cds_o_42

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

• Loss: 2.7811

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
4.4941	1.0	496	3.2923
3.0413	2.0	992	2.9782
2.8102	3.0	1488	2.8686
2.6891	4.0	1984	2.8072
2.6052	5.0	2480	2.7683
2.5395	6.0	2976	2.7413
2.4828	7.0	3472	2.7251
2.4322	8.0	3968	2.7148
2.3849	9.0	4464	2.7071
2.3401	10.0	4960	2.7079
2.2972	11.0	5456	2.7084
2.2562	12.0	5952	2.7148
2.217	13.0	6448	2.7239
2.1795	14.0	6944	2.7321
2.1431	15.0	7440	2.7408
2.111	16.0	7936	2.7535
2.0833	17.0	8432	2.7617
2.059	18.0	8928	2.7704
2.0384	19.0	9424	2.7765
2.0226	20.0	9920	2.7811

Framework versions

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