SmolLM2-135M-Instruct-relevance-sft

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

  • Loss: 0.7045

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: 2024
  • distributed_type: multi-GPU
  • num_devices: 8
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 512
  • total_eval_batch_size: 64
  • optimizer: Use OptimizerNames.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: 0.1
  • num_epochs: 3

Training results

Training Loss Epoch Step Validation Loss
0.916 0.3854 500 0.7372
0.8854 0.7707 1000 0.7177
0.9783 1.1562 1500 0.7117
0.9635 1.5415 2000 0.7066
0.9591 1.9269 2500 0.7046
0.8954 2.3123 3000 0.7044
0.8896 2.6977 3500 0.7045

Framework versions

  • Transformers 4.46.3
  • Pytorch 2.5.1
  • Datasets 3.1.0
  • Tokenizers 0.20.3
Downloads last month
156
Safetensors
Model size
135M params
Tensor type
BF16
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for wandb/relevance_scorer

Finetuned
(32)
this model