cds_np_51

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

• Loss: 3.1253

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: 51
• 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
4.808	1.0	495	3.7858
3.5376	2.0	990	3.4346
3.2817	3.0	1485	3.2914
3.1383	4.0	1980	3.2090
3.0368	5.0	2475	3.1553
2.9567	6.0	2970	3.1168
2.8885	7.0	3465	3.0940
2.8281	8.0	3960	3.0766
2.7725	9.0	4455	3.0667
2.721	10.0	4950	3.0609
2.6721	11.0	5445	3.0640
2.6256	12.0	5940	3.0668
2.5807	13.0	6435	3.0716
2.5395	14.0	6930	3.0825
2.5023	15.0	7425	3.0874
2.4689	16.0	7920	3.0990
2.4392	17.0	8415	3.1047
2.4133	18.0	8910	3.1144
2.3913	19.0	9405	3.1208
2.3741	20.0	9900	3.1253

Framework versions

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