cds_o_new_51

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

• Loss: 2.7795

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: 51
• 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
4.4691	1.0	495	3.2805
3.0377	2.0	990	2.9782
2.8107	3.0	1485	2.8653
2.6911	4.0	1980	2.8056
2.6078	5.0	2475	2.7674
2.5419	6.0	2970	2.7416
2.4854	7.0	3465	2.7232
2.4346	8.0	3960	2.7114
2.3875	9.0	4455	2.7084
2.3426	10.0	4950	2.7085
2.2995	11.0	5445	2.7069
2.2582	12.0	5940	2.7145
2.219	13.0	6435	2.7212
2.1812	14.0	6930	2.7267
2.1452	15.0	7425	2.7415
2.1129	16.0	7920	2.7492
2.0848	17.0	8415	2.7625
2.0606	18.0	8910	2.7692
2.0402	19.0	9405	2.7763
2.0243	20.0	9900	2.7795

Framework versions

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