TTS_NB

This model is a fine-tuned version of Edmon02/TTS_NB on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.4601

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: 2e-05
• train_batch_size: 4
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 1000
• training_steps: 6000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.6192	27.3973	500	0.5595
0.5686	54.7945	1000	0.5097
0.537	82.1918	1500	0.4940
0.5239	109.5890	2000	0.4815
0.5143	136.9863	2500	0.4775
0.5087	166.2740	3000	0.4622
0.5007	193.6712	3500	0.4592
0.5083	137.5527	4000	0.4671
0.5025	154.4304	4500	0.4657
0.4963	171.3080	5000	0.4626
0.4982	188.1857	5500	0.4603
0.4939	205.0633	6000	0.4601

Framework versions

• Transformers 4.43.3
• Pytorch 2.4.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1