Math-SmolLM2-1.7B

This model is a fine-tuned version of HuggingFaceTB/SmolLM2-1.7B-Instruct on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0102

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: 0.0002
  • train_batch_size: 4
  • eval_batch_size: 4
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 16
  • optimizer: Use adamw_torch 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: 0.03
  • num_epochs: 1
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
0.0174 0.2 100 0.0146
0.0122 0.4 200 0.0117
0.0108 0.6 300 0.0106
0.0101 0.8 400 0.0103
0.0101 1.0 500 0.0102

Framework versions

  • PEFT 0.13.2
  • Transformers 4.46.2
  • Pytorch 2.5.1+cu121
  • Datasets 3.1.0
  • Tokenizers 0.20.3
Downloads last month
84
Inference API
Unable to determine this model’s pipeline type. Check the docs .

Model tree for Joash2024/Math-SmolLM2-1.7B

Adapter
(3)
this model

Spaces using Joash2024/Math-SmolLM2-1.7B 3