okai-musiclang-content-t5-stable

This model is a fine-tuned version of sandernotenbaert/okai-musiclang-content-t5-stable on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 2.1688

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: 0.0001
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 64
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine_with_restarts
• lr_scheduler_warmup_ratio: 0.1
• lr_scheduler_warmup_steps: 200
• num_epochs: 8
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
2.4966	1.6556	500	2.3381
2.3699	3.3113	1000	2.2373
2.3337	4.9669	1500	2.1878
2.3111	6.6225	2000	2.1688

Framework versions

• Transformers 4.54.1
• Pytorch 2.6.0+cu124
• Datasets 4.0.0
• Tokenizers 0.21.4