|
--- |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- city_learn |
|
model-index: |
|
- name: decision_transformer_random |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# decision_transformer_random |
|
|
|
This model is a fine-tuned version of [](https://huggingface.co/) on the city_learn dataset. |
|
|
|
## Model description |
|
|
|
|
|
|
|
state_mean = np.array([ 6.525973284621532, 3.9928073981048064, 12.498801233017467, 16.836990550577212, 16.837287388159297, 16.83684213167729, 16.837161803003287, 73.00388172165772, 73.00331088023746, 73.00445256307798, 73.00331088023746, 208.30597100125584, 208.30597100125584, 208.20287704075807, 208.30597100125584, 201.25448110514898, 201.25448110514898, 201.16189062678387, 201.25448110514898, 0.15652765849893777, 1.0663012570140091, 0.6994348432433195, 0.5023924181838172, 0.49339119658209996, 0.2731373418679261, 0.2731373418679261, 0.2731373418679261, 0.2731373418679261]) |
|
|
|
state_std = np.array([ 3.448045414453991, 2.0032677368929734, 6.921673394725967, 3.564552828057008, 3.5647828974724476, 3.5643565817901974, 3.564711987899257, 16.480221141108398, 16.480030755727572, 16.480238315742053, 16.480030755727565, 292.79094956097464, 292.79094956097464, 292.70528837855596, 292.79094956097543, 296.18549714910006, 296.18549714910023, 296.1216266457902, 296.18549714910006, 0.035369600587780235, 0.8889958578862672, 1.0171468928300462, 0.40202104980478576, 2.6674362928093682, 0.11780233435944305, 0.11780233435944333, 0.11780233435944351, 0.11780233435944402]) |
|
|
|
|
|
|
|
## 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: 10 |
|
|
|
### Training results |
|
|
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.26.1 |
|
- Pytorch 1.13.1+cu116 |
|
- Datasets 2.10.0 |
|
- Tokenizers 0.13.2 |
|
|
