tags:
- generated_from_trainer
datasets:
- city_learn
model-index:
- name: output
results: []
output
This model is a fine-tuned version of on the city_learn dataset.
Model description
state_mean: [6.51944444e+00 3.98379630e+00 1.25000000e+01 1.67850000e+01 1.67849190e+01 1.67851968e+01 1.67854977e+01 7.28990741e+01 7.29056713e+01 7.29093750e+01 7.29134259e+01 2.07319097e+02 2.07319097e+02 2.07185417e+02 2.07236111e+02 2.01118634e+02 2.01118634e+02 2.00806481e+02 2.00887616e+02 1.56366486e-01 1.05916886e+00 6.96371636e-01 2.91179937e-01 3.99157702e-01 2.73105321e-01 2.73105321e-01 2.73105321e-01 2.73105321e-01] state_std: [3.47125753e+00 2.00155513e+00 6.92218755e+00 3.55389420e+00 3.55381195e+00 3.55403913e+00 3.55461251e+00 1.65420140e+01 1.65465337e+01 1.65478974e+01 1.65489647e+01 2.91883900e+02 2.91883900e+02 2.91755278e+02 2.91833913e+02 2.96415007e+02 2.96415007e+02 2.96260649e+02 2.96305327e+02 3.53750260e-02 8.83521126e-01 1.01549677e+00 3.23319869e-01 9.20646312e-01 1.17879328e-01 1.17879328e-01 1.17879328e-01 1.17879328e-01]
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: 0.0001
- train_batch_size: 64
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 360
Training results
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2