Training in progress, step 50

adapter_config.json

@@ -10,23 +10,23 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 1,
+  "lora_alpha": 8,
   "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",
-    "gate_proj",
-    "down_proj",
+    "k_proj",
     "o_proj",
     "q_proj",
-    "v_proj",
-    "k_proj"
+    "gate_proj",
+    "down_proj",
+    "up_proj",
+    "v_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:d87365100be548bb629157f36c166dd2fbd639027f9cf131990e1fb654e9f156
-size 2332095256
+oid sha256:0dc53da8154b2215e335c93745f6f95a948073702033c61346df61824c7f3643
+size 3611357976

runs/Apr04_08-41-59_b562675953c9/events.out.tfevents.1712220131.b562675953c9.118101.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31f4be93dcea86246ec38728cb33c94c0cb79582080e0814cda14e871131c864
+size 5410

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f25f22e5af78cfd4cb3a350fdbf786ce0ae235cbee7ecd9ec95b99be916d80f3
+oid sha256:ce176e5dfe3d42e67c031fb5df98cf1004e81fc2615720db9b436d2585f0e4ba
 size 4984