metadata
license: apache-2.0
base_model: allenai/led-base-16384
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: LongFormer-docNMT
results: []
LongFormer-docNMT
This model is a fine-tuned version of allenai/led-base-16384 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.6309
- Bleu: 17.1793
- Meteor: 0.3591
- Comet: 0.4192
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: 3e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Meteor | Comet |
|---|---|---|---|---|---|---|
| 3.1806 | 1.0 | 197 | 1.9841 | 10.0127 | 0.2483 | 0.3147 |
| 2.0319 | 2.0 | 394 | 1.7005 | 15.4518 | 0.3323 | 0.3909 |
| 1.7954 | 3.0 | 591 | 1.6309 | 17.1793 | 0.3591 | 0.4192 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.10.0+cu128
- Datasets 4.0.0
- Tokenizers 0.19.1