cds_o_new_67

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

• Loss: 2.7801

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: 67
• 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
4.4886	1.0	495	3.2815
3.039	2.0	990	2.9778
2.8114	3.0	1485	2.8664
2.6915	4.0	1980	2.8042
2.608	5.0	2475	2.7660
2.5421	6.0	2970	2.7402
2.4856	7.0	3465	2.7220
2.435	8.0	3960	2.7119
2.3873	9.0	4455	2.7069
2.3425	10.0	4950	2.7067
2.2996	11.0	5445	2.7088
2.2582	12.0	5940	2.7140
2.219	13.0	6435	2.7213
2.1811	14.0	6930	2.7304
2.1448	15.0	7425	2.7409
2.1127	16.0	7920	2.7512
2.0845	17.0	8415	2.7606
2.0602	18.0	8910	2.7694
2.04	19.0	9405	2.7762
2.0238	20.0	9900	2.7801

Framework versions

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