business-news-generator_moredecay

This model is a fine-tuned version of HuggingFaceTB/SmolLM2-135M on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 2.8505

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: 0.0005
• train_batch_size: 8
• eval_batch_size: 8
• 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: cosine
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss
3.3356	0.1333	200	3.4433
3.0754	0.2667	400	3.3116
2.996	0.4	600	3.2476
2.8609	0.5333	800	3.1403
2.8215	0.6667	1000	3.0865
2.6704	0.8	1200	3.0253
2.6402	0.9333	1400	2.9448
2.0893	1.0667	1600	3.0050
1.6794	1.2	1800	2.9873
1.6491	1.3333	2000	2.9438
1.5772	1.4667	2200	2.8991
1.5501	1.6	2400	2.8744
1.4884	1.7333	2600	2.8597
1.4942	1.8667	2800	2.8518
1.5178	2.0	3000	2.8505

Framework versions

• Transformers 4.56.1
• Pytorch 2.8.0+cu126
• Datasets 4.0.0
• Tokenizers 0.22.0