A-mlp-linear-46L

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

• Loss: 2.8153

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: 0.001
• train_batch_size: 512
• eval_batch_size: 512
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: constant
• training_steps: 1000

Training results

Training Loss	Epoch	Step	Validation Loss
5.9943	0.0270	50	5.6660
5.4216	0.0539	100	5.3673
5.1264	0.0809	150	4.9933
4.7248	0.1078	200	4.6469
4.4794	0.1348	250	4.4149
4.1928	0.1617	300	4.1563
4.0202	0.1887	350	3.9751
3.7941	0.2156	400	3.7661
3.6807	0.2426	450	3.6146
3.5234	0.2695	500	3.4892
3.4312	0.2965	550	3.3768
3.3176	0.3235	600	3.3391
3.2724	0.3504	650	3.2303
3.1910	0.3774	700	3.1677
3.1384	0.4043	750	3.0951
3.0459	0.4313	800	3.0226
3.0106	0.4582	850	2.9586
2.9290	0.4852	900	2.9079
2.8933	0.5121	950	2.8532
2.8351	0.5391	1000	2.8153

Framework versions

• Transformers 5.15.0.dev0
• Pytorch 2.6.0+cu124
• Datasets 5.0.1
• Tokenizers 0.22.2