|
--- |
|
datasets: |
|
- multi_news |
|
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=7710 |
|
training_loss=2.1297076629757417 |
|
metrics={'train_runtime': 6059.0418, |
|
'train_samples_per_second': 17.813, |
|
'train_steps_per_second': 1.272, |
|
'total_flos': 2.3389776681055027e+17, |
|
'train_loss': 2.1297076629757417, |
|
'epoch': 3.0} |
|
|
|
# Training Results |
|
|
|
| Epoch | Training Loss | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Bleu | Gen Len | |
|
|:----- |:------------ |:--------------- |:-------- | :------- |:-------- |:--------- |:-------- |:--------- | |
|
| 1 | 2.223100 | 2.038599 | 0.147400 | 0.054800 | 0.113500 | 0.113500 | 0.001400 | 20.000000 | |
|
| 2 | 2.078100 | 2.009619 | 0.152900 | 0.057800 | 0.117000 | 0.117000 | 0.001600 | 20.000000 | |
|
| 3 | 1.989000 | 2.006006 | 0.152900 | 0.057300 | 0.116700 | 0.116700 | 0.001700 | 20.000000 | |
