Hugging Face's logo

Biswaj45
/
Bank-service

PEFT
TensorBoard
Safetensors
trl
sft
Generated from Trainer
Model card Files Metrics Community
Bank-service / README.md
Biswaj45's picture
Biswaj45
End of training
b1ea729 verified
preview code
|
raw
history blame contribute delete
1.7 kB
metadata
license: mit
library_name: peft
tags:
  - trl
  - sft
  - generated_from_trainer
base_model: microsoft/Phi-3-mini-128k-instruct
model-index:
  - name: Bank-service
    results: []

Bank-service

This model is a fine-tuned version of microsoft/Phi-3-mini-128k-instruct on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 2.5234

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: 0.0001
  • train_batch_size: 4
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 16
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.05
  • num_epochs: 2
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
2.4397 0.4 2 2.6366
2.5565 0.8 4 2.5772
2.2994 1.2 6 2.5455
2.472 1.6 8 2.5278
2.2456 2.0 10 2.5234

Framework versions

  • PEFT 0.11.1
  • Transformers 4.41.1
  • Pytorch 2.3.0+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1