|
--- |
|
datasets: |
|
- ccdv/govreport-summarization |
|
metrics: |
|
- rouge |
|
- bleu |
|
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=2.0113779983241042, |
|
metrics={'train_runtime': 12268.4376, |
|
'train_samples_per_second': 3.427, |
|
'train_steps_per_second': 0.245, |
|
'total_flos': 1.2147019450889011e+17, |
|
'train_loss': 2.0113779983241042, |
|
'epoch': 3.0} |
|
|
|
# Training Results |
|
|
|
| Epoch | Training Loss | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Bleu | Gen Len | |
|
|:----- |:------------ |:--------------- |:-------- | :------- |:-------- |:--------- |:-------- |:--------- | |
|
1| 2.035800| 1.906599| 0.365400| 0.150500| 0.243200 |0.243500 |0.366300| 227.230300| |
|
2| 1.976100| 1.878923| 0.393700| 0.167800| 0.263500 |0.263800 |0.423600| 193.114200| |
|
3| 1.956800| 1.871454| 0.409300| 0.175100| 0.273400 |0.273600 |0.457000| 172.294500| |
