Good-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: 2.4267

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: 0.0003
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 16
• total_train_batch_size: 128
• 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: 0.12
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
3.3182	0.1067	25	2.9325
2.7389	0.2133	50	2.7289
2.6049	0.32	75	2.6352
2.4956	0.4267	100	2.5653
2.4569	0.5333	125	2.5161
2.4627	0.64	150	2.4759
2.3903	0.7467	175	2.4464
2.3572	0.8533	200	2.4319
2.3607	0.96	225	2.4267

Framework versions

• Transformers 4.57.1
• Pytorch 2.8.0+cu126
• Datasets 4.0.0
• Tokenizers 0.22.1