metadata
base_model: aubmindlab/aragpt2-base
tags:
- generated_from_trainer
metrics:
- bleu
- rouge
model-index:
- name: res_nw_eg_aragpt2-base
results: []
res_nw_eg_aragpt2-base
This model is a fine-tuned version of aubmindlab/aragpt2-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1032
- Bleu: 0.1405
- Rouge1: 0.4455
- Rouge2: 0.2251
- Rougel: 0.4383
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 20.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Rouge1 | Rouge2 | Rougel |
|---|---|---|---|---|---|---|---|
| 0.2542 | 1.0 | 7105 | 0.1199 | 0.0729 | 0.3187 | 0.1103 | 0.3094 |
| 0.1078 | 2.0 | 14210 | 0.1119 | 0.1044 | 0.3803 | 0.1636 | 0.3720 |
| 0.0972 | 3.0 | 21315 | 0.1077 | 0.1222 | 0.4109 | 0.1933 | 0.4033 |
| 0.0902 | 4.0 | 28420 | 0.1051 | 0.1312 | 0.4294 | 0.2090 | 0.4223 |
| 0.0846 | 5.0 | 35525 | 0.1032 | 0.1405 | 0.4455 | 0.2251 | 0.4383 |
| 0.0799 | 6.0 | 42630 | 0.1041 | 0.1454 | 0.4537 | 0.2338 | 0.4466 |
| 0.0759 | 7.0 | 49735 | 0.1044 | 0.1494 | 0.4623 | 0.2425 | 0.4553 |
| 0.0722 | 8.0 | 56840 | 0.1044 | 0.1527 | 0.4655 | 0.2470 | 0.4587 |
| 0.069 | 9.0 | 63945 | 0.1058 | 0.1536 | 0.4689 | 0.2489 | 0.4621 |
| 0.066 | 10.0 | 71050 | 0.1062 | 0.1550 | 0.4724 | 0.2523 | 0.4657 |
Framework versions
- Transformers 4.45.0.dev0
- Pytorch 2.3.1+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1