Training in progress, epoch 0

adapter_config.json

@@ -9,24 +9,23 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 128,
-  "lora_dropout": 0.05,
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 256,
+  "r": 32,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "w3",
-    "o_proj",
-    "v_proj",
     "q_proj",
-    "k_proj",
-    "w1",
-    "gate",
-    "w2"
+    "down_proj",
+    "v_proj",
+    "gate_proj",
+    "o_proj",
+    "up_proj",
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_rslora": false

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03cf4ecbf519cfd2191c52843c45f1f95228d9caba9646ae10d3b988bbe6f598
-size 6228803672
+oid sha256:887977b6761d09cd9a6ee7df4eacfdbe5f70c76356d4de75ca6f51ef2b49c884
+size 2155941056

runs/May24_09-20-05_7b5cac4c8b77/events.out.tfevents.1716535212.7b5cac4c8b77.6738.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df585f9af591ed68a6ad06f4ddedcc48eccce4214f23e17be49e728e73e1ffbe
+size 7725

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c88030686ce249880b5e796c1f6ad903e9e94d0d4947f16c386a752ae67830c8
-size 4728
+oid sha256:939a5941c4930400e6cd1c6cec19687665ca95ffa7886bd0664ac3783c603108
+size 4792