Training in progress, step 50

adapter_config.json

@@ -10,23 +10,23 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
+  "lora_alpha": 512,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 128,
+  "r": 256,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
+    "q_proj",
+    "k_proj",
     "down_proj",
+    "up_proj",
     "v_proj",
     "o_proj",
-    "gate_proj",
-    "k_proj",
-    "q_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:dc0a0d36685063abfcb83bd2cf7302e9a5a76cc58234819556b8db357fd35706
-size 2332095256
+oid sha256:aecfd56b4f402b9943762609df0524c4754b22c57ba888b4d52195299eff8b33
+size 3611357976

runs/Apr02_05-35-06_1f3fbe1ee1c0/events.out.tfevents.1712036116.1f3fbe1ee1c0.6359.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f60026f6982a5ff91d155134bed4c265e684a098277413be985912a4f372ec23
+size 5411

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d7194c454de1c8662e06109a53ffbaecc7e48f2be8a3a6cd4d3907e4aefec0c
+oid sha256:0bcbaa9e0c85cfabcfcb328cfdf2cf920c56178cee9b246cdd4a0bb41c090cae
 size 4984