Training in progress, step 10

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",
@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "dense_4h_to_h",
-    "dense",
     "query_key_value",
-    "dense_h_to_4h"
+    "dense_h_to_4h",
+    "dense",
+    "dense_4h_to_h"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40dcd1f7839991f190fba13241228af937bcc2fcee566b8555955a02e8d5e424
+oid sha256:ed8379a0eefb5eed5482309566d9553a24d335155a7a97bdeb1735851e0ad728
 size 261131840

runs/Aug01_08-42-50_8aebd631e25d/events.out.tfevents.1722501785.8aebd631e25d.776.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea773f0d95663673da471ffbda2ed59bd5bd206f625a11c73da5da0866b7cb32
+size 6635

runs/Aug01_08-47-12_8aebd631e25d/events.out.tfevents.1722502035.8aebd631e25d.4724.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f2d43b09db7c7545c3efd6b1835ff6736adf9e12895cb5865978f99a0f1db7e
+size 8291

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15123861d1579986d47e4fec1802dc934a3445e3f0989adc19b463dde1f440ad
+oid sha256:c156420d9a576c16f34b9aaa38779494b369131ddf069a2746f8a0f2561af849
 size 5432