MikeMpapa/lmd_8bar_final_test

lmd-8bars-2048-epochs40_v4

This model is a fine-tuned version of juancopi81/lmd-8bars-2048-epochs30_v4 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.9128

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: 0.0005
• train_batch_size: 8
• eval_batch_size: 4
• seed: 1
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.01
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss
0.959	0.5	4994	0.9735
0.9841	1.0	9988	0.9691
0.9779	1.5	14982	0.9632
0.9818	2.0	19976	0.9590
0.9736	2.5	24970	0.9610
0.9715	3.0	29964	0.9552
0.9629	3.5	34958	0.9520
0.9623	4.0	39952	0.9435
0.9509	4.5	44946	0.9442
0.9499	5.0	49940	0.9404
0.9367	5.5	54934	0.9334
0.9376	6.0	59928	0.9308
0.9247	6.5	64922	0.9270
0.9255	7.0	69916	0.9200
0.9163	7.5	74910	0.9184
0.9123	8.0	79904	0.9160
0.9071	8.5	84898	0.9147
0.9042	9.0	89892	0.9132
0.9026	9.5	94886	0.9124
0.9012	10.0	99880	0.9128

Framework versions

• Transformers 4.31.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.4
• Tokenizers 0.13.3