cds_np_67

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

• Loss: 3.1210

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: 67
• 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
4.8361	1.0	495	3.7897
3.538	2.0	990	3.4327
3.2785	3.0	1485	3.2872
3.1342	4.0	1980	3.2071
3.032	5.0	2475	3.1511
2.9514	6.0	2970	3.1132
2.8836	7.0	3465	3.0901
2.8231	8.0	3960	3.0736
2.7678	9.0	4455	3.0633
2.7164	10.0	4950	3.0574
2.6678	11.0	5445	3.0589
2.6213	12.0	5940	3.0614
2.5765	13.0	6435	3.0655
2.5352	14.0	6930	3.0753
2.4983	15.0	7425	3.0819
2.4651	16.0	7920	3.0909
2.4353	17.0	8415	3.1027
2.4096	18.0	8910	3.1099
2.3879	19.0	9405	3.1155
2.3706	20.0	9900	3.1210

Framework versions

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