candor_o_13

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

• Loss: 3.4956

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
5.2978	1.0	422	4.0581
3.7637	2.0	844	3.7319
3.5494	3.0	1266	3.6136
3.4387	4.0	1688	3.5481
3.3599	5.0	2110	3.5039
3.2964	6.0	2532	3.4744
3.2407	7.0	2954	3.4528
3.1902	8.0	3376	3.4394
3.143	9.0	3798	3.4321
3.0978	10.0	4220	3.4266
3.054	11.0	4642	3.4252
3.0117	12.0	5064	3.4315
2.9708	13.0	5486	3.4373
2.9316	14.0	5908	3.4445
2.8935	15.0	6330	3.4546
2.8589	16.0	6752	3.4669
2.8288	17.0	7174	3.4778
2.8031	18.0	7596	3.4841
2.7814	19.0	8018	3.4919
2.7646	20.0	8440	3.4956

Framework versions

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