data_root_dir: /iliad/group/datasets/OXE_OCTO | |
hf_token: .hf_token | |
image_aug: false | |
is_resume: true | |
pretrained_checkpoint: runs/prism-qwen25-dinosiglip-224px+0_5b+mx-bridge+n1+b16+x7--bridge_vq_extra_tokenizer_lowlr/checkpoints/step-305000-epoch-18-loss=0.5682.pt | |
resume_epoch: 18 | |
resume_step: 305000 | |
run_id: prism-qwen25-dinosiglip-224px+0_5b+mx-bridge+n1+b16+x7--bridge_vq_extra_tokenizer_evenlowerlr | |
run_id_note: bridge_vq_extra_tokenizer_evenlowerlr | |
run_root_dir: runs | |
save_interval: 2500 | |
seed: 7 | |
trackers: | |
- jsonl | |
- wandb | |
vla: | |
action_tokenizer: bridge_vq_extra_action_tokenizer | |
base_vlm: prism-qwen25-dinosiglip-224px+0_5b | |
data_mix: bridge_dataset | |
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: 128 | |
image_sequence_len: 1 | |
learning_rate: 1.0e-06 | |
lr_scheduler_type: constant | |
max_grad_norm: 1.0 | |
max_steps: null | |
per_device_batch_size: 16 | |
reduce_in_full_precision: true | |
save_every_n_steps: 25000 | |
shuffle_buffer_size: 256000 | |
train_strategy: fsdp-full-shard | |
type: prism-qwen25-dinosiglip-224px+0_5b+mx-bridge | |
unfreeze_last_llm_layer: false | |
use_wrist_image: false | |
vla_id: prism-qwen25-dinosiglip-224px+0_5b+mx-bridge | |
warmup_ratio: 0.0 | |
weight_decay: 0.0 | |
wandb_entity: null | |
wandb_project: prismatic | |