cds_o_fr_13

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

• Loss: 2.9088

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
5.8188	1.0	145	4.1782
3.6451	2.0	290	3.4042
3.2742	3.0	435	3.1872
3.1065	4.0	580	3.0692
3.0059	5.0	725	3.0006
2.9407	6.0	870	2.9596
2.8903	7.0	1015	2.9294
2.8492	8.0	1160	2.9076
2.8124	9.0	1305	2.8944
2.7787	10.0	1450	2.8837
2.7466	11.0	1595	2.8761
2.7144	12.0	1740	2.8737
2.6832	13.0	1885	2.8720
2.6516	14.0	2030	2.8742
2.6203	15.0	2175	2.8789
2.5899	16.0	2320	2.8853
2.561	17.0	2465	2.8913
2.5336	18.0	2610	2.8993
2.5111	19.0	2755	2.9061
2.4944	20.0	2900	2.9088

Framework versions

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