cds_sh1_42

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

• Loss: 3.1664

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: 42
• 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
4.8895	1.0	495	3.9068
3.6476	2.0	990	3.5451
3.3809	3.0	1485	3.3822
3.2288	4.0	1980	3.2913
3.1213	5.0	2475	3.2308
3.0375	6.0	2970	3.1927
2.9663	7.0	3465	3.1607
2.9042	8.0	3960	3.1398
2.8473	9.0	4455	3.1283
2.7963	10.0	4950	3.1195
2.7467	11.0	5445	3.1206
2.7012	12.0	5940	3.1164
2.6561	13.0	6435	3.1189
2.615	14.0	6930	3.1275
2.5788	15.0	7425	3.1326
2.5452	16.0	7920	3.1433
2.5148	17.0	8415	3.1499
2.4904	18.0	8910	3.1584
2.468	19.0	9405	3.1654
2.4511	20.0	9900	3.1664

Framework versions

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