cds_sh1_13

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

• Loss: 3.1630

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
4.8939	1.0	495	3.9290
3.6468	2.0	990	3.5378
3.3754	3.0	1485	3.3858
3.2248	4.0	1980	3.2939
3.1189	5.0	2475	3.2257
3.0357	6.0	2970	3.1881
2.9645	7.0	3465	3.1580
2.9035	8.0	3960	3.1353
2.8468	9.0	4455	3.1218
2.7951	10.0	4950	3.1151
2.7449	11.0	5445	3.1136
2.6994	12.0	5940	3.1114
2.6552	13.0	6435	3.1170
2.6143	14.0	6930	3.1238
2.5771	15.0	7425	3.1313
2.5442	16.0	7920	3.1412
2.5148	17.0	8415	3.1452
2.4885	18.0	8910	3.1524
2.467	19.0	9405	3.1597
2.4502	20.0	9900	3.1630

Framework versions

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