<!-- 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. -->

null_ignore_me-1685487306

This model is a fine-tuned version of Sunbird/t5-base-intermediate-2-merged on the None dataset. It achieves the following results on the evaluation set:

• eval_loss: 3.2728
• eval_BLEU_ach: 7.7529
• eval_BLEU_lgg: 6.6489
• eval_BLEU_lug: 19.7677
• eval_BLEU_nyn: 12.4485
• eval_BLEU_teo: 8.7934
• eval_BLEU_mean: 11.0823
• eval_runtime: 287.0849
• eval_samples_per_second: 8.708
• eval_steps_per_second: 1.742
• step: 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: 0.0005
• train_batch_size: 5
• eval_batch_size: 5
• seed: 42
• gradient_accumulation_steps: 600
• total_train_batch_size: 3000
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant
• num_epochs: 5
• label_smoothing_factor: 0.1

Framework versions

• Transformers 4.29.2
• Pytorch 2.0.1+cu118
• Datasets 2.12.0
• Tokenizers 0.13.3