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: 2.9683

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
6.7811	1.0	88	5.2394
4.5139	2.0	176	3.9491
3.6757	3.0	264	3.5220
3.3963	4.0	352	3.3253
3.231	5.0	440	3.2012
3.1208	6.0	528	3.1181
3.0376	7.0	616	3.0612
2.9745	8.0	704	3.0232
2.9249	9.0	792	2.9973
2.8817	10.0	880	2.9814
2.8433	11.0	968	2.9646
2.8071	12.0	1056	2.9579
2.7723	13.0	1144	2.9513
2.7393	14.0	1232	2.9497
2.7064	15.0	1320	2.9499
2.6751	16.0	1408	2.9523
2.6443	17.0	1496	2.9577
2.616	18.0	1584	2.9620
2.5925	19.0	1672	2.9667
2.5748	20.0	1760	2.9683

Framework versions

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