exp_acha_mluke_base_1e_4_warmpup_02

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: 0.2797

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: 0.0001
• train_batch_size: 16
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.2
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss
0.3661	1.0	208	0.4168
0.4296	2.0	416	0.7619
0.4223	3.0	624	0.3506
0.3795	4.0	832	0.3102
0.4992	5.0	1040	0.5101
0.4629	6.0	1248	0.4456
0.406	7.0	1456	0.4701
0.3229	8.0	1664	0.3865
0.262	9.0	1872	0.3046
0.3361	10.0	2080	0.2797

Framework versions

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