tamil-finetuning

This model is a fine-tuned version of 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