Hugging Face's logo

Stanford-ILIAD
/
minivla-vq-bridge-prismatic

Image-Text-to-Text
Transformers
English
robotics
vla
multimodal
pretraining
Inference Endpoints
Model card Files Community
1
belkhale commited on
Commit
15f0c5c
·
verified ·
1 Parent(s): f13a9b2

Upload folder using huggingface_hub

Browse files
Files changed (7) hide show
  1. .gitattributes +1 -0
  2. checkpoints/step-362500-epoch-21-loss=0.2259.pt +3 -0
  3. config.json +48 -0
  4. config.yaml +44 -0
  5. dataset_statistics.json +127 -0
  6. prism-qwen25-dinosiglip-224px+0_5b+mx-bridge+n1+b16+x7--bridge_vq_extra_tokenizer_evenlowerlr.jsonl +3 -0
  7. run-metrics.jsonl +1 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ prism-qwen25-dinosiglip-224px+0_5b+mx-bridge+n1+b16+x7--bridge_vq_extra_tokenizer_evenlowerlr.jsonl filter=lfs diff=lfs merge=lfs -text
checkpoints/step-362500-epoch-21-loss=0.2259.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b1828f4fb96b0b7a4f3d191fde4ee96938b293c70f8616fb44dd85f5c85cadc
3
+ size 5554882540
config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "data_root_dir": "/iliad/group/datasets/OXE_OCTO",
3
+ "hf_token": ".hf_token",
4
+ "image_aug": false,
5
+ "is_resume": true,
6
+ "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",
7
+ "resume_epoch": 18,
8
+ "resume_step": 305000,
9
+ "run_id": "prism-qwen25-dinosiglip-224px+0_5b+mx-bridge+n1+b16+x7--bridge_vq_extra_tokenizer_evenlowerlr",
10
+ "run_id_note": "bridge_vq_extra_tokenizer_evenlowerlr",
11
+ "run_root_dir": "runs",
12
+ "save_interval": 2500,
13
+ "seed": 7,
14
+ "trackers": [
15
+ "jsonl",
16
+ "wandb"
17
+ ],
18
+ "vla": {
19
+ "action_tokenizer": "bridge_vq_extra_action_tokenizer",
20
+ "base_vlm": "prism-qwen25-extra-dinosiglip-224px+0_5b",
21
+ "data_mix": "bridge_dataset",
22
+ "enable_gradient_checkpointing": true,
23
+ "enable_mixed_precision_training": true,
24
+ "epochs": 1000,
25
+ "expected_world_size": 8,
26
+ "freeze_llm_backbone": false,
27
+ "freeze_vision_backbone": false,
28
+ "global_batch_size": 128,
29
+ "image_sequence_len": 1,
30
+ "learning_rate": 1e-06,
31
+ "lr_scheduler_type": "constant",
32
+ "max_grad_norm": 1.0,
33
+ "max_steps": null,
34
+ "per_device_batch_size": 16,
35
+ "reduce_in_full_precision": true,
36
+ "save_every_n_steps": 25000,
37
+ "shuffle_buffer_size": 256000,
38
+ "train_strategy": "fsdp-full-shard",
39
+ "type": "prism-qwen25-dinosiglip-224px+0_5b+mx-bridge",
40
+ "unfreeze_last_llm_layer": false,
41
+ "use_wrist_image": false,
42
+ "vla_id": "prism-qwen25-dinosiglip-224px+0_5b+mx-bridge",
43
+ "warmup_ratio": 0.0,
44
+ "weight_decay": 0.0
45
+ },
46
+ "wandb_entity": null,
47
+ "wandb_project": "prismatic"
48
+ }
config.yaml ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ data_root_dir: /iliad/group/datasets/OXE_OCTO
2
+ hf_token: .hf_token
3
+ image_aug: false
4
+ is_resume: true
5
+ 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
6
+ resume_epoch: 18
7
+ resume_step: 305000
8
+ run_id: prism-qwen25-dinosiglip-224px+0_5b+mx-bridge+n1+b16+x7--bridge_vq_extra_tokenizer_evenlowerlr
9
+ run_id_note: bridge_vq_extra_tokenizer_evenlowerlr
10
+ run_root_dir: runs
11
+ save_interval: 2500
12
+ seed: 7
13
+ trackers:
14
+ - jsonl
15
+ - wandb
16
+ vla:
17
+ action_tokenizer: bridge_vq_extra_action_tokenizer
18
+ base_vlm: prism-qwen25-dinosiglip-224px+0_5b
19
+ data_mix: bridge_dataset
20
+ enable_gradient_checkpointing: true
21
+ enable_mixed_precision_training: true
22
+ epochs: 1000
23
+ expected_world_size: 8
24
+ freeze_llm_backbone: false
25
+ freeze_vision_backbone: false
26
+ global_batch_size: 128
27
+ image_sequence_len: 1
28
+ learning_rate: 1.0e-06
29
+ lr_scheduler_type: constant
30
+ max_grad_norm: 1.0
31
+ max_steps: null
32
+ per_device_batch_size: 16
33
+ reduce_in_full_precision: true
34
+ save_every_n_steps: 25000
35
+ shuffle_buffer_size: 256000
36
+ train_strategy: fsdp-full-shard
37
+ type: prism-qwen25-dinosiglip-224px+0_5b+mx-bridge
38
+ unfreeze_last_llm_layer: false
39
+ use_wrist_image: false
40
+ vla_id: prism-qwen25-dinosiglip-224px+0_5b+mx-bridge
41
+ warmup_ratio: 0.0
42
+ weight_decay: 0.0
43
+ wandb_entity: null
44
+ wandb_project: prismatic
dataset_statistics.json ADDED
@@ -0,0 +1,127 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bridge_dataset": {
3
+ "action": {
4
+ "mean": [
5
+ 0.00023341951600741595,
6
+ 0.00013004841457586735,
7
+ -0.00012762370170094073,
8
+ -0.00015565504145342857,
9
+ -0.00040393343078903854,
10
+ 0.00023557768145110458,
11
+ 0.5764579176902771
12
+ ],
13
+ "std": [
14
+ 0.009765920229256153,
15
+ 0.013689135201275349,
16
+ 0.01266736164689064,
17
+ 0.02853427641093731,
18
+ 0.030637990683317184,
19
+ 0.0769147127866745,
20
+ 0.49736854434013367
21
+ ],
22
+ "max": [
23
+ 0.41691166162490845,
24
+ 0.25864794850349426,
25
+ 0.21218234300613403,
26
+ 3.122201919555664,
27
+ 1.8618112802505493,
28
+ 6.280478477478027,
29
+ 1.0
30
+ ],
31
+ "min": [
32
+ -0.4007510244846344,
33
+ -0.13874775171279907,
34
+ -0.22553899884223938,
35
+ -3.2010786533355713,
36
+ -1.8618112802505493,
37
+ -6.279075622558594,
38
+ 0.0
39
+ ],
40
+ "q01": [
41
+ -0.02872725307941437,
42
+ -0.04170349963009357,
43
+ -0.026093858778476715,
44
+ -0.08092105075716972,
45
+ -0.09288699507713317,
46
+ -0.20718276381492615,
47
+ 0.0
48
+ ],
49
+ "q99": [
50
+ 0.028309678435325586,
51
+ 0.040855254605412394,
52
+ 0.040161586627364146,
53
+ 0.08192047759890528,
54
+ 0.07792850524187081,
55
+ 0.20382574498653397,
56
+ 1.0
57
+ ],
58
+ "mask": [
59
+ true,
60
+ true,
61
+ true,
62
+ true,
63
+ true,
64
+ true,
65
+ false
66
+ ]
67
+ },
68
+ "proprio": {
69
+ "mean": [
70
+ 0.0,
71
+ 0.0,
72
+ 0.0,
73
+ 0.0,
74
+ 0.0,
75
+ 0.0,
76
+ 0.0
77
+ ],
78
+ "std": [
79
+ 0.0,
80
+ 0.0,
81
+ 0.0,
82
+ 0.0,
83
+ 0.0,
84
+ 0.0,
85
+ 0.0
86
+ ],
87
+ "max": [
88
+ 0.0,
89
+ 0.0,
90
+ 0.0,
91
+ 0.0,
92
+ 0.0,
93
+ 0.0,
94
+ 0.0
95
+ ],
96
+ "min": [
97
+ 0.0,
98
+ 0.0,
99
+ 0.0,
100
+ 0.0,
101
+ 0.0,
102
+ 0.0,
103
+ 0.0
104
+ ],
105
+ "q01": [
106
+ 0.0,
107
+ 0.0,
108
+ 0.0,
109
+ 0.0,
110
+ 0.0,
111
+ 0.0,
112
+ 0.0
113
+ ],
114
+ "q99": [
115
+ 0.0,
116
+ 0.0,
117
+ 0.0,
118
+ 0.0,
119
+ 0.0,
120
+ 0.0,
121
+ 0.0
122
+ ]
123
+ },
124
+ "num_transitions": 2135463,
125
+ "num_trajectories": 60064
126
+ }
127
+ }
prism-qwen25-dinosiglip-224px+0_5b+mx-bridge+n1+b16+x7--bridge_vq_extra_tokenizer_evenlowerlr.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79e30022be1b39d861bb03554272c3073a75abd6adf389733eb5b9ccc40fdfc3
3
+ size 76106884
run-metrics.jsonl ADDED
@@ -0,0 +1 @@
 
 
1
+ {"hparams": {"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": 1e-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"}, "run_id": "prism-qwen25-dinosiglip-224px+0_5b+mx-bridge+n1+b16+x7--bridge_vq_extra_tokenizer_evenlowerlr"}