okai-musiclang-content-t5-small

This model is a fine-tuned version of sandernotenbaert/okai-musiclang-content-t5-small on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.1968

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: 8e-05
• 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: 100
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
1.4556	0.2226	500	1.3230
1.4166	0.4452	1000	1.3003
1.3956	0.6679	1500	1.2741
1.3865	0.8905	2000	1.2605
1.3589	1.1131	2500	1.2368
1.3514	1.3357	3000	1.2370
1.3349	1.5583	3500	1.2322
1.3163	1.7809	4000	1.2099
1.3183	2.0036	4500	1.2062
1.3204	2.2262	5000	1.2014
1.303	2.4488	5500	1.2008
1.3205	2.6714	6000	1.1953
1.3108	2.8940	6500	1.1968

Framework versions

• Transformers 4.54.1
• Pytorch 2.6.0+cu124
• Datasets 4.0.0
• Tokenizers 0.21.2