trustml-users commited on
Commit
bc86784
·
verified ·
1 Parent(s): 2a74180

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. 17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_004000/pretrained_model/README.md +204 -0
  2. 17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_004000/pretrained_model/adapter_config.json +46 -0
  3. 17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_004000/pretrained_model/adapter_model.safetensors +3 -0
  4. 17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_004000/pretrained_model/config.json +102 -0
  5. 17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_004000/pretrained_model/gk_config.json +112 -0
  6. 17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_004000/pretrained_model/gk_router.safetensors +3 -0
  7. 17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_004000/pretrained_model/policy_postprocessor.json +32 -0
  8. 17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_004000/pretrained_model/policy_postprocessor_step_0_unnormalizer_processor.safetensors +3 -0
  9. 17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_004000/pretrained_model/policy_preprocessor.json +92 -0
  10. 17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_004000/pretrained_model/policy_preprocessor_step_5_normalizer_processor.safetensors +3 -0
  11. 17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_004000/pretrained_model/tokenizer/chat_template.jinja +2 -0
  12. 17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_004000/pretrained_model/tokenizer/tokenizer.json +0 -0
  13. 17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_004000/pretrained_model/tokenizer/tokenizer_config.json +27 -0
  14. 17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_004000/pretrained_model/train_config.json +590 -0
  15. 17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_004000/training_state/checkpoint_complete.json +3 -0
  16. 17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_004000/training_state/optimizer_param_groups.json +593 -0
  17. 17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_004000/training_state/optimizer_state.safetensors +3 -0
  18. 17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_004000/training_state/rng_state.safetensors +3 -0
  19. 17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_004000/training_state/rng_state_rank_0.safetensors +3 -0
  20. 17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_004000/training_state/scheduler_state.json +15 -0
  21. 17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_004000/training_state/sequential_state.json +904 -0
  22. 17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_004000/training_state/training_step.json +12 -0
  23. 17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_005000/pretrained_model/README.md +204 -0
  24. 17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_005000/pretrained_model/adapter_config.json +46 -0
  25. 17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_005000/pretrained_model/adapter_model.safetensors +3 -0
  26. 17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_005000/pretrained_model/config.json +102 -0
  27. 17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_005000/pretrained_model/gk_config.json +132 -0
  28. 17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_005000/pretrained_model/gk_router.safetensors +3 -0
  29. 17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_005000/pretrained_model/policy_postprocessor.json +32 -0
  30. 17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_005000/pretrained_model/policy_postprocessor_step_0_unnormalizer_processor.safetensors +3 -0
  31. 17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_005000/pretrained_model/policy_preprocessor.json +92 -0
  32. 17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_005000/pretrained_model/policy_preprocessor_step_5_normalizer_processor.safetensors +3 -0
  33. 17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_005000/pretrained_model/tokenizer/chat_template.jinja +2 -0
  34. 17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_005000/pretrained_model/tokenizer/tokenizer.json +0 -0
  35. 17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_005000/pretrained_model/tokenizer/tokenizer_config.json +27 -0
  36. 17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_005000/pretrained_model/train_config.json +590 -0
  37. 17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_005000/training_state/checkpoint_complete.json +3 -0
  38. 17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_005000/training_state/optimizer_param_groups.json +593 -0
  39. 17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_005000/training_state/optimizer_state.safetensors +3 -0
  40. 17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_005000/training_state/rng_state.safetensors +3 -0
  41. 17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_005000/training_state/rng_state_rank_0.safetensors +3 -0
  42. 17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_005000/training_state/scheduler_state.json +15 -0
  43. 17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_005000/training_state/sequential_state.json +904 -0
  44. 17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_005000/training_state/training_step.json +12 -0
  45. 17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_006000/pretrained_model/README.md +204 -0
  46. 17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_006000/pretrained_model/adapter_config.json +46 -0
  47. 17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_006000/pretrained_model/adapter_model.safetensors +3 -0
  48. 17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_006000/pretrained_model/config.json +102 -0
  49. 17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_006000/pretrained_model/gk_config.json +152 -0
  50. 17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_006000/pretrained_model/gk_router.safetensors +3 -0
17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_004000/pretrained_model/README.md ADDED
@@ -0,0 +1,204 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ tags:
4
+ - base_model:adapter:lerobot/smolvla_base
5
+ - lora
6
+ ---
7
+
8
+ # Model Card for Model ID
9
+
10
+ <!-- Provide a quick summary of what the model is/does. -->
11
+
12
+
13
+
14
+ ## Model Details
15
+
16
+ ### Model Description
17
+
18
+ <!-- Provide a longer summary of what this model is. -->
19
+
20
+
21
+
22
+ - **Developed by:** [More Information Needed]
23
+ - **Funded by [optional]:** [More Information Needed]
24
+ - **Shared by [optional]:** [More Information Needed]
25
+ - **Model type:** [More Information Needed]
26
+ - **Language(s) (NLP):** [More Information Needed]
27
+ - **License:** [More Information Needed]
28
+ - **Finetuned from model [optional]:** [More Information Needed]
29
+
30
+ ### Model Sources [optional]
31
+
32
+ <!-- Provide the basic links for the model. -->
33
+
34
+ - **Repository:** [More Information Needed]
35
+ - **Paper [optional]:** [More Information Needed]
36
+ - **Demo [optional]:** [More Information Needed]
37
+
38
+ ## Uses
39
+
40
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
41
+
42
+ ### Direct Use
43
+
44
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
45
+
46
+ [More Information Needed]
47
+
48
+ ### Downstream Use [optional]
49
+
50
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
51
+
52
+ [More Information Needed]
53
+
54
+ ### Out-of-Scope Use
55
+
56
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
57
+
58
+ [More Information Needed]
59
+
60
+ ## Bias, Risks, and Limitations
61
+
62
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
63
+
64
+ [More Information Needed]
65
+
66
+ ### Recommendations
67
+
68
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
69
+
70
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
71
+
72
+ ## How to Get Started with the Model
73
+
74
+ Use the code below to get started with the model.
75
+
76
+ [More Information Needed]
77
+
78
+ ## Training Details
79
+
80
+ ### Training Data
81
+
82
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
83
+
84
+ [More Information Needed]
85
+
86
+ ### Training Procedure
87
+
88
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
89
+
90
+ #### Preprocessing [optional]
91
+
92
+ [More Information Needed]
93
+
94
+
95
+ #### Training Hyperparameters
96
+
97
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
98
+
99
+ #### Speeds, Sizes, Times [optional]
100
+
101
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
102
+
103
+ [More Information Needed]
104
+
105
+ ## Evaluation
106
+
107
+ <!-- This section describes the evaluation protocols and provides the results. -->
108
+
109
+ ### Testing Data, Factors & Metrics
110
+
111
+ #### Testing Data
112
+
113
+ <!-- This should link to a Dataset Card if possible. -->
114
+
115
+ [More Information Needed]
116
+
117
+ #### Factors
118
+
119
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
120
+
121
+ [More Information Needed]
122
+
123
+ #### Metrics
124
+
125
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
126
+
127
+ [More Information Needed]
128
+
129
+ ### Results
130
+
131
+ [More Information Needed]
132
+
133
+ #### Summary
134
+
135
+
136
+
137
+ ## Model Examination [optional]
138
+
139
+ <!-- Relevant interpretability work for the model goes here -->
140
+
141
+ [More Information Needed]
142
+
143
+ ## Environmental Impact
144
+
145
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
146
+
147
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
148
+
149
+ - **Hardware Type:** [More Information Needed]
150
+ - **Hours used:** [More Information Needed]
151
+ - **Cloud Provider:** [More Information Needed]
152
+ - **Compute Region:** [More Information Needed]
153
+ - **Carbon Emitted:** [More Information Needed]
154
+
155
+ ## Technical Specifications [optional]
156
+
157
+ ### Model Architecture and Objective
158
+
159
+ [More Information Needed]
160
+
161
+ ### Compute Infrastructure
162
+
163
+ [More Information Needed]
164
+
165
+ #### Hardware
166
+
167
+ [More Information Needed]
168
+
169
+ #### Software
170
+
171
+ [More Information Needed]
172
+
173
+ ## Citation [optional]
174
+
175
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
176
+
177
+ **BibTeX:**
178
+
179
+ [More Information Needed]
180
+
181
+ **APA:**
182
+
183
+ [More Information Needed]
184
+
185
+ ## Glossary [optional]
186
+
187
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
188
+
189
+ [More Information Needed]
190
+
191
+ ## More Information [optional]
192
+
193
+ [More Information Needed]
194
+
195
+ ## Model Card Authors [optional]
196
+
197
+ [More Information Needed]
198
+
199
+ ## Model Card Contact
200
+
201
+ [More Information Needed]
202
+ ### Framework versions
203
+
204
+ - PEFT 0.21.0
17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_004000/pretrained_model/adapter_config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": {
6
+ "base_model_class": "SmolVLAPolicy",
7
+ "parent_library": "lerobot.policies.smolvla.modeling_smolvla"
8
+ },
9
+ "base_model_name_or_path": "lerobot/smolvla_base",
10
+ "bias": "none",
11
+ "corda_config": null,
12
+ "ensure_weight_tying": false,
13
+ "eva_config": null,
14
+ "exclude_modules": null,
15
+ "fan_in_fan_out": false,
16
+ "inference_mode": true,
17
+ "init_lora_weights": true,
18
+ "kasa_config": null,
19
+ "layer_replication": null,
20
+ "layers_pattern": null,
21
+ "layers_to_transform": null,
22
+ "loftq_config": {},
23
+ "lora_alpha": 16,
24
+ "lora_bias": false,
25
+ "lora_dropout": 0.0,
26
+ "lora_ga_config": null,
27
+ "megatron_config": null,
28
+ "megatron_core": "megatron.core",
29
+ "modules_to_save": [],
30
+ "monteclora_config": null,
31
+ "peft_type": "LORA",
32
+ "peft_version": "0.21.0",
33
+ "qalora_group_size": 16,
34
+ "r": 16,
35
+ "rank_pattern": {},
36
+ "revision": null,
37
+ "target_modules": "(model\\.vlm_with_expert\\.lm_expert\\..*\\.(q|v)_proj|model\\.(action_in_proj|action_out_proj|action_time_mlp_in|action_time_mlp_out))",
38
+ "target_parameters": null,
39
+ "task_type": null,
40
+ "trainable_token_indices": null,
41
+ "use_bdlora": null,
42
+ "use_dora": false,
43
+ "use_qalora": false,
44
+ "use_rslora": false,
45
+ "velora_config": null
46
+ }
17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_004000/pretrained_model/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ce9ff637e555ed56cd80ef1337705b9f2266b432bc5d9a4493f08f1e374bd82
3
+ size 2918168
17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_004000/pretrained_model/config.json ADDED
@@ -0,0 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "smolvla",
3
+ "n_obs_steps": 1,
4
+ "input_features": {
5
+ "observation.state": {
6
+ "type": "STATE",
7
+ "shape": [
8
+ 6
9
+ ]
10
+ },
11
+ "observation.images.camera1": {
12
+ "type": "VISUAL",
13
+ "shape": [
14
+ 3,
15
+ 256,
16
+ 256
17
+ ]
18
+ },
19
+ "observation.images.camera2": {
20
+ "type": "VISUAL",
21
+ "shape": [
22
+ 3,
23
+ 256,
24
+ 256
25
+ ]
26
+ },
27
+ "observation.images.camera3": {
28
+ "type": "VISUAL",
29
+ "shape": [
30
+ 3,
31
+ 256,
32
+ 256
33
+ ]
34
+ }
35
+ },
36
+ "output_features": {
37
+ "action": {
38
+ "type": "ACTION",
39
+ "shape": [
40
+ 6
41
+ ]
42
+ }
43
+ },
44
+ "device": "cuda",
45
+ "use_amp": false,
46
+ "use_peft": true,
47
+ "push_to_hub": false,
48
+ "repo_id": null,
49
+ "private": null,
50
+ "tags": null,
51
+ "license": null,
52
+ "pretrained_path": "lerobot/smolvla_base",
53
+ "pretrained_revision": null,
54
+ "chunk_size": 50,
55
+ "n_action_steps": 50,
56
+ "normalization_mapping": {
57
+ "VISUAL": "IDENTITY",
58
+ "STATE": "MEAN_STD",
59
+ "ACTION": "MEAN_STD"
60
+ },
61
+ "max_state_dim": 32,
62
+ "max_action_dim": 32,
63
+ "resize_imgs_with_padding": [
64
+ 512,
65
+ 512
66
+ ],
67
+ "empty_cameras": 0,
68
+ "adapt_to_pi_aloha": false,
69
+ "use_delta_joint_actions_aloha": false,
70
+ "tokenizer_max_length": 48,
71
+ "num_steps": 10,
72
+ "use_cache": true,
73
+ "freeze_vision_encoder": true,
74
+ "train_expert_only": true,
75
+ "train_state_proj": true,
76
+ "optimizer_lr": 0.0003,
77
+ "optimizer_betas": [
78
+ 0.9,
79
+ 0.95
80
+ ],
81
+ "optimizer_eps": 1e-08,
82
+ "optimizer_weight_decay": 1e-10,
83
+ "optimizer_grad_clip_norm": 10.0,
84
+ "scheduler_warmup_steps": 0,
85
+ "scheduler_decay_steps": 5000,
86
+ "scheduler_decay_lr": 0.0003,
87
+ "vlm_model_name": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct",
88
+ "load_vlm_weights": true,
89
+ "add_image_special_tokens": false,
90
+ "attention_mode": "cross_attn",
91
+ "prefix_length": 0,
92
+ "pad_language_to": "max_length",
93
+ "num_expert_layers": 0,
94
+ "num_vlm_layers": 16,
95
+ "self_attn_every_n_layers": 2,
96
+ "expert_width_multiplier": 0.75,
97
+ "min_period": 0.004,
98
+ "max_period": 4.0,
99
+ "rtc_config": null,
100
+ "compile_model": false,
101
+ "compile_mode": "max-autotune"
102
+ }
17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_004000/pretrained_model/gk_config.json ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "adapter_names": [
3
+ "default"
4
+ ],
5
+ "algorithm_type": "gk_adp",
6
+ "embedding_layer": -1,
7
+ "epsilon": 1e-06,
8
+ "inference_routing": "top1",
9
+ "inference_temperature": 1.0,
10
+ "inference_top_k": 0,
11
+ "interval_routed_batches": [
12
+ 0
13
+ ],
14
+ "log_expert_statistics": false,
15
+ "modalities": [
16
+ "vision",
17
+ "language"
18
+ ],
19
+ "reset_scheduler_on_expansion": true,
20
+ "routed_batches": [
21
+ 4000
22
+ ],
23
+ "router_statistics_unit": "inputs",
24
+ "router_statistics_version": 2,
25
+ "router_variance_semantics": "seeded_m2_population",
26
+ "sigma_init": 1.0,
27
+ "total_expansions": 1,
28
+ "wandb_history_counts": [
29
+ [
30
+ 200
31
+ ],
32
+ [
33
+ 400
34
+ ],
35
+ [
36
+ 600
37
+ ],
38
+ [
39
+ 800
40
+ ],
41
+ [
42
+ 1000
43
+ ],
44
+ [
45
+ 1200
46
+ ],
47
+ [
48
+ 1400
49
+ ],
50
+ [
51
+ 1600
52
+ ],
53
+ [
54
+ 1800
55
+ ],
56
+ [
57
+ 2000
58
+ ],
59
+ [
60
+ 2200
61
+ ],
62
+ [
63
+ 2400
64
+ ],
65
+ [
66
+ 2600
67
+ ],
68
+ [
69
+ 2800
70
+ ],
71
+ [
72
+ 3000
73
+ ],
74
+ [
75
+ 3200
76
+ ],
77
+ [
78
+ 3400
79
+ ],
80
+ [
81
+ 3600
82
+ ],
83
+ [
84
+ 3800
85
+ ],
86
+ [
87
+ 4000
88
+ ]
89
+ ],
90
+ "wandb_history_steps": [
91
+ 200,
92
+ 400,
93
+ 600,
94
+ 800,
95
+ 1000,
96
+ 1200,
97
+ 1400,
98
+ 1600,
99
+ 1800,
100
+ 2000,
101
+ 2200,
102
+ 2400,
103
+ 2600,
104
+ 2800,
105
+ 3000,
106
+ 3200,
107
+ 3400,
108
+ 3600,
109
+ 3800,
110
+ 4000
111
+ ]
112
+ }
17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_004000/pretrained_model/gk_router.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8efe2847a6789f9af39ff770ae0564b6dff33433d98b231beefb879134774e3
3
+ size 15564
17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_004000/pretrained_model/policy_postprocessor.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "policy_postprocessor",
3
+ "steps": [
4
+ {
5
+ "registry_name": "unnormalizer_processor",
6
+ "config": {
7
+ "eps": 1e-08,
8
+ "features": {
9
+ "action": {
10
+ "type": "ACTION",
11
+ "shape": [
12
+ 6
13
+ ]
14
+ }
15
+ },
16
+ "norm_map": {
17
+ "VISUAL": "IDENTITY",
18
+ "STATE": "MEAN_STD",
19
+ "ACTION": "MEAN_STD"
20
+ }
21
+ },
22
+ "state_file": "policy_postprocessor_step_0_unnormalizer_processor.safetensors"
23
+ },
24
+ {
25
+ "registry_name": "device_processor",
26
+ "config": {
27
+ "device": "cpu",
28
+ "float_dtype": null
29
+ }
30
+ }
31
+ ]
32
+ }
17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_004000/pretrained_model/policy_postprocessor_step_0_unnormalizer_processor.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d9ca31ecf0fe1c9ad4552e701c429441bd8d7e0136ab810f541e3e41fc0d964
3
+ size 6584
17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_004000/pretrained_model/policy_preprocessor.json ADDED
@@ -0,0 +1,92 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "policy_preprocessor",
3
+ "steps": [
4
+ {
5
+ "registry_name": "rename_observations_processor",
6
+ "config": {
7
+ "rename_map": {
8
+ "observation.images.front": "observation.images.camera1"
9
+ }
10
+ }
11
+ },
12
+ {
13
+ "registry_name": "to_batch_processor",
14
+ "config": {}
15
+ },
16
+ {
17
+ "registry_name": "smolvla_new_line_processor",
18
+ "config": {}
19
+ },
20
+ {
21
+ "registry_name": "tokenizer_processor",
22
+ "config": {
23
+ "max_length": 48,
24
+ "task_key": "task",
25
+ "padding_side": "right",
26
+ "padding": "max_length",
27
+ "truncation": true,
28
+ "tokenizer_name": "tokenizer"
29
+ },
30
+ "artifacts": {
31
+ "tokenizer_name": "tokenizer"
32
+ }
33
+ },
34
+ {
35
+ "registry_name": "device_processor",
36
+ "config": {
37
+ "device": "cuda",
38
+ "float_dtype": null
39
+ }
40
+ },
41
+ {
42
+ "registry_name": "normalizer_processor",
43
+ "config": {
44
+ "eps": 1e-08,
45
+ "features": {
46
+ "observation.state": {
47
+ "type": "STATE",
48
+ "shape": [
49
+ 6
50
+ ]
51
+ },
52
+ "observation.images.camera1": {
53
+ "type": "VISUAL",
54
+ "shape": [
55
+ 3,
56
+ 256,
57
+ 256
58
+ ]
59
+ },
60
+ "observation.images.camera2": {
61
+ "type": "VISUAL",
62
+ "shape": [
63
+ 3,
64
+ 256,
65
+ 256
66
+ ]
67
+ },
68
+ "observation.images.camera3": {
69
+ "type": "VISUAL",
70
+ "shape": [
71
+ 3,
72
+ 256,
73
+ 256
74
+ ]
75
+ },
76
+ "action": {
77
+ "type": "ACTION",
78
+ "shape": [
79
+ 6
80
+ ]
81
+ }
82
+ },
83
+ "norm_map": {
84
+ "VISUAL": "IDENTITY",
85
+ "STATE": "MEAN_STD",
86
+ "ACTION": "MEAN_STD"
87
+ }
88
+ },
89
+ "state_file": "policy_preprocessor_step_5_normalizer_processor.safetensors"
90
+ }
91
+ ]
92
+ }
17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_004000/pretrained_model/policy_preprocessor_step_5_normalizer_processor.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3eb9132f106bcea24a90aa2ce834285c158f8c88b60aef65695dc416321743fa
3
+ size 6584
17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_004000/pretrained_model/tokenizer/chat_template.jinja ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ <|im_start|>{% for message in messages %}{{message['role'] | capitalize}}{% if message['content'][0]['type'] == 'image' %}{{':'}}{% else %}{{': '}}{% endif %}{% for line in message['content'] %}{% if line['type'] == 'text' %}{{line['text']}}{% elif line['type'] == 'image' %}{{ '<image>' }}{% endif %}{% endfor %}<end_of_utterance>
2
+ {% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}
17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_004000/pretrained_model/tokenizer/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_004000/pretrained_model/tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<|im_start|>",
5
+ "clean_up_tokenization_spaces": false,
6
+ "end_of_utterance_token": "<end_of_utterance>",
7
+ "eos_token": "<end_of_utterance>",
8
+ "errors": "replace",
9
+ "fake_image_token": "<fake_token_around_image>",
10
+ "global_image_token": "<global-img>",
11
+ "image_token": "<image>",
12
+ "is_local": false,
13
+ "legacy": false,
14
+ "model_max_length": 8192,
15
+ "model_specific_special_tokens": {
16
+ "end_of_utterance_token": "<end_of_utterance>",
17
+ "fake_image_token": "<fake_token_around_image>",
18
+ "global_image_token": "<global-img>",
19
+ "image_token": "<image>"
20
+ },
21
+ "pad_token": "<|im_end|>",
22
+ "processor_class": "SmolVLMProcessor",
23
+ "tokenizer_class": "GPT2Tokenizer",
24
+ "truncation_side": "left",
25
+ "unk_token": "<|endoftext|>",
26
+ "vocab_size": 49152
27
+ }
17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_004000/pretrained_model/train_config.json ADDED
@@ -0,0 +1,590 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "tml-lab/real",
4
+ "repo_type": "dataset",
5
+ "root": null,
6
+ "episodes": [
7
+ 0,
8
+ 1,
9
+ 2,
10
+ 3,
11
+ 4,
12
+ 5,
13
+ 6,
14
+ 7,
15
+ 8,
16
+ 9,
17
+ 10,
18
+ 11,
19
+ 12,
20
+ 13,
21
+ 14,
22
+ 15,
23
+ 16,
24
+ 17,
25
+ 18,
26
+ 19,
27
+ 20,
28
+ 21,
29
+ 22,
30
+ 23,
31
+ 24,
32
+ 25,
33
+ 26,
34
+ 27,
35
+ 28,
36
+ 29,
37
+ 30,
38
+ 31,
39
+ 32,
40
+ 33,
41
+ 34,
42
+ 35,
43
+ 36,
44
+ 37,
45
+ 38,
46
+ 39,
47
+ 40,
48
+ 41,
49
+ 42,
50
+ 43,
51
+ 44,
52
+ 45,
53
+ 46,
54
+ 47,
55
+ 48,
56
+ 49,
57
+ 50,
58
+ 51,
59
+ 52,
60
+ 53,
61
+ 54,
62
+ 55,
63
+ 56,
64
+ 57,
65
+ 58,
66
+ 59,
67
+ 60,
68
+ 61,
69
+ 62,
70
+ 63,
71
+ 64,
72
+ 65,
73
+ 66,
74
+ 67,
75
+ 68,
76
+ 69,
77
+ 70,
78
+ 71,
79
+ 72,
80
+ 73,
81
+ 74,
82
+ 75,
83
+ 76,
84
+ 77,
85
+ 78,
86
+ 79,
87
+ 80,
88
+ 81,
89
+ 82,
90
+ 83,
91
+ 84,
92
+ 85,
93
+ 86,
94
+ 87,
95
+ 88,
96
+ 89,
97
+ 90,
98
+ 91,
99
+ 92,
100
+ 93,
101
+ 94,
102
+ 95,
103
+ 96,
104
+ 97,
105
+ 98,
106
+ 99,
107
+ 100,
108
+ 101,
109
+ 102,
110
+ 103,
111
+ 104,
112
+ 105,
113
+ 106,
114
+ 107,
115
+ 108,
116
+ 109,
117
+ 110,
118
+ 111,
119
+ 112,
120
+ 113,
121
+ 114,
122
+ 115,
123
+ 116,
124
+ 117,
125
+ 118,
126
+ 119,
127
+ 120,
128
+ 121,
129
+ 122,
130
+ 123,
131
+ 124,
132
+ 125,
133
+ 126,
134
+ 127,
135
+ 128,
136
+ 129,
137
+ 130,
138
+ 131,
139
+ 132,
140
+ 133,
141
+ 134,
142
+ 135,
143
+ 136,
144
+ 137,
145
+ 138,
146
+ 139,
147
+ 140,
148
+ 141,
149
+ 142,
150
+ 143,
151
+ 144,
152
+ 145,
153
+ 146,
154
+ 147,
155
+ 148,
156
+ 149,
157
+ 150,
158
+ 151,
159
+ 152,
160
+ 153,
161
+ 154,
162
+ 155,
163
+ 156,
164
+ 157,
165
+ 158,
166
+ 159,
167
+ 160,
168
+ 161,
169
+ 162,
170
+ 163,
171
+ 164,
172
+ 165,
173
+ 166,
174
+ 167,
175
+ 168,
176
+ 169,
177
+ 170,
178
+ 171,
179
+ 172,
180
+ 173,
181
+ 174,
182
+ 175,
183
+ 176,
184
+ 177,
185
+ 178,
186
+ 179,
187
+ 180,
188
+ 181,
189
+ 182,
190
+ 183,
191
+ 184,
192
+ 185,
193
+ 186,
194
+ 187,
195
+ 188,
196
+ 189,
197
+ 190,
198
+ 191,
199
+ 192,
200
+ 193,
201
+ 194,
202
+ 195,
203
+ 196,
204
+ 197,
205
+ 198,
206
+ 199,
207
+ 200,
208
+ 201,
209
+ 202,
210
+ 203,
211
+ 204,
212
+ 205,
213
+ 206,
214
+ 207,
215
+ 208,
216
+ 209,
217
+ 210,
218
+ 211,
219
+ 212,
220
+ 213,
221
+ 214,
222
+ 215,
223
+ 216,
224
+ 217,
225
+ 218,
226
+ 219,
227
+ 220,
228
+ 221,
229
+ 222,
230
+ 223,
231
+ 224,
232
+ 225,
233
+ 226,
234
+ 227,
235
+ 228,
236
+ 229,
237
+ 230,
238
+ 231,
239
+ 232,
240
+ 233,
241
+ 234,
242
+ 235,
243
+ 236,
244
+ 237,
245
+ 238,
246
+ 239,
247
+ 240,
248
+ 241,
249
+ 242,
250
+ 243,
251
+ 244,
252
+ 245,
253
+ 246,
254
+ 247,
255
+ 248,
256
+ 249
257
+ ],
258
+ "exclude_episodes": null,
259
+ "filter_failed_trajectories": false,
260
+ "image_transforms": {
261
+ "enable": false,
262
+ "max_num_transforms": 3,
263
+ "random_order": false,
264
+ "tfs": {
265
+ "brightness": {
266
+ "weight": 1.0,
267
+ "type": "ColorJitter",
268
+ "kwargs": {
269
+ "brightness": [
270
+ 0.8,
271
+ 1.2
272
+ ]
273
+ }
274
+ },
275
+ "contrast": {
276
+ "weight": 1.0,
277
+ "type": "ColorJitter",
278
+ "kwargs": {
279
+ "contrast": [
280
+ 0.8,
281
+ 1.2
282
+ ]
283
+ }
284
+ },
285
+ "saturation": {
286
+ "weight": 1.0,
287
+ "type": "ColorJitter",
288
+ "kwargs": {
289
+ "saturation": [
290
+ 0.5,
291
+ 1.5
292
+ ]
293
+ }
294
+ },
295
+ "hue": {
296
+ "weight": 1.0,
297
+ "type": "ColorJitter",
298
+ "kwargs": {
299
+ "hue": [
300
+ -0.05,
301
+ 0.05
302
+ ]
303
+ }
304
+ },
305
+ "sharpness": {
306
+ "weight": 1.0,
307
+ "type": "SharpnessJitter",
308
+ "kwargs": {
309
+ "sharpness": [
310
+ 0.5,
311
+ 1.5
312
+ ]
313
+ }
314
+ },
315
+ "affine": {
316
+ "weight": 1.0,
317
+ "type": "RandomAffine",
318
+ "kwargs": {
319
+ "degrees": [
320
+ -5.0,
321
+ 5.0
322
+ ],
323
+ "translate": [
324
+ 0.05,
325
+ 0.05
326
+ ]
327
+ }
328
+ }
329
+ }
330
+ },
331
+ "revision": null,
332
+ "use_imagenet_stats": true,
333
+ "video_backend": "torchcodec",
334
+ "return_uint8": false,
335
+ "depth_output_unit": "mm",
336
+ "streaming": false,
337
+ "eval_split": 0.0
338
+ },
339
+ "env": null,
340
+ "policy": {
341
+ "type": "smolvla",
342
+ "n_obs_steps": 1,
343
+ "input_features": {
344
+ "observation.state": {
345
+ "type": "STATE",
346
+ "shape": [
347
+ 6
348
+ ]
349
+ },
350
+ "observation.images.camera1": {
351
+ "type": "VISUAL",
352
+ "shape": [
353
+ 3,
354
+ 256,
355
+ 256
356
+ ]
357
+ },
358
+ "observation.images.camera2": {
359
+ "type": "VISUAL",
360
+ "shape": [
361
+ 3,
362
+ 256,
363
+ 256
364
+ ]
365
+ },
366
+ "observation.images.camera3": {
367
+ "type": "VISUAL",
368
+ "shape": [
369
+ 3,
370
+ 256,
371
+ 256
372
+ ]
373
+ }
374
+ },
375
+ "output_features": {
376
+ "action": {
377
+ "type": "ACTION",
378
+ "shape": [
379
+ 6
380
+ ]
381
+ }
382
+ },
383
+ "device": "cuda",
384
+ "use_amp": false,
385
+ "use_peft": true,
386
+ "push_to_hub": false,
387
+ "repo_id": null,
388
+ "private": null,
389
+ "tags": null,
390
+ "license": null,
391
+ "pretrained_path": "lerobot/smolvla_base",
392
+ "pretrained_revision": null,
393
+ "chunk_size": 50,
394
+ "n_action_steps": 50,
395
+ "normalization_mapping": {
396
+ "VISUAL": "IDENTITY",
397
+ "STATE": "MEAN_STD",
398
+ "ACTION": "MEAN_STD"
399
+ },
400
+ "max_state_dim": 32,
401
+ "max_action_dim": 32,
402
+ "resize_imgs_with_padding": [
403
+ 512,
404
+ 512
405
+ ],
406
+ "empty_cameras": 0,
407
+ "adapt_to_pi_aloha": false,
408
+ "use_delta_joint_actions_aloha": false,
409
+ "tokenizer_max_length": 48,
410
+ "num_steps": 10,
411
+ "use_cache": true,
412
+ "freeze_vision_encoder": true,
413
+ "train_expert_only": true,
414
+ "train_state_proj": true,
415
+ "optimizer_lr": 0.0003,
416
+ "optimizer_betas": [
417
+ 0.9,
418
+ 0.95
419
+ ],
420
+ "optimizer_eps": 1e-08,
421
+ "optimizer_weight_decay": 1e-10,
422
+ "optimizer_grad_clip_norm": 10.0,
423
+ "scheduler_warmup_steps": 0,
424
+ "scheduler_decay_steps": 5000,
425
+ "scheduler_decay_lr": 0.0003,
426
+ "vlm_model_name": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct",
427
+ "load_vlm_weights": true,
428
+ "add_image_special_tokens": false,
429
+ "attention_mode": "cross_attn",
430
+ "prefix_length": 0,
431
+ "pad_language_to": "max_length",
432
+ "num_expert_layers": 0,
433
+ "num_vlm_layers": 16,
434
+ "self_attn_every_n_layers": 2,
435
+ "expert_width_multiplier": 0.75,
436
+ "min_period": 0.004,
437
+ "max_period": 4.0,
438
+ "rtc_config": null,
439
+ "compile_model": false,
440
+ "compile_mode": "max-autotune"
441
+ },
442
+ "reward_model": null,
443
+ "output_dir": "outputs/train/2026-09-24/17-36-42_smolvla_gk_adp_real_3e-4",
444
+ "job_name": "smolvla_gk_adp_real_3e-4",
445
+ "resume": false,
446
+ "seed": 1000,
447
+ "cudnn_deterministic": false,
448
+ "num_workers": 8,
449
+ "batch_size": 128,
450
+ "prefetch_factor": 1,
451
+ "persistent_workers": true,
452
+ "dataloader_multiprocessing_context": "fork",
453
+ "steps": 50000,
454
+ "env_eval_freq": 20000,
455
+ "log_freq": 200,
456
+ "eval_steps": 0,
457
+ "max_eval_samples": 0,
458
+ "tolerance_s": 0.0001,
459
+ "save_checkpoint": true,
460
+ "save_freq": 1000,
461
+ "checkpoint_format": "safetensors",
462
+ "use_policy_training_preset": true,
463
+ "optimizer": {
464
+ "type": "adamw",
465
+ "lr": 0.0003,
466
+ "weight_decay": 1e-10,
467
+ "grad_clip_norm": 10.0,
468
+ "betas": [
469
+ 0.9,
470
+ 0.95
471
+ ],
472
+ "eps": 1e-08
473
+ },
474
+ "scheduler": {
475
+ "type": "cosine_decay_with_warmup",
476
+ "num_warmup_steps": 0,
477
+ "num_decay_steps": 5000,
478
+ "peak_lr": 0.0003,
479
+ "decay_lr": 0.0003
480
+ },
481
+ "parallelism": {
482
+ "dp_replicate": 1,
483
+ "dp_shard": 1,
484
+ "context_parallel": {
485
+ "ring_degree": 1,
486
+ "ulysses_degree": 1
487
+ },
488
+ "cfg_parallel": 1
489
+ },
490
+ "accelerator": {
491
+ "mixed_precision": "no",
492
+ "gradient_accumulation": {
493
+ "steps": 1
494
+ },
495
+ "fsdp": {
496
+ "reshard_after_forward": true,
497
+ "wrap_modules": null,
498
+ "min_num_params": null,
499
+ "cpu_offload": false,
500
+ "ignored_modules": null
501
+ },
502
+ "ddp": {
503
+ "find_unused_parameters": true,
504
+ "gradient_as_bucket_view": false,
505
+ "static_graph": false
506
+ },
507
+ "compile": {
508
+ "enabled": false,
509
+ "backend": "inductor",
510
+ "mode": null,
511
+ "regional": true
512
+ },
513
+ "activation_checkpointing": {
514
+ "mode": "none"
515
+ }
516
+ },
517
+ "eval": {
518
+ "n_episodes": 50,
519
+ "tail_task_key": null,
520
+ "batch_size": 50,
521
+ "use_async_envs": true,
522
+ "recording": false,
523
+ "recording_repo_id": null,
524
+ "recording_private": false
525
+ },
526
+ "ema": {
527
+ "enable": false,
528
+ "decay": null,
529
+ "update_after_step": 0,
530
+ "inv_gamma": 1.0,
531
+ "power": 0.75,
532
+ "min_decay": 0.0,
533
+ "max_decay": 0.9999,
534
+ "use_for_eval": true
535
+ },
536
+ "wandb": {
537
+ "enable": true,
538
+ "disable_artifact": false,
539
+ "project": "lerobot",
540
+ "entity": null,
541
+ "notes": null,
542
+ "run_id": "2nambrcl",
543
+ "mode": null,
544
+ "add_tags": true
545
+ },
546
+ "peft": {
547
+ "target_modules": null,
548
+ "full_training_modules": null,
549
+ "method_type": "LORA",
550
+ "init_type": null,
551
+ "r": 16,
552
+ "lora_alpha": 16
553
+ },
554
+ "job": {
555
+ "target": null,
556
+ "image": "huggingface/lerobot-gpu:latest",
557
+ "timeout": "2d",
558
+ "detach": false,
559
+ "tags": []
560
+ },
561
+ "save_checkpoint_to_hub": false,
562
+ "sample_weighting": null,
563
+ "rename_map": {
564
+ "observation.images.front": "observation.images.camera1"
565
+ },
566
+ "checkpoint_path": null,
567
+ "task_info_path": "task_information/real.jsonl",
568
+ "task_suite": "real",
569
+ "task_order": null,
570
+ "num_tasks": null,
571
+ "steps_per_task": 10000,
572
+ "drop_last": true,
573
+ "learning_algorithm": {
574
+ "type": "gk_adp",
575
+ "sigma_init": 1.0,
576
+ "epsilon": 1e-06,
577
+ "embedding_layer": -1,
578
+ "modalities": [
579
+ "vision",
580
+ "language"
581
+ ],
582
+ "inference_routing": "top1",
583
+ "inference_top_k": 0,
584
+ "inference_temperature": 1.0,
585
+ "reset_scheduler_on_expansion": true,
586
+ "log_expert_statistics": false
587
+ },
588
+ "reset_optimizer_per_task": false,
589
+ "reset_scheduler_per_task": false
590
+ }
17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_004000/training_state/checkpoint_complete.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "step": 4000
3
+ }
17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_004000/training_state/optimizer_param_groups.json ADDED
@@ -0,0 +1,593 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "lr": 0.0003,
4
+ "betas": [
5
+ 0.9,
6
+ 0.95
7
+ ],
8
+ "eps": 1e-08,
9
+ "weight_decay": 1e-10,
10
+ "amsgrad": false,
11
+ "maximize": false,
12
+ "foreach": null,
13
+ "capturable": false,
14
+ "differentiable": false,
15
+ "fused": null,
16
+ "decoupled_weight_decay": true,
17
+ "initial_lr": 0.0003,
18
+ "params": [
19
+ 0,
20
+ 1,
21
+ 2,
22
+ 3,
23
+ 4,
24
+ 5,
25
+ 6,
26
+ 7,
27
+ 8,
28
+ 9,
29
+ 10,
30
+ 11,
31
+ 12,
32
+ 13,
33
+ 14,
34
+ 15,
35
+ 16,
36
+ 17,
37
+ 18,
38
+ 19,
39
+ 20,
40
+ 21,
41
+ 22,
42
+ 23,
43
+ 24,
44
+ 25,
45
+ 26,
46
+ 27,
47
+ 28,
48
+ 29,
49
+ 30,
50
+ 31,
51
+ 32,
52
+ 33,
53
+ 34,
54
+ 35,
55
+ 36,
56
+ 37,
57
+ 38,
58
+ 39,
59
+ 40,
60
+ 41,
61
+ 42,
62
+ 43,
63
+ 44,
64
+ 45,
65
+ 46,
66
+ 47,
67
+ 48,
68
+ 49,
69
+ 50,
70
+ 51,
71
+ 52,
72
+ 53,
73
+ 54,
74
+ 55,
75
+ 56,
76
+ 57,
77
+ 58,
78
+ 59,
79
+ 60,
80
+ 61,
81
+ 62,
82
+ 63,
83
+ 64,
84
+ 65,
85
+ 66,
86
+ 67,
87
+ 68,
88
+ 69,
89
+ 70,
90
+ 71,
91
+ 72,
92
+ 73,
93
+ 74,
94
+ 75,
95
+ 76,
96
+ 77,
97
+ 78,
98
+ 79,
99
+ 80,
100
+ 81,
101
+ 82,
102
+ 83,
103
+ 84,
104
+ 85,
105
+ 86,
106
+ 87,
107
+ 88,
108
+ 89,
109
+ 90,
110
+ 91,
111
+ 92,
112
+ 93,
113
+ 94,
114
+ 95,
115
+ 96,
116
+ 97,
117
+ 98,
118
+ 99,
119
+ 100,
120
+ 101,
121
+ 102,
122
+ 103,
123
+ 104,
124
+ 105,
125
+ 106,
126
+ 107,
127
+ 108,
128
+ 109,
129
+ 110,
130
+ 111,
131
+ 112,
132
+ 113,
133
+ 114,
134
+ 115,
135
+ 116,
136
+ 117,
137
+ 118,
138
+ 119,
139
+ 120,
140
+ 121,
141
+ 122,
142
+ 123,
143
+ 124,
144
+ 125,
145
+ 126,
146
+ 127,
147
+ 128,
148
+ 129,
149
+ 130,
150
+ 131,
151
+ 132,
152
+ 133,
153
+ 134,
154
+ 135,
155
+ 136,
156
+ 137,
157
+ 138,
158
+ 139,
159
+ 140,
160
+ 141,
161
+ 142,
162
+ 143,
163
+ 144,
164
+ 145,
165
+ 146,
166
+ 147,
167
+ 148,
168
+ 149,
169
+ 150,
170
+ 151,
171
+ 152,
172
+ 153,
173
+ 154,
174
+ 155,
175
+ 156,
176
+ 157,
177
+ 158,
178
+ 159,
179
+ 160,
180
+ 161,
181
+ 162,
182
+ 163,
183
+ 164,
184
+ 165,
185
+ 166,
186
+ 167,
187
+ 168,
188
+ 169,
189
+ 170,
190
+ 171,
191
+ 172,
192
+ 173,
193
+ 174,
194
+ 175,
195
+ 176,
196
+ 177,
197
+ 178,
198
+ 179,
199
+ 180,
200
+ 181,
201
+ 182,
202
+ 183,
203
+ 184,
204
+ 185,
205
+ 186,
206
+ 187,
207
+ 188,
208
+ 189,
209
+ 190,
210
+ 191,
211
+ 192,
212
+ 193,
213
+ 194,
214
+ 195,
215
+ 196,
216
+ 197,
217
+ 198,
218
+ 199,
219
+ 200,
220
+ 201,
221
+ 202,
222
+ 203,
223
+ 204,
224
+ 205,
225
+ 206,
226
+ 207,
227
+ 208,
228
+ 209,
229
+ 210,
230
+ 211,
231
+ 212,
232
+ 213,
233
+ 214,
234
+ 215,
235
+ 216,
236
+ 217,
237
+ 218,
238
+ 219,
239
+ 220,
240
+ 221,
241
+ 222,
242
+ 223,
243
+ 224,
244
+ 225,
245
+ 226,
246
+ 227,
247
+ 228,
248
+ 229,
249
+ 230,
250
+ 231,
251
+ 232,
252
+ 233,
253
+ 234,
254
+ 235,
255
+ 236,
256
+ 237,
257
+ 238,
258
+ 239,
259
+ 240,
260
+ 241,
261
+ 242,
262
+ 243,
263
+ 244,
264
+ 245,
265
+ 246,
266
+ 247,
267
+ 248,
268
+ 249,
269
+ 250,
270
+ 251,
271
+ 252,
272
+ 253,
273
+ 254,
274
+ 255,
275
+ 256,
276
+ 257,
277
+ 258,
278
+ 259,
279
+ 260,
280
+ 261,
281
+ 262,
282
+ 263,
283
+ 264,
284
+ 265,
285
+ 266,
286
+ 267,
287
+ 268,
288
+ 269,
289
+ 270,
290
+ 271,
291
+ 272,
292
+ 273,
293
+ 274,
294
+ 275,
295
+ 276,
296
+ 277,
297
+ 278,
298
+ 279,
299
+ 280,
300
+ 281,
301
+ 282,
302
+ 283,
303
+ 284,
304
+ 285,
305
+ 286,
306
+ 287,
307
+ 288,
308
+ 289,
309
+ 290,
310
+ 291,
311
+ 292,
312
+ 293,
313
+ 294,
314
+ 295,
315
+ 296,
316
+ 297,
317
+ 298,
318
+ 299,
319
+ 300,
320
+ 301,
321
+ 302,
322
+ 303,
323
+ 304,
324
+ 305,
325
+ 306,
326
+ 307,
327
+ 308,
328
+ 309,
329
+ 310,
330
+ 311,
331
+ 312,
332
+ 313,
333
+ 314,
334
+ 315,
335
+ 316,
336
+ 317,
337
+ 318,
338
+ 319,
339
+ 320,
340
+ 321,
341
+ 322,
342
+ 323,
343
+ 324,
344
+ 325,
345
+ 326,
346
+ 327,
347
+ 328,
348
+ 329,
349
+ 330,
350
+ 331,
351
+ 332,
352
+ 333,
353
+ 334,
354
+ 335,
355
+ 336,
356
+ 337,
357
+ 338,
358
+ 339,
359
+ 340,
360
+ 341,
361
+ 342,
362
+ 343,
363
+ 344,
364
+ 345,
365
+ 346,
366
+ 347,
367
+ 348,
368
+ 349,
369
+ 350,
370
+ 351,
371
+ 352,
372
+ 353,
373
+ 354,
374
+ 355,
375
+ 356,
376
+ 357,
377
+ 358,
378
+ 359,
379
+ 360,
380
+ 361,
381
+ 362,
382
+ 363,
383
+ 364,
384
+ 365,
385
+ 366,
386
+ 367,
387
+ 368,
388
+ 369,
389
+ 370,
390
+ 371,
391
+ 372,
392
+ 373,
393
+ 374,
394
+ 375,
395
+ 376,
396
+ 377,
397
+ 378,
398
+ 379,
399
+ 380,
400
+ 381,
401
+ 382,
402
+ 383,
403
+ 384,
404
+ 385,
405
+ 386,
406
+ 387,
407
+ 388,
408
+ 389,
409
+ 390,
410
+ 391,
411
+ 392,
412
+ 393,
413
+ 394,
414
+ 395,
415
+ 396,
416
+ 397,
417
+ 398,
418
+ 399,
419
+ 400,
420
+ 401,
421
+ 402,
422
+ 403,
423
+ 404,
424
+ 405,
425
+ 406,
426
+ 407,
427
+ 408,
428
+ 409,
429
+ 410,
430
+ 411,
431
+ 412,
432
+ 413,
433
+ 414,
434
+ 415,
435
+ 416,
436
+ 417,
437
+ 418,
438
+ 419,
439
+ 420,
440
+ 421,
441
+ 422,
442
+ 423,
443
+ 424,
444
+ 425,
445
+ 426,
446
+ 427,
447
+ 428,
448
+ 429,
449
+ 430,
450
+ 431,
451
+ 432,
452
+ 433,
453
+ 434,
454
+ 435,
455
+ 436,
456
+ 437,
457
+ 438,
458
+ 439,
459
+ 440,
460
+ 441,
461
+ 442,
462
+ 443,
463
+ 444,
464
+ 445,
465
+ 446,
466
+ 447,
467
+ 448,
468
+ 449,
469
+ 450,
470
+ 451,
471
+ 452,
472
+ 453,
473
+ 454,
474
+ 455,
475
+ 456,
476
+ 457,
477
+ 458,
478
+ 459,
479
+ 460,
480
+ 461,
481
+ 462,
482
+ 463,
483
+ 464,
484
+ 465,
485
+ 466,
486
+ 467,
487
+ 468,
488
+ 469,
489
+ 470,
490
+ 471,
491
+ 472,
492
+ 473,
493
+ 474,
494
+ 475,
495
+ 476,
496
+ 477,
497
+ 478,
498
+ 479,
499
+ 480,
500
+ 481,
501
+ 482,
502
+ 483,
503
+ 484,
504
+ 485,
505
+ 486,
506
+ 487,
507
+ 488,
508
+ 489,
509
+ 490,
510
+ 491,
511
+ 492,
512
+ 493,
513
+ 494,
514
+ 495,
515
+ 496,
516
+ 497,
517
+ 498,
518
+ 499,
519
+ 500,
520
+ 501,
521
+ 502,
522
+ 503,
523
+ 504,
524
+ 505,
525
+ 506,
526
+ 507,
527
+ 508,
528
+ 509,
529
+ 510,
530
+ 511,
531
+ 512,
532
+ 513,
533
+ 514,
534
+ 515,
535
+ 516,
536
+ 517,
537
+ 518,
538
+ 519,
539
+ 520,
540
+ 521,
541
+ 522,
542
+ 523,
543
+ 524,
544
+ 525,
545
+ 526,
546
+ 527,
547
+ 528,
548
+ 529,
549
+ 530,
550
+ 531,
551
+ 532,
552
+ 533,
553
+ 534,
554
+ 535,
555
+ 536,
556
+ 537,
557
+ 538,
558
+ 539,
559
+ 540,
560
+ 541,
561
+ 542,
562
+ 543,
563
+ 544,
564
+ 545,
565
+ 546,
566
+ 547,
567
+ 548,
568
+ 549,
569
+ 550,
570
+ 551,
571
+ 552,
572
+ 553,
573
+ 554,
574
+ 555,
575
+ 556,
576
+ 557,
577
+ 558,
578
+ 559,
579
+ 560,
580
+ 561,
581
+ 562,
582
+ 563,
583
+ 564,
584
+ 565,
585
+ 566,
586
+ 567,
587
+ 568,
588
+ 569,
589
+ 570,
590
+ 571
591
+ ]
592
+ }
593
+ ]
17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_004000/training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50595b5755da6c410028a5434dbf87651915f256e6b5f6ea866ed066dc6ac8f7
3
+ size 5832632
17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_004000/training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab74f296f5b2af60a666899e0fbe76b6136e982ac6a7888078835e5d4cf6771b
3
+ size 15708
17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_004000/training_state/rng_state_rank_0.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab74f296f5b2af60a666899e0fbe76b6136e982ac6a7888078835e5d4cf6771b
3
+ size 15708
17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_004000/training_state/scheduler_state.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_lrs": [
3
+ 0.0003
4
+ ],
5
+ "last_epoch": 4000,
6
+ "_step_count": 4001,
7
+ "_is_initial": false,
8
+ "_get_lr_called_within_step": false,
9
+ "_last_lr": [
10
+ 0.0003
11
+ ],
12
+ "lr_lambdas": [
13
+ null
14
+ ]
15
+ }
17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_004000/training_state/sequential_state.json ADDED
@@ -0,0 +1,904 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": 1,
3
+ "step": 4000,
4
+ "task_position": 0,
5
+ "task_step": 4000,
6
+ "steps_per_task": 10000,
7
+ "drop_last": true,
8
+ "task_sequence": [
9
+ {
10
+ "task_suite": "real",
11
+ "task_index_within_suite": 0,
12
+ "task_index": 0,
13
+ "task": "Put the tape in the bowl",
14
+ "task_pattern": null,
15
+ "task_indices": [],
16
+ "instructions": [],
17
+ "episodes": [
18
+ 0,
19
+ 1,
20
+ 2,
21
+ 3,
22
+ 4,
23
+ 5,
24
+ 6,
25
+ 7,
26
+ 8,
27
+ 9,
28
+ 50,
29
+ 51,
30
+ 52,
31
+ 53,
32
+ 54,
33
+ 55,
34
+ 56,
35
+ 57,
36
+ 58,
37
+ 59,
38
+ 60,
39
+ 61,
40
+ 62,
41
+ 63,
42
+ 64,
43
+ 65,
44
+ 66,
45
+ 67,
46
+ 68,
47
+ 69,
48
+ 70,
49
+ 71,
50
+ 72,
51
+ 73,
52
+ 74,
53
+ 75,
54
+ 76,
55
+ 77,
56
+ 78,
57
+ 79,
58
+ 80,
59
+ 81,
60
+ 82,
61
+ 83,
62
+ 84,
63
+ 85,
64
+ 86,
65
+ 87,
66
+ 88,
67
+ 89
68
+ ]
69
+ },
70
+ {
71
+ "task_suite": "real",
72
+ "task_index_within_suite": 1,
73
+ "task_index": 1,
74
+ "task": "Put the pen in the cup",
75
+ "task_pattern": null,
76
+ "task_indices": [],
77
+ "instructions": [],
78
+ "episodes": [
79
+ 10,
80
+ 11,
81
+ 12,
82
+ 13,
83
+ 14,
84
+ 15,
85
+ 16,
86
+ 17,
87
+ 18,
88
+ 19,
89
+ 90,
90
+ 91,
91
+ 92,
92
+ 93,
93
+ 94,
94
+ 95,
95
+ 96,
96
+ 97,
97
+ 98,
98
+ 99,
99
+ 100,
100
+ 101,
101
+ 102,
102
+ 103,
103
+ 104,
104
+ 105,
105
+ 106,
106
+ 107,
107
+ 108,
108
+ 109,
109
+ 110,
110
+ 111,
111
+ 112,
112
+ 113,
113
+ 114,
114
+ 115,
115
+ 116,
116
+ 117,
117
+ 118,
118
+ 119,
119
+ 120,
120
+ 121,
121
+ 122,
122
+ 123,
123
+ 124,
124
+ 125,
125
+ 126,
126
+ 127,
127
+ 128,
128
+ 129
129
+ ]
130
+ },
131
+ {
132
+ "task_suite": "real",
133
+ "task_index_within_suite": 2,
134
+ "task_index": 2,
135
+ "task": "Turn the cup upright",
136
+ "task_pattern": null,
137
+ "task_indices": [],
138
+ "instructions": [],
139
+ "episodes": [
140
+ 20,
141
+ 21,
142
+ 22,
143
+ 23,
144
+ 24,
145
+ 25,
146
+ 26,
147
+ 27,
148
+ 28,
149
+ 29,
150
+ 130,
151
+ 131,
152
+ 132,
153
+ 133,
154
+ 134,
155
+ 135,
156
+ 136,
157
+ 137,
158
+ 138,
159
+ 139,
160
+ 140,
161
+ 141,
162
+ 142,
163
+ 143,
164
+ 144,
165
+ 145,
166
+ 146,
167
+ 147,
168
+ 148,
169
+ 149,
170
+ 150,
171
+ 151,
172
+ 152,
173
+ 153,
174
+ 154,
175
+ 155,
176
+ 156,
177
+ 157,
178
+ 158,
179
+ 159,
180
+ 160,
181
+ 161,
182
+ 242,
183
+ 243,
184
+ 244,
185
+ 245,
186
+ 246,
187
+ 247,
188
+ 248,
189
+ 249
190
+ ]
191
+ },
192
+ {
193
+ "task_suite": "real",
194
+ "task_index_within_suite": 3,
195
+ "task_index": 0,
196
+ "task": "Put the tape in the bowl",
197
+ "task_pattern": null,
198
+ "task_indices": [],
199
+ "instructions": [],
200
+ "episodes": [
201
+ 30,
202
+ 31,
203
+ 32,
204
+ 33,
205
+ 34,
206
+ 35,
207
+ 36,
208
+ 37,
209
+ 38,
210
+ 39,
211
+ 162,
212
+ 163,
213
+ 164,
214
+ 165,
215
+ 166,
216
+ 167,
217
+ 168,
218
+ 169,
219
+ 170,
220
+ 171,
221
+ 172,
222
+ 173,
223
+ 174,
224
+ 175,
225
+ 176,
226
+ 177,
227
+ 178,
228
+ 179,
229
+ 180,
230
+ 181,
231
+ 182,
232
+ 183,
233
+ 184,
234
+ 185,
235
+ 186,
236
+ 187,
237
+ 188,
238
+ 189,
239
+ 190,
240
+ 191,
241
+ 192,
242
+ 193,
243
+ 194,
244
+ 195,
245
+ 196,
246
+ 197,
247
+ 198,
248
+ 199,
249
+ 200,
250
+ 201
251
+ ]
252
+ },
253
+ {
254
+ "task_suite": "real",
255
+ "task_index_within_suite": 4,
256
+ "task_index": 3,
257
+ "task": "Put the pen into the cup",
258
+ "task_pattern": null,
259
+ "task_indices": [],
260
+ "instructions": [],
261
+ "episodes": [
262
+ 40,
263
+ 41,
264
+ 42,
265
+ 43,
266
+ 44,
267
+ 45,
268
+ 46,
269
+ 47,
270
+ 48,
271
+ 49,
272
+ 202,
273
+ 203,
274
+ 204,
275
+ 205,
276
+ 206,
277
+ 207,
278
+ 208,
279
+ 209,
280
+ 210,
281
+ 211,
282
+ 212,
283
+ 213,
284
+ 214,
285
+ 215,
286
+ 216,
287
+ 217,
288
+ 218,
289
+ 219,
290
+ 220,
291
+ 221,
292
+ 222,
293
+ 223,
294
+ 224,
295
+ 225,
296
+ 226,
297
+ 227,
298
+ 228,
299
+ 229,
300
+ 230,
301
+ 231,
302
+ 232,
303
+ 233,
304
+ 234,
305
+ 235,
306
+ 236,
307
+ 237,
308
+ 238,
309
+ 239,
310
+ 240,
311
+ 241
312
+ ]
313
+ }
314
+ ],
315
+ "config": {
316
+ "dataset": {
317
+ "repo_id": "tml-lab/real",
318
+ "repo_type": "dataset",
319
+ "root": null,
320
+ "episodes": [
321
+ 0,
322
+ 1,
323
+ 2,
324
+ 3,
325
+ 4,
326
+ 5,
327
+ 6,
328
+ 7,
329
+ 8,
330
+ 9,
331
+ 10,
332
+ 11,
333
+ 12,
334
+ 13,
335
+ 14,
336
+ 15,
337
+ 16,
338
+ 17,
339
+ 18,
340
+ 19,
341
+ 20,
342
+ 21,
343
+ 22,
344
+ 23,
345
+ 24,
346
+ 25,
347
+ 26,
348
+ 27,
349
+ 28,
350
+ 29,
351
+ 30,
352
+ 31,
353
+ 32,
354
+ 33,
355
+ 34,
356
+ 35,
357
+ 36,
358
+ 37,
359
+ 38,
360
+ 39,
361
+ 40,
362
+ 41,
363
+ 42,
364
+ 43,
365
+ 44,
366
+ 45,
367
+ 46,
368
+ 47,
369
+ 48,
370
+ 49,
371
+ 50,
372
+ 51,
373
+ 52,
374
+ 53,
375
+ 54,
376
+ 55,
377
+ 56,
378
+ 57,
379
+ 58,
380
+ 59,
381
+ 60,
382
+ 61,
383
+ 62,
384
+ 63,
385
+ 64,
386
+ 65,
387
+ 66,
388
+ 67,
389
+ 68,
390
+ 69,
391
+ 70,
392
+ 71,
393
+ 72,
394
+ 73,
395
+ 74,
396
+ 75,
397
+ 76,
398
+ 77,
399
+ 78,
400
+ 79,
401
+ 80,
402
+ 81,
403
+ 82,
404
+ 83,
405
+ 84,
406
+ 85,
407
+ 86,
408
+ 87,
409
+ 88,
410
+ 89,
411
+ 90,
412
+ 91,
413
+ 92,
414
+ 93,
415
+ 94,
416
+ 95,
417
+ 96,
418
+ 97,
419
+ 98,
420
+ 99,
421
+ 100,
422
+ 101,
423
+ 102,
424
+ 103,
425
+ 104,
426
+ 105,
427
+ 106,
428
+ 107,
429
+ 108,
430
+ 109,
431
+ 110,
432
+ 111,
433
+ 112,
434
+ 113,
435
+ 114,
436
+ 115,
437
+ 116,
438
+ 117,
439
+ 118,
440
+ 119,
441
+ 120,
442
+ 121,
443
+ 122,
444
+ 123,
445
+ 124,
446
+ 125,
447
+ 126,
448
+ 127,
449
+ 128,
450
+ 129,
451
+ 130,
452
+ 131,
453
+ 132,
454
+ 133,
455
+ 134,
456
+ 135,
457
+ 136,
458
+ 137,
459
+ 138,
460
+ 139,
461
+ 140,
462
+ 141,
463
+ 142,
464
+ 143,
465
+ 144,
466
+ 145,
467
+ 146,
468
+ 147,
469
+ 148,
470
+ 149,
471
+ 150,
472
+ 151,
473
+ 152,
474
+ 153,
475
+ 154,
476
+ 155,
477
+ 156,
478
+ 157,
479
+ 158,
480
+ 159,
481
+ 160,
482
+ 161,
483
+ 162,
484
+ 163,
485
+ 164,
486
+ 165,
487
+ 166,
488
+ 167,
489
+ 168,
490
+ 169,
491
+ 170,
492
+ 171,
493
+ 172,
494
+ 173,
495
+ 174,
496
+ 175,
497
+ 176,
498
+ 177,
499
+ 178,
500
+ 179,
501
+ 180,
502
+ 181,
503
+ 182,
504
+ 183,
505
+ 184,
506
+ 185,
507
+ 186,
508
+ 187,
509
+ 188,
510
+ 189,
511
+ 190,
512
+ 191,
513
+ 192,
514
+ 193,
515
+ 194,
516
+ 195,
517
+ 196,
518
+ 197,
519
+ 198,
520
+ 199,
521
+ 200,
522
+ 201,
523
+ 202,
524
+ 203,
525
+ 204,
526
+ 205,
527
+ 206,
528
+ 207,
529
+ 208,
530
+ 209,
531
+ 210,
532
+ 211,
533
+ 212,
534
+ 213,
535
+ 214,
536
+ 215,
537
+ 216,
538
+ 217,
539
+ 218,
540
+ 219,
541
+ 220,
542
+ 221,
543
+ 222,
544
+ 223,
545
+ 224,
546
+ 225,
547
+ 226,
548
+ 227,
549
+ 228,
550
+ 229,
551
+ 230,
552
+ 231,
553
+ 232,
554
+ 233,
555
+ 234,
556
+ 235,
557
+ 236,
558
+ 237,
559
+ 238,
560
+ 239,
561
+ 240,
562
+ 241,
563
+ 242,
564
+ 243,
565
+ 244,
566
+ 245,
567
+ 246,
568
+ 247,
569
+ 248,
570
+ 249
571
+ ],
572
+ "exclude_episodes": null,
573
+ "filter_failed_trajectories": false,
574
+ "image_transforms": {
575
+ "enable": false,
576
+ "max_num_transforms": 3,
577
+ "random_order": false,
578
+ "tfs": {
579
+ "brightness": {
580
+ "weight": 1.0,
581
+ "type": "ColorJitter",
582
+ "kwargs": {
583
+ "brightness": [
584
+ 0.8,
585
+ 1.2
586
+ ]
587
+ }
588
+ },
589
+ "contrast": {
590
+ "weight": 1.0,
591
+ "type": "ColorJitter",
592
+ "kwargs": {
593
+ "contrast": [
594
+ 0.8,
595
+ 1.2
596
+ ]
597
+ }
598
+ },
599
+ "saturation": {
600
+ "weight": 1.0,
601
+ "type": "ColorJitter",
602
+ "kwargs": {
603
+ "saturation": [
604
+ 0.5,
605
+ 1.5
606
+ ]
607
+ }
608
+ },
609
+ "hue": {
610
+ "weight": 1.0,
611
+ "type": "ColorJitter",
612
+ "kwargs": {
613
+ "hue": [
614
+ -0.05,
615
+ 0.05
616
+ ]
617
+ }
618
+ },
619
+ "sharpness": {
620
+ "weight": 1.0,
621
+ "type": "SharpnessJitter",
622
+ "kwargs": {
623
+ "sharpness": [
624
+ 0.5,
625
+ 1.5
626
+ ]
627
+ }
628
+ },
629
+ "affine": {
630
+ "weight": 1.0,
631
+ "type": "RandomAffine",
632
+ "kwargs": {
633
+ "degrees": [
634
+ -5.0,
635
+ 5.0
636
+ ],
637
+ "translate": [
638
+ 0.05,
639
+ 0.05
640
+ ]
641
+ }
642
+ }
643
+ }
644
+ },
645
+ "revision": null,
646
+ "use_imagenet_stats": true,
647
+ "video_backend": "torchcodec",
648
+ "return_uint8": false,
649
+ "depth_output_unit": "mm",
650
+ "streaming": false,
651
+ "eval_split": 0.0
652
+ },
653
+ "env": null,
654
+ "policy": {
655
+ "type": "smolvla",
656
+ "n_obs_steps": 1,
657
+ "input_features": {
658
+ "observation.state": {
659
+ "type": "STATE",
660
+ "shape": [
661
+ 6
662
+ ]
663
+ },
664
+ "observation.images.camera1": {
665
+ "type": "VISUAL",
666
+ "shape": [
667
+ 3,
668
+ 256,
669
+ 256
670
+ ]
671
+ },
672
+ "observation.images.camera2": {
673
+ "type": "VISUAL",
674
+ "shape": [
675
+ 3,
676
+ 256,
677
+ 256
678
+ ]
679
+ },
680
+ "observation.images.camera3": {
681
+ "type": "VISUAL",
682
+ "shape": [
683
+ 3,
684
+ 256,
685
+ 256
686
+ ]
687
+ }
688
+ },
689
+ "output_features": {
690
+ "action": {
691
+ "type": "ACTION",
692
+ "shape": [
693
+ 6
694
+ ]
695
+ }
696
+ },
697
+ "device": "cuda",
698
+ "use_amp": false,
699
+ "use_peft": true,
700
+ "push_to_hub": false,
701
+ "repo_id": null,
702
+ "private": null,
703
+ "tags": null,
704
+ "license": null,
705
+ "pretrained_path": "<resume-source>",
706
+ "pretrained_revision": null,
707
+ "chunk_size": 50,
708
+ "n_action_steps": 50,
709
+ "normalization_mapping": {
710
+ "VISUAL": "IDENTITY",
711
+ "STATE": "MEAN_STD",
712
+ "ACTION": "MEAN_STD"
713
+ },
714
+ "max_state_dim": 32,
715
+ "max_action_dim": 32,
716
+ "resize_imgs_with_padding": [
717
+ 512,
718
+ 512
719
+ ],
720
+ "empty_cameras": 0,
721
+ "adapt_to_pi_aloha": false,
722
+ "use_delta_joint_actions_aloha": false,
723
+ "tokenizer_max_length": 48,
724
+ "num_steps": 10,
725
+ "use_cache": true,
726
+ "freeze_vision_encoder": true,
727
+ "train_expert_only": true,
728
+ "train_state_proj": true,
729
+ "optimizer_lr": 0.0003,
730
+ "optimizer_betas": [
731
+ 0.9,
732
+ 0.95
733
+ ],
734
+ "optimizer_eps": 1e-08,
735
+ "optimizer_weight_decay": 1e-10,
736
+ "optimizer_grad_clip_norm": 10.0,
737
+ "scheduler_warmup_steps": 0,
738
+ "scheduler_decay_steps": 5000,
739
+ "scheduler_decay_lr": 0.0003,
740
+ "vlm_model_name": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct",
741
+ "load_vlm_weights": true,
742
+ "add_image_special_tokens": false,
743
+ "attention_mode": "cross_attn",
744
+ "prefix_length": 0,
745
+ "pad_language_to": "max_length",
746
+ "num_expert_layers": 0,
747
+ "num_vlm_layers": 16,
748
+ "self_attn_every_n_layers": 2,
749
+ "expert_width_multiplier": 0.75,
750
+ "min_period": 0.004,
751
+ "max_period": 4.0,
752
+ "rtc_config": null,
753
+ "compile_model": false,
754
+ "compile_mode": "max-autotune"
755
+ },
756
+ "reward_model": null,
757
+ "output_dir": "/home/tml_lab/lerobot-061-cl/outputs/train/2026-09-24/17-36-42_smolvla_gk_adp_real_3e-4",
758
+ "job_name": "smolvla_gk_adp_real_3e-4",
759
+ "resume": false,
760
+ "seed": 1000,
761
+ "cudnn_deterministic": false,
762
+ "num_workers": 8,
763
+ "batch_size": 128,
764
+ "prefetch_factor": 1,
765
+ "persistent_workers": true,
766
+ "dataloader_multiprocessing_context": "fork",
767
+ "steps": 50000,
768
+ "env_eval_freq": 20000,
769
+ "log_freq": 200,
770
+ "eval_steps": 0,
771
+ "max_eval_samples": 0,
772
+ "tolerance_s": 0.0001,
773
+ "save_checkpoint": true,
774
+ "save_freq": 1000,
775
+ "checkpoint_format": "safetensors",
776
+ "use_policy_training_preset": true,
777
+ "optimizer": {
778
+ "type": "adamw",
779
+ "lr": 0.0003,
780
+ "weight_decay": 1e-10,
781
+ "grad_clip_norm": 10.0,
782
+ "betas": [
783
+ 0.9,
784
+ 0.95
785
+ ],
786
+ "eps": 1e-08
787
+ },
788
+ "scheduler": {
789
+ "type": "cosine_decay_with_warmup",
790
+ "num_warmup_steps": 0,
791
+ "num_decay_steps": 5000,
792
+ "peak_lr": 0.0003,
793
+ "decay_lr": 0.0003
794
+ },
795
+ "parallelism": {
796
+ "dp_replicate": 1,
797
+ "dp_shard": 1,
798
+ "context_parallel": {
799
+ "ring_degree": 1,
800
+ "ulysses_degree": 1
801
+ },
802
+ "cfg_parallel": 1
803
+ },
804
+ "accelerator": {
805
+ "mixed_precision": "no",
806
+ "gradient_accumulation": {
807
+ "steps": 1
808
+ },
809
+ "fsdp": {
810
+ "reshard_after_forward": true,
811
+ "wrap_modules": null,
812
+ "min_num_params": null,
813
+ "cpu_offload": false,
814
+ "ignored_modules": null
815
+ },
816
+ "ddp": {
817
+ "find_unused_parameters": true,
818
+ "gradient_as_bucket_view": false,
819
+ "static_graph": false
820
+ },
821
+ "compile": {
822
+ "enabled": false,
823
+ "backend": "inductor",
824
+ "mode": null,
825
+ "regional": true
826
+ },
827
+ "activation_checkpointing": {
828
+ "mode": "none"
829
+ }
830
+ },
831
+ "eval": {
832
+ "n_episodes": 50,
833
+ "batch_size": 50,
834
+ "use_async_envs": true,
835
+ "recording": false,
836
+ "recording_repo_id": null,
837
+ "recording_private": false
838
+ },
839
+ "ema": {
840
+ "enable": false,
841
+ "decay": null,
842
+ "update_after_step": 0,
843
+ "inv_gamma": 1.0,
844
+ "power": 0.75,
845
+ "min_decay": 0.0,
846
+ "max_decay": 0.9999,
847
+ "use_for_eval": true
848
+ },
849
+ "wandb": {
850
+ "enable": true,
851
+ "disable_artifact": false,
852
+ "project": "lerobot",
853
+ "entity": null,
854
+ "notes": null,
855
+ "run_id": "2nambrcl",
856
+ "mode": null,
857
+ "add_tags": true
858
+ },
859
+ "peft": {
860
+ "target_modules": null,
861
+ "full_training_modules": null,
862
+ "method_type": "LORA",
863
+ "init_type": null,
864
+ "r": 16,
865
+ "lora_alpha": 16
866
+ },
867
+ "job": {
868
+ "target": null,
869
+ "image": "huggingface/lerobot-gpu:latest",
870
+ "timeout": "2d",
871
+ "detach": false,
872
+ "tags": []
873
+ },
874
+ "save_checkpoint_to_hub": false,
875
+ "sample_weighting": null,
876
+ "rename_map": {
877
+ "observation.images.front": "observation.images.camera1"
878
+ },
879
+ "checkpoint_path": null,
880
+ "task_info_path": "task_information/real.jsonl",
881
+ "task_suite": "real",
882
+ "task_order": null,
883
+ "num_tasks": null,
884
+ "steps_per_task": 10000,
885
+ "drop_last": true,
886
+ "learning_algorithm": {
887
+ "type": "gk_adp",
888
+ "sigma_init": 1.0,
889
+ "epsilon": 1e-06,
890
+ "embedding_layer": -1,
891
+ "modalities": [
892
+ "vision",
893
+ "language"
894
+ ],
895
+ "inference_routing": "top1",
896
+ "inference_top_k": 0,
897
+ "inference_temperature": 1.0,
898
+ "reset_scheduler_on_expansion": true,
899
+ "log_expert_statistics": false
900
+ },
901
+ "reset_optimizer_per_task": false,
902
+ "reset_scheduler_per_task": false
903
+ }
904
+ }
17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_004000/training_state/training_step.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "step": 4000,
3
+ "dp_world_size": 1,
4
+ "batch_size": 128,
5
+ "grad_accum_steps": 1,
6
+ "parallelism": {
7
+ "dp_replicate": 1,
8
+ "dp_shard": 1,
9
+ "ring_degree": 1,
10
+ "ulysses_degree": 1
11
+ }
12
+ }
17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_005000/pretrained_model/README.md ADDED
@@ -0,0 +1,204 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ tags:
4
+ - base_model:adapter:lerobot/smolvla_base
5
+ - lora
6
+ ---
7
+
8
+ # Model Card for Model ID
9
+
10
+ <!-- Provide a quick summary of what the model is/does. -->
11
+
12
+
13
+
14
+ ## Model Details
15
+
16
+ ### Model Description
17
+
18
+ <!-- Provide a longer summary of what this model is. -->
19
+
20
+
21
+
22
+ - **Developed by:** [More Information Needed]
23
+ - **Funded by [optional]:** [More Information Needed]
24
+ - **Shared by [optional]:** [More Information Needed]
25
+ - **Model type:** [More Information Needed]
26
+ - **Language(s) (NLP):** [More Information Needed]
27
+ - **License:** [More Information Needed]
28
+ - **Finetuned from model [optional]:** [More Information Needed]
29
+
30
+ ### Model Sources [optional]
31
+
32
+ <!-- Provide the basic links for the model. -->
33
+
34
+ - **Repository:** [More Information Needed]
35
+ - **Paper [optional]:** [More Information Needed]
36
+ - **Demo [optional]:** [More Information Needed]
37
+
38
+ ## Uses
39
+
40
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
41
+
42
+ ### Direct Use
43
+
44
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
45
+
46
+ [More Information Needed]
47
+
48
+ ### Downstream Use [optional]
49
+
50
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
51
+
52
+ [More Information Needed]
53
+
54
+ ### Out-of-Scope Use
55
+
56
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
57
+
58
+ [More Information Needed]
59
+
60
+ ## Bias, Risks, and Limitations
61
+
62
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
63
+
64
+ [More Information Needed]
65
+
66
+ ### Recommendations
67
+
68
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
69
+
70
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
71
+
72
+ ## How to Get Started with the Model
73
+
74
+ Use the code below to get started with the model.
75
+
76
+ [More Information Needed]
77
+
78
+ ## Training Details
79
+
80
+ ### Training Data
81
+
82
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
83
+
84
+ [More Information Needed]
85
+
86
+ ### Training Procedure
87
+
88
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
89
+
90
+ #### Preprocessing [optional]
91
+
92
+ [More Information Needed]
93
+
94
+
95
+ #### Training Hyperparameters
96
+
97
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
98
+
99
+ #### Speeds, Sizes, Times [optional]
100
+
101
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
102
+
103
+ [More Information Needed]
104
+
105
+ ## Evaluation
106
+
107
+ <!-- This section describes the evaluation protocols and provides the results. -->
108
+
109
+ ### Testing Data, Factors & Metrics
110
+
111
+ #### Testing Data
112
+
113
+ <!-- This should link to a Dataset Card if possible. -->
114
+
115
+ [More Information Needed]
116
+
117
+ #### Factors
118
+
119
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
120
+
121
+ [More Information Needed]
122
+
123
+ #### Metrics
124
+
125
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
126
+
127
+ [More Information Needed]
128
+
129
+ ### Results
130
+
131
+ [More Information Needed]
132
+
133
+ #### Summary
134
+
135
+
136
+
137
+ ## Model Examination [optional]
138
+
139
+ <!-- Relevant interpretability work for the model goes here -->
140
+
141
+ [More Information Needed]
142
+
143
+ ## Environmental Impact
144
+
145
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
146
+
147
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
148
+
149
+ - **Hardware Type:** [More Information Needed]
150
+ - **Hours used:** [More Information Needed]
151
+ - **Cloud Provider:** [More Information Needed]
152
+ - **Compute Region:** [More Information Needed]
153
+ - **Carbon Emitted:** [More Information Needed]
154
+
155
+ ## Technical Specifications [optional]
156
+
157
+ ### Model Architecture and Objective
158
+
159
+ [More Information Needed]
160
+
161
+ ### Compute Infrastructure
162
+
163
+ [More Information Needed]
164
+
165
+ #### Hardware
166
+
167
+ [More Information Needed]
168
+
169
+ #### Software
170
+
171
+ [More Information Needed]
172
+
173
+ ## Citation [optional]
174
+
175
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
176
+
177
+ **BibTeX:**
178
+
179
+ [More Information Needed]
180
+
181
+ **APA:**
182
+
183
+ [More Information Needed]
184
+
185
+ ## Glossary [optional]
186
+
187
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
188
+
189
+ [More Information Needed]
190
+
191
+ ## More Information [optional]
192
+
193
+ [More Information Needed]
194
+
195
+ ## Model Card Authors [optional]
196
+
197
+ [More Information Needed]
198
+
199
+ ## Model Card Contact
200
+
201
+ [More Information Needed]
202
+ ### Framework versions
203
+
204
+ - PEFT 0.21.0
17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_005000/pretrained_model/adapter_config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": {
6
+ "base_model_class": "SmolVLAPolicy",
7
+ "parent_library": "lerobot.policies.smolvla.modeling_smolvla"
8
+ },
9
+ "base_model_name_or_path": "lerobot/smolvla_base",
10
+ "bias": "none",
11
+ "corda_config": null,
12
+ "ensure_weight_tying": false,
13
+ "eva_config": null,
14
+ "exclude_modules": null,
15
+ "fan_in_fan_out": false,
16
+ "inference_mode": true,
17
+ "init_lora_weights": true,
18
+ "kasa_config": null,
19
+ "layer_replication": null,
20
+ "layers_pattern": null,
21
+ "layers_to_transform": null,
22
+ "loftq_config": {},
23
+ "lora_alpha": 16,
24
+ "lora_bias": false,
25
+ "lora_dropout": 0.0,
26
+ "lora_ga_config": null,
27
+ "megatron_config": null,
28
+ "megatron_core": "megatron.core",
29
+ "modules_to_save": [],
30
+ "monteclora_config": null,
31
+ "peft_type": "LORA",
32
+ "peft_version": "0.21.0",
33
+ "qalora_group_size": 16,
34
+ "r": 16,
35
+ "rank_pattern": {},
36
+ "revision": null,
37
+ "target_modules": "(model\\.vlm_with_expert\\.lm_expert\\..*\\.(q|v)_proj|model\\.(action_in_proj|action_out_proj|action_time_mlp_in|action_time_mlp_out))",
38
+ "target_parameters": null,
39
+ "task_type": null,
40
+ "trainable_token_indices": null,
41
+ "use_bdlora": null,
42
+ "use_dora": false,
43
+ "use_qalora": false,
44
+ "use_rslora": false,
45
+ "velora_config": null
46
+ }
17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_005000/pretrained_model/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1534a78741b4fb2cb8609440bd5a087fa194a2e4aab97460de584a9efcee07c
3
+ size 2918168
17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_005000/pretrained_model/config.json ADDED
@@ -0,0 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "smolvla",
3
+ "n_obs_steps": 1,
4
+ "input_features": {
5
+ "observation.state": {
6
+ "type": "STATE",
7
+ "shape": [
8
+ 6
9
+ ]
10
+ },
11
+ "observation.images.camera1": {
12
+ "type": "VISUAL",
13
+ "shape": [
14
+ 3,
15
+ 256,
16
+ 256
17
+ ]
18
+ },
19
+ "observation.images.camera2": {
20
+ "type": "VISUAL",
21
+ "shape": [
22
+ 3,
23
+ 256,
24
+ 256
25
+ ]
26
+ },
27
+ "observation.images.camera3": {
28
+ "type": "VISUAL",
29
+ "shape": [
30
+ 3,
31
+ 256,
32
+ 256
33
+ ]
34
+ }
35
+ },
36
+ "output_features": {
37
+ "action": {
38
+ "type": "ACTION",
39
+ "shape": [
40
+ 6
41
+ ]
42
+ }
43
+ },
44
+ "device": "cuda",
45
+ "use_amp": false,
46
+ "use_peft": true,
47
+ "push_to_hub": false,
48
+ "repo_id": null,
49
+ "private": null,
50
+ "tags": null,
51
+ "license": null,
52
+ "pretrained_path": "lerobot/smolvla_base",
53
+ "pretrained_revision": null,
54
+ "chunk_size": 50,
55
+ "n_action_steps": 50,
56
+ "normalization_mapping": {
57
+ "VISUAL": "IDENTITY",
58
+ "STATE": "MEAN_STD",
59
+ "ACTION": "MEAN_STD"
60
+ },
61
+ "max_state_dim": 32,
62
+ "max_action_dim": 32,
63
+ "resize_imgs_with_padding": [
64
+ 512,
65
+ 512
66
+ ],
67
+ "empty_cameras": 0,
68
+ "adapt_to_pi_aloha": false,
69
+ "use_delta_joint_actions_aloha": false,
70
+ "tokenizer_max_length": 48,
71
+ "num_steps": 10,
72
+ "use_cache": true,
73
+ "freeze_vision_encoder": true,
74
+ "train_expert_only": true,
75
+ "train_state_proj": true,
76
+ "optimizer_lr": 0.0003,
77
+ "optimizer_betas": [
78
+ 0.9,
79
+ 0.95
80
+ ],
81
+ "optimizer_eps": 1e-08,
82
+ "optimizer_weight_decay": 1e-10,
83
+ "optimizer_grad_clip_norm": 10.0,
84
+ "scheduler_warmup_steps": 0,
85
+ "scheduler_decay_steps": 5000,
86
+ "scheduler_decay_lr": 0.0003,
87
+ "vlm_model_name": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct",
88
+ "load_vlm_weights": true,
89
+ "add_image_special_tokens": false,
90
+ "attention_mode": "cross_attn",
91
+ "prefix_length": 0,
92
+ "pad_language_to": "max_length",
93
+ "num_expert_layers": 0,
94
+ "num_vlm_layers": 16,
95
+ "self_attn_every_n_layers": 2,
96
+ "expert_width_multiplier": 0.75,
97
+ "min_period": 0.004,
98
+ "max_period": 4.0,
99
+ "rtc_config": null,
100
+ "compile_model": false,
101
+ "compile_mode": "max-autotune"
102
+ }
17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_005000/pretrained_model/gk_config.json ADDED
@@ -0,0 +1,132 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "adapter_names": [
3
+ "default"
4
+ ],
5
+ "algorithm_type": "gk_adp",
6
+ "embedding_layer": -1,
7
+ "epsilon": 1e-06,
8
+ "inference_routing": "top1",
9
+ "inference_temperature": 1.0,
10
+ "inference_top_k": 0,
11
+ "interval_routed_batches": [
12
+ 0
13
+ ],
14
+ "log_expert_statistics": false,
15
+ "modalities": [
16
+ "vision",
17
+ "language"
18
+ ],
19
+ "reset_scheduler_on_expansion": true,
20
+ "routed_batches": [
21
+ 5000
22
+ ],
23
+ "router_statistics_unit": "inputs",
24
+ "router_statistics_version": 2,
25
+ "router_variance_semantics": "seeded_m2_population",
26
+ "sigma_init": 1.0,
27
+ "total_expansions": 1,
28
+ "wandb_history_counts": [
29
+ [
30
+ 200
31
+ ],
32
+ [
33
+ 400
34
+ ],
35
+ [
36
+ 600
37
+ ],
38
+ [
39
+ 800
40
+ ],
41
+ [
42
+ 1000
43
+ ],
44
+ [
45
+ 1200
46
+ ],
47
+ [
48
+ 1400
49
+ ],
50
+ [
51
+ 1600
52
+ ],
53
+ [
54
+ 1800
55
+ ],
56
+ [
57
+ 2000
58
+ ],
59
+ [
60
+ 2200
61
+ ],
62
+ [
63
+ 2400
64
+ ],
65
+ [
66
+ 2600
67
+ ],
68
+ [
69
+ 2800
70
+ ],
71
+ [
72
+ 3000
73
+ ],
74
+ [
75
+ 3200
76
+ ],
77
+ [
78
+ 3400
79
+ ],
80
+ [
81
+ 3600
82
+ ],
83
+ [
84
+ 3800
85
+ ],
86
+ [
87
+ 4000
88
+ ],
89
+ [
90
+ 4200
91
+ ],
92
+ [
93
+ 4400
94
+ ],
95
+ [
96
+ 4600
97
+ ],
98
+ [
99
+ 4800
100
+ ],
101
+ [
102
+ 5000
103
+ ]
104
+ ],
105
+ "wandb_history_steps": [
106
+ 200,
107
+ 400,
108
+ 600,
109
+ 800,
110
+ 1000,
111
+ 1200,
112
+ 1400,
113
+ 1600,
114
+ 1800,
115
+ 2000,
116
+ 2200,
117
+ 2400,
118
+ 2600,
119
+ 2800,
120
+ 3000,
121
+ 3200,
122
+ 3400,
123
+ 3600,
124
+ 3800,
125
+ 4000,
126
+ 4200,
127
+ 4400,
128
+ 4600,
129
+ 4800,
130
+ 5000
131
+ ]
132
+ }
17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_005000/pretrained_model/gk_router.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:074a33fe54e40512bc05d5b610bf4448acf13e6d5dc94c984e2a822a22e5faf4
3
+ size 15564
17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_005000/pretrained_model/policy_postprocessor.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "policy_postprocessor",
3
+ "steps": [
4
+ {
5
+ "registry_name": "unnormalizer_processor",
6
+ "config": {
7
+ "eps": 1e-08,
8
+ "features": {
9
+ "action": {
10
+ "type": "ACTION",
11
+ "shape": [
12
+ 6
13
+ ]
14
+ }
15
+ },
16
+ "norm_map": {
17
+ "VISUAL": "IDENTITY",
18
+ "STATE": "MEAN_STD",
19
+ "ACTION": "MEAN_STD"
20
+ }
21
+ },
22
+ "state_file": "policy_postprocessor_step_0_unnormalizer_processor.safetensors"
23
+ },
24
+ {
25
+ "registry_name": "device_processor",
26
+ "config": {
27
+ "device": "cpu",
28
+ "float_dtype": null
29
+ }
30
+ }
31
+ ]
32
+ }
17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_005000/pretrained_model/policy_postprocessor_step_0_unnormalizer_processor.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d9ca31ecf0fe1c9ad4552e701c429441bd8d7e0136ab810f541e3e41fc0d964
3
+ size 6584
17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_005000/pretrained_model/policy_preprocessor.json ADDED
@@ -0,0 +1,92 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "policy_preprocessor",
3
+ "steps": [
4
+ {
5
+ "registry_name": "rename_observations_processor",
6
+ "config": {
7
+ "rename_map": {
8
+ "observation.images.front": "observation.images.camera1"
9
+ }
10
+ }
11
+ },
12
+ {
13
+ "registry_name": "to_batch_processor",
14
+ "config": {}
15
+ },
16
+ {
17
+ "registry_name": "smolvla_new_line_processor",
18
+ "config": {}
19
+ },
20
+ {
21
+ "registry_name": "tokenizer_processor",
22
+ "config": {
23
+ "max_length": 48,
24
+ "task_key": "task",
25
+ "padding_side": "right",
26
+ "padding": "max_length",
27
+ "truncation": true,
28
+ "tokenizer_name": "tokenizer"
29
+ },
30
+ "artifacts": {
31
+ "tokenizer_name": "tokenizer"
32
+ }
33
+ },
34
+ {
35
+ "registry_name": "device_processor",
36
+ "config": {
37
+ "device": "cuda",
38
+ "float_dtype": null
39
+ }
40
+ },
41
+ {
42
+ "registry_name": "normalizer_processor",
43
+ "config": {
44
+ "eps": 1e-08,
45
+ "features": {
46
+ "observation.state": {
47
+ "type": "STATE",
48
+ "shape": [
49
+ 6
50
+ ]
51
+ },
52
+ "observation.images.camera1": {
53
+ "type": "VISUAL",
54
+ "shape": [
55
+ 3,
56
+ 256,
57
+ 256
58
+ ]
59
+ },
60
+ "observation.images.camera2": {
61
+ "type": "VISUAL",
62
+ "shape": [
63
+ 3,
64
+ 256,
65
+ 256
66
+ ]
67
+ },
68
+ "observation.images.camera3": {
69
+ "type": "VISUAL",
70
+ "shape": [
71
+ 3,
72
+ 256,
73
+ 256
74
+ ]
75
+ },
76
+ "action": {
77
+ "type": "ACTION",
78
+ "shape": [
79
+ 6
80
+ ]
81
+ }
82
+ },
83
+ "norm_map": {
84
+ "VISUAL": "IDENTITY",
85
+ "STATE": "MEAN_STD",
86
+ "ACTION": "MEAN_STD"
87
+ }
88
+ },
89
+ "state_file": "policy_preprocessor_step_5_normalizer_processor.safetensors"
90
+ }
91
+ ]
92
+ }
17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_005000/pretrained_model/policy_preprocessor_step_5_normalizer_processor.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3eb9132f106bcea24a90aa2ce834285c158f8c88b60aef65695dc416321743fa
3
+ size 6584
17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_005000/pretrained_model/tokenizer/chat_template.jinja ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ <|im_start|>{% for message in messages %}{{message['role'] | capitalize}}{% if message['content'][0]['type'] == 'image' %}{{':'}}{% else %}{{': '}}{% endif %}{% for line in message['content'] %}{% if line['type'] == 'text' %}{{line['text']}}{% elif line['type'] == 'image' %}{{ '<image>' }}{% endif %}{% endfor %}<end_of_utterance>
2
+ {% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}
17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_005000/pretrained_model/tokenizer/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_005000/pretrained_model/tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<|im_start|>",
5
+ "clean_up_tokenization_spaces": false,
6
+ "end_of_utterance_token": "<end_of_utterance>",
7
+ "eos_token": "<end_of_utterance>",
8
+ "errors": "replace",
9
+ "fake_image_token": "<fake_token_around_image>",
10
+ "global_image_token": "<global-img>",
11
+ "image_token": "<image>",
12
+ "is_local": false,
13
+ "legacy": false,
14
+ "model_max_length": 8192,
15
+ "model_specific_special_tokens": {
16
+ "end_of_utterance_token": "<end_of_utterance>",
17
+ "fake_image_token": "<fake_token_around_image>",
18
+ "global_image_token": "<global-img>",
19
+ "image_token": "<image>"
20
+ },
21
+ "pad_token": "<|im_end|>",
22
+ "processor_class": "SmolVLMProcessor",
23
+ "tokenizer_class": "GPT2Tokenizer",
24
+ "truncation_side": "left",
25
+ "unk_token": "<|endoftext|>",
26
+ "vocab_size": 49152
27
+ }
17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_005000/pretrained_model/train_config.json ADDED
@@ -0,0 +1,590 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "tml-lab/real",
4
+ "repo_type": "dataset",
5
+ "root": null,
6
+ "episodes": [
7
+ 0,
8
+ 1,
9
+ 2,
10
+ 3,
11
+ 4,
12
+ 5,
13
+ 6,
14
+ 7,
15
+ 8,
16
+ 9,
17
+ 10,
18
+ 11,
19
+ 12,
20
+ 13,
21
+ 14,
22
+ 15,
23
+ 16,
24
+ 17,
25
+ 18,
26
+ 19,
27
+ 20,
28
+ 21,
29
+ 22,
30
+ 23,
31
+ 24,
32
+ 25,
33
+ 26,
34
+ 27,
35
+ 28,
36
+ 29,
37
+ 30,
38
+ 31,
39
+ 32,
40
+ 33,
41
+ 34,
42
+ 35,
43
+ 36,
44
+ 37,
45
+ 38,
46
+ 39,
47
+ 40,
48
+ 41,
49
+ 42,
50
+ 43,
51
+ 44,
52
+ 45,
53
+ 46,
54
+ 47,
55
+ 48,
56
+ 49,
57
+ 50,
58
+ 51,
59
+ 52,
60
+ 53,
61
+ 54,
62
+ 55,
63
+ 56,
64
+ 57,
65
+ 58,
66
+ 59,
67
+ 60,
68
+ 61,
69
+ 62,
70
+ 63,
71
+ 64,
72
+ 65,
73
+ 66,
74
+ 67,
75
+ 68,
76
+ 69,
77
+ 70,
78
+ 71,
79
+ 72,
80
+ 73,
81
+ 74,
82
+ 75,
83
+ 76,
84
+ 77,
85
+ 78,
86
+ 79,
87
+ 80,
88
+ 81,
89
+ 82,
90
+ 83,
91
+ 84,
92
+ 85,
93
+ 86,
94
+ 87,
95
+ 88,
96
+ 89,
97
+ 90,
98
+ 91,
99
+ 92,
100
+ 93,
101
+ 94,
102
+ 95,
103
+ 96,
104
+ 97,
105
+ 98,
106
+ 99,
107
+ 100,
108
+ 101,
109
+ 102,
110
+ 103,
111
+ 104,
112
+ 105,
113
+ 106,
114
+ 107,
115
+ 108,
116
+ 109,
117
+ 110,
118
+ 111,
119
+ 112,
120
+ 113,
121
+ 114,
122
+ 115,
123
+ 116,
124
+ 117,
125
+ 118,
126
+ 119,
127
+ 120,
128
+ 121,
129
+ 122,
130
+ 123,
131
+ 124,
132
+ 125,
133
+ 126,
134
+ 127,
135
+ 128,
136
+ 129,
137
+ 130,
138
+ 131,
139
+ 132,
140
+ 133,
141
+ 134,
142
+ 135,
143
+ 136,
144
+ 137,
145
+ 138,
146
+ 139,
147
+ 140,
148
+ 141,
149
+ 142,
150
+ 143,
151
+ 144,
152
+ 145,
153
+ 146,
154
+ 147,
155
+ 148,
156
+ 149,
157
+ 150,
158
+ 151,
159
+ 152,
160
+ 153,
161
+ 154,
162
+ 155,
163
+ 156,
164
+ 157,
165
+ 158,
166
+ 159,
167
+ 160,
168
+ 161,
169
+ 162,
170
+ 163,
171
+ 164,
172
+ 165,
173
+ 166,
174
+ 167,
175
+ 168,
176
+ 169,
177
+ 170,
178
+ 171,
179
+ 172,
180
+ 173,
181
+ 174,
182
+ 175,
183
+ 176,
184
+ 177,
185
+ 178,
186
+ 179,
187
+ 180,
188
+ 181,
189
+ 182,
190
+ 183,
191
+ 184,
192
+ 185,
193
+ 186,
194
+ 187,
195
+ 188,
196
+ 189,
197
+ 190,
198
+ 191,
199
+ 192,
200
+ 193,
201
+ 194,
202
+ 195,
203
+ 196,
204
+ 197,
205
+ 198,
206
+ 199,
207
+ 200,
208
+ 201,
209
+ 202,
210
+ 203,
211
+ 204,
212
+ 205,
213
+ 206,
214
+ 207,
215
+ 208,
216
+ 209,
217
+ 210,
218
+ 211,
219
+ 212,
220
+ 213,
221
+ 214,
222
+ 215,
223
+ 216,
224
+ 217,
225
+ 218,
226
+ 219,
227
+ 220,
228
+ 221,
229
+ 222,
230
+ 223,
231
+ 224,
232
+ 225,
233
+ 226,
234
+ 227,
235
+ 228,
236
+ 229,
237
+ 230,
238
+ 231,
239
+ 232,
240
+ 233,
241
+ 234,
242
+ 235,
243
+ 236,
244
+ 237,
245
+ 238,
246
+ 239,
247
+ 240,
248
+ 241,
249
+ 242,
250
+ 243,
251
+ 244,
252
+ 245,
253
+ 246,
254
+ 247,
255
+ 248,
256
+ 249
257
+ ],
258
+ "exclude_episodes": null,
259
+ "filter_failed_trajectories": false,
260
+ "image_transforms": {
261
+ "enable": false,
262
+ "max_num_transforms": 3,
263
+ "random_order": false,
264
+ "tfs": {
265
+ "brightness": {
266
+ "weight": 1.0,
267
+ "type": "ColorJitter",
268
+ "kwargs": {
269
+ "brightness": [
270
+ 0.8,
271
+ 1.2
272
+ ]
273
+ }
274
+ },
275
+ "contrast": {
276
+ "weight": 1.0,
277
+ "type": "ColorJitter",
278
+ "kwargs": {
279
+ "contrast": [
280
+ 0.8,
281
+ 1.2
282
+ ]
283
+ }
284
+ },
285
+ "saturation": {
286
+ "weight": 1.0,
287
+ "type": "ColorJitter",
288
+ "kwargs": {
289
+ "saturation": [
290
+ 0.5,
291
+ 1.5
292
+ ]
293
+ }
294
+ },
295
+ "hue": {
296
+ "weight": 1.0,
297
+ "type": "ColorJitter",
298
+ "kwargs": {
299
+ "hue": [
300
+ -0.05,
301
+ 0.05
302
+ ]
303
+ }
304
+ },
305
+ "sharpness": {
306
+ "weight": 1.0,
307
+ "type": "SharpnessJitter",
308
+ "kwargs": {
309
+ "sharpness": [
310
+ 0.5,
311
+ 1.5
312
+ ]
313
+ }
314
+ },
315
+ "affine": {
316
+ "weight": 1.0,
317
+ "type": "RandomAffine",
318
+ "kwargs": {
319
+ "degrees": [
320
+ -5.0,
321
+ 5.0
322
+ ],
323
+ "translate": [
324
+ 0.05,
325
+ 0.05
326
+ ]
327
+ }
328
+ }
329
+ }
330
+ },
331
+ "revision": null,
332
+ "use_imagenet_stats": true,
333
+ "video_backend": "torchcodec",
334
+ "return_uint8": false,
335
+ "depth_output_unit": "mm",
336
+ "streaming": false,
337
+ "eval_split": 0.0
338
+ },
339
+ "env": null,
340
+ "policy": {
341
+ "type": "smolvla",
342
+ "n_obs_steps": 1,
343
+ "input_features": {
344
+ "observation.state": {
345
+ "type": "STATE",
346
+ "shape": [
347
+ 6
348
+ ]
349
+ },
350
+ "observation.images.camera1": {
351
+ "type": "VISUAL",
352
+ "shape": [
353
+ 3,
354
+ 256,
355
+ 256
356
+ ]
357
+ },
358
+ "observation.images.camera2": {
359
+ "type": "VISUAL",
360
+ "shape": [
361
+ 3,
362
+ 256,
363
+ 256
364
+ ]
365
+ },
366
+ "observation.images.camera3": {
367
+ "type": "VISUAL",
368
+ "shape": [
369
+ 3,
370
+ 256,
371
+ 256
372
+ ]
373
+ }
374
+ },
375
+ "output_features": {
376
+ "action": {
377
+ "type": "ACTION",
378
+ "shape": [
379
+ 6
380
+ ]
381
+ }
382
+ },
383
+ "device": "cuda",
384
+ "use_amp": false,
385
+ "use_peft": true,
386
+ "push_to_hub": false,
387
+ "repo_id": null,
388
+ "private": null,
389
+ "tags": null,
390
+ "license": null,
391
+ "pretrained_path": "lerobot/smolvla_base",
392
+ "pretrained_revision": null,
393
+ "chunk_size": 50,
394
+ "n_action_steps": 50,
395
+ "normalization_mapping": {
396
+ "VISUAL": "IDENTITY",
397
+ "STATE": "MEAN_STD",
398
+ "ACTION": "MEAN_STD"
399
+ },
400
+ "max_state_dim": 32,
401
+ "max_action_dim": 32,
402
+ "resize_imgs_with_padding": [
403
+ 512,
404
+ 512
405
+ ],
406
+ "empty_cameras": 0,
407
+ "adapt_to_pi_aloha": false,
408
+ "use_delta_joint_actions_aloha": false,
409
+ "tokenizer_max_length": 48,
410
+ "num_steps": 10,
411
+ "use_cache": true,
412
+ "freeze_vision_encoder": true,
413
+ "train_expert_only": true,
414
+ "train_state_proj": true,
415
+ "optimizer_lr": 0.0003,
416
+ "optimizer_betas": [
417
+ 0.9,
418
+ 0.95
419
+ ],
420
+ "optimizer_eps": 1e-08,
421
+ "optimizer_weight_decay": 1e-10,
422
+ "optimizer_grad_clip_norm": 10.0,
423
+ "scheduler_warmup_steps": 0,
424
+ "scheduler_decay_steps": 5000,
425
+ "scheduler_decay_lr": 0.0003,
426
+ "vlm_model_name": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct",
427
+ "load_vlm_weights": true,
428
+ "add_image_special_tokens": false,
429
+ "attention_mode": "cross_attn",
430
+ "prefix_length": 0,
431
+ "pad_language_to": "max_length",
432
+ "num_expert_layers": 0,
433
+ "num_vlm_layers": 16,
434
+ "self_attn_every_n_layers": 2,
435
+ "expert_width_multiplier": 0.75,
436
+ "min_period": 0.004,
437
+ "max_period": 4.0,
438
+ "rtc_config": null,
439
+ "compile_model": false,
440
+ "compile_mode": "max-autotune"
441
+ },
442
+ "reward_model": null,
443
+ "output_dir": "outputs/train/2026-09-24/17-36-42_smolvla_gk_adp_real_3e-4",
444
+ "job_name": "smolvla_gk_adp_real_3e-4",
445
+ "resume": false,
446
+ "seed": 1000,
447
+ "cudnn_deterministic": false,
448
+ "num_workers": 8,
449
+ "batch_size": 128,
450
+ "prefetch_factor": 1,
451
+ "persistent_workers": true,
452
+ "dataloader_multiprocessing_context": "fork",
453
+ "steps": 50000,
454
+ "env_eval_freq": 20000,
455
+ "log_freq": 200,
456
+ "eval_steps": 0,
457
+ "max_eval_samples": 0,
458
+ "tolerance_s": 0.0001,
459
+ "save_checkpoint": true,
460
+ "save_freq": 1000,
461
+ "checkpoint_format": "safetensors",
462
+ "use_policy_training_preset": true,
463
+ "optimizer": {
464
+ "type": "adamw",
465
+ "lr": 0.0003,
466
+ "weight_decay": 1e-10,
467
+ "grad_clip_norm": 10.0,
468
+ "betas": [
469
+ 0.9,
470
+ 0.95
471
+ ],
472
+ "eps": 1e-08
473
+ },
474
+ "scheduler": {
475
+ "type": "cosine_decay_with_warmup",
476
+ "num_warmup_steps": 0,
477
+ "num_decay_steps": 5000,
478
+ "peak_lr": 0.0003,
479
+ "decay_lr": 0.0003
480
+ },
481
+ "parallelism": {
482
+ "dp_replicate": 1,
483
+ "dp_shard": 1,
484
+ "context_parallel": {
485
+ "ring_degree": 1,
486
+ "ulysses_degree": 1
487
+ },
488
+ "cfg_parallel": 1
489
+ },
490
+ "accelerator": {
491
+ "mixed_precision": "no",
492
+ "gradient_accumulation": {
493
+ "steps": 1
494
+ },
495
+ "fsdp": {
496
+ "reshard_after_forward": true,
497
+ "wrap_modules": null,
498
+ "min_num_params": null,
499
+ "cpu_offload": false,
500
+ "ignored_modules": null
501
+ },
502
+ "ddp": {
503
+ "find_unused_parameters": true,
504
+ "gradient_as_bucket_view": false,
505
+ "static_graph": false
506
+ },
507
+ "compile": {
508
+ "enabled": false,
509
+ "backend": "inductor",
510
+ "mode": null,
511
+ "regional": true
512
+ },
513
+ "activation_checkpointing": {
514
+ "mode": "none"
515
+ }
516
+ },
517
+ "eval": {
518
+ "n_episodes": 50,
519
+ "tail_task_key": null,
520
+ "batch_size": 50,
521
+ "use_async_envs": true,
522
+ "recording": false,
523
+ "recording_repo_id": null,
524
+ "recording_private": false
525
+ },
526
+ "ema": {
527
+ "enable": false,
528
+ "decay": null,
529
+ "update_after_step": 0,
530
+ "inv_gamma": 1.0,
531
+ "power": 0.75,
532
+ "min_decay": 0.0,
533
+ "max_decay": 0.9999,
534
+ "use_for_eval": true
535
+ },
536
+ "wandb": {
537
+ "enable": true,
538
+ "disable_artifact": false,
539
+ "project": "lerobot",
540
+ "entity": null,
541
+ "notes": null,
542
+ "run_id": "2nambrcl",
543
+ "mode": null,
544
+ "add_tags": true
545
+ },
546
+ "peft": {
547
+ "target_modules": null,
548
+ "full_training_modules": null,
549
+ "method_type": "LORA",
550
+ "init_type": null,
551
+ "r": 16,
552
+ "lora_alpha": 16
553
+ },
554
+ "job": {
555
+ "target": null,
556
+ "image": "huggingface/lerobot-gpu:latest",
557
+ "timeout": "2d",
558
+ "detach": false,
559
+ "tags": []
560
+ },
561
+ "save_checkpoint_to_hub": false,
562
+ "sample_weighting": null,
563
+ "rename_map": {
564
+ "observation.images.front": "observation.images.camera1"
565
+ },
566
+ "checkpoint_path": null,
567
+ "task_info_path": "task_information/real.jsonl",
568
+ "task_suite": "real",
569
+ "task_order": null,
570
+ "num_tasks": null,
571
+ "steps_per_task": 10000,
572
+ "drop_last": true,
573
+ "learning_algorithm": {
574
+ "type": "gk_adp",
575
+ "sigma_init": 1.0,
576
+ "epsilon": 1e-06,
577
+ "embedding_layer": -1,
578
+ "modalities": [
579
+ "vision",
580
+ "language"
581
+ ],
582
+ "inference_routing": "top1",
583
+ "inference_top_k": 0,
584
+ "inference_temperature": 1.0,
585
+ "reset_scheduler_on_expansion": true,
586
+ "log_expert_statistics": false
587
+ },
588
+ "reset_optimizer_per_task": false,
589
+ "reset_scheduler_per_task": false
590
+ }
17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_005000/training_state/checkpoint_complete.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "step": 5000
3
+ }
17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_005000/training_state/optimizer_param_groups.json ADDED
@@ -0,0 +1,593 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "lr": 0.0003,
4
+ "betas": [
5
+ 0.9,
6
+ 0.95
7
+ ],
8
+ "eps": 1e-08,
9
+ "weight_decay": 1e-10,
10
+ "amsgrad": false,
11
+ "maximize": false,
12
+ "foreach": null,
13
+ "capturable": false,
14
+ "differentiable": false,
15
+ "fused": null,
16
+ "decoupled_weight_decay": true,
17
+ "initial_lr": 0.0003,
18
+ "params": [
19
+ 0,
20
+ 1,
21
+ 2,
22
+ 3,
23
+ 4,
24
+ 5,
25
+ 6,
26
+ 7,
27
+ 8,
28
+ 9,
29
+ 10,
30
+ 11,
31
+ 12,
32
+ 13,
33
+ 14,
34
+ 15,
35
+ 16,
36
+ 17,
37
+ 18,
38
+ 19,
39
+ 20,
40
+ 21,
41
+ 22,
42
+ 23,
43
+ 24,
44
+ 25,
45
+ 26,
46
+ 27,
47
+ 28,
48
+ 29,
49
+ 30,
50
+ 31,
51
+ 32,
52
+ 33,
53
+ 34,
54
+ 35,
55
+ 36,
56
+ 37,
57
+ 38,
58
+ 39,
59
+ 40,
60
+ 41,
61
+ 42,
62
+ 43,
63
+ 44,
64
+ 45,
65
+ 46,
66
+ 47,
67
+ 48,
68
+ 49,
69
+ 50,
70
+ 51,
71
+ 52,
72
+ 53,
73
+ 54,
74
+ 55,
75
+ 56,
76
+ 57,
77
+ 58,
78
+ 59,
79
+ 60,
80
+ 61,
81
+ 62,
82
+ 63,
83
+ 64,
84
+ 65,
85
+ 66,
86
+ 67,
87
+ 68,
88
+ 69,
89
+ 70,
90
+ 71,
91
+ 72,
92
+ 73,
93
+ 74,
94
+ 75,
95
+ 76,
96
+ 77,
97
+ 78,
98
+ 79,
99
+ 80,
100
+ 81,
101
+ 82,
102
+ 83,
103
+ 84,
104
+ 85,
105
+ 86,
106
+ 87,
107
+ 88,
108
+ 89,
109
+ 90,
110
+ 91,
111
+ 92,
112
+ 93,
113
+ 94,
114
+ 95,
115
+ 96,
116
+ 97,
117
+ 98,
118
+ 99,
119
+ 100,
120
+ 101,
121
+ 102,
122
+ 103,
123
+ 104,
124
+ 105,
125
+ 106,
126
+ 107,
127
+ 108,
128
+ 109,
129
+ 110,
130
+ 111,
131
+ 112,
132
+ 113,
133
+ 114,
134
+ 115,
135
+ 116,
136
+ 117,
137
+ 118,
138
+ 119,
139
+ 120,
140
+ 121,
141
+ 122,
142
+ 123,
143
+ 124,
144
+ 125,
145
+ 126,
146
+ 127,
147
+ 128,
148
+ 129,
149
+ 130,
150
+ 131,
151
+ 132,
152
+ 133,
153
+ 134,
154
+ 135,
155
+ 136,
156
+ 137,
157
+ 138,
158
+ 139,
159
+ 140,
160
+ 141,
161
+ 142,
162
+ 143,
163
+ 144,
164
+ 145,
165
+ 146,
166
+ 147,
167
+ 148,
168
+ 149,
169
+ 150,
170
+ 151,
171
+ 152,
172
+ 153,
173
+ 154,
174
+ 155,
175
+ 156,
176
+ 157,
177
+ 158,
178
+ 159,
179
+ 160,
180
+ 161,
181
+ 162,
182
+ 163,
183
+ 164,
184
+ 165,
185
+ 166,
186
+ 167,
187
+ 168,
188
+ 169,
189
+ 170,
190
+ 171,
191
+ 172,
192
+ 173,
193
+ 174,
194
+ 175,
195
+ 176,
196
+ 177,
197
+ 178,
198
+ 179,
199
+ 180,
200
+ 181,
201
+ 182,
202
+ 183,
203
+ 184,
204
+ 185,
205
+ 186,
206
+ 187,
207
+ 188,
208
+ 189,
209
+ 190,
210
+ 191,
211
+ 192,
212
+ 193,
213
+ 194,
214
+ 195,
215
+ 196,
216
+ 197,
217
+ 198,
218
+ 199,
219
+ 200,
220
+ 201,
221
+ 202,
222
+ 203,
223
+ 204,
224
+ 205,
225
+ 206,
226
+ 207,
227
+ 208,
228
+ 209,
229
+ 210,
230
+ 211,
231
+ 212,
232
+ 213,
233
+ 214,
234
+ 215,
235
+ 216,
236
+ 217,
237
+ 218,
238
+ 219,
239
+ 220,
240
+ 221,
241
+ 222,
242
+ 223,
243
+ 224,
244
+ 225,
245
+ 226,
246
+ 227,
247
+ 228,
248
+ 229,
249
+ 230,
250
+ 231,
251
+ 232,
252
+ 233,
253
+ 234,
254
+ 235,
255
+ 236,
256
+ 237,
257
+ 238,
258
+ 239,
259
+ 240,
260
+ 241,
261
+ 242,
262
+ 243,
263
+ 244,
264
+ 245,
265
+ 246,
266
+ 247,
267
+ 248,
268
+ 249,
269
+ 250,
270
+ 251,
271
+ 252,
272
+ 253,
273
+ 254,
274
+ 255,
275
+ 256,
276
+ 257,
277
+ 258,
278
+ 259,
279
+ 260,
280
+ 261,
281
+ 262,
282
+ 263,
283
+ 264,
284
+ 265,
285
+ 266,
286
+ 267,
287
+ 268,
288
+ 269,
289
+ 270,
290
+ 271,
291
+ 272,
292
+ 273,
293
+ 274,
294
+ 275,
295
+ 276,
296
+ 277,
297
+ 278,
298
+ 279,
299
+ 280,
300
+ 281,
301
+ 282,
302
+ 283,
303
+ 284,
304
+ 285,
305
+ 286,
306
+ 287,
307
+ 288,
308
+ 289,
309
+ 290,
310
+ 291,
311
+ 292,
312
+ 293,
313
+ 294,
314
+ 295,
315
+ 296,
316
+ 297,
317
+ 298,
318
+ 299,
319
+ 300,
320
+ 301,
321
+ 302,
322
+ 303,
323
+ 304,
324
+ 305,
325
+ 306,
326
+ 307,
327
+ 308,
328
+ 309,
329
+ 310,
330
+ 311,
331
+ 312,
332
+ 313,
333
+ 314,
334
+ 315,
335
+ 316,
336
+ 317,
337
+ 318,
338
+ 319,
339
+ 320,
340
+ 321,
341
+ 322,
342
+ 323,
343
+ 324,
344
+ 325,
345
+ 326,
346
+ 327,
347
+ 328,
348
+ 329,
349
+ 330,
350
+ 331,
351
+ 332,
352
+ 333,
353
+ 334,
354
+ 335,
355
+ 336,
356
+ 337,
357
+ 338,
358
+ 339,
359
+ 340,
360
+ 341,
361
+ 342,
362
+ 343,
363
+ 344,
364
+ 345,
365
+ 346,
366
+ 347,
367
+ 348,
368
+ 349,
369
+ 350,
370
+ 351,
371
+ 352,
372
+ 353,
373
+ 354,
374
+ 355,
375
+ 356,
376
+ 357,
377
+ 358,
378
+ 359,
379
+ 360,
380
+ 361,
381
+ 362,
382
+ 363,
383
+ 364,
384
+ 365,
385
+ 366,
386
+ 367,
387
+ 368,
388
+ 369,
389
+ 370,
390
+ 371,
391
+ 372,
392
+ 373,
393
+ 374,
394
+ 375,
395
+ 376,
396
+ 377,
397
+ 378,
398
+ 379,
399
+ 380,
400
+ 381,
401
+ 382,
402
+ 383,
403
+ 384,
404
+ 385,
405
+ 386,
406
+ 387,
407
+ 388,
408
+ 389,
409
+ 390,
410
+ 391,
411
+ 392,
412
+ 393,
413
+ 394,
414
+ 395,
415
+ 396,
416
+ 397,
417
+ 398,
418
+ 399,
419
+ 400,
420
+ 401,
421
+ 402,
422
+ 403,
423
+ 404,
424
+ 405,
425
+ 406,
426
+ 407,
427
+ 408,
428
+ 409,
429
+ 410,
430
+ 411,
431
+ 412,
432
+ 413,
433
+ 414,
434
+ 415,
435
+ 416,
436
+ 417,
437
+ 418,
438
+ 419,
439
+ 420,
440
+ 421,
441
+ 422,
442
+ 423,
443
+ 424,
444
+ 425,
445
+ 426,
446
+ 427,
447
+ 428,
448
+ 429,
449
+ 430,
450
+ 431,
451
+ 432,
452
+ 433,
453
+ 434,
454
+ 435,
455
+ 436,
456
+ 437,
457
+ 438,
458
+ 439,
459
+ 440,
460
+ 441,
461
+ 442,
462
+ 443,
463
+ 444,
464
+ 445,
465
+ 446,
466
+ 447,
467
+ 448,
468
+ 449,
469
+ 450,
470
+ 451,
471
+ 452,
472
+ 453,
473
+ 454,
474
+ 455,
475
+ 456,
476
+ 457,
477
+ 458,
478
+ 459,
479
+ 460,
480
+ 461,
481
+ 462,
482
+ 463,
483
+ 464,
484
+ 465,
485
+ 466,
486
+ 467,
487
+ 468,
488
+ 469,
489
+ 470,
490
+ 471,
491
+ 472,
492
+ 473,
493
+ 474,
494
+ 475,
495
+ 476,
496
+ 477,
497
+ 478,
498
+ 479,
499
+ 480,
500
+ 481,
501
+ 482,
502
+ 483,
503
+ 484,
504
+ 485,
505
+ 486,
506
+ 487,
507
+ 488,
508
+ 489,
509
+ 490,
510
+ 491,
511
+ 492,
512
+ 493,
513
+ 494,
514
+ 495,
515
+ 496,
516
+ 497,
517
+ 498,
518
+ 499,
519
+ 500,
520
+ 501,
521
+ 502,
522
+ 503,
523
+ 504,
524
+ 505,
525
+ 506,
526
+ 507,
527
+ 508,
528
+ 509,
529
+ 510,
530
+ 511,
531
+ 512,
532
+ 513,
533
+ 514,
534
+ 515,
535
+ 516,
536
+ 517,
537
+ 518,
538
+ 519,
539
+ 520,
540
+ 521,
541
+ 522,
542
+ 523,
543
+ 524,
544
+ 525,
545
+ 526,
546
+ 527,
547
+ 528,
548
+ 529,
549
+ 530,
550
+ 531,
551
+ 532,
552
+ 533,
553
+ 534,
554
+ 535,
555
+ 536,
556
+ 537,
557
+ 538,
558
+ 539,
559
+ 540,
560
+ 541,
561
+ 542,
562
+ 543,
563
+ 544,
564
+ 545,
565
+ 546,
566
+ 547,
567
+ 548,
568
+ 549,
569
+ 550,
570
+ 551,
571
+ 552,
572
+ 553,
573
+ 554,
574
+ 555,
575
+ 556,
576
+ 557,
577
+ 558,
578
+ 559,
579
+ 560,
580
+ 561,
581
+ 562,
582
+ 563,
583
+ 564,
584
+ 565,
585
+ 566,
586
+ 567,
587
+ 568,
588
+ 569,
589
+ 570,
590
+ 571
591
+ ]
592
+ }
593
+ ]
17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_005000/training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de7dc361efcf388a2f1c6d0e5c4a1fc931882131735decb24550d4c1e0032cbf
3
+ size 5832632
17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_005000/training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2585334d5b18b6fa38af093befc34fb27e9edd6174ed01c2cfe806c31f4e28a
3
+ size 15708
17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_005000/training_state/rng_state_rank_0.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2585334d5b18b6fa38af093befc34fb27e9edd6174ed01c2cfe806c31f4e28a
3
+ size 15708
17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_005000/training_state/scheduler_state.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_lrs": [
3
+ 0.0003
4
+ ],
5
+ "last_epoch": 5000,
6
+ "_step_count": 5001,
7
+ "_is_initial": false,
8
+ "_get_lr_called_within_step": false,
9
+ "_last_lr": [
10
+ 0.0003
11
+ ],
12
+ "lr_lambdas": [
13
+ null
14
+ ]
15
+ }
17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_005000/training_state/sequential_state.json ADDED
@@ -0,0 +1,904 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": 1,
3
+ "step": 5000,
4
+ "task_position": 0,
5
+ "task_step": 5000,
6
+ "steps_per_task": 10000,
7
+ "drop_last": true,
8
+ "task_sequence": [
9
+ {
10
+ "task_suite": "real",
11
+ "task_index_within_suite": 0,
12
+ "task_index": 0,
13
+ "task": "Put the tape in the bowl",
14
+ "task_pattern": null,
15
+ "task_indices": [],
16
+ "instructions": [],
17
+ "episodes": [
18
+ 0,
19
+ 1,
20
+ 2,
21
+ 3,
22
+ 4,
23
+ 5,
24
+ 6,
25
+ 7,
26
+ 8,
27
+ 9,
28
+ 50,
29
+ 51,
30
+ 52,
31
+ 53,
32
+ 54,
33
+ 55,
34
+ 56,
35
+ 57,
36
+ 58,
37
+ 59,
38
+ 60,
39
+ 61,
40
+ 62,
41
+ 63,
42
+ 64,
43
+ 65,
44
+ 66,
45
+ 67,
46
+ 68,
47
+ 69,
48
+ 70,
49
+ 71,
50
+ 72,
51
+ 73,
52
+ 74,
53
+ 75,
54
+ 76,
55
+ 77,
56
+ 78,
57
+ 79,
58
+ 80,
59
+ 81,
60
+ 82,
61
+ 83,
62
+ 84,
63
+ 85,
64
+ 86,
65
+ 87,
66
+ 88,
67
+ 89
68
+ ]
69
+ },
70
+ {
71
+ "task_suite": "real",
72
+ "task_index_within_suite": 1,
73
+ "task_index": 1,
74
+ "task": "Put the pen in the cup",
75
+ "task_pattern": null,
76
+ "task_indices": [],
77
+ "instructions": [],
78
+ "episodes": [
79
+ 10,
80
+ 11,
81
+ 12,
82
+ 13,
83
+ 14,
84
+ 15,
85
+ 16,
86
+ 17,
87
+ 18,
88
+ 19,
89
+ 90,
90
+ 91,
91
+ 92,
92
+ 93,
93
+ 94,
94
+ 95,
95
+ 96,
96
+ 97,
97
+ 98,
98
+ 99,
99
+ 100,
100
+ 101,
101
+ 102,
102
+ 103,
103
+ 104,
104
+ 105,
105
+ 106,
106
+ 107,
107
+ 108,
108
+ 109,
109
+ 110,
110
+ 111,
111
+ 112,
112
+ 113,
113
+ 114,
114
+ 115,
115
+ 116,
116
+ 117,
117
+ 118,
118
+ 119,
119
+ 120,
120
+ 121,
121
+ 122,
122
+ 123,
123
+ 124,
124
+ 125,
125
+ 126,
126
+ 127,
127
+ 128,
128
+ 129
129
+ ]
130
+ },
131
+ {
132
+ "task_suite": "real",
133
+ "task_index_within_suite": 2,
134
+ "task_index": 2,
135
+ "task": "Turn the cup upright",
136
+ "task_pattern": null,
137
+ "task_indices": [],
138
+ "instructions": [],
139
+ "episodes": [
140
+ 20,
141
+ 21,
142
+ 22,
143
+ 23,
144
+ 24,
145
+ 25,
146
+ 26,
147
+ 27,
148
+ 28,
149
+ 29,
150
+ 130,
151
+ 131,
152
+ 132,
153
+ 133,
154
+ 134,
155
+ 135,
156
+ 136,
157
+ 137,
158
+ 138,
159
+ 139,
160
+ 140,
161
+ 141,
162
+ 142,
163
+ 143,
164
+ 144,
165
+ 145,
166
+ 146,
167
+ 147,
168
+ 148,
169
+ 149,
170
+ 150,
171
+ 151,
172
+ 152,
173
+ 153,
174
+ 154,
175
+ 155,
176
+ 156,
177
+ 157,
178
+ 158,
179
+ 159,
180
+ 160,
181
+ 161,
182
+ 242,
183
+ 243,
184
+ 244,
185
+ 245,
186
+ 246,
187
+ 247,
188
+ 248,
189
+ 249
190
+ ]
191
+ },
192
+ {
193
+ "task_suite": "real",
194
+ "task_index_within_suite": 3,
195
+ "task_index": 0,
196
+ "task": "Put the tape in the bowl",
197
+ "task_pattern": null,
198
+ "task_indices": [],
199
+ "instructions": [],
200
+ "episodes": [
201
+ 30,
202
+ 31,
203
+ 32,
204
+ 33,
205
+ 34,
206
+ 35,
207
+ 36,
208
+ 37,
209
+ 38,
210
+ 39,
211
+ 162,
212
+ 163,
213
+ 164,
214
+ 165,
215
+ 166,
216
+ 167,
217
+ 168,
218
+ 169,
219
+ 170,
220
+ 171,
221
+ 172,
222
+ 173,
223
+ 174,
224
+ 175,
225
+ 176,
226
+ 177,
227
+ 178,
228
+ 179,
229
+ 180,
230
+ 181,
231
+ 182,
232
+ 183,
233
+ 184,
234
+ 185,
235
+ 186,
236
+ 187,
237
+ 188,
238
+ 189,
239
+ 190,
240
+ 191,
241
+ 192,
242
+ 193,
243
+ 194,
244
+ 195,
245
+ 196,
246
+ 197,
247
+ 198,
248
+ 199,
249
+ 200,
250
+ 201
251
+ ]
252
+ },
253
+ {
254
+ "task_suite": "real",
255
+ "task_index_within_suite": 4,
256
+ "task_index": 3,
257
+ "task": "Put the pen into the cup",
258
+ "task_pattern": null,
259
+ "task_indices": [],
260
+ "instructions": [],
261
+ "episodes": [
262
+ 40,
263
+ 41,
264
+ 42,
265
+ 43,
266
+ 44,
267
+ 45,
268
+ 46,
269
+ 47,
270
+ 48,
271
+ 49,
272
+ 202,
273
+ 203,
274
+ 204,
275
+ 205,
276
+ 206,
277
+ 207,
278
+ 208,
279
+ 209,
280
+ 210,
281
+ 211,
282
+ 212,
283
+ 213,
284
+ 214,
285
+ 215,
286
+ 216,
287
+ 217,
288
+ 218,
289
+ 219,
290
+ 220,
291
+ 221,
292
+ 222,
293
+ 223,
294
+ 224,
295
+ 225,
296
+ 226,
297
+ 227,
298
+ 228,
299
+ 229,
300
+ 230,
301
+ 231,
302
+ 232,
303
+ 233,
304
+ 234,
305
+ 235,
306
+ 236,
307
+ 237,
308
+ 238,
309
+ 239,
310
+ 240,
311
+ 241
312
+ ]
313
+ }
314
+ ],
315
+ "config": {
316
+ "dataset": {
317
+ "repo_id": "tml-lab/real",
318
+ "repo_type": "dataset",
319
+ "root": null,
320
+ "episodes": [
321
+ 0,
322
+ 1,
323
+ 2,
324
+ 3,
325
+ 4,
326
+ 5,
327
+ 6,
328
+ 7,
329
+ 8,
330
+ 9,
331
+ 10,
332
+ 11,
333
+ 12,
334
+ 13,
335
+ 14,
336
+ 15,
337
+ 16,
338
+ 17,
339
+ 18,
340
+ 19,
341
+ 20,
342
+ 21,
343
+ 22,
344
+ 23,
345
+ 24,
346
+ 25,
347
+ 26,
348
+ 27,
349
+ 28,
350
+ 29,
351
+ 30,
352
+ 31,
353
+ 32,
354
+ 33,
355
+ 34,
356
+ 35,
357
+ 36,
358
+ 37,
359
+ 38,
360
+ 39,
361
+ 40,
362
+ 41,
363
+ 42,
364
+ 43,
365
+ 44,
366
+ 45,
367
+ 46,
368
+ 47,
369
+ 48,
370
+ 49,
371
+ 50,
372
+ 51,
373
+ 52,
374
+ 53,
375
+ 54,
376
+ 55,
377
+ 56,
378
+ 57,
379
+ 58,
380
+ 59,
381
+ 60,
382
+ 61,
383
+ 62,
384
+ 63,
385
+ 64,
386
+ 65,
387
+ 66,
388
+ 67,
389
+ 68,
390
+ 69,
391
+ 70,
392
+ 71,
393
+ 72,
394
+ 73,
395
+ 74,
396
+ 75,
397
+ 76,
398
+ 77,
399
+ 78,
400
+ 79,
401
+ 80,
402
+ 81,
403
+ 82,
404
+ 83,
405
+ 84,
406
+ 85,
407
+ 86,
408
+ 87,
409
+ 88,
410
+ 89,
411
+ 90,
412
+ 91,
413
+ 92,
414
+ 93,
415
+ 94,
416
+ 95,
417
+ 96,
418
+ 97,
419
+ 98,
420
+ 99,
421
+ 100,
422
+ 101,
423
+ 102,
424
+ 103,
425
+ 104,
426
+ 105,
427
+ 106,
428
+ 107,
429
+ 108,
430
+ 109,
431
+ 110,
432
+ 111,
433
+ 112,
434
+ 113,
435
+ 114,
436
+ 115,
437
+ 116,
438
+ 117,
439
+ 118,
440
+ 119,
441
+ 120,
442
+ 121,
443
+ 122,
444
+ 123,
445
+ 124,
446
+ 125,
447
+ 126,
448
+ 127,
449
+ 128,
450
+ 129,
451
+ 130,
452
+ 131,
453
+ 132,
454
+ 133,
455
+ 134,
456
+ 135,
457
+ 136,
458
+ 137,
459
+ 138,
460
+ 139,
461
+ 140,
462
+ 141,
463
+ 142,
464
+ 143,
465
+ 144,
466
+ 145,
467
+ 146,
468
+ 147,
469
+ 148,
470
+ 149,
471
+ 150,
472
+ 151,
473
+ 152,
474
+ 153,
475
+ 154,
476
+ 155,
477
+ 156,
478
+ 157,
479
+ 158,
480
+ 159,
481
+ 160,
482
+ 161,
483
+ 162,
484
+ 163,
485
+ 164,
486
+ 165,
487
+ 166,
488
+ 167,
489
+ 168,
490
+ 169,
491
+ 170,
492
+ 171,
493
+ 172,
494
+ 173,
495
+ 174,
496
+ 175,
497
+ 176,
498
+ 177,
499
+ 178,
500
+ 179,
501
+ 180,
502
+ 181,
503
+ 182,
504
+ 183,
505
+ 184,
506
+ 185,
507
+ 186,
508
+ 187,
509
+ 188,
510
+ 189,
511
+ 190,
512
+ 191,
513
+ 192,
514
+ 193,
515
+ 194,
516
+ 195,
517
+ 196,
518
+ 197,
519
+ 198,
520
+ 199,
521
+ 200,
522
+ 201,
523
+ 202,
524
+ 203,
525
+ 204,
526
+ 205,
527
+ 206,
528
+ 207,
529
+ 208,
530
+ 209,
531
+ 210,
532
+ 211,
533
+ 212,
534
+ 213,
535
+ 214,
536
+ 215,
537
+ 216,
538
+ 217,
539
+ 218,
540
+ 219,
541
+ 220,
542
+ 221,
543
+ 222,
544
+ 223,
545
+ 224,
546
+ 225,
547
+ 226,
548
+ 227,
549
+ 228,
550
+ 229,
551
+ 230,
552
+ 231,
553
+ 232,
554
+ 233,
555
+ 234,
556
+ 235,
557
+ 236,
558
+ 237,
559
+ 238,
560
+ 239,
561
+ 240,
562
+ 241,
563
+ 242,
564
+ 243,
565
+ 244,
566
+ 245,
567
+ 246,
568
+ 247,
569
+ 248,
570
+ 249
571
+ ],
572
+ "exclude_episodes": null,
573
+ "filter_failed_trajectories": false,
574
+ "image_transforms": {
575
+ "enable": false,
576
+ "max_num_transforms": 3,
577
+ "random_order": false,
578
+ "tfs": {
579
+ "brightness": {
580
+ "weight": 1.0,
581
+ "type": "ColorJitter",
582
+ "kwargs": {
583
+ "brightness": [
584
+ 0.8,
585
+ 1.2
586
+ ]
587
+ }
588
+ },
589
+ "contrast": {
590
+ "weight": 1.0,
591
+ "type": "ColorJitter",
592
+ "kwargs": {
593
+ "contrast": [
594
+ 0.8,
595
+ 1.2
596
+ ]
597
+ }
598
+ },
599
+ "saturation": {
600
+ "weight": 1.0,
601
+ "type": "ColorJitter",
602
+ "kwargs": {
603
+ "saturation": [
604
+ 0.5,
605
+ 1.5
606
+ ]
607
+ }
608
+ },
609
+ "hue": {
610
+ "weight": 1.0,
611
+ "type": "ColorJitter",
612
+ "kwargs": {
613
+ "hue": [
614
+ -0.05,
615
+ 0.05
616
+ ]
617
+ }
618
+ },
619
+ "sharpness": {
620
+ "weight": 1.0,
621
+ "type": "SharpnessJitter",
622
+ "kwargs": {
623
+ "sharpness": [
624
+ 0.5,
625
+ 1.5
626
+ ]
627
+ }
628
+ },
629
+ "affine": {
630
+ "weight": 1.0,
631
+ "type": "RandomAffine",
632
+ "kwargs": {
633
+ "degrees": [
634
+ -5.0,
635
+ 5.0
636
+ ],
637
+ "translate": [
638
+ 0.05,
639
+ 0.05
640
+ ]
641
+ }
642
+ }
643
+ }
644
+ },
645
+ "revision": null,
646
+ "use_imagenet_stats": true,
647
+ "video_backend": "torchcodec",
648
+ "return_uint8": false,
649
+ "depth_output_unit": "mm",
650
+ "streaming": false,
651
+ "eval_split": 0.0
652
+ },
653
+ "env": null,
654
+ "policy": {
655
+ "type": "smolvla",
656
+ "n_obs_steps": 1,
657
+ "input_features": {
658
+ "observation.state": {
659
+ "type": "STATE",
660
+ "shape": [
661
+ 6
662
+ ]
663
+ },
664
+ "observation.images.camera1": {
665
+ "type": "VISUAL",
666
+ "shape": [
667
+ 3,
668
+ 256,
669
+ 256
670
+ ]
671
+ },
672
+ "observation.images.camera2": {
673
+ "type": "VISUAL",
674
+ "shape": [
675
+ 3,
676
+ 256,
677
+ 256
678
+ ]
679
+ },
680
+ "observation.images.camera3": {
681
+ "type": "VISUAL",
682
+ "shape": [
683
+ 3,
684
+ 256,
685
+ 256
686
+ ]
687
+ }
688
+ },
689
+ "output_features": {
690
+ "action": {
691
+ "type": "ACTION",
692
+ "shape": [
693
+ 6
694
+ ]
695
+ }
696
+ },
697
+ "device": "cuda",
698
+ "use_amp": false,
699
+ "use_peft": true,
700
+ "push_to_hub": false,
701
+ "repo_id": null,
702
+ "private": null,
703
+ "tags": null,
704
+ "license": null,
705
+ "pretrained_path": "<resume-source>",
706
+ "pretrained_revision": null,
707
+ "chunk_size": 50,
708
+ "n_action_steps": 50,
709
+ "normalization_mapping": {
710
+ "VISUAL": "IDENTITY",
711
+ "STATE": "MEAN_STD",
712
+ "ACTION": "MEAN_STD"
713
+ },
714
+ "max_state_dim": 32,
715
+ "max_action_dim": 32,
716
+ "resize_imgs_with_padding": [
717
+ 512,
718
+ 512
719
+ ],
720
+ "empty_cameras": 0,
721
+ "adapt_to_pi_aloha": false,
722
+ "use_delta_joint_actions_aloha": false,
723
+ "tokenizer_max_length": 48,
724
+ "num_steps": 10,
725
+ "use_cache": true,
726
+ "freeze_vision_encoder": true,
727
+ "train_expert_only": true,
728
+ "train_state_proj": true,
729
+ "optimizer_lr": 0.0003,
730
+ "optimizer_betas": [
731
+ 0.9,
732
+ 0.95
733
+ ],
734
+ "optimizer_eps": 1e-08,
735
+ "optimizer_weight_decay": 1e-10,
736
+ "optimizer_grad_clip_norm": 10.0,
737
+ "scheduler_warmup_steps": 0,
738
+ "scheduler_decay_steps": 5000,
739
+ "scheduler_decay_lr": 0.0003,
740
+ "vlm_model_name": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct",
741
+ "load_vlm_weights": true,
742
+ "add_image_special_tokens": false,
743
+ "attention_mode": "cross_attn",
744
+ "prefix_length": 0,
745
+ "pad_language_to": "max_length",
746
+ "num_expert_layers": 0,
747
+ "num_vlm_layers": 16,
748
+ "self_attn_every_n_layers": 2,
749
+ "expert_width_multiplier": 0.75,
750
+ "min_period": 0.004,
751
+ "max_period": 4.0,
752
+ "rtc_config": null,
753
+ "compile_model": false,
754
+ "compile_mode": "max-autotune"
755
+ },
756
+ "reward_model": null,
757
+ "output_dir": "/home/tml_lab/lerobot-061-cl/outputs/train/2026-09-24/17-36-42_smolvla_gk_adp_real_3e-4",
758
+ "job_name": "smolvla_gk_adp_real_3e-4",
759
+ "resume": false,
760
+ "seed": 1000,
761
+ "cudnn_deterministic": false,
762
+ "num_workers": 8,
763
+ "batch_size": 128,
764
+ "prefetch_factor": 1,
765
+ "persistent_workers": true,
766
+ "dataloader_multiprocessing_context": "fork",
767
+ "steps": 50000,
768
+ "env_eval_freq": 20000,
769
+ "log_freq": 200,
770
+ "eval_steps": 0,
771
+ "max_eval_samples": 0,
772
+ "tolerance_s": 0.0001,
773
+ "save_checkpoint": true,
774
+ "save_freq": 1000,
775
+ "checkpoint_format": "safetensors",
776
+ "use_policy_training_preset": true,
777
+ "optimizer": {
778
+ "type": "adamw",
779
+ "lr": 0.0003,
780
+ "weight_decay": 1e-10,
781
+ "grad_clip_norm": 10.0,
782
+ "betas": [
783
+ 0.9,
784
+ 0.95
785
+ ],
786
+ "eps": 1e-08
787
+ },
788
+ "scheduler": {
789
+ "type": "cosine_decay_with_warmup",
790
+ "num_warmup_steps": 0,
791
+ "num_decay_steps": 5000,
792
+ "peak_lr": 0.0003,
793
+ "decay_lr": 0.0003
794
+ },
795
+ "parallelism": {
796
+ "dp_replicate": 1,
797
+ "dp_shard": 1,
798
+ "context_parallel": {
799
+ "ring_degree": 1,
800
+ "ulysses_degree": 1
801
+ },
802
+ "cfg_parallel": 1
803
+ },
804
+ "accelerator": {
805
+ "mixed_precision": "no",
806
+ "gradient_accumulation": {
807
+ "steps": 1
808
+ },
809
+ "fsdp": {
810
+ "reshard_after_forward": true,
811
+ "wrap_modules": null,
812
+ "min_num_params": null,
813
+ "cpu_offload": false,
814
+ "ignored_modules": null
815
+ },
816
+ "ddp": {
817
+ "find_unused_parameters": true,
818
+ "gradient_as_bucket_view": false,
819
+ "static_graph": false
820
+ },
821
+ "compile": {
822
+ "enabled": false,
823
+ "backend": "inductor",
824
+ "mode": null,
825
+ "regional": true
826
+ },
827
+ "activation_checkpointing": {
828
+ "mode": "none"
829
+ }
830
+ },
831
+ "eval": {
832
+ "n_episodes": 50,
833
+ "batch_size": 50,
834
+ "use_async_envs": true,
835
+ "recording": false,
836
+ "recording_repo_id": null,
837
+ "recording_private": false
838
+ },
839
+ "ema": {
840
+ "enable": false,
841
+ "decay": null,
842
+ "update_after_step": 0,
843
+ "inv_gamma": 1.0,
844
+ "power": 0.75,
845
+ "min_decay": 0.0,
846
+ "max_decay": 0.9999,
847
+ "use_for_eval": true
848
+ },
849
+ "wandb": {
850
+ "enable": true,
851
+ "disable_artifact": false,
852
+ "project": "lerobot",
853
+ "entity": null,
854
+ "notes": null,
855
+ "run_id": "2nambrcl",
856
+ "mode": null,
857
+ "add_tags": true
858
+ },
859
+ "peft": {
860
+ "target_modules": null,
861
+ "full_training_modules": null,
862
+ "method_type": "LORA",
863
+ "init_type": null,
864
+ "r": 16,
865
+ "lora_alpha": 16
866
+ },
867
+ "job": {
868
+ "target": null,
869
+ "image": "huggingface/lerobot-gpu:latest",
870
+ "timeout": "2d",
871
+ "detach": false,
872
+ "tags": []
873
+ },
874
+ "save_checkpoint_to_hub": false,
875
+ "sample_weighting": null,
876
+ "rename_map": {
877
+ "observation.images.front": "observation.images.camera1"
878
+ },
879
+ "checkpoint_path": null,
880
+ "task_info_path": "task_information/real.jsonl",
881
+ "task_suite": "real",
882
+ "task_order": null,
883
+ "num_tasks": null,
884
+ "steps_per_task": 10000,
885
+ "drop_last": true,
886
+ "learning_algorithm": {
887
+ "type": "gk_adp",
888
+ "sigma_init": 1.0,
889
+ "epsilon": 1e-06,
890
+ "embedding_layer": -1,
891
+ "modalities": [
892
+ "vision",
893
+ "language"
894
+ ],
895
+ "inference_routing": "top1",
896
+ "inference_top_k": 0,
897
+ "inference_temperature": 1.0,
898
+ "reset_scheduler_on_expansion": true,
899
+ "log_expert_statistics": false
900
+ },
901
+ "reset_optimizer_per_task": false,
902
+ "reset_scheduler_per_task": false
903
+ }
904
+ }
17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_005000/training_state/training_step.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "step": 5000,
3
+ "dp_world_size": 1,
4
+ "batch_size": 128,
5
+ "grad_accum_steps": 1,
6
+ "parallelism": {
7
+ "dp_replicate": 1,
8
+ "dp_shard": 1,
9
+ "ring_degree": 1,
10
+ "ulysses_degree": 1
11
+ }
12
+ }
17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_006000/pretrained_model/README.md ADDED
@@ -0,0 +1,204 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ tags:
4
+ - base_model:adapter:lerobot/smolvla_base
5
+ - lora
6
+ ---
7
+
8
+ # Model Card for Model ID
9
+
10
+ <!-- Provide a quick summary of what the model is/does. -->
11
+
12
+
13
+
14
+ ## Model Details
15
+
16
+ ### Model Description
17
+
18
+ <!-- Provide a longer summary of what this model is. -->
19
+
20
+
21
+
22
+ - **Developed by:** [More Information Needed]
23
+ - **Funded by [optional]:** [More Information Needed]
24
+ - **Shared by [optional]:** [More Information Needed]
25
+ - **Model type:** [More Information Needed]
26
+ - **Language(s) (NLP):** [More Information Needed]
27
+ - **License:** [More Information Needed]
28
+ - **Finetuned from model [optional]:** [More Information Needed]
29
+
30
+ ### Model Sources [optional]
31
+
32
+ <!-- Provide the basic links for the model. -->
33
+
34
+ - **Repository:** [More Information Needed]
35
+ - **Paper [optional]:** [More Information Needed]
36
+ - **Demo [optional]:** [More Information Needed]
37
+
38
+ ## Uses
39
+
40
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
41
+
42
+ ### Direct Use
43
+
44
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
45
+
46
+ [More Information Needed]
47
+
48
+ ### Downstream Use [optional]
49
+
50
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
51
+
52
+ [More Information Needed]
53
+
54
+ ### Out-of-Scope Use
55
+
56
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
57
+
58
+ [More Information Needed]
59
+
60
+ ## Bias, Risks, and Limitations
61
+
62
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
63
+
64
+ [More Information Needed]
65
+
66
+ ### Recommendations
67
+
68
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
69
+
70
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
71
+
72
+ ## How to Get Started with the Model
73
+
74
+ Use the code below to get started with the model.
75
+
76
+ [More Information Needed]
77
+
78
+ ## Training Details
79
+
80
+ ### Training Data
81
+
82
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
83
+
84
+ [More Information Needed]
85
+
86
+ ### Training Procedure
87
+
88
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
89
+
90
+ #### Preprocessing [optional]
91
+
92
+ [More Information Needed]
93
+
94
+
95
+ #### Training Hyperparameters
96
+
97
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
98
+
99
+ #### Speeds, Sizes, Times [optional]
100
+
101
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
102
+
103
+ [More Information Needed]
104
+
105
+ ## Evaluation
106
+
107
+ <!-- This section describes the evaluation protocols and provides the results. -->
108
+
109
+ ### Testing Data, Factors & Metrics
110
+
111
+ #### Testing Data
112
+
113
+ <!-- This should link to a Dataset Card if possible. -->
114
+
115
+ [More Information Needed]
116
+
117
+ #### Factors
118
+
119
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
120
+
121
+ [More Information Needed]
122
+
123
+ #### Metrics
124
+
125
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
126
+
127
+ [More Information Needed]
128
+
129
+ ### Results
130
+
131
+ [More Information Needed]
132
+
133
+ #### Summary
134
+
135
+
136
+
137
+ ## Model Examination [optional]
138
+
139
+ <!-- Relevant interpretability work for the model goes here -->
140
+
141
+ [More Information Needed]
142
+
143
+ ## Environmental Impact
144
+
145
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
146
+
147
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
148
+
149
+ - **Hardware Type:** [More Information Needed]
150
+ - **Hours used:** [More Information Needed]
151
+ - **Cloud Provider:** [More Information Needed]
152
+ - **Compute Region:** [More Information Needed]
153
+ - **Carbon Emitted:** [More Information Needed]
154
+
155
+ ## Technical Specifications [optional]
156
+
157
+ ### Model Architecture and Objective
158
+
159
+ [More Information Needed]
160
+
161
+ ### Compute Infrastructure
162
+
163
+ [More Information Needed]
164
+
165
+ #### Hardware
166
+
167
+ [More Information Needed]
168
+
169
+ #### Software
170
+
171
+ [More Information Needed]
172
+
173
+ ## Citation [optional]
174
+
175
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
176
+
177
+ **BibTeX:**
178
+
179
+ [More Information Needed]
180
+
181
+ **APA:**
182
+
183
+ [More Information Needed]
184
+
185
+ ## Glossary [optional]
186
+
187
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
188
+
189
+ [More Information Needed]
190
+
191
+ ## More Information [optional]
192
+
193
+ [More Information Needed]
194
+
195
+ ## Model Card Authors [optional]
196
+
197
+ [More Information Needed]
198
+
199
+ ## Model Card Contact
200
+
201
+ [More Information Needed]
202
+ ### Framework versions
203
+
204
+ - PEFT 0.21.0
17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_006000/pretrained_model/adapter_config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": {
6
+ "base_model_class": "SmolVLAPolicy",
7
+ "parent_library": "lerobot.policies.smolvla.modeling_smolvla"
8
+ },
9
+ "base_model_name_or_path": "lerobot/smolvla_base",
10
+ "bias": "none",
11
+ "corda_config": null,
12
+ "ensure_weight_tying": false,
13
+ "eva_config": null,
14
+ "exclude_modules": null,
15
+ "fan_in_fan_out": false,
16
+ "inference_mode": true,
17
+ "init_lora_weights": true,
18
+ "kasa_config": null,
19
+ "layer_replication": null,
20
+ "layers_pattern": null,
21
+ "layers_to_transform": null,
22
+ "loftq_config": {},
23
+ "lora_alpha": 16,
24
+ "lora_bias": false,
25
+ "lora_dropout": 0.0,
26
+ "lora_ga_config": null,
27
+ "megatron_config": null,
28
+ "megatron_core": "megatron.core",
29
+ "modules_to_save": [],
30
+ "monteclora_config": null,
31
+ "peft_type": "LORA",
32
+ "peft_version": "0.21.0",
33
+ "qalora_group_size": 16,
34
+ "r": 16,
35
+ "rank_pattern": {},
36
+ "revision": null,
37
+ "target_modules": "(model\\.vlm_with_expert\\.lm_expert\\..*\\.(q|v)_proj|model\\.(action_in_proj|action_out_proj|action_time_mlp_in|action_time_mlp_out))",
38
+ "target_parameters": null,
39
+ "task_type": null,
40
+ "trainable_token_indices": null,
41
+ "use_bdlora": null,
42
+ "use_dora": false,
43
+ "use_qalora": false,
44
+ "use_rslora": false,
45
+ "velora_config": null
46
+ }
17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_006000/pretrained_model/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4172d4944d6502be058e72c49aeaf284e4718e5f229bb64b6b33b40ca735e00e
3
+ size 2918168
17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_006000/pretrained_model/config.json ADDED
@@ -0,0 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "smolvla",
3
+ "n_obs_steps": 1,
4
+ "input_features": {
5
+ "observation.state": {
6
+ "type": "STATE",
7
+ "shape": [
8
+ 6
9
+ ]
10
+ },
11
+ "observation.images.camera1": {
12
+ "type": "VISUAL",
13
+ "shape": [
14
+ 3,
15
+ 256,
16
+ 256
17
+ ]
18
+ },
19
+ "observation.images.camera2": {
20
+ "type": "VISUAL",
21
+ "shape": [
22
+ 3,
23
+ 256,
24
+ 256
25
+ ]
26
+ },
27
+ "observation.images.camera3": {
28
+ "type": "VISUAL",
29
+ "shape": [
30
+ 3,
31
+ 256,
32
+ 256
33
+ ]
34
+ }
35
+ },
36
+ "output_features": {
37
+ "action": {
38
+ "type": "ACTION",
39
+ "shape": [
40
+ 6
41
+ ]
42
+ }
43
+ },
44
+ "device": "cuda",
45
+ "use_amp": false,
46
+ "use_peft": true,
47
+ "push_to_hub": false,
48
+ "repo_id": null,
49
+ "private": null,
50
+ "tags": null,
51
+ "license": null,
52
+ "pretrained_path": "lerobot/smolvla_base",
53
+ "pretrained_revision": null,
54
+ "chunk_size": 50,
55
+ "n_action_steps": 50,
56
+ "normalization_mapping": {
57
+ "VISUAL": "IDENTITY",
58
+ "STATE": "MEAN_STD",
59
+ "ACTION": "MEAN_STD"
60
+ },
61
+ "max_state_dim": 32,
62
+ "max_action_dim": 32,
63
+ "resize_imgs_with_padding": [
64
+ 512,
65
+ 512
66
+ ],
67
+ "empty_cameras": 0,
68
+ "adapt_to_pi_aloha": false,
69
+ "use_delta_joint_actions_aloha": false,
70
+ "tokenizer_max_length": 48,
71
+ "num_steps": 10,
72
+ "use_cache": true,
73
+ "freeze_vision_encoder": true,
74
+ "train_expert_only": true,
75
+ "train_state_proj": true,
76
+ "optimizer_lr": 0.0003,
77
+ "optimizer_betas": [
78
+ 0.9,
79
+ 0.95
80
+ ],
81
+ "optimizer_eps": 1e-08,
82
+ "optimizer_weight_decay": 1e-10,
83
+ "optimizer_grad_clip_norm": 10.0,
84
+ "scheduler_warmup_steps": 0,
85
+ "scheduler_decay_steps": 5000,
86
+ "scheduler_decay_lr": 0.0003,
87
+ "vlm_model_name": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct",
88
+ "load_vlm_weights": true,
89
+ "add_image_special_tokens": false,
90
+ "attention_mode": "cross_attn",
91
+ "prefix_length": 0,
92
+ "pad_language_to": "max_length",
93
+ "num_expert_layers": 0,
94
+ "num_vlm_layers": 16,
95
+ "self_attn_every_n_layers": 2,
96
+ "expert_width_multiplier": 0.75,
97
+ "min_period": 0.004,
98
+ "max_period": 4.0,
99
+ "rtc_config": null,
100
+ "compile_model": false,
101
+ "compile_mode": "max-autotune"
102
+ }
17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_006000/pretrained_model/gk_config.json ADDED
@@ -0,0 +1,152 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "adapter_names": [
3
+ "default"
4
+ ],
5
+ "algorithm_type": "gk_adp",
6
+ "embedding_layer": -1,
7
+ "epsilon": 1e-06,
8
+ "inference_routing": "top1",
9
+ "inference_temperature": 1.0,
10
+ "inference_top_k": 0,
11
+ "interval_routed_batches": [
12
+ 0
13
+ ],
14
+ "log_expert_statistics": false,
15
+ "modalities": [
16
+ "vision",
17
+ "language"
18
+ ],
19
+ "reset_scheduler_on_expansion": true,
20
+ "routed_batches": [
21
+ 6000
22
+ ],
23
+ "router_statistics_unit": "inputs",
24
+ "router_statistics_version": 2,
25
+ "router_variance_semantics": "seeded_m2_population",
26
+ "sigma_init": 1.0,
27
+ "total_expansions": 1,
28
+ "wandb_history_counts": [
29
+ [
30
+ 200
31
+ ],
32
+ [
33
+ 400
34
+ ],
35
+ [
36
+ 600
37
+ ],
38
+ [
39
+ 800
40
+ ],
41
+ [
42
+ 1000
43
+ ],
44
+ [
45
+ 1200
46
+ ],
47
+ [
48
+ 1400
49
+ ],
50
+ [
51
+ 1600
52
+ ],
53
+ [
54
+ 1800
55
+ ],
56
+ [
57
+ 2000
58
+ ],
59
+ [
60
+ 2200
61
+ ],
62
+ [
63
+ 2400
64
+ ],
65
+ [
66
+ 2600
67
+ ],
68
+ [
69
+ 2800
70
+ ],
71
+ [
72
+ 3000
73
+ ],
74
+ [
75
+ 3200
76
+ ],
77
+ [
78
+ 3400
79
+ ],
80
+ [
81
+ 3600
82
+ ],
83
+ [
84
+ 3800
85
+ ],
86
+ [
87
+ 4000
88
+ ],
89
+ [
90
+ 4200
91
+ ],
92
+ [
93
+ 4400
94
+ ],
95
+ [
96
+ 4600
97
+ ],
98
+ [
99
+ 4800
100
+ ],
101
+ [
102
+ 5000
103
+ ],
104
+ [
105
+ 5200
106
+ ],
107
+ [
108
+ 5400
109
+ ],
110
+ [
111
+ 5600
112
+ ],
113
+ [
114
+ 5800
115
+ ],
116
+ [
117
+ 6000
118
+ ]
119
+ ],
120
+ "wandb_history_steps": [
121
+ 200,
122
+ 400,
123
+ 600,
124
+ 800,
125
+ 1000,
126
+ 1200,
127
+ 1400,
128
+ 1600,
129
+ 1800,
130
+ 2000,
131
+ 2200,
132
+ 2400,
133
+ 2600,
134
+ 2800,
135
+ 3000,
136
+ 3200,
137
+ 3400,
138
+ 3600,
139
+ 3800,
140
+ 4000,
141
+ 4200,
142
+ 4400,
143
+ 4600,
144
+ 4800,
145
+ 5000,
146
+ 5200,
147
+ 5400,
148
+ 5600,
149
+ 5800,
150
+ 6000
151
+ ]
152
+ }
17-36-42_smolvla_gk_adp_real_3e-4/checkpoints/real_task00_006000/pretrained_model/gk_router.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be3b3949d2f43f71b7c3ba45e28b0954748a2a77f278d2830535386507178805
3
+ size 15564