FT-S

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

• eval_loss: 1.0798
• eval_wer: 0.3496
• eval_runtime: 1317.3251
• eval_samples_per_second: 15.128
• eval_steps_per_second: 1.891
• epoch: 0.9
• step: 13000

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: 3e-05
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 3
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.17.0
• Pytorch 2.10.0+cu128
• Datasets 3.6.0
• Tokenizers 0.22.2