cds_np_13

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

• Loss: 3.1209

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: 13
• 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
4.8272	1.0	495	3.7847
3.5402	2.0	990	3.4386
3.2821	3.0	1485	3.2927
3.137	4.0	1980	3.2117
3.0348	5.0	2475	3.1546
2.954	6.0	2970	3.1158
2.8855	7.0	3465	3.0910
2.825	8.0	3960	3.0728
2.7694	9.0	4455	3.0644
2.7177	10.0	4950	3.0593
2.669	11.0	5445	3.0597
2.6224	12.0	5940	3.0583
2.5777	13.0	6435	3.0667
2.5359	14.0	6930	3.0735
2.4989	15.0	7425	3.0843
2.4655	16.0	7920	3.0919
2.4359	17.0	8415	3.1010
2.4099	18.0	8910	3.1109
2.388	19.0	9405	3.1171
2.3712	20.0	9900	3.1209

Framework versions

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