|
--- |
|
license: apache-2.0 |
|
base_model: t5-small |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: tamil-finetuning |
|
results: [] |
|
datasets: |
|
- ai4bharat/samanantar |
|
language: |
|
- ta |
|
- en |
|
metrics: |
|
- bleu |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# tamil-finetuning |
|
|
|
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the samanantar dataset. |
|
It achieves the following results on the evaluation set: |
|
- eval_loss: 0.3531 |
|
- eval_bleu: 14.4184 |
|
- eval_gen_len: 32.6451 |
|
- eval_runtime: 7195.8762 |
|
- eval_samples_per_second: 2.223 |
|
- eval_steps_per_second: 2.223 |
|
- epoch: 2.0 |
|
- step: 8000 |
|
|
|
## Model description |
|
|
|
t5-small finetuned for translation in en-ta |
|
|
|
## Intended uses & limitations |
|
|
|
More information needed |
|
|
|
## Training and evaluation data |
|
|
|
ai4bharath/samanantar -> 80-20 split |
|
|
|
## Training procedure |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 5e-05 |
|
- train_batch_size: 1 |
|
- eval_batch_size: 1 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 16 |
|
- total_train_batch_size: 16 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 3 |
|
|
|
### Framework versions |
|
|
|
- Transformers 4.42.3 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
