Training in progress, step 500

adapter_config.json

@@ -10,23 +10,23 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
+  "lora_alpha": 32,
   "lora_dropout": 0,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 64,
+  "r": 128,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "up_proj",
     "down_proj",
+    "gate_proj",
     "v_proj",
     "k_proj",
-    "q_proj",
     "o_proj",
-    "gate_proj",
-    "up_proj"
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c4b69318e165602cb40d74436cda254b9b0138cb28bbef85bb785a88fe8bde1
-size 864368280
+oid sha256:7b15d9a9e19b5c1bfb4e4f2036c24ef3308c57b09fa3c5cd44260c99ae270bc2
+size 1728658208

runs/Nov24_12-55-24_5638fd9fa0c6/events.out.tfevents.1732453046.5638fd9fa0c6.30511.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a672ae66dff3526f139d1e8ad02d76cd95c604b2cc4bd7969ba72525b378b61
-size 216529
+oid sha256:61a1f1cc2e9606d7d77311ea966cd1dfd6c4e4ab0e87f5ae66eb2c9fb1820c0e
+size 220749

runs/Nov24_17-22-04_5638fd9fa0c6/events.out.tfevents.1732468929.5638fd9fa0c6.99758.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bc0eb3e41c32d0a6db60cea636a95a886a6549e5d01afe82fcb50ee12a02be6
+size 111033

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22661b6db94abb271f4271ee8ac79945f18d7ca9cee0c1fbed7cdbc14a6f4c0a
+oid sha256:548101c102bd26acbf38711e1fb89c1b07a45521a64e122a7fcd7d8cbb44529c
 size 5560