End of training

README.md

@@ -38,7 +38,7 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 2
+- num_epochs: 5
 
 ### Training results
 

adapter_config.json

@@ -9,15 +9,15 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "lora_alpha": 32,
-  "lora_dropout": 0.1,
+  "lora_dropout": 0.05,
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 8,
+  "r": 32,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v",
-    "q"
+    "q",
+    "v"
   ],
   "task_type": "SEQ_2_SEQ_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e7fe2f536d90b8617971466b943a33f100d775b68e658d1854e6a3077d2eb2d
-size 1389456
+oid sha256:a47390e56a49e236db25c0a34067615e1df710a60e026c3da4378f5ff2910cae
+size 5518432

runs/Nov11_17-05-50_e969487f6c0c/events.out.tfevents.1699722357.e969487f6c0c.27.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ff256325c7ab3156cbc991faa36435c5d60cabd27687ae8e76ff26dff45210f
+size 31650

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05b5767661ae0f7e25cd7c7a347d7c6c723305f7db84d7b6c9f64ef8d1024e36
+oid sha256:b1af9fd52320d0cabdc11f09f85c419b165234baaf8cfd509dc8a7181f3f955b
 size 4091