databricks_smoLLM / README.md
Rahul13's picture
End of training
6b7b81a verified
|
raw
history blame
1.76 kB
metadata
license: apache-2.0
base_model: HuggingFaceTB/SmolLM-135M
tags:
  - generated_from_trainer
model-index:
  - name: databricks_smoLLM
    results: []

databricks_smoLLM

This model is a fine-tuned version of HuggingFaceTB/SmolLM-135M on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 2.3961

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: 2e-05
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss
No log 1.0 375 2.2360
2.2313 2.0 750 2.2261
1.9899 3.0 1125 2.2366
1.8532 4.0 1500 2.2560
1.8532 5.0 1875 2.2812
1.7256 6.0 2250 2.3115
1.6295 7.0 2625 2.3371
1.5634 8.0 3000 2.3663
1.5634 9.0 3375 2.3875
1.5089 10.0 3750 2.3961

Framework versions

  • Transformers 4.42.3
  • Pytorch 2.1.2
  • Datasets 2.20.0
  • Tokenizers 0.19.1