amhmt5-base-finetuned-amt5

This model is a fine-tuned version of Samuael/amt5-base on an unknown dataset. It achieves the following results on the evaluation set:

• eval_loss: 0.3710
• eval_rouge1: 0.0
• eval_rouge2: 0.0
• eval_rougeL: 0.0
• eval_rougeLsum: 0.0
• eval_gen_len: 18.5905
• eval_wer: 0.6072
• eval_cer: 0.5393
• eval_runtime: 4.0504
• eval_samples_per_second: 88.633
• eval_steps_per_second: 1.481
• epoch: 4.0
• step: 5672

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: 0.0002
• train_batch_size: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 30

Framework versions

• Transformers 4.37.2
• Pytorch 2.1.0+cu121
• Datasets 2.17.1
• Tokenizers 0.15.2