exp_mluke_base_auan

This model is a fine-tuned version of studio-ousia/mluke-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1706

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: 8
• eval_batch_size: 16
• seed: 618
• gradient_accumulation_steps: 8
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss
0.5369	0.9932	55	0.4464
0.2825	1.9865	110	0.2670
0.2248	2.9977	166	0.2278
0.1797	3.9910	221	0.2210
0.111	4.9842	276	0.1788
0.1056	5.9955	332	0.1682
0.0981	6.9887	387	0.1899
0.0803	8.0	443	0.1720
0.0768	8.9932	498	0.1572
0.0504	9.9323	550	0.1706

Framework versions

• Transformers 4.40.1
• Pytorch 2.2.1+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1