game_music_gen_V05

This model is a fine-tuned version of gpt2 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.0130

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
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.01
• num_epochs: 25

Training results

Training Loss	Epoch	Step	Validation Loss
1.3149	2.7027	500	1.3922
1.1922	5.4054	1000	1.3253
1.0644	8.1081	1500	1.2489
0.9377	10.8108	2000	1.1704
0.8152	13.5135	2500	1.0953
0.6979	16.2162	3000	1.0621
0.6121	18.9189	3500	1.0206
0.5481	21.6216	4000	1.0147
0.524	24.3243	4500	1.0130

Framework versions

• Transformers 4.47.1
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0