Hugging Peers

Assignment2-modified-V3

☆ Save
by WilliamHH text-generation transformers apache-2.0
42 downloads 0 likes on Hugging Face updated

Model card

Assignment2-modified-V3

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

  • Loss: 2.8475

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: 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: 3

Training results

Training Loss Epoch Step Validation Loss
3.1903 0.16 200 3.1292
2.9116 0.32 400 3.0152
2.816 0.48 600 2.9535
2.7771 0.64 800 2.9106
2.667 0.8 1000 2.8754
2.601 0.96 1200 2.8459
2.4006 1.12 1400 2.8570
2.3205 1.28 1600 2.8472
2.2893 1.44 1800 2.8359
2.2799 1.6 2000 2.8233
2.2825 1.76 2200 2.8158
2.2442 1.92 2400 2.8081
2.1474 2.08 2600 2.8409
2.0325 2.24 2800 2.8517
2.0814 2.4 3000 2.8483
2.0453 2.56 3200 2.8479
2.0474 2.7200 3400 2.8474
2.0077 2.88 3600 2.8475

Framework versions

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