End of training

README.md

@@ -40,7 +40,7 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
-- training_steps: 100
+- training_steps: 50
 - mixed_precision_training: Native AMP
 
 ### Training results

adapter_config.json

@@ -20,8 +20,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj"
+    "v_proj",
+    "q_proj"
   ],
   "task_type": "SEQ_2_SEQ_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba8437022963018c73d4829c895eee8e4168766b735a48e5d54b072ee898060c
+oid sha256:cfab55395fe2f807f329fdca306b539e296d22d4d0dd95ab0a3ac46da737d70d
 size 2369344

runs/Jun01_15-12-13_57f9e1f95c64/events.out.tfevents.1717254734.57f9e1f95c64.647.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ab64fce5c6e1ea36545f29dabdc562a2923a9ce7c0fa488aaff64eda981f4eb
+size 6120

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58f8d09f71e7dec06464b662f10569952822541e71a3c31eb19adc9337de5a6e
+oid sha256:2504fe56b905e4af304ee895b57b2b6e5f374f56533c76da7ef2f37afb8b33f3
 size 5304