Training in progress, epoch 1

adapter_config.json

@@ -9,24 +9,24 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 128,
+  "lora_alpha": 64,
   "lora_dropout": 0.5,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 256,
+  "r": 128,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
     "o_proj",
-    "v_proj",
+    "gate_proj",
     "lm_head",
-    "q_proj",
     "up_proj",
-    "k_proj",
-    "down_proj"
+    "q_proj",
+    "down_proj",
+    "v_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 sha256:8a5163c0958fb8dfe7f7e892851f8b9443ec335afaa2b0734dca243ee7a92177
-size 1046440320
+oid sha256:7554ef5d6275a598777603ea2e4073b3226a7a241f7637ce4aebff323451667b
+size 674441048

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cc282d0318c9b0c569c69bbecb6488cdc47169d34406dee9e534624658a1514
-size 6255
+oid sha256:e9468d7707d89302e1a3e3acea4265db6d572f93d329fc55d704426592a1a145
+size 6569

runs/Jul11_12-13-08_613c368fef6f/events.out.tfevents.1720699996.613c368fef6f.31176.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5d6e0696b3e134541ec48a69e61a5224ab3f1561833f17c21e16584ca136f5c
+size 5239

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d520296b7f1465671928f9daad982b90dd35d531536385261fa593ad5cd48f7
+oid sha256:34ab2d4e310879ab32422ec1e483fb7c90007ef315569052cb6d71555519b735
 size 4728