tabeehive-ft-2

This model is a fine-tuned version of TheBloke/Mistral-7B-Instruct-v0.2-GPTQ on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.6212

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: 16
  • eval_batch_size: 16
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 64
  • optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 2
  • num_epochs: 10
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
2.7337 1.0 3 2.4865
2.3332 2.0 6 2.0148
1.9239 3.0 9 1.7024
1.6376 4.0 12 1.4442
1.3897 5.0 15 1.2083
1.1686 6.0 18 1.0030
0.9796 7.0 21 0.8399
0.8304 8.0 24 0.7174
0.7297 9.0 27 0.6498
0.6753 10.0 30 0.6212

Framework versions

  • PEFT 0.16.0
  • Transformers 4.53.1
  • Pytorch 2.6.0+cu124
  • Datasets 2.14.4
  • Tokenizers 0.21.2
Downloads last month
-
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for tabeehive/tabeehive-ft-2