cds_o_new_13

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

• Loss: 2.7822

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
4.4821	1.0	495	3.2838
3.0363	2.0	990	2.9754
2.8089	3.0	1485	2.8664
2.6892	4.0	1980	2.8051
2.6067	5.0	2475	2.7665
2.5413	6.0	2970	2.7397
2.4849	7.0	3465	2.7240
2.4344	8.0	3960	2.7145
2.3871	9.0	4455	2.7076
2.3423	10.0	4950	2.7081
2.2993	11.0	5445	2.7078
2.2581	12.0	5940	2.7138
2.2187	13.0	6435	2.7229
2.1811	14.0	6930	2.7325
2.1447	15.0	7425	2.7418
2.1127	16.0	7920	2.7536
2.0843	17.0	8415	2.7616
2.0601	18.0	8910	2.7711
2.0398	19.0	9405	2.7793
2.0237	20.0	9900	2.7822

Framework versions

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