NMTBaliIndoBART / README.md
pijarcandra22's picture
Training in progress epoch 104
9967ac6
|
raw
history blame
5.61 kB
---
license: apache-2.0
base_model: facebook/bart-base
tags:
- generated_from_keras_callback
model-index:
- name: pijarcandra22/NMTBaliIndoBART
results: []
---
<!-- This model card has been generated automatically according to the information Keras had access to. You should
probably proofread and complete it, then remove this comment. -->
# pijarcandra22/NMTBaliIndoBART
This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co./facebook/bart-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 5.4691
- Validation Loss: 5.8972
- Epoch: 104
## 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:
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 0.02, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: float32
### Training results
| Train Loss | Validation Loss | Epoch |
|:----------:|:---------------:|:-----:|
| 9.3368 | 5.6757 | 0 |
| 5.5627 | 5.5987 | 1 |
| 5.5311 | 5.5419 | 2 |
| 5.5152 | 5.5201 | 3 |
| 5.5005 | 5.6477 | 4 |
| 5.4704 | 5.5914 | 5 |
| 5.4610 | 6.0922 | 6 |
| 5.4584 | 5.7137 | 7 |
| 5.4528 | 5.8658 | 8 |
| 5.4820 | 5.5628 | 9 |
| 5.4874 | 5.5309 | 10 |
| 5.4917 | 5.7595 | 11 |
| 5.4898 | 5.7333 | 12 |
| 5.4833 | 5.6789 | 13 |
| 5.4767 | 5.9588 | 14 |
| 5.4883 | 5.9895 | 15 |
| 5.4694 | 6.0100 | 16 |
| 5.4663 | 6.0316 | 17 |
| 5.4602 | 5.9233 | 18 |
| 5.4576 | 6.0051 | 19 |
| 5.4559 | 5.9966 | 20 |
| 5.4651 | 6.0025 | 21 |
| 5.4660 | 6.0160 | 22 |
| 5.4626 | 5.8324 | 23 |
| 5.4647 | 5.8383 | 24 |
| 5.4695 | 6.0272 | 25 |
| 5.4614 | 6.0724 | 26 |
| 5.4623 | 5.9454 | 27 |
| 5.4678 | 6.0196 | 28 |
| 5.4860 | 5.5949 | 29 |
| 5.4851 | 5.8838 | 30 |
| 5.4666 | 5.8506 | 31 |
| 5.4715 | 6.0391 | 32 |
| 5.4630 | 6.0870 | 33 |
| 5.4646 | 6.2195 | 34 |
| 5.4574 | 5.9696 | 35 |
| 5.4564 | 5.8970 | 36 |
| 5.4570 | 5.9522 | 37 |
| 5.4559 | 6.1518 | 38 |
| 5.4584 | 6.1860 | 39 |
| 5.4732 | 6.1168 | 40 |
| 5.4625 | 6.1588 | 41 |
| 5.4601 | 5.9868 | 42 |
| 5.4645 | 5.9606 | 43 |
| 5.4664 | 6.1495 | 44 |
| 5.4698 | 6.0152 | 45 |
| 5.4666 | 6.2713 | 46 |
| 5.4557 | 6.2708 | 47 |
| 5.4557 | 6.0003 | 48 |
| 5.4693 | 5.9321 | 49 |
| 5.4928 | 5.8971 | 50 |
| 5.5032 | 6.0766 | 51 |
| 5.4749 | 5.8919 | 52 |
| 5.4689 | 5.9853 | 53 |
| 5.4665 | 5.9329 | 54 |
| 5.4574 | 5.9770 | 55 |
| 5.4686 | 6.1022 | 56 |
| 5.4727 | 5.8973 | 57 |
| 5.4692 | 5.9633 | 58 |
| 5.4608 | 6.0480 | 59 |
| 5.4613 | 5.9596 | 60 |
| 5.4607 | 6.1158 | 61 |
| 5.4531 | 6.0617 | 62 |
| 5.4610 | 6.0375 | 63 |
| 5.4631 | 6.1184 | 64 |
| 5.4627 | 6.0465 | 65 |
| 5.4685 | 6.0011 | 66 |
| 5.4642 | 6.0828 | 67 |
| 5.4577 | 6.0883 | 68 |
| 5.4615 | 5.9523 | 69 |
| 5.4673 | 5.7216 | 70 |
| 5.4724 | 6.0274 | 71 |
| 5.4601 | 6.0344 | 72 |
| 5.4640 | 5.9661 | 73 |
| 5.4590 | 6.0013 | 74 |
| 5.4622 | 6.0172 | 75 |
| 5.4666 | 5.8407 | 76 |
| 5.4669 | 6.0261 | 77 |
| 5.4859 | 5.9295 | 78 |
| 5.5042 | 6.1254 | 79 |
| 5.4845 | 5.8930 | 80 |
| 5.5001 | 5.8867 | 81 |
| 5.4923 | 5.9480 | 82 |
| 5.4909 | 6.0475 | 83 |
| 5.4780 | 5.9289 | 84 |
| 5.4867 | 5.8134 | 85 |
| 5.4877 | 6.0032 | 86 |
| 5.4806 | 6.0884 | 87 |
| 5.4784 | 6.0567 | 88 |
| 5.4830 | 5.9790 | 89 |
| 5.4894 | 5.8919 | 90 |
| 5.4890 | 5.9626 | 91 |
| 5.4774 | 6.0267 | 92 |
| 5.5033 | 6.1150 | 93 |
| 5.4765 | 5.9776 | 94 |
| 5.4657 | 6.1395 | 95 |
| 5.4720 | 5.9938 | 96 |
| 5.4748 | 5.9656 | 97 |
| 5.4701 | 6.0163 | 98 |
| 5.4718 | 6.1462 | 99 |
| 5.4672 | 6.0804 | 100 |
| 5.4775 | 6.1055 | 101 |
| 5.4775 | 6.0936 | 102 |
| 5.4673 | 5.9839 | 103 |
| 5.4691 | 5.8972 | 104 |
### Framework versions
- Transformers 4.40.2
- TensorFlow 2.15.0
- Datasets 2.19.1
- Tokenizers 0.19.1