metadata
library_name: peft
license: apache-2.0
base_model: facebook/bart-large
tags:
- generated_from_trainer
model-index:
- name: ami-bart-large-finetune
results: []
ami-bart-large-finetune
This model is a fine-tuned version of facebook/bart-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 4.3972
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: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Use 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: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 13 | 4.8590 |
| No log | 2.0 | 26 | 4.7617 |
| No log | 3.0 | 39 | 4.6763 |
| No log | 4.0 | 52 | 4.5952 |
| No log | 5.0 | 65 | 4.5264 |
| No log | 6.0 | 78 | 4.4725 |
| No log | 7.0 | 91 | 4.4330 |
| No log | 8.0 | 104 | 4.4088 |
| No log | 9.0 | 117 | 4.3983 |
| No log | 9.24 | 120 | 4.3972 |
Framework versions
- PEFT 0.14.0
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0