cds_np_30

This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 3.1222

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: 256
• eval_batch_size: 256
• seed: 30
• optimizer: Use 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: 500
• num_epochs: 20
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
4.8295	1.0	495	3.7844
3.5371	2.0	990	3.4360
3.2797	3.0	1485	3.2933
3.1349	4.0	1980	3.2079
3.0332	5.0	2475	3.1528
2.9527	6.0	2970	3.1139
2.8841	7.0	3465	3.0916
2.824	8.0	3960	3.0747
2.7682	9.0	4455	3.0630
2.7163	10.0	4950	3.0596
2.6677	11.0	5445	3.0574
2.6216	12.0	5940	3.0626
2.576	13.0	6435	3.0706
2.5352	14.0	6930	3.0741
2.4975	15.0	7425	3.0858
2.4642	16.0	7920	3.0938
2.435	17.0	8415	3.1037
2.4088	18.0	8910	3.1112
2.3869	19.0	9405	3.1176
2.3697	20.0	9900	3.1222

Framework versions

• Transformers 4.56.1
• Pytorch 2.8.0+cu128
• Datasets 4.0.0
• Tokenizers 0.22.0