|
--- |
|
datasets: |
|
- pszemraj/scientific_lay_summarisation-plos-norm |
|
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=4248, |
|
training_loss=2.172659089111788, |
|
metrics={'train_runtime': 3371.7912, |
|
'train_samples_per_second': 17.633, |
|
'train_steps_per_second': 1.26, |
|
'total_flos': 1.2884303701396685e+17, |
|
'train_loss': 2.172659089111788, |
|
'epoch': 3.0} |
|
|
|
# Training Results |
|
|
|
| Epoch | Training Loss | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Bleu | Gen Len | |
|
|:----- |:------------ |:--------------- |:-------- | :------- |:-------- |:--------- |:-------- |:--------- | |
|
| 1 | 2.318000 | 2.079500 | 0.128100 | 0.046700 | 0.104200 | 0.104200 | 0.001100 | 20.000000 | |
|
| 2 | 2.130000 | 2.043523 | 0.130200 | 0.047400 | 0.105400 | 0.105300 | 0.001300 | 20.000000 | |
|
| 3 | 2.047100 | 2.034664 | 0.130700 | 0.047800 | 0.105900 | 0.105900 | 0.001300 | 20.000000 | |
