End of training

README.md

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: google/flan-t5-base
+base_model: google/flan-t5-small
 tags:
 - generated_from_trainer
 library_name: peft
@@ -33,13 +33,13 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.001
+- learning_rate: 1e-05
 - train_batch_size: 32
 - eval_batch_size: 32
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 6
+- num_epochs: 8
 
 ### Training results
 

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "google/flan-t5-base",
+  "base_model_name_or_path": "google/flan-t5-small",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -19,8 +19,8 @@
   "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 sha256:56ce65836cae5f72da61720ff56c619ba52b541d6529e270d35965a012a8db23
-size 7098016
+oid sha256:4ae2def3736d75c1a9f8aa0fc077f32b4e1d30b774b9b46b283ef60879d40adc
+size 2765880

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:303a0e4d66335ffc24cfdd0f562f79f146a04971e2375498ca107f88386b1cc6
+oid sha256:c101e3c4223da2a18d639ab84aebb09086d318f2ad8e71e4d5af8f92e37e9231
 size 4856