Hugging Face's logo

santis2
/
gpt2-alpaca-instruction-fine-tuning-qlora

Generated from Trainer
Model card Files Community
gpt2-alpaca-instruction-fine-tuning-qlora / README.md
santis2's picture
santis2
End of training
c5d1933
preview code
|
raw history blame
No virus
3.82 kB
metadata
license: mit
base_model: gpt2
tags:
  - generated_from_trainer
model-index:
  - name: gpt2-alpaca-instruction-fine-tuning-qlora
    results: []

gpt2-alpaca-instruction-fine-tuning-qlora

This model is a fine-tuned version of gpt2 on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 1.8887

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: 0.0005
  • 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: cosine
  • lr_scheduler_warmup_steps: 1000
  • num_epochs: 1

Training results

Training Loss Epoch Step Validation Loss
No log 0.02 50 2.4375
No log 0.04 100 2.375
No log 0.06 150 2.2637
No log 0.08 200 2.1855
No log 0.1 250 2.1094
No log 0.12 300 2.0840
No log 0.14 350 2.0977
No log 0.16 400 2.0488
No log 0.18 450 2.0332
No log 0.2 500 2.0312
No log 0.22 550 2.0352
No log 0.24 600 2.0430
No log 0.26 650 2.0117
No log 0.28 700 2.0117
No log 0.3 750 2.0059
No log 0.32 800 1.9961
No log 0.34 850 1.9551
No log 0.36 900 1.9463
No log 0.38 950 1.9854
2.4218 0.4 1000 1.9883
2.4218 0.42 1050 1.9766
2.4218 0.44 1100 1.9424
2.4218 0.46 1150 1.9727
2.4218 0.48 1200 1.9473
2.4218 0.5 1250 1.9580
2.4218 0.52 1300 1.9404
2.4218 0.54 1350 1.9287
2.4218 0.56 1400 1.9473
2.4218 0.58 1450 1.9209
2.4218 0.6 1500 1.9219
2.4218 0.62 1550 1.9336
2.4218 0.64 1600 1.9287
2.4218 0.66 1650 1.9082
2.4218 0.68 1700 1.9219
2.4218 0.7 1750 1.8994
2.4218 0.72 1800 1.9092
2.4218 0.74 1850 1.8877
2.4218 0.76 1900 1.8994
2.4218 0.78 1950 1.8955
2.1818 0.8 2000 1.8896
2.1818 0.82 2050 1.8867
2.1818 0.84 2100 1.8857
2.1818 0.86 2150 1.8916
2.1818 0.88 2200 1.8857
2.1818 0.9 2250 1.8916
2.1818 0.92 2300 1.8926
2.1818 0.94 2350 1.8896
2.1818 0.96 2400 1.8887
2.1818 0.98 2450 1.8887
2.1818 1.0 2500 1.8887

Framework versions

  • Transformers 4.33.3
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.5
  • Tokenizers 0.13.3