|
--- |
|
base_model: ai4bharat/IndicBART |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- bleu |
|
model-index: |
|
- name: my_awesome_english_to_nepali_tst |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# my_awesome_english_to_nepali_tst |
|
|
|
This model is a fine-tuned version of [ai4bharat/IndicBART](https://huggingface.co/ai4bharat/IndicBART) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: nan |
|
- Bleu: 0.0 |
|
- Gen Len: 2.0 |
|
|
|
## 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: 32 |
|
- eval_batch_size: 32 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 10 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:| |
|
| No log | 1.0 | 32 | 10.9086 | 1.3699 | 20.0 | |
|
| No log | 2.0 | 64 | 10.4023 | 1.7857 | 20.0 | |
|
| No log | 3.0 | 96 | 10.2752 | 1.7702 | 20.0 | |
|
| No log | 4.0 | 128 | 10.2502 | 1.7664 | 20.0 | |
|
| No log | 5.0 | 160 | 10.2474 | 1.7664 | 20.0 | |
|
| No log | 6.0 | 192 | 10.2469 | 1.7664 | 20.0 | |
|
| No log | 7.0 | 224 | 10.2469 | 1.7664 | 20.0 | |
|
| No log | 8.0 | 256 | 10.2468 | 1.7664 | 20.0 | |
|
| No log | 9.0 | 288 | 10.2469 | 1.7664 | 20.0 | |
|
| No log | 10.0 | 320 | nan | 0.0 | 2.0 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.3 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
