Hugging Face's logo

gremlin97
/
remote_sensing_gpt

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
remote_sensing_gpt / README.md
gremlin97's picture
gremlin97
End of training
9bdc901 verified
preview code
|
raw
history blame contribute delete
1.44 kB
metadata
license: bigscience-bloom-rail-1.0
library_name: peft
tags:
  - generated_from_trainer
base_model: bigscience/bloom-1b1
model-index:
  - name: remote_sensing_gpt
    results: []

remote_sensing_gpt

This model is a fine-tuned version of bigscience/bloom-1b1 on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 4.8886

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: 0.0003
  • train_batch_size: 8
  • eval_batch_size: 8
  • 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
No log 1.0 415 5.0368
5.1787 2.0 830 4.9311
4.9154 3.0 1245 4.8886

Framework versions

  • PEFT 0.9.0
  • Transformers 4.36.2
  • Pytorch 2.2.1+cu121
  • Datasets 2.15.0
  • Tokenizers 0.15.0