Hugging Face's logo

bisoye
/
phi-2-for-mental-health-3-5-epochs

PEFT
Safetensors
trl
sft
Generated from Trainer
Model card Files Community
phi-2-for-mental-health-3-5-epochs / README.md
bisoye's picture
bisoye
End of training
a9e9c78 verified
preview code
|
raw
history blame contribute delete
No virus
1.26 kB
metadata
base_model: microsoft/phi-2
library_name: peft
license: mit
tags:
  - trl
  - sft
  - generated_from_trainer
model-index:
  - name: phi-2-for-mental-health-3-5-epochs
    results: []

phi-2-for-mental-health-3-5-epochs

This model is a fine-tuned version of microsoft/phi-2 on an unknown dataset.

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: 3
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 6
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: constant
  • lr_scheduler_warmup_ratio: 0.03
  • num_epochs: 5
  • mixed_precision_training: Native AMP

Training results

Framework versions

  • PEFT 0.12.0
  • Transformers 4.44.2
  • Pytorch 2.4.0
  • Datasets 2.21.0
  • Tokenizers 0.19.1