Xlnet-large-2026

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

• Loss: 1.0670
• F1 Macro: 0.5169
• F1 Weighted: 0.5171
• Accuracy: 0.5227

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: 1e-05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	F1 Macro	F1 Weighted	Accuracy
1.1377	1.0	121	1.1484	0.2513	0.2785	0.4006
1.1248	2.0	242	1.0915	0.2198	0.2024	0.2986
1.1006	3.0	363	1.0871	0.3050	0.2977	0.3632
1.026	4.0	484	1.0585	0.4120	0.4139	0.4464
0.9893	5.0	605	0.9897	0.5040	0.5036	0.5068
0.9102	6.0	726	1.0506	0.4851	0.4865	0.5047
0.8586	7.0	847	1.0322	0.4985	0.5023	0.5213
0.8061	8.0	968	1.0200	0.5279	0.5250	0.5255
0.7535	9.0	1089	1.0180	0.5494	0.5499	0.5525
0.7005	10.0	1210	1.0557	0.5344	0.5343	0.5369

Framework versions

• Transformers 4.57.1
• Pytorch 2.7.1+cu118
• Datasets 4.2.0
• Tokenizers 0.22.1