Edit model card

Model Card for Model ID

This is the T5 Model on that is trained on the BillSum dataset.
Trained on the Google Colab's T4 GPU

Training Arguments

training_args = Seq2SeqTrainingArguments(
"bert-on-the-billsum",
evaluation_strategy="epoch",
learning_rate=2e-5,
per_device_train_batch_size=2,
per_device_eval_batch_size=2,
weight_decay=0.01,
save_total_limit=3,
num_train_epochs=4,
predict_with_generate=True,
fp16=True,
push_to_hub=True,
)

Training Results

Epoch Training_Loss Validation_Loss Rouge1 Rouge2 Rougel Rougelsum Gen_Len
1 No log 1.920353 0.193900 0.105400 0.168900 0.168800 19.000000
2 2.296300 1.860363 0.195300 0.105100 0.171400 0.171400 19.000000
3 1.927000 1.834611 0.195500 0.106800 0.171600 0.171500 19.000000
4 1.849100 1.826394 0.195000 0.105200 0.171400 0.171300 19.000000

Downloads last month
10
Safetensors
Model size
223M params
Tensor type
F32
·

Dataset used to train Reyansh4/T5_on_Billsum