ciCic/decisionTransformer

Running training

• —Num examples = 1000
• —Num Epochs = 120
• —Instantaneous batch size per device = 64
• —Total train batch size = 64
• —Gradient Accumulation steps = 1
• —Total optimization steps = 1920

Train Output

• —global_step = 1920
• —train_runtime = 1849.2158
• —trainsamplesper_second = 64.892
• —trainstepsper_second = 1.038
• —train_loss = 0.04717305501302083
• —epoch = 120.0

Dataset

• —edbeeching/decisiontransformergym_replay
• —halfcheetah-expert-v2