|
--- |
|
datasets: |
|
- ccdv/govreport-summarization |
|
metrics: |
|
- bleu |
|
- rouge |
|
pipeline_tag: summarization |
|
--- |
|
# Hyperparameters |
|
learning_rate=2e-5 |
|
per_device_train_batch_size=14 |
|
per_device_eval_batch_size=14 |
|
weight_decay=0.01 |
|
save_total_limit=3 |
|
num_train_epochs=3 |
|
predict_with_generate=True |
|
fp16=True |
|
|
|
# Training Output |
|
global_step=3003, |
|
training_loss=2.5178213735600132, |
|
metrics={'train_runtime': 8703.174, |
|
'train_samples_per_second': 4.83, |
|
'train_steps_per_second': 0.345, |
|
'total_flos': 9.272950245870797e+16, |
|
'train_loss': 2.5178213735600132, |
|
'epoch': 3.0} |
|
|
|
# Training Results |
|
|
|
| Epoch | Training Loss | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Bleu | Gen Len | |
|
|:----- |:------------ |:--------------- |:-------- | :------- |:-------- |:--------- |:-------- |:--------- | |
|
1| 2.661100| 2.469111| 0.451300| 0.185200| 0.279000| 0.278900| 0.553300| 141.720300| |
|
2| 2.434100| 2.403647| 0.456900| 0.192800| 0.284500| 0.284500| 0.556800| 141.763100| |
|
3| 2.313700| 2.393932| 0.459500| 0.194400| 0.286300| 0.286200| 0.559200| 141.571600| |
