cds_o_new_30

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

• Loss: 2.7814

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
4.4879	1.0	495	3.2843
3.0405	2.0	990	2.9764
2.8127	3.0	1485	2.8672
2.6921	4.0	1980	2.8085
2.6083	5.0	2475	2.7677
2.5423	6.0	2970	2.7409
2.4857	7.0	3465	2.7247
2.4348	8.0	3960	2.7134
2.3875	9.0	4455	2.7091
2.3424	10.0	4950	2.7065
2.2993	11.0	5445	2.7101
2.2581	12.0	5940	2.7128
2.2186	13.0	6435	2.7230
2.1809	14.0	6930	2.7306
2.1446	15.0	7425	2.7436
2.1124	16.0	7920	2.7526
2.0842	17.0	8415	2.7624
2.06	18.0	8910	2.7703
2.0395	19.0	9405	2.7773
2.0236	20.0	9900	2.7814

Framework versions

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