cds_w_30

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

• Loss: 3.1756

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: 30
• 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
4.588	1.0	496	3.5284
3.3226	2.0	992	3.3046
3.1682	3.0	1488	3.2201
3.0809	4.0	1984	3.1739
3.0157	5.0	2480	3.1432
2.9617	6.0	2976	3.1231
2.9134	7.0	3472	3.1108
2.8706	8.0	3968	3.1021
2.828	9.0	4464	3.0960
2.7883	10.0	4960	3.0958
2.7484	11.0	5456	3.0989
2.7102	12.0	5952	3.1046
2.6743	13.0	6448	3.1135
2.6381	14.0	6944	3.1234
2.6059	15.0	7440	3.1337
2.5728	16.0	7936	3.1445
2.5441	17.0	8432	3.1567
2.5208	18.0	8928	3.1650
2.5005	19.0	9424	3.1699
2.4848	20.0	9920	3.1756

Framework versions

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