Add model checkpoint gr00t_n1_5_rbcs_bs32_60k

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.json filter=lfs diff=lfs merge=lfs -text
+*.yaml filter=lfs diff=lfs merge=lfs -text

checkpoints/step-010000-epoch-00-loss=0.0325.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5dd7039b2b2315135886a18d171d296c4080d4c3c049cd227c1d4f60e086c90
+size 32681495061

checkpoints/step-020000-epoch-00-loss=0.0370.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:558f4ebd1648c6da1527d690fc1d88a2285b113097f7a1db06d64299528db4fd
+size 32681495061

config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a730131662d3766ce2f7681853fcbabf4119c2860cb88213dcd4c6da0e4ed63
+size 2569

config.yaml

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c46afcd8287dc164b2e60c2901bc5129902a045cde4f5aa49c5f881e1768c410
+size 2147

dataset_statistics.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebd47beb7c2a64827bf3c5aaeeb2ce16a3575537bc414015522f6e939ca70c15
+size 2263

run-metrics.jsonl

@@ -0,0 +1 @@
+{"hparams": {"action_dim": 7, "action_model_type": "DiT-B", "alignment_loss_weight": 0.1, "data_root_dir": "/fsx/OpenXRLDS/bridgev2_processed", "freeze_meta_emb": false, "future_action_window_size": 15, "gate_bias_init": -2.0, "hf_token": "HF_TOKEN", "image_aug": true, "is_resume": false, "load_all_data_for_training": true, "load_meta_emb_from": "/fsx/daewon/ckpt/bridge/tcl-bsz64-fix/prism-dinosiglip-224px+oxe+diffusion+n0+b32+x42+t1757732137--image_aug/checkpoints/step-010000-epoch-00-loss=0.0015.pt", "memory_hidden_factor": 4, "memory_num_layers": 2, "memory_type": "transformer", "n_meta_queries": 1, "past_action_window_size": 0, "past_length": 4, "prealign_meta_queries_with": null, "pretrained_checkpoint": "CogACT/CogACT-Base", "re_initialize_memory": false, "repeated_diffusion_steps": 8, "resume_epoch": null, "resume_step": null, "run_id": "prism-dinosiglip-224px+oxe+diffusion+n0+b8+x42+t1757956583--image_aug", "run_id_note": null, "run_root_dir": "/fsx/daewon/ckpt/bridege/cogact_base_transformer_z_emb_no_time_mq1", "save_interval": 5000, "scalar_gate": false, "seed": 42, "tcl_tau": 0.07, "tmf_hidden_act": "silu", "tmf_initializer_range": 0.02, "tmf_max_position_embeddings": 3, "tmf_num_attention_heads": 16, "tmf_num_key_value_heads": 16, "tmf_rms_norm_eps": 1e-05, "token_wise_memory": true, "trackers": ["jsonl", "wandb"], "use_block_attn": false, "use_ema": false, "use_gate": false, "use_meta_queries": true, "use_mq_time_embedder": false, "use_mq_z_embedder": true, "use_original_max_pos_emb": false, "use_past_meta_queries_recursive": true, "use_projection_layer": false, "use_sinu_pe": false, "vla": {"base_vlm": "prism-dinosiglip-224px+7b", "data_mix": "bridge", "enable_gradient_checkpointing": true, "enable_mixed_precision_training": true, "epochs": 100, "expected_world_size": 4, "freeze_llm_backbone": false, "freeze_vision_backbone": false, "global_batch_size": 32, "learning_rate": 2e-05, "lr_scheduler_type": "constant", "max_grad_norm": 1.0, "max_steps": 60000, "per_device_batch_size": 8, "reduce_in_full_precision": true, "shuffle_buffer_size": 250000, "train_strategy": "fsdp-full-shard", "type": "prism-dinosiglip-224px+oxe+diffusion", "unfreeze_last_llm_layer": false, "vla_id": "prism-dinosiglip-224px+oxe+diffusion", "warmup_ratio": 0.0, "weight_decay": 0.0}, "wandb_entity": "daeone0920", "wandb_project": "CogACT-Bridge"}, "run_id": "prism-dinosiglip-224px+oxe+diffusion+n0+b8+x42+t1757956583--image_aug"}