metadata
license: apache-2.0
base_model: moussaKam/barthez-orangesum-abstract
tags:
- generated_from_trainer
model-index:
- name: sarcasm_BARThez_v3
results: []
sarcasm_BARThez_v3
This model is a fine-tuned version of moussaKam/barthez-orangesum-abstract on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5479
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: 2.5e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.4699 | 1.0 | 732 | 0.5757 |
| 0.6393 | 2.0 | 1464 | 0.5460 |
| 0.455 | 3.0 | 2196 | 0.5150 |
| 0.3906 | 4.0 | 2928 | 0.5079 |
| 0.3015 | 5.0 | 3660 | 0.5104 |
| 0.27 | 6.0 | 4392 | 0.5223 |
| 0.2124 | 7.0 | 5124 | 0.5343 |
| 0.2049 | 8.0 | 5856 | 0.5390 |
| 0.1656 | 9.0 | 6588 | 0.5433 |
| 0.1688 | 10.0 | 7320 | 0.5479 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2