|
--- |
|
datasets: |
|
- multi_news |
|
language: |
|
- en |
|
metrics: |
|
- bleu |
|
- rouge |
|
library_name: transformers |
|
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=7710, |
|
training_loss=2.8554159399445727, |
|
metrics={'train_runtime': 21924.7566, |
|
'train_samples_per_second': 4.923, |
|
'train_steps_per_second': 0.352, |
|
'total_flos': 2.3807388210639667e+17, |
|
'train_loss': 2.8554159399445727, |
|
'epoch': 3.0} |
|
|
|
# Training Results |
|
|
|
| Epoch | Training Loss | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Bleu | Gen Len | |
|
|:----- |:------------ |:--------------- |:-------- | :------- |:-------- |:--------- |:-------- |:--------- | |
|
1| 2.981200| 2.831641| 0.414500| 0.147000| 0.230700| 0.230600| 0.512800| 140.734900| |
|
2 |2.800900| 2.789402| 0.417300| 0.148400| 0.231800| 0.231700| 0.516000| 141.158200| |
|
3 |2.680300| 2.780862| 0.418300| 0.148400| 0.232200| 0.232100| 0.516800| 140.872300| |