|
--- |
|
datasets: |
|
- ccdv/govreport-summarization |
|
language: |
|
- en |
|
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=1.8524150695953217, |
|
metrics={'train_runtime': 2319.7329, |
|
'train_samples_per_second': 18.122, |
|
'train_steps_per_second': 1.295, |
|
'total_flos': 9.110291036818637e+16, |
|
'train_loss': 1.8524150695953217, |
|
'epoch': 3.0} |
|
|
|
# Training Results |
|
|
|
| Epoch | Training Loss | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Bleu | Gen Len | |
|
|:----- |:------------ |:--------------- |:-------- | :------- |:-------- |:--------- |:-------- |:--------- | |
|
| 1 | 1.969100 | 1.756651 | 0.159100 | 0.088300 | 0.138800 | 0.138900 | 0.001600 | 20.000000 | |
|
| 2 | 1.794000 | 1.699691 | 0.158500 | 0.090300 | 0.139500 | 0.139600 | 0.001400 | 20.000000 | |
|
| 3 | 1.713700 | 1.687554 | 0.162700 | 0.091900 | 0.141800 | 0.141900 | 0.001660 | 20.000000 | |
