business-news-generator

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: 2.5782

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: 16
• 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
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
3.1453	0.2667	2000	2.9693
2.8051	0.5333	4000	2.8105
2.6904	0.8	6000	2.7251
2.5723	1.0667	8000	2.6785
2.4023	1.3333	10000	2.6394
2.3717	1.6	12000	2.6095
2.3554	1.8667	14000	2.5820
2.2466	2.1333	16000	2.5917
2.1586	2.4	18000	2.5847
2.1441	2.6667	20000	2.5795
2.1513	2.9333	22000	2.5783

Framework versions

• Transformers 4.56.2
• Pytorch 2.8.0+cu126
• Datasets 4.0.0
• Tokenizers 0.22.1