Hugging Face's logo

Aditya149
/
Mental-Yi-6B

PEFT
TensorBoard
Safetensors
trl
sft
Generated from Trainer
Model card Files Metrics Community
Mental-Yi-6B / README.md
Aditya149's picture
Aditya149
End of training
128f804 verified
preview code
|
raw
history blame contribute delete
1.44 kB
metadata
license: other
library_name: peft
tags:
  - trl
  - sft
  - generated_from_trainer
base_model: 01-ai/Yi-6B-Chat
model-index:
  - name: Mental-Yi-6B
    results: []

Mental-Yi-6B

This model is a fine-tuned version of 01-ai/Yi-6B-Chat on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 2.1702

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: 1e-05
  • train_batch_size: 1
  • eval_batch_size: 1
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • num_epochs: 3
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
2.3241 1.0 1000 2.1771
2.1687 1.99 2000 2.1709
2.1664 2.99 3000 2.1702

Framework versions

  • PEFT 0.8.2
  • Transformers 4.38.1
  • Pytorch 2.1.2
  • Datasets 2.17.1
  • Tokenizers 0.15.1