Hugging Face's logo

ArunaMak
/
phi2_fine_tuned

PEFT
Safetensors
trl
sft
Generated from Trainer
Model card Files Community
phi2_fine_tuned / README.md
ArunaMak's picture
ArunaMak
End of training
d8fefb3 verified
preview code
|
raw
history blame contribute delete
No virus
1.92 kB
metadata
base_model: microsoft/phi-2
datasets:
  - generator
library_name: peft
license: mit
tags:
  - trl
  - sft
  - generated_from_trainer
model-index:
  - name: ERC_SUMMARY_phi2_peft
    results: []

Visualize in Weights & Biases

ERC_SUMMARY_phi2_peft

This model is a fine-tuned version of microsoft/phi-2 on the ArunaMak/ERC_summary dataset. It achieves the following results on the evaluation set:

  • Loss: 1.4798

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
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 4
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • num_epochs: 6

Training results

Training Loss Epoch Step Validation Loss
1.5888 1.0 40 1.5819
1.5677 2.0 80 1.5202
1.5819 3.0 120 1.4962
1.4227 4.0 160 1.4842
1.4786 5.0 200 1.4798
1.5015 6.0 240 1.4798

Framework versions

  • PEFT 0.12.0
  • Transformers 4.43.0.dev0
  • Pytorch 2.3.1+cu118
  • Datasets 2.20.0
  • Tokenizers 0.19.1