Hugging Face's logo

thorirhrafn
/
gpt_icesum

Text Generation
Transformers
TensorBoard
Safetensors
gpt2
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
gpt_icesum / README.md
thorirhrafn's picture
thorirhrafn
End of training
249a687 verified
preview code
|
raw
history blame
1.95 kB
metadata
license: apache-2.0
library_name: peft
tags:
  - generated_from_trainer
base_model: AI-Sweden-Models/gpt-sw3-1.3b
model-index:
  - name: gpt_icesum
    results: []

gpt_icesum

This model is a fine-tuned version of AI-Sweden-Models/gpt-sw3-1.3b on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.7824

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: 2e-05
  • train_batch_size: 4
  • eval_batch_size: 4
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 3

Training results

Training Loss Epoch Step Validation Loss
1.9553 0.22 50 1.8683
1.9425 0.44 100 1.8240
1.8376 0.67 150 1.8040
2.0224 0.89 200 1.7953
1.8172 1.11 250 1.7903
1.9457 1.33 300 1.7875
1.8177 1.56 350 1.7853
1.82 1.78 400 1.7837
1.9207 2.0 450 1.7830
1.7946 2.22 500 1.7832
1.8675 2.44 550 1.7828
1.8384 2.67 600 1.7826
1.9814 2.89 650 1.7824

Framework versions

  • PEFT 0.8.2
  • Transformers 4.38.1
  • Pytorch 2.2.0+cu118
  • Datasets 2.17.1
  • Tokenizers 0.15.2