waxal-lid

This model is a fine-tuned version of sulaimank/w2v-bert-waxal on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0535
• Acc: 0.9917

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: 16
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 0.1
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Acc
1.1406	0.2667	100	0.4611	0.99
0.3675	0.5333	200	0.1759	0.99
0.1697	0.8	300	0.0989	0.9917
0.1199	1.0667	400	0.0739	0.9917
0.1036	1.3333	500	0.0632	0.9917
0.1042	1.6	600	0.0548	0.99
0.0707	1.8667	700	0.0535	0.9917
0.0593	2.0	750	0.0535	0.9917

Framework versions

• Transformers 5.13.0
• Pytorch 2.12.1+cu130
• Datasets 3.6.0
• Tokenizers 0.22.2