Training in progress, step 100

adapter_config.json

@@ -10,23 +10,23 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
+  "lora_alpha": 64,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 16,
+  "r": 32,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "q_proj",
-    "o_proj",
+    "up_proj",
     "v_proj",
+    "k_proj",
+    "q_proj",
     "gate_proj",
-    "up_proj",
-    "k_proj"
+    "down_proj",
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:930ea29ccd95814b32285a5e5c862b2d3de141e67205b09e2d91eb1f7ddcf5a8
-size 39256960
+oid sha256:5b991ee0eaf82b43ed847090bf7c527ef6051479e867c82c0ab458f0666eccd6
+size 78480320

runs/Jun10_07-38-05_48ddfe8e991f/events.out.tfevents.1718005108.48ddfe8e991f.245392.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ff0e48b16dc26f1129f3b625e7ece6f73d2c1bad27726ecd19a414034d23f28
+size 9955

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dc409c4c05b7a2392f06cb69b4db7b59eb53e01c5613fb8b47544acbcdf3db9
+oid sha256:b2743ef25dde04fd587046e84999fece049676d107d0838fc9353f5b4df3542e
 size 5304