pkbiswas's picture
End of training
90fd67b verified
metadata
license: mit
library_name: peft
tags:
  - trl
  - sft
  - generated_from_trainer
base_model: microsoft/Phi-3-mini-128k-instruct
datasets:
  - scitldr
model-index:
  - name: Summarization-Phi-3
    results: []

Summarization-Phi-3

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

  • Loss: 2.1554

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: 1
  • eval_batch_size: 1
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 2
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
2.0689 0.2510 500 2.1439
2.0455 0.5020 1000 2.1388
2.0665 0.7530 1500 2.1349
2.0481 1.0040 2000 2.1308
1.9051 1.2550 2500 2.1573
1.8524 1.5060 3000 2.1588
1.8247 1.7570 3500 2.1554

Framework versions

  • PEFT 0.10.0
  • Transformers 4.40.0
  • Pytorch 2.2.1+cu121
  • Datasets 2.19.0
  • Tokenizers 0.19.1