|
|
--- |
|
|
library_name: transformers |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
- decision_transformer |
|
|
model-index: |
|
|
- name: decision_transformer_gym_hopper |
|
|
results: [] |
|
|
datasets: |
|
|
- edbeeching/decision_transformer_gym_replay |
|
|
base_model: |
|
|
- edbeeching/decision-transformer-gym-hopper-medium |
|
|
--- |
|
|
|
|
|
<!-- 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_gym_hopper |
|
|
|
|
|
This model is a fine-tuned version of [](https://huggingface.co/) on edbeeching/decision_transformer_gym_replay. |
|
|
|
|
|
## Model description |
|
|
|
|
|
Decision Transformer training on gym hoppers (RL dataset). |
|
|
|
|
|
## 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: 120 |
|
|
|
|
|
### Training results |
|
|
|
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.44.2 |
|
|
- Pytorch 2.4.1+cu121 |
|
|
- Datasets 3.0.1 |
|
|
- Tokenizers 0.19.1 |
