Upload folder using huggingface_hub

checkpoints/latest-checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad800213ee533cac437aa1b641295c22335e0ac22768ad9b8b80cbca2547a11f
+size 13862118977

checkpoints/wget-log

@@ -0,0 +1,14 @@
+--2025-05-25 20:27:25--  https://aries-dav.skis.ltd/ariesdv0/agopalkr/openvla-logs/pi-0-224px-bridge_cotraining_st_8/checkpoints/step-362500-epoch-21-loss=0.0626.pt
+Resolving aries-dav.skis.ltd (aries-dav.skis.ltd)... 184.105.6.99
+Connecting to aries-dav.skis.ltd (aries-dav.skis.ltd)|184.105.6.99|:443... connected.
+HTTP request sent, awaiting response... 401 Unauthorized
+Authentication selected: Basic realm="Restricted"
+Reusing existing connection to aries-dav.skis.ltd:443.
+HTTP request sent, awaiting response... 200 OK
+Length: 13862118977 (13G) [application/zip]
+Saving to: ‘step-362500-epoch-21-loss=0.0626.pt’
+
+
+
+2025-05-25 21:08:50 (5.32 MB/s) - ‘step-362500-epoch-21-loss=0.0626.pt’ saved [13862118977/13862118977]
+

config.json

@@ -0,0 +1,62 @@
+{
+  "_name_or_path": "final-hf/paligemma-3b-pt-224-main",
+  "architectures": [
+    "PaliGemmaForConditionalGeneration"
+  ],
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "hidden_size": 2048,
+  "ignore_index": -100,
+  "image_token_index": 257152,
+  "model_type": "paligemma",
+  "pad_token_id": 0,
+  "projection_dim": 2048,
+  "text_config": {
+    "hidden_size": 2048,
+    "intermediate_size": 16384,
+    "model_type": "gemma",
+    "num_attention_heads": 8,
+    "num_hidden_layers": 18,
+    "num_image_tokens": 256,
+    "num_key_value_heads": 1,
+    "torch_dtype": "float32",
+    "vocab_size": 257216
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.0.dev0",
+  "vision_config": {
+    "hidden_size": 1152,
+    "intermediate_size": 4304,
+    "model_type": "siglip_vision_model",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 27,
+    "num_image_tokens": 256,
+    "patch_size": 14,
+    "projection_dim": 2048,
+    "projector_hidden_act": "gelu_fast",
+    "vision_use_head": false
+  },
+  "vocab_size": 257216,
+  "model": {
+    "llm_backbone_id": "gemma-2b",
+    "llm_max_length": 2048,
+    "model_id": "paligemma-224px+3b",
+    "type": "paligemma-224px+3b",
+    "vision_backbone_id": "siglip-vit-so400m",
+    "arch_specifier": "linear",
+    "image_resize_strategy": "resize-naive",
+    "reduce_in_full_precision": false,
+    "align_epochs": 1,
+    "align_global_batch_size": 256,
+    "align_learning_rate": 0.001,
+    "align_lr_scheduler_type": "linear-warmup+cosine-decay",
+    "align_max_grad_norm": 1.0,
+    "align_max_steps": null,
+    "align_per_device_batch_size": 16,
+    "align_train_strategy": "fsdp-shard-grad-op",
+    "align_warmup_ratio": 0.03,
+    "align_weight_decay": 0.0,
+    "enable_gradient_checkpointing": true,
+    "enable_mixed_precision_training": true
+  }
+}

config.yaml

@@ -0,0 +1,44 @@
+co_training: true
+data_root_dir: data
+hf_token: ./hf-token
+image_aug: false
+is_resume: true
+local_rank: 0
+pretrained_checkpoint: /ariesdv0/agopalkr/openvla-logs/pi-0-224px-bridge_cotraining_st_8/checkpoints/step-285000-epoch-17-loss=0.0839.pt
+resume_epoch: 17
+resume_step: 285000
+run_id: pi-0-224px-bridge_cotraining_st_8
+run_id_note: null
+run_root_dir: logs
+save_interval: 2500
+seed: 7
+trackers:
+- jsonl
+- wandb
+vla:
+  base_vlm: paligemma-224px+3b
+  co_training_data_mix: all+trace
+  data_mix: bridge
+  enable_gradient_checkpointing: true
+  enable_mixed_precision_training: true
+  enable_tf32: true
+  epochs: 50
+  expected_world_size: 8
+  freeze_llm_backbone: false
+  freeze_vision_backbone: false
+  global_batch_size: 128
+  learning_rate: 2.0e-05
+  lr_scheduler_type: linear-warmup+cosine-decay
+  max_grad_norm: 1.0
+  max_steps: null
+  per_device_batch_size: 16
+  reduce_in_full_precision: true
+  shuffle_buffer_size: 256000
+  train_strategy: fsdp-full-shard
+  type: pi-0-224px-bridge_cotraining_st_8
+  unfreeze_last_llm_layer: false
+  vla_id: pi-0-224px-bridge_cotraining_st_8
+  warmup_ratio: 0.0
+  weight_decay: 0.0
+wandb_entity: SU-Lab-openvla
+wandb_project: pi-0-cotraining

dataset_statistics.json

@@ -0,0 +1,127 @@
+{
+  "bridge_dataset": {
+    "action": {
+      "mean": [
+        0.00023341714404523373,
+        0.0001300422882195562,
+        -0.00012762560800183564,
+        -0.00015565801004413515,
+        -0.0004039341874886304,
+        0.0002355830802116543,
+        0.5764582753181458
+      ],
+      "std": [
+        0.00976572372019291,
+        0.013689479790627956,
+        0.012667072005569935,
+        0.028534546494483948,
+        0.03063802234828472,
+        0.07691710442304611,
+        0.49736642837524414
+      ],
+      "max": [
+        0.41691166162490845,
+        0.25864794850349426,
+        0.21218234300613403,
+        3.122201919555664,
+        1.8618112802505493,
+        6.280478477478027,
+        1.0
+      ],
+      "min": [
+        -0.4007510244846344,
+        -0.13874775171279907,
+        -0.22553899884223938,
+        -3.2010786533355713,
+        -1.8618112802505493,
+        -6.279075622558594,
+        0.0
+      ],
+      "q01": [
+        -0.02872725307941437,
+        -0.04170349963009357,
+        -0.026093858778476715,
+        -0.08092105075716972,
+        -0.09288699507713317,
+        -0.20718276381492615,
+        0.0
+      ],
+      "q99": [
+        0.028309678435325586,
+        0.040855254605412394,
+        0.040161586627364146,
+        0.08192047759890528,
+        0.07792850524187081,
+        0.20382574498653397,
+        1.0
+      ],
+      "mask": [
+        true,
+        true,
+        true,
+        true,
+        true,
+        true,
+        false
+      ]
+    },
+    "proprio": {
+      "mean": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "std": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "max": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "min": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "q01": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "q99": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ]
+    },
+    "num_transitions": 2135463,
+    "num_trajectories": 60064
+  }
+}