e81c4fd9ecf815800bbbc3004
+size 5639

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 sha256:442ee676c956fc65c04961ce59c62197bd0e9fd000789efd75bc9789e72e667a
-size 5112
+oid sha256:eeae958a419b66025b4b30b9d1bd3b00ab9fedb7d156497c71643c43de96c382
+size 5176