Training in progress, epoch 1

adapter_config.json

@@ -10,7 +10,7 @@
   "layers_to_transform": null,
   "loftq_config": {},
   "lora_alpha": 128,
-  "lora_dropout": 0.05,
+  "lora_dropout": 0.5,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
@@ -19,14 +19,14 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "lm_head",
-    "q_proj",
     "gate_proj",
-    "down_proj",
+    "o_proj",
     "v_proj",
+    "lm_head",
+    "q_proj",
     "up_proj",
     "k_proj",
-    "o_proj"
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_rslora": false

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23bc6126fd630331b1389479adcc565c46ece98b896bafa38ae6e38c514921e2
+oid sha256:81d9201f55b0294b8d89c22982936e1a33e72a178c92641b4d0e0cb26ac336c9
 size 1046440320

runs/Jul11_10-36-38_613c368fef6f/events.out.tfevents.1720694202.613c368fef6f.3160.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14e1c76930c94def227a88f3418893af5aded289e8e3160249bbc5996c0c58ea
-size 6255
+oid sha256:7454fa271ddce242bc184ceced8a9c636550ecbbd2306e69eb8d20b253630877
+size 6840

runs/Jul11_11-25-44_613c368fef6f/events.out.tfevents.1720697149.613c368fef6f.17666.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:813fee139c824701c429cb8a0579689bf7fcdb4b42ae79f4999a865b1a16ca4e
+size 5242

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0eccd748d316ebce84f2d44254590fd6bd3c2e125728e1851ac1099b11129eea
+oid sha256:9d520296b7f1465671928f9daad982b90dd35d531536385261fa593ad5cd48f7
 size 4728