train_3

This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1216

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: 5e-05
• train_batch_size: 96
• eval_batch_size: 96
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_APEX_FUSED with betas=(0.826646043090655,0.991636944120939) and epsilon=3.4341677539323e-07 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 5000
• num_epochs: 200

Training results

Training Loss	Epoch	Step	Validation Loss
0.0354	1.0	13725	0.1157
0.0345	2.0	27450	0.1158
0.0332	3.0	41175	0.1191
0.0322	4.0	54900	0.1190
0.0333	5.0	68625	0.1163
0.0323	6.0	82350	0.1172
0.0317	7.0	96075	0.1170
0.0306	8.0	109800	0.1182
0.0295	9.0	123525	0.1188
0.029	10.0	137250	0.1213
0.0286	11.0	150975	0.1197
0.0278	12.0	164700	0.1201
0.0272	13.0	178425	0.1212
0.0266	14.0	192150	0.1208
0.0266	15.0	205875	0.1208
0.0259	16.0	219600	0.1216

Framework versions

• Transformers 4.50.3
• Pytorch 2.6.0+cu126
• Datasets 3.3.0
• Tokenizers 0.21.1