RichardErkhov/marc4gov_-_my-szw-model-8bits

Quantization made by Richard Erkhov.

Github

Discord

Request more models

my-szw-model - bnb 8bits

• Model creator: https://huggingface.co/marc4gov/
• Original model: https://huggingface.co/marc4gov/my-szw-model/

Original model description:

library_name: transformers license: mit base_model: BramVanroy/fietje-2-instruct tags: - generated_from_trainer model-index: - name: my-szw-model results: []

my-szw-model

This model is a fine-tuned version of BramVanroy/fietje-2-instruct on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.3317

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: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	67	1.1677
No log	2.0	134	1.2020
No log	3.0	201	1.3317

Framework versions

• Transformers 4.46.2
• Pytorch 2.5.1
• Datasets 3.1.0
• Tokenizers 0.20.3