metadata
library_name: peft
base_model: MingZhong/DialogLED-base-16384
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: LED-dialog-sum
results: []
LED-dialog-sum
This model is a fine-tuned version of MingZhong/DialogLED-base-16384 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.7399
- Rouge1: 0.3862
- Rouge2: 0.2783
- Rougel: 0.2541
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: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 2
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel |
|---|---|---|---|---|---|---|
| 4.4889 | 1.0 | 800 | 3.2528 | 0.3814 | 0.2739 | 0.2511 |
| 3.0117 | 2.0 | 1600 | 2.7399 | 0.3862 | 0.2783 | 0.2541 |
Framework versions
- PEFT 0.14.0
- Transformers 4.50.3
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.21.1