---
license: apache-2.0
base_model: t5-small
tags:
- generated_from_trainer
datasets:
- itihasa
metrics:
- bleu
model-index:
- name: sanskrit-to-english
  results:
  - task:
      name: Sequence-to-sequence Language Modeling
      type: text2text-generation
    dataset:
      name: itihasa
      type: itihasa
      config: Itihasa
      split: test
      args: Itihasa
    metrics:
    - name: Bleu
      type: bleu
      value: 0.288
---

<!-- 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. -->

# sanskrit-to-english

This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the itihasa dataset.
It achieves the following results on the evaluation set:
- Loss: 3.5134
- Bleu: 0.288
- Gen Len: 19.0

## 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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step  | Validation Loss | Bleu   | Gen Len |
|:-------------:|:-----:|:-----:|:---------------:|:------:|:-------:|
| 3.9554        | 1.0   | 4698  | 3.7250          | 0.3772 | 19.0    |
| 3.8183        | 2.0   | 9396  | 3.6050          | 0.3216 | 19.0    |
| 3.746         | 3.0   | 14094 | 3.5497          | 0.2743 | 19.0    |
| 3.7183        | 4.0   | 18792 | 3.5229          | 0.2787 | 19.0    |
| 3.7124        | 5.0   | 23490 | 3.5134          | 0.288  | 19.0    |


### Framework versions

- Transformers 4.35.0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.14.1