Training in progress, epoch 0

adapter_config.json

@@ -9,13 +9,13 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 1024,
+  "lora_alpha": 256,
   "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 256,
+  "r": 128,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcc0e0ef0919c59fcc3bb42c47034e1851c860bc23aeea8e4a66a6d44114023c
-size 100677976
+oid sha256:6aa33e843e2e2ac8293b20a151986f2977bdf431fcd5c1b1ba4f8477c3975bec
+size 50342216

runs/Apr19_14-31-10_gpu-1/events.out.tfevents.1713537071.gpu-1.21346.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dcbe9e76c6e638bd7a8cb07d1d197390dfb2ed85db2084474c54011b6619374
+size 7910

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a12ffd7f6d652becaac0ab7d27e1cfca85dfbfbb4502da39b8fbb76b748236b
+oid sha256:06e8929a80de28e12f45968923085ba26bb8d13767d86353b9fd7035e7568046
 size 4920