bart_finetuned_wo_clarify_aspects
This model is a fine-tuned version of facebook/bart-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0568
- Micro Precision: 0.2171
- Micro Recall: 0.0791
- Micro F1: 0.1159
- Macro Precision: 0.2197
- Macro Recall: 0.0745
- Macro F1: 0.1113
- Bleu: 0.8569
- Rouge1: 0.8387
- Rouge2: 0.6017
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: 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: 5
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Micro Precision | Micro Recall | Micro F1 | Macro Precision | Macro Recall | Macro F1 | Bleu | Rouge1 | Rouge2 |
---|---|---|---|---|---|---|---|---|---|---|---|---|
4.825 | 0.2404 | 50 | 2.1160 | 0.1789 | 0.1415 | 0.1580 | 0.0874 | 0.1668 | 0.1147 | 0.6783 | 0.7342 | 0.4167 |
1.8129 | 0.4808 | 100 | 0.9011 | 0.1879 | 0.0843 | 0.1164 | 0.0902 | 0.0969 | 0.0935 | 0.7651 | 0.7498 | 0.4283 |
0.7361 | 0.7212 | 150 | 0.2399 | 0.175 | 0.0073 | 0.0140 | 0.0833 | 0.0083 | 0.0151 | 0.8218 | 0.7783 | 0.4456 |
0.2197 | 0.9615 | 200 | 0.0935 | 0.125 | 0.0354 | 0.0552 | 0.0579 | 0.0372 | 0.0453 | 0.7687 | 0.7806 | 0.4456 |
0.1028 | 1.2019 | 250 | 0.0708 | 0.2719 | 0.0614 | 0.1002 | 0.1580 | 0.0518 | 0.0780 | 0.8472 | 0.8119 | 0.4532 |
0.0823 | 1.4423 | 300 | 0.0799 | 0.2542 | 0.1582 | 0.1950 | 0.1917 | 0.1613 | 0.1752 | 0.5872 | 0.7242 | 0.4584 |
0.0752 | 1.6827 | 350 | 0.0675 | 0.3778 | 0.0708 | 0.1192 | 0.1901 | 0.0558 | 0.0863 | 0.8392 | 0.8324 | 0.4612 |
0.077 | 1.9231 | 400 | 0.0632 | 0.2111 | 0.1228 | 0.1553 | 0.1563 | 0.1030 | 0.1242 | 0.8627 | 0.8203 | 0.5084 |
0.0694 | 2.1635 | 450 | 0.0669 | 0.2963 | 0.1498 | 0.1990 | 0.1738 | 0.1542 | 0.1634 | 0.6446 | 0.7494 | 0.5162 |
0.0712 | 2.4038 | 500 | 0.0638 | 0.1220 | 0.0052 | 0.0100 | 0.1668 | 0.0058 | 0.0112 | 0.8664 | 0.8404 | 0.5668 |
0.0672 | 2.6442 | 550 | 0.0628 | 0.1651 | 0.0364 | 0.0597 | 0.1776 | 0.0377 | 0.0621 | 0.8526 | 0.8284 | 0.5668 |
0.0644 | 2.8846 | 600 | 0.0595 | 0.1377 | 0.0239 | 0.0408 | 0.1742 | 0.0232 | 0.0410 | 0.8551 | 0.8255 | 0.5221 |
0.0648 | 3.125 | 650 | 0.0597 | 0.1166 | 0.0198 | 0.0338 | 0.1773 | 0.0197 | 0.0354 | 0.8584 | 0.8412 | 0.5764 |
0.0626 | 3.3654 | 700 | 0.0604 | 0.1861 | 0.0447 | 0.0721 | 0.2103 | 0.0439 | 0.0726 | 0.8511 | 0.8153 | 0.5498 |
0.0614 | 3.6058 | 750 | 0.0571 | 0.1412 | 0.0375 | 0.0592 | 0.1542 | 0.0387 | 0.0619 | 0.8469 | 0.8240 | 0.5769 |
0.0582 | 3.8462 | 800 | 0.0573 | 0.2205 | 0.0739 | 0.1107 | 0.2194 | 0.0737 | 0.1104 | 0.8534 | 0.8349 | 0.5965 |
0.0596 | 4.0865 | 850 | 0.0579 | 0.2287 | 0.0895 | 0.1286 | 0.2266 | 0.0889 | 0.1276 | 0.8358 | 0.8195 | 0.5896 |
0.0574 | 4.3269 | 900 | 0.0586 | 0.224 | 0.0874 | 0.1257 | 0.2235 | 0.0882 | 0.1265 | 0.8443 | 0.8186 | 0.5709 |
0.0592 | 4.5673 | 950 | 0.0579 | 0.2186 | 0.0905 | 0.1280 | 0.2259 | 0.0875 | 0.1262 | 0.8567 | 0.8301 | 0.5902 |
0.061 | 4.8077 | 1000 | 0.0568 | 0.2171 | 0.0791 | 0.1159 | 0.2197 | 0.0745 | 0.1113 | 0.8569 | 0.8387 | 0.6017 |
Framework versions
- Transformers 4.51.1
- Pytorch 2.5.1+cu124
- Datasets 3.5.0
- Tokenizers 0.21.0
- Downloads last month
- 2
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
๐
Ask for provider support
Model tree for tlam25/bart_finetuned_wo_clarify_aspects
Base model
facebook/bart-base