cds_w_13

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

• Loss: 3.1763

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
4.5857	1.0	496	3.5241
3.3228	2.0	992	3.3001
3.1656	3.0	1488	3.2203
3.078	4.0	1984	3.1739
3.0125	5.0	2480	3.1434
2.9601	6.0	2976	3.1195
2.9126	7.0	3472	3.1073
2.868	8.0	3968	3.1036
2.8271	9.0	4464	3.0964
2.787	10.0	4960	3.0980
2.7475	11.0	5456	3.0985
2.71	12.0	5952	3.1066
2.6721	13.0	6448	3.1152
2.6369	14.0	6944	3.1243
2.6025	15.0	7440	3.1367
2.5712	16.0	7936	3.1456
2.5427	17.0	8432	3.1547
2.519	18.0	8928	3.1654
2.4987	19.0	9424	3.1713
2.4831	20.0	9920	3.1763

Framework versions

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