| vla: | |
| action_tokenizer: action_tokenizer | |
| base_vlm: prism-dinosiglip-224px+7b | |
| data_mix: bridge | |
| enable_gradient_checkpointing: true | |
| enable_mixed_precision_training: true | |
| epochs: 1000 | |
| expected_world_size: 8 | |
| freeze_llm_backbone: false | |
| freeze_vision_backbone: false | |
| global_batch_size: 256 | |
| image_sequence_len: 1 | |
| learning_rate: 2.0e-05 | |
| lr_scheduler_type: constant | |
| max_grad_norm: 1.0 | |
| max_steps: null | |
| per_device_batch_size: 32 | |
| reduce_in_full_precision: true | |
| save_every_n_steps: 25000 | |
| shuffle_buffer_size: 256000 | |
| train_strategy: fsdp-full-shard | |
| type: prism-dinosiglip-224px+mx-bridge | |
| unfreeze_last_llm_layer: false | |
| use_wrist_image: false | |
| vla_id: prism-dinosiglip-224px+mx-bridge | |
| warmup_ratio: 0.0 | |
| weight_decay: 0.0 |