cds_w_42

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

• Loss: 3.1754

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: 42
• 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
4.585	1.0	496	3.5160
3.3235	2.0	992	3.3005
3.1692	3.0	1488	3.2236
3.0793	4.0	1984	3.1785
3.0144	5.0	2480	3.1462
2.9616	6.0	2976	3.1218
2.9137	7.0	3472	3.1084
2.8691	8.0	3968	3.0996
2.8269	9.0	4464	3.0946
2.7864	10.0	4960	3.0964
2.7482	11.0	5456	3.1013
2.7091	12.0	5952	3.1038
2.6712	13.0	6448	3.1147
2.637	14.0	6944	3.1215
2.6037	15.0	7440	3.1335
2.571	16.0	7936	3.1451
2.5432	17.0	8432	3.1547
2.5189	18.0	8928	3.1651
2.4994	19.0	9424	3.1719
2.4839	20.0	9920	3.1754

Framework versions

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