Training in progress, step 9800

adapter_config.json

@@ -6,6 +6,7 @@
   "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": true,
+  "layer_replication": null,
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
@@ -19,14 +20,15 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
     "up_proj",
-    "q_proj",
-    "v_proj",
-    "o_proj",
+    "k_proj",
     "down_proj",
-    "gate_proj"
+    "gate_proj",
+    "v_proj",
+    "q_proj",
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM",
+  "use_dora": false,
   "use_rslora": false
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d96ad2b2d6f118a446967b4debac5542680094b6799e01841c074ddab8cd121
+oid sha256:270faa4bbd2414fdde052a0e29af8131e07a22ff50660163c28815407865ae05
 size 1279323952

runs/Apr23_17-32-31_kao-dgxa-e10-u17/events.out.tfevents.1713889994.kao-dgxa-e10-u17.2570641.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8deaa8bf4c30d53e0ab51ee95ece15c70a030cd97083f37c82bd5f2f35460405
-size 1915904
+oid sha256:cb4259ecb93766008cd4ed2bfeee4b4d246d65a153e8ddf15b5bba661097574e
+size 2070958

runs/Apr25_13-58-59_kao-dgxa-e10-u17/events.out.tfevents.1714049944.kao-dgxa-e10-u17.1372452.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c91d05865c3b0d0aaebb37ca731a07fbde75cffe300ac88ef62073c8b3e7ab13
+size 47975

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:230a0e6ecc55e3ac3db0634341f495d0fc218e198cb8b8101c8006c07d88ff40
-size 5112
+oid sha256:0490a23edda05a4edbaad9171f37b3ad6b45a4f23c98b4b715b411787f36b66a
+size 5176