End of training

README.md

@@ -1,6 +1,8 @@
 ---
 base_model: google-t5/t5-small
 library_name: peft
+metrics:
+- accuracy
 tags:
 - generated_from_trainer
 model-index:
@@ -11,10 +13,13 @@ model-index:
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/zhuangc19/cs5740-sp24-assignment-4-Marcozc19/runs/hj1n2hx5)
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/zhuangc19/cs5740-sp24-assignment-4-Marcozc19/runs/qpe1e9fe)
 # ft-t5-small-on-airlineDB
 
 This model is a fine-tuned version of [google t5-small](https://huggingface.co/google t5-small) on the custom airlineDB dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1025
+- Accuracy: 0.0064
 
 ## Model description
 
@@ -39,11 +44,14 @@ 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: 0
+- num_epochs: 1
 - mixed_precision_training: Native AMP
 
 ### Training results
 
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.1773        | 1.0   | 1057 | 0.1025          | 0.0064   |
 
 
 ### Framework versions

adapter_config.json

@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v",
     "k",
     "o",
-    "q"
+    "q",
+    "v"
   ],
   "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 sha256:93a479c3b20851a1675f8c95b456602e7515b4adaf79005585a12ae6eb51f8d9
+oid sha256:9a3147f6cf51ca9d0cf3ad00f3876686cc3900f491598ae9bb0e410f93b1dcaa
 size 1199384

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e148be22a31a4a75005ebb470e79e4f5c3f397a102a4da98a2b78ecf6057bb85
+oid sha256:4bb32ae384cee172a5834aabdd4f735507adbbae1c2561c3ff9628c10bde6b57
 size 5240