4_bar_lmd_clean_custom_epochs10

This model is a fine-tuned version of MikeMpapa/4_bar_lmd_clean_custom_epochs10 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.8099

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: 0.005
• train_batch_size: 48
• eval_batch_size: 32
• seed: 1
• gradient_accumulation_steps: 2
• total_train_batch_size: 96
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.01
• num_epochs: 81

Training results

Training Loss	Epoch	Step	Validation Loss
1.078	9.42	12000	0.9938
0.9861	18.84	24000	0.9498
0.9367	28.26	36000	0.9170
0.8959	37.68	48000	0.8851
0.855	47.1	60000	0.8653
0.8125	56.51	72000	0.8325
0.772	65.93	84000	0.8155
0.7409	75.35	96000	0.8099

Framework versions

• Transformers 4.36.0
• Pytorch 2.1.0
• Datasets 2.15.0
• Tokenizers 0.15.1