metadata
tags:
- generated_from_trainer
datasets:
- opus_books
metrics:
- bleu
model-index:
- name: my_awesome_opus_books_model
results:
- task:
name: Sequence-to-sequence Language Modeling
type: text2text-generation
dataset:
name: opus_books
type: opus_books
config: de-en
split: train
args: de-en
metrics:
- name: Bleu
type: bleu
value: 4.9544
my_awesome_opus_books_model
This model was trained from scratch on the opus_books dataset. It achieves the following results on the evaluation set:
- Loss: 2.6349
- Bleu: 4.9544
- Gen Len: 16.4563
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| 3.0491 | 1.0 | 2574 | 2.7656 | 4.2008 | 16.5119 |
| 2.9604 | 2.0 | 5148 | 2.6959 | 4.589 | 16.4523 |
| 2.9114 | 3.0 | 7722 | 2.6601 | 4.8097 | 16.461 |
| 2.8991 | 4.0 | 10296 | 2.6408 | 4.9246 | 16.4609 |
| 2.8777 | 5.0 | 12870 | 2.6349 | 4.9544 | 16.4563 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3