Training in progress, step 50

adapter_config.json

@@ -10,7 +10,7 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
+  "lora_alpha": 16,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "up_proj",
     "v_proj",
     "q_proj",
-    "k_proj",
+    "o_proj",
     "gate_proj",
+    "up_proj",
+    "k_proj",
     "down_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37597c3d7e258afac498056817c9707ad704910389c883c46eedb56f1f33a272
+oid sha256:2e8a1dfbbd6261ba810dd5070b2037346c9f48e0ca00b5a4a3e341a63daddb2b
 size 2332095256

runs/Apr03_00-57-30_7e7dbb80658f/events.out.tfevents.1712105860.7e7dbb80658f.1971.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bb8ccf6078d92f680ad3e35c75b5a093bcc6971a353aa1cca4ab6f5145d19fb
+size 5411

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7429726cd8d2c5c6d4f0cc837af40995e4af7e7154a174cf10b52ff0a9a8b26d
+oid sha256:9d6b7728ebd5084cc3d8f3eba3f5c02a8b62ec3cb6aa6428dde2a2a245350d95
 size 4984