tonyyuyiding commited on
Commit
5131fba
·
verified ·
1 Parent(s): 9e21f76

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. checkpoints/002000/pretrained_model/README.md +204 -0
  2. checkpoints/002000/pretrained_model/adapter_config.json +46 -0
  3. checkpoints/002000/pretrained_model/adapter_model.safetensors +3 -0
  4. checkpoints/002000/pretrained_model/config.json +101 -0
  5. checkpoints/002000/pretrained_model/policy_postprocessor.json +32 -0
  6. checkpoints/002000/pretrained_model/policy_postprocessor_step_0_unnormalizer_processor.safetensors +3 -0
  7. checkpoints/002000/pretrained_model/policy_preprocessor.json +89 -0
  8. checkpoints/002000/pretrained_model/policy_preprocessor_step_5_normalizer_processor.safetensors +3 -0
  9. checkpoints/002000/pretrained_model/train_config.json +250 -0
  10. checkpoints/002000/training_state/optimizer_param_groups.json +697 -0
  11. checkpoints/002000/training_state/optimizer_state.safetensors +3 -0
  12. checkpoints/002000/training_state/rng_state.safetensors +3 -0
  13. checkpoints/002000/training_state/scheduler_state.json +15 -0
  14. checkpoints/002000/training_state/training_step.json +3 -0
  15. checkpoints/004000/pretrained_model/README.md +204 -0
  16. checkpoints/004000/pretrained_model/adapter_config.json +46 -0
  17. checkpoints/004000/pretrained_model/adapter_model.safetensors +3 -0
  18. checkpoints/004000/pretrained_model/config.json +101 -0
  19. checkpoints/004000/pretrained_model/policy_postprocessor.json +32 -0
  20. checkpoints/004000/pretrained_model/policy_postprocessor_step_0_unnormalizer_processor.safetensors +3 -0
  21. checkpoints/004000/pretrained_model/policy_preprocessor.json +89 -0
  22. checkpoints/004000/pretrained_model/policy_preprocessor_step_5_normalizer_processor.safetensors +3 -0
  23. checkpoints/004000/pretrained_model/train_config.json +250 -0
  24. checkpoints/004000/training_state/optimizer_param_groups.json +697 -0
  25. checkpoints/004000/training_state/optimizer_state.safetensors +3 -0
  26. checkpoints/004000/training_state/rng_state.safetensors +3 -0
  27. checkpoints/004000/training_state/scheduler_state.json +15 -0
  28. checkpoints/004000/training_state/training_step.json +3 -0
  29. checkpoints/006000/pretrained_model/README.md +204 -0
  30. checkpoints/006000/pretrained_model/adapter_config.json +46 -0
  31. checkpoints/006000/pretrained_model/adapter_model.safetensors +3 -0
  32. checkpoints/006000/pretrained_model/config.json +101 -0
  33. checkpoints/006000/pretrained_model/policy_postprocessor.json +32 -0
  34. checkpoints/006000/pretrained_model/policy_postprocessor_step_0_unnormalizer_processor.safetensors +3 -0
  35. checkpoints/006000/pretrained_model/policy_preprocessor.json +89 -0
  36. checkpoints/006000/pretrained_model/policy_preprocessor_step_5_normalizer_processor.safetensors +3 -0
  37. checkpoints/006000/pretrained_model/train_config.json +250 -0
  38. checkpoints/006000/training_state/optimizer_param_groups.json +697 -0
  39. checkpoints/006000/training_state/optimizer_state.safetensors +3 -0
  40. checkpoints/006000/training_state/rng_state.safetensors +3 -0
  41. checkpoints/006000/training_state/scheduler_state.json +15 -0
  42. checkpoints/006000/training_state/training_step.json +3 -0
  43. checkpoints/008000/pretrained_model/README.md +204 -0
  44. checkpoints/008000/pretrained_model/adapter_config.json +46 -0
  45. checkpoints/008000/pretrained_model/adapter_model.safetensors +3 -0
  46. checkpoints/008000/pretrained_model/config.json +101 -0
  47. checkpoints/008000/pretrained_model/policy_postprocessor.json +32 -0
  48. checkpoints/008000/pretrained_model/policy_postprocessor_step_0_unnormalizer_processor.safetensors +3 -0
  49. checkpoints/008000/pretrained_model/policy_preprocessor.json +89 -0
  50. checkpoints/008000/pretrained_model/policy_preprocessor_step_5_normalizer_processor.safetensors +3 -0
checkpoints/002000/pretrained_model/README.md ADDED
@@ -0,0 +1,204 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ tags:
4
+ - base_model:adapter:outputs/train/2026-05-19/16-29-49_smolvla/checkpoints/last/pretrained_model
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 0.19.1
checkpoints/002000/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": "outputs/train/2026-05-19/16-29-49_smolvla/checkpoints/last/pretrained_model",
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
+ "layer_replication": null,
19
+ "layers_pattern": null,
20
+ "layers_to_transform": null,
21
+ "loftq_config": {},
22
+ "lora_alpha": 8,
23
+ "lora_bias": false,
24
+ "lora_dropout": 0.0,
25
+ "lora_ga_config": null,
26
+ "megatron_config": null,
27
+ "megatron_core": "megatron.core",
28
+ "modules_to_save": [],
29
+ "peft_type": "LORA",
30
+ "peft_version": "0.19.1",
31
+ "qalora_group_size": 16,
32
+ "r": 64,
33
+ "rank_pattern": {},
34
+ "revision": null,
35
+ "target_modules": [
36
+ "q_proj",
37
+ "v_proj"
38
+ ],
39
+ "target_parameters": null,
40
+ "task_type": null,
41
+ "trainable_token_indices": null,
42
+ "use_bdlora": null,
43
+ "use_dora": false,
44
+ "use_qalora": false,
45
+ "use_rslora": false
46
+ }
checkpoints/002000/pretrained_model/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2342ba3060294c0718b2b2e1050df2cf1122a611542921b0673773531619b6f
3
+ size 32895960
checkpoints/002000/pretrained_model/config.json ADDED
@@ -0,0 +1,101 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true,
48
+ "repo_id": "robot_learning_group47/eval3_test",
49
+ "private": null,
50
+ "tags": null,
51
+ "license": null,
52
+ "pretrained_path": "outputs/train/2026-05-19/16-29-49_smolvla/checkpoints/last/pretrained_model",
53
+ "chunk_size": 50,
54
+ "n_action_steps": 50,
55
+ "normalization_mapping": {
56
+ "VISUAL": "IDENTITY",
57
+ "STATE": "MEAN_STD",
58
+ "ACTION": "MEAN_STD"
59
+ },
60
+ "max_state_dim": 32,
61
+ "max_action_dim": 32,
62
+ "resize_imgs_with_padding": [
63
+ 512,
64
+ 512
65
+ ],
66
+ "empty_cameras": 0,
67
+ "adapt_to_pi_aloha": false,
68
+ "use_delta_joint_actions_aloha": false,
69
+ "tokenizer_max_length": 48,
70
+ "num_steps": 10,
71
+ "use_cache": true,
72
+ "freeze_vision_encoder": true,
73
+ "train_expert_only": true,
74
+ "train_state_proj": true,
75
+ "optimizer_lr": 0.0001,
76
+ "optimizer_betas": [
77
+ 0.9,
78
+ 0.95
79
+ ],
80
+ "optimizer_eps": 1e-08,
81
+ "optimizer_weight_decay": 1e-10,
82
+ "optimizer_grad_clip_norm": 10.0,
83
+ "scheduler_warmup_steps": 1000,
84
+ "scheduler_decay_steps": 30000,
85
+ "scheduler_decay_lr": 2.5e-06,
86
+ "vlm_model_name": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct",
87
+ "load_vlm_weights": true,
88
+ "add_image_special_tokens": false,
89
+ "attention_mode": "cross_attn",
90
+ "prefix_length": 0,
91
+ "pad_language_to": "max_length",
92
+ "num_expert_layers": 0,
93
+ "num_vlm_layers": 16,
94
+ "self_attn_every_n_layers": 2,
95
+ "expert_width_multiplier": 0.75,
96
+ "min_period": 0.004,
97
+ "max_period": 4.0,
98
+ "rtc_config": null,
99
+ "compile_model": false,
100
+ "compile_mode": "max-autotune"
101
+ }
checkpoints/002000/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
+ }
checkpoints/002000/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 sha256:95b1027d071458ea98ce5cad20f02497ee126ffb777eaba0854f405c81181c94
3
+ size 6560
checkpoints/002000/pretrained_model/policy_preprocessor.json ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct"
29
+ }
30
+ },
31
+ {
32
+ "registry_name": "device_processor",
33
+ "config": {
34
+ "device": "cuda",
35
+ "float_dtype": null
36
+ }
37
+ },
38
+ {
39
+ "registry_name": "normalizer_processor",
40
+ "config": {
41
+ "eps": 1e-08,
42
+ "features": {
43
+ "observation.state": {
44
+ "type": "STATE",
45
+ "shape": [
46
+ 6
47
+ ]
48
+ },
49
+ "observation.images.camera1": {
50
+ "type": "VISUAL",
51
+ "shape": [
52
+ 3,
53
+ 256,
54
+ 256
55
+ ]
56
+ },
57
+ "observation.images.camera2": {
58
+ "type": "VISUAL",
59
+ "shape": [
60
+ 3,
61
+ 256,
62
+ 256
63
+ ]
64
+ },
65
+ "observation.images.camera3": {
66
+ "type": "VISUAL",
67
+ "shape": [
68
+ 3,
69
+ 256,
70
+ 256
71
+ ]
72
+ },
73
+ "action": {
74
+ "type": "ACTION",
75
+ "shape": [
76
+ 6
77
+ ]
78
+ }
79
+ },
80
+ "norm_map": {
81
+ "VISUAL": "IDENTITY",
82
+ "STATE": "MEAN_STD",
83
+ "ACTION": "MEAN_STD"
84
+ }
85
+ },
86
+ "state_file": "policy_preprocessor_step_5_normalizer_processor.safetensors"
87
+ }
88
+ ]
89
+ }
checkpoints/002000/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 sha256:95b1027d071458ea98ce5cad20f02497ee126ffb777eaba0854f405c81181c94
3
+ size 6560
checkpoints/002000/pretrained_model/train_config.json ADDED
@@ -0,0 +1,250 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "robot-learning-group47/eval3_toy_video",
4
+ "root": "./data/eval3_toy_video",
5
+ "episodes": null,
6
+ "image_transforms": {
7
+ "enable": false,
8
+ "max_num_transforms": 3,
9
+ "random_order": false,
10
+ "tfs": {
11
+ "brightness": {
12
+ "weight": 1.0,
13
+ "type": "ColorJitter",
14
+ "kwargs": {
15
+ "brightness": [
16
+ 0.8,
17
+ 1.2
18
+ ]
19
+ }
20
+ },
21
+ "contrast": {
22
+ "weight": 1.0,
23
+ "type": "ColorJitter",
24
+ "kwargs": {
25
+ "contrast": [
26
+ 0.8,
27
+ 1.2
28
+ ]
29
+ }
30
+ },
31
+ "saturation": {
32
+ "weight": 1.0,
33
+ "type": "ColorJitter",
34
+ "kwargs": {
35
+ "saturation": [
36
+ 0.5,
37
+ 1.5
38
+ ]
39
+ }
40
+ },
41
+ "hue": {
42
+ "weight": 1.0,
43
+ "type": "ColorJitter",
44
+ "kwargs": {
45
+ "hue": [
46
+ -0.05,
47
+ 0.05
48
+ ]
49
+ }
50
+ },
51
+ "sharpness": {
52
+ "weight": 1.0,
53
+ "type": "SharpnessJitter",
54
+ "kwargs": {
55
+ "sharpness": [
56
+ 0.5,
57
+ 1.5
58
+ ]
59
+ }
60
+ },
61
+ "affine": {
62
+ "weight": 1.0,
63
+ "type": "RandomAffine",
64
+ "kwargs": {
65
+ "degrees": [
66
+ -5.0,
67
+ 5.0
68
+ ],
69
+ "translate": [
70
+ 0.05,
71
+ 0.05
72
+ ]
73
+ }
74
+ }
75
+ }
76
+ },
77
+ "revision": null,
78
+ "use_imagenet_stats": true,
79
+ "video_backend": "torchcodec",
80
+ "streaming": false
81
+ },
82
+ "env": null,
83
+ "policy": {
84
+ "type": "smolvla",
85
+ "n_obs_steps": 1,
86
+ "input_features": {
87
+ "observation.state": {
88
+ "type": "STATE",
89
+ "shape": [
90
+ 6
91
+ ]
92
+ },
93
+ "observation.images.camera1": {
94
+ "type": "VISUAL",
95
+ "shape": [
96
+ 3,
97
+ 256,
98
+ 256
99
+ ]
100
+ },
101
+ "observation.images.camera2": {
102
+ "type": "VISUAL",
103
+ "shape": [
104
+ 3,
105
+ 256,
106
+ 256
107
+ ]
108
+ },
109
+ "observation.images.camera3": {
110
+ "type": "VISUAL",
111
+ "shape": [
112
+ 3,
113
+ 256,
114
+ 256
115
+ ]
116
+ }
117
+ },
118
+ "output_features": {
119
+ "action": {
120
+ "type": "ACTION",
121
+ "shape": [
122
+ 6
123
+ ]
124
+ }
125
+ },
126
+ "device": "cuda",
127
+ "use_amp": false,
128
+ "use_peft": true,
129
+ "push_to_hub": true,
130
+ "repo_id": "robot_learning_group47/eval3_test",
131
+ "private": null,
132
+ "tags": null,
133
+ "license": null,
134
+ "pretrained_path": "outputs/train/2026-05-19/16-29-49_smolvla/checkpoints/last/pretrained_model",
135
+ "chunk_size": 50,
136
+ "n_action_steps": 50,
137
+ "normalization_mapping": {
138
+ "VISUAL": "IDENTITY",
139
+ "STATE": "MEAN_STD",
140
+ "ACTION": "MEAN_STD"
141
+ },
142
+ "max_state_dim": 32,
143
+ "max_action_dim": 32,
144
+ "resize_imgs_with_padding": [
145
+ 512,
146
+ 512
147
+ ],
148
+ "empty_cameras": 0,
149
+ "adapt_to_pi_aloha": false,
150
+ "use_delta_joint_actions_aloha": false,
151
+ "tokenizer_max_length": 48,
152
+ "num_steps": 10,
153
+ "use_cache": true,
154
+ "freeze_vision_encoder": true,
155
+ "train_expert_only": true,
156
+ "train_state_proj": true,
157
+ "optimizer_lr": 0.0001,
158
+ "optimizer_betas": [
159
+ 0.9,
160
+ 0.95
161
+ ],
162
+ "optimizer_eps": 1e-08,
163
+ "optimizer_weight_decay": 1e-10,
164
+ "optimizer_grad_clip_norm": 10.0,
165
+ "scheduler_warmup_steps": 1000,
166
+ "scheduler_decay_steps": 30000,
167
+ "scheduler_decay_lr": 2.5e-06,
168
+ "vlm_model_name": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct",
169
+ "load_vlm_weights": true,
170
+ "add_image_special_tokens": false,
171
+ "attention_mode": "cross_attn",
172
+ "prefix_length": 0,
173
+ "pad_language_to": "max_length",
174
+ "num_expert_layers": 0,
175
+ "num_vlm_layers": 16,
176
+ "self_attn_every_n_layers": 2,
177
+ "expert_width_multiplier": 0.75,
178
+ "min_period": 0.004,
179
+ "max_period": 4.0,
180
+ "rtc_config": null,
181
+ "compile_model": false,
182
+ "compile_mode": "max-autotune"
183
+ },
184
+ "output_dir": "outputs/train/2026-05-19/17-12-35_smolvla",
185
+ "job_name": "smolvla",
186
+ "resume": false,
187
+ "seed": 1000,
188
+ "cudnn_deterministic": false,
189
+ "num_workers": 4,
190
+ "batch_size": 32,
191
+ "steps": 30000,
192
+ "eval_freq": 20000,
193
+ "log_freq": 200,
194
+ "tolerance_s": 0.0001,
195
+ "save_checkpoint": true,
196
+ "save_freq": 2000,
197
+ "use_policy_training_preset": true,
198
+ "optimizer": {
199
+ "type": "adamw",
200
+ "lr": 0.0001,
201
+ "weight_decay": 1e-10,
202
+ "grad_clip_norm": 10.0,
203
+ "betas": [
204
+ 0.9,
205
+ 0.95
206
+ ],
207
+ "eps": 1e-08
208
+ },
209
+ "scheduler": {
210
+ "type": "cosine_decay_with_warmup",
211
+ "num_warmup_steps": 1000,
212
+ "num_decay_steps": 30000,
213
+ "peak_lr": 0.0001,
214
+ "decay_lr": 2.5e-06
215
+ },
216
+ "eval": {
217
+ "n_episodes": 50,
218
+ "batch_size": 50,
219
+ "use_async_envs": false
220
+ },
221
+ "wandb": {
222
+ "enable": false,
223
+ "disable_artifact": false,
224
+ "project": "lerobot",
225
+ "entity": null,
226
+ "notes": null,
227
+ "run_id": null,
228
+ "mode": null,
229
+ "add_tags": true
230
+ },
231
+ "peft": {
232
+ "target_modules": [
233
+ "q_proj",
234
+ "v_proj"
235
+ ],
236
+ "full_training_modules": null,
237
+ "method_type": "LORA",
238
+ "init_type": null,
239
+ "r": 64
240
+ },
241
+ "use_rabc": false,
242
+ "rabc_progress_path": null,
243
+ "rabc_kappa": 0.01,
244
+ "rabc_epsilon": 1e-06,
245
+ "rabc_head_mode": "sparse",
246
+ "rename_map": {
247
+ "observation.images.front": "observation.images.camera1"
248
+ },
249
+ "checkpoint_path": null
250
+ }
checkpoints/002000/training_state/optimizer_param_groups.json ADDED
@@ -0,0 +1,697 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "lr": 9.893469553577303e-05,
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": 0.0001,
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
+ 572,
592
+ 573,
593
+ 574,
594
+ 575,
595
+ 576,
596
+ 577,
597
+ 578,
598
+ 579,
599
+ 580,
600
+ 581,
601
+ 582,
602
+ 583,
603
+ 584,
604
+ 585,
605
+ 586,
606
+ 587,
607
+ 588,
608
+ 589,
609
+ 590,
610
+ 591,
611
+ 592,
612
+ 593,
613
+ 594,
614
+ 595,
615
+ 596,
616
+ 597,
617
+ 598,
618
+ 599,
619
+ 600,
620
+ 601,
621
+ 602,
622
+ 603,
623
+ 604,
624
+ 605,
625
+ 606,
626
+ 607,
627
+ 608,
628
+ 609,
629
+ 610,
630
+ 611,
631
+ 612,
632
+ 613,
633
+ 614,
634
+ 615,
635
+ 616,
636
+ 617,
637
+ 618,
638
+ 619,
639
+ 620,
640
+ 621,
641
+ 622,
642
+ 623,
643
+ 624,
644
+ 625,
645
+ 626,
646
+ 627,
647
+ 628,
648
+ 629,
649
+ 630,
650
+ 631,
651
+ 632,
652
+ 633,
653
+ 634,
654
+ 635,
655
+ 636,
656
+ 637,
657
+ 638,
658
+ 639,
659
+ 640,
660
+ 641,
661
+ 642,
662
+ 643,
663
+ 644,
664
+ 645,
665
+ 646,
666
+ 647,
667
+ 648,
668
+ 649,
669
+ 650,
670
+ 651,
671
+ 652,
672
+ 653,
673
+ 654,
674
+ 655,
675
+ 656,
676
+ 657,
677
+ 658,
678
+ 659,
679
+ 660,
680
+ 661,
681
+ 662,
682
+ 663,
683
+ 664,
684
+ 665,
685
+ 666,
686
+ 667,
687
+ 668,
688
+ 669,
689
+ 670,
690
+ 671,
691
+ 672,
692
+ 673,
693
+ 674,
694
+ 675
695
+ ]
696
+ }
697
+ ]
checkpoints/002000/training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32f1b5e9d7c04682a908c709217ef5fc4b7c03776859b0975af8fc2e8858d0f8
3
+ size 64794928
checkpoints/002000/training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f0dbf1afbf99f75bc960c5734cd621f966263c389cb625edcafa4c0dc2786d4
3
+ size 15708
checkpoints/002000/training_state/scheduler_state.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_lrs": [
3
+ 0.0001
4
+ ],
5
+ "last_epoch": 2000,
6
+ "_step_count": 2001,
7
+ "_is_initial": false,
8
+ "_get_lr_called_within_step": false,
9
+ "_last_lr": [
10
+ 9.893469553577303e-05
11
+ ],
12
+ "lr_lambdas": [
13
+ null
14
+ ]
15
+ }
checkpoints/002000/training_state/training_step.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "step": 2000
3
+ }
checkpoints/004000/pretrained_model/README.md ADDED
@@ -0,0 +1,204 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ tags:
4
+ - base_model:adapter:outputs/train/2026-05-19/16-29-49_smolvla/checkpoints/last/pretrained_model
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 0.19.1
checkpoints/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": "outputs/train/2026-05-19/16-29-49_smolvla/checkpoints/last/pretrained_model",
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
+ "layer_replication": null,
19
+ "layers_pattern": null,
20
+ "layers_to_transform": null,
21
+ "loftq_config": {},
22
+ "lora_alpha": 8,
23
+ "lora_bias": false,
24
+ "lora_dropout": 0.0,
25
+ "lora_ga_config": null,
26
+ "megatron_config": null,
27
+ "megatron_core": "megatron.core",
28
+ "modules_to_save": [],
29
+ "peft_type": "LORA",
30
+ "peft_version": "0.19.1",
31
+ "qalora_group_size": 16,
32
+ "r": 64,
33
+ "rank_pattern": {},
34
+ "revision": null,
35
+ "target_modules": [
36
+ "q_proj",
37
+ "v_proj"
38
+ ],
39
+ "target_parameters": null,
40
+ "task_type": null,
41
+ "trainable_token_indices": null,
42
+ "use_bdlora": null,
43
+ "use_dora": false,
44
+ "use_qalora": false,
45
+ "use_rslora": false
46
+ }
checkpoints/004000/pretrained_model/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff87eb4fc46261ac1d53d5bf774d2f1e914dc6bbec4fd0a4840e05b2f9c9e137
3
+ size 32895960
checkpoints/004000/pretrained_model/config.json ADDED
@@ -0,0 +1,101 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true,
48
+ "repo_id": "robot_learning_group47/eval3_test",
49
+ "private": null,
50
+ "tags": null,
51
+ "license": null,
52
+ "pretrained_path": "outputs/train/2026-05-19/16-29-49_smolvla/checkpoints/last/pretrained_model",
53
+ "chunk_size": 50,
54
+ "n_action_steps": 50,
55
+ "normalization_mapping": {
56
+ "VISUAL": "IDENTITY",
57
+ "STATE": "MEAN_STD",
58
+ "ACTION": "MEAN_STD"
59
+ },
60
+ "max_state_dim": 32,
61
+ "max_action_dim": 32,
62
+ "resize_imgs_with_padding": [
63
+ 512,
64
+ 512
65
+ ],
66
+ "empty_cameras": 0,
67
+ "adapt_to_pi_aloha": false,
68
+ "use_delta_joint_actions_aloha": false,
69
+ "tokenizer_max_length": 48,
70
+ "num_steps": 10,
71
+ "use_cache": true,
72
+ "freeze_vision_encoder": true,
73
+ "train_expert_only": true,
74
+ "train_state_proj": true,
75
+ "optimizer_lr": 0.0001,
76
+ "optimizer_betas": [
77
+ 0.9,
78
+ 0.95
79
+ ],
80
+ "optimizer_eps": 1e-08,
81
+ "optimizer_weight_decay": 1e-10,
82
+ "optimizer_grad_clip_norm": 10.0,
83
+ "scheduler_warmup_steps": 1000,
84
+ "scheduler_decay_steps": 30000,
85
+ "scheduler_decay_lr": 2.5e-06,
86
+ "vlm_model_name": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct",
87
+ "load_vlm_weights": true,
88
+ "add_image_special_tokens": false,
89
+ "attention_mode": "cross_attn",
90
+ "prefix_length": 0,
91
+ "pad_language_to": "max_length",
92
+ "num_expert_layers": 0,
93
+ "num_vlm_layers": 16,
94
+ "self_attn_every_n_layers": 2,
95
+ "expert_width_multiplier": 0.75,
96
+ "min_period": 0.004,
97
+ "max_period": 4.0,
98
+ "rtc_config": null,
99
+ "compile_model": false,
100
+ "compile_mode": "max-autotune"
101
+ }
checkpoints/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
+ }
checkpoints/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 sha256:95b1027d071458ea98ce5cad20f02497ee126ffb777eaba0854f405c81181c94
3
+ size 6560
checkpoints/004000/pretrained_model/policy_preprocessor.json ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct"
29
+ }
30
+ },
31
+ {
32
+ "registry_name": "device_processor",
33
+ "config": {
34
+ "device": "cuda",
35
+ "float_dtype": null
36
+ }
37
+ },
38
+ {
39
+ "registry_name": "normalizer_processor",
40
+ "config": {
41
+ "eps": 1e-08,
42
+ "features": {
43
+ "observation.state": {
44
+ "type": "STATE",
45
+ "shape": [
46
+ 6
47
+ ]
48
+ },
49
+ "observation.images.camera1": {
50
+ "type": "VISUAL",
51
+ "shape": [
52
+ 3,
53
+ 256,
54
+ 256
55
+ ]
56
+ },
57
+ "observation.images.camera2": {
58
+ "type": "VISUAL",
59
+ "shape": [
60
+ 3,
61
+ 256,
62
+ 256
63
+ ]
64
+ },
65
+ "observation.images.camera3": {
66
+ "type": "VISUAL",
67
+ "shape": [
68
+ 3,
69
+ 256,
70
+ 256
71
+ ]
72
+ },
73
+ "action": {
74
+ "type": "ACTION",
75
+ "shape": [
76
+ 6
77
+ ]
78
+ }
79
+ },
80
+ "norm_map": {
81
+ "VISUAL": "IDENTITY",
82
+ "STATE": "MEAN_STD",
83
+ "ACTION": "MEAN_STD"
84
+ }
85
+ },
86
+ "state_file": "policy_preprocessor_step_5_normalizer_processor.safetensors"
87
+ }
88
+ ]
89
+ }
checkpoints/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 sha256:95b1027d071458ea98ce5cad20f02497ee126ffb777eaba0854f405c81181c94
3
+ size 6560
checkpoints/004000/pretrained_model/train_config.json ADDED
@@ -0,0 +1,250 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "robot-learning-group47/eval3_toy_video",
4
+ "root": "./data/eval3_toy_video",
5
+ "episodes": null,
6
+ "image_transforms": {
7
+ "enable": false,
8
+ "max_num_transforms": 3,
9
+ "random_order": false,
10
+ "tfs": {
11
+ "brightness": {
12
+ "weight": 1.0,
13
+ "type": "ColorJitter",
14
+ "kwargs": {
15
+ "brightness": [
16
+ 0.8,
17
+ 1.2
18
+ ]
19
+ }
20
+ },
21
+ "contrast": {
22
+ "weight": 1.0,
23
+ "type": "ColorJitter",
24
+ "kwargs": {
25
+ "contrast": [
26
+ 0.8,
27
+ 1.2
28
+ ]
29
+ }
30
+ },
31
+ "saturation": {
32
+ "weight": 1.0,
33
+ "type": "ColorJitter",
34
+ "kwargs": {
35
+ "saturation": [
36
+ 0.5,
37
+ 1.5
38
+ ]
39
+ }
40
+ },
41
+ "hue": {
42
+ "weight": 1.0,
43
+ "type": "ColorJitter",
44
+ "kwargs": {
45
+ "hue": [
46
+ -0.05,
47
+ 0.05
48
+ ]
49
+ }
50
+ },
51
+ "sharpness": {
52
+ "weight": 1.0,
53
+ "type": "SharpnessJitter",
54
+ "kwargs": {
55
+ "sharpness": [
56
+ 0.5,
57
+ 1.5
58
+ ]
59
+ }
60
+ },
61
+ "affine": {
62
+ "weight": 1.0,
63
+ "type": "RandomAffine",
64
+ "kwargs": {
65
+ "degrees": [
66
+ -5.0,
67
+ 5.0
68
+ ],
69
+ "translate": [
70
+ 0.05,
71
+ 0.05
72
+ ]
73
+ }
74
+ }
75
+ }
76
+ },
77
+ "revision": null,
78
+ "use_imagenet_stats": true,
79
+ "video_backend": "torchcodec",
80
+ "streaming": false
81
+ },
82
+ "env": null,
83
+ "policy": {
84
+ "type": "smolvla",
85
+ "n_obs_steps": 1,
86
+ "input_features": {
87
+ "observation.state": {
88
+ "type": "STATE",
89
+ "shape": [
90
+ 6
91
+ ]
92
+ },
93
+ "observation.images.camera1": {
94
+ "type": "VISUAL",
95
+ "shape": [
96
+ 3,
97
+ 256,
98
+ 256
99
+ ]
100
+ },
101
+ "observation.images.camera2": {
102
+ "type": "VISUAL",
103
+ "shape": [
104
+ 3,
105
+ 256,
106
+ 256
107
+ ]
108
+ },
109
+ "observation.images.camera3": {
110
+ "type": "VISUAL",
111
+ "shape": [
112
+ 3,
113
+ 256,
114
+ 256
115
+ ]
116
+ }
117
+ },
118
+ "output_features": {
119
+ "action": {
120
+ "type": "ACTION",
121
+ "shape": [
122
+ 6
123
+ ]
124
+ }
125
+ },
126
+ "device": "cuda",
127
+ "use_amp": false,
128
+ "use_peft": true,
129
+ "push_to_hub": true,
130
+ "repo_id": "robot_learning_group47/eval3_test",
131
+ "private": null,
132
+ "tags": null,
133
+ "license": null,
134
+ "pretrained_path": "outputs/train/2026-05-19/16-29-49_smolvla/checkpoints/last/pretrained_model",
135
+ "chunk_size": 50,
136
+ "n_action_steps": 50,
137
+ "normalization_mapping": {
138
+ "VISUAL": "IDENTITY",
139
+ "STATE": "MEAN_STD",
140
+ "ACTION": "MEAN_STD"
141
+ },
142
+ "max_state_dim": 32,
143
+ "max_action_dim": 32,
144
+ "resize_imgs_with_padding": [
145
+ 512,
146
+ 512
147
+ ],
148
+ "empty_cameras": 0,
149
+ "adapt_to_pi_aloha": false,
150
+ "use_delta_joint_actions_aloha": false,
151
+ "tokenizer_max_length": 48,
152
+ "num_steps": 10,
153
+ "use_cache": true,
154
+ "freeze_vision_encoder": true,
155
+ "train_expert_only": true,
156
+ "train_state_proj": true,
157
+ "optimizer_lr": 0.0001,
158
+ "optimizer_betas": [
159
+ 0.9,
160
+ 0.95
161
+ ],
162
+ "optimizer_eps": 1e-08,
163
+ "optimizer_weight_decay": 1e-10,
164
+ "optimizer_grad_clip_norm": 10.0,
165
+ "scheduler_warmup_steps": 1000,
166
+ "scheduler_decay_steps": 30000,
167
+ "scheduler_decay_lr": 2.5e-06,
168
+ "vlm_model_name": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct",
169
+ "load_vlm_weights": true,
170
+ "add_image_special_tokens": false,
171
+ "attention_mode": "cross_attn",
172
+ "prefix_length": 0,
173
+ "pad_language_to": "max_length",
174
+ "num_expert_layers": 0,
175
+ "num_vlm_layers": 16,
176
+ "self_attn_every_n_layers": 2,
177
+ "expert_width_multiplier": 0.75,
178
+ "min_period": 0.004,
179
+ "max_period": 4.0,
180
+ "rtc_config": null,
181
+ "compile_model": false,
182
+ "compile_mode": "max-autotune"
183
+ },
184
+ "output_dir": "outputs/train/2026-05-19/17-12-35_smolvla",
185
+ "job_name": "smolvla",
186
+ "resume": false,
187
+ "seed": 1000,
188
+ "cudnn_deterministic": false,
189
+ "num_workers": 4,
190
+ "batch_size": 32,
191
+ "steps": 30000,
192
+ "eval_freq": 20000,
193
+ "log_freq": 200,
194
+ "tolerance_s": 0.0001,
195
+ "save_checkpoint": true,
196
+ "save_freq": 2000,
197
+ "use_policy_training_preset": true,
198
+ "optimizer": {
199
+ "type": "adamw",
200
+ "lr": 0.0001,
201
+ "weight_decay": 1e-10,
202
+ "grad_clip_norm": 10.0,
203
+ "betas": [
204
+ 0.9,
205
+ 0.95
206
+ ],
207
+ "eps": 1e-08
208
+ },
209
+ "scheduler": {
210
+ "type": "cosine_decay_with_warmup",
211
+ "num_warmup_steps": 1000,
212
+ "num_decay_steps": 30000,
213
+ "peak_lr": 0.0001,
214
+ "decay_lr": 2.5e-06
215
+ },
216
+ "eval": {
217
+ "n_episodes": 50,
218
+ "batch_size": 50,
219
+ "use_async_envs": false
220
+ },
221
+ "wandb": {
222
+ "enable": false,
223
+ "disable_artifact": false,
224
+ "project": "lerobot",
225
+ "entity": null,
226
+ "notes": null,
227
+ "run_id": null,
228
+ "mode": null,
229
+ "add_tags": true
230
+ },
231
+ "peft": {
232
+ "target_modules": [
233
+ "q_proj",
234
+ "v_proj"
235
+ ],
236
+ "full_training_modules": null,
237
+ "method_type": "LORA",
238
+ "init_type": null,
239
+ "r": 64
240
+ },
241
+ "use_rabc": false,
242
+ "rabc_progress_path": null,
243
+ "rabc_kappa": 0.01,
244
+ "rabc_epsilon": 1e-06,
245
+ "rabc_head_mode": "sparse",
246
+ "rename_map": {
247
+ "observation.images.front": "observation.images.camera1"
248
+ },
249
+ "checkpoint_path": null
250
+ }
checkpoints/004000/training_state/optimizer_param_groups.json ADDED
@@ -0,0 +1,697 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "lr": 9.578534106007679e-05,
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": 0.0001,
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
+ 572,
592
+ 573,
593
+ 574,
594
+ 575,
595
+ 576,
596
+ 577,
597
+ 578,
598
+ 579,
599
+ 580,
600
+ 581,
601
+ 582,
602
+ 583,
603
+ 584,
604
+ 585,
605
+ 586,
606
+ 587,
607
+ 588,
608
+ 589,
609
+ 590,
610
+ 591,
611
+ 592,
612
+ 593,
613
+ 594,
614
+ 595,
615
+ 596,
616
+ 597,
617
+ 598,
618
+ 599,
619
+ 600,
620
+ 601,
621
+ 602,
622
+ 603,
623
+ 604,
624
+ 605,
625
+ 606,
626
+ 607,
627
+ 608,
628
+ 609,
629
+ 610,
630
+ 611,
631
+ 612,
632
+ 613,
633
+ 614,
634
+ 615,
635
+ 616,
636
+ 617,
637
+ 618,
638
+ 619,
639
+ 620,
640
+ 621,
641
+ 622,
642
+ 623,
643
+ 624,
644
+ 625,
645
+ 626,
646
+ 627,
647
+ 628,
648
+ 629,
649
+ 630,
650
+ 631,
651
+ 632,
652
+ 633,
653
+ 634,
654
+ 635,
655
+ 636,
656
+ 637,
657
+ 638,
658
+ 639,
659
+ 640,
660
+ 641,
661
+ 642,
662
+ 643,
663
+ 644,
664
+ 645,
665
+ 646,
666
+ 647,
667
+ 648,
668
+ 649,
669
+ 650,
670
+ 651,
671
+ 652,
672
+ 653,
673
+ 654,
674
+ 655,
675
+ 656,
676
+ 657,
677
+ 658,
678
+ 659,
679
+ 660,
680
+ 661,
681
+ 662,
682
+ 663,
683
+ 664,
684
+ 665,
685
+ 666,
686
+ 667,
687
+ 668,
688
+ 669,
689
+ 670,
690
+ 671,
691
+ 672,
692
+ 673,
693
+ 674,
694
+ 675
695
+ ]
696
+ }
697
+ ]
checkpoints/004000/training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a26ffcba2c886845de2e9272edb66f627bb589bf6140a94140ae53cb92dc8ae8
3
+ size 64794928
checkpoints/004000/training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:529ef0c04ddf7db3007558121ff090200139ef9018571bf3ff4de5d1a486ef97
3
+ size 15708
checkpoints/004000/training_state/scheduler_state.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_lrs": [
3
+ 0.0001
4
+ ],
5
+ "last_epoch": 4000,
6
+ "_step_count": 4001,
7
+ "_is_initial": false,
8
+ "_get_lr_called_within_step": false,
9
+ "_last_lr": [
10
+ 9.578534106007679e-05
11
+ ],
12
+ "lr_lambdas": [
13
+ null
14
+ ]
15
+ }
checkpoints/004000/training_state/training_step.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "step": 4000
3
+ }
checkpoints/006000/pretrained_model/README.md ADDED
@@ -0,0 +1,204 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ tags:
4
+ - base_model:adapter:outputs/train/2026-05-19/16-29-49_smolvla/checkpoints/last/pretrained_model
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 0.19.1
checkpoints/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": "outputs/train/2026-05-19/16-29-49_smolvla/checkpoints/last/pretrained_model",
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
+ "layer_replication": null,
19
+ "layers_pattern": null,
20
+ "layers_to_transform": null,
21
+ "loftq_config": {},
22
+ "lora_alpha": 8,
23
+ "lora_bias": false,
24
+ "lora_dropout": 0.0,
25
+ "lora_ga_config": null,
26
+ "megatron_config": null,
27
+ "megatron_core": "megatron.core",
28
+ "modules_to_save": [],
29
+ "peft_type": "LORA",
30
+ "peft_version": "0.19.1",
31
+ "qalora_group_size": 16,
32
+ "r": 64,
33
+ "rank_pattern": {},
34
+ "revision": null,
35
+ "target_modules": [
36
+ "q_proj",
37
+ "v_proj"
38
+ ],
39
+ "target_parameters": null,
40
+ "task_type": null,
41
+ "trainable_token_indices": null,
42
+ "use_bdlora": null,
43
+ "use_dora": false,
44
+ "use_qalora": false,
45
+ "use_rslora": false
46
+ }
checkpoints/006000/pretrained_model/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8651d68801e678b37ad3a40a1916c6010b17541916526f6ea5e3698d2474101b
3
+ size 32895960
checkpoints/006000/pretrained_model/config.json ADDED
@@ -0,0 +1,101 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true,
48
+ "repo_id": "robot_learning_group47/eval3_test",
49
+ "private": null,
50
+ "tags": null,
51
+ "license": null,
52
+ "pretrained_path": "outputs/train/2026-05-19/16-29-49_smolvla/checkpoints/last/pretrained_model",
53
+ "chunk_size": 50,
54
+ "n_action_steps": 50,
55
+ "normalization_mapping": {
56
+ "VISUAL": "IDENTITY",
57
+ "STATE": "MEAN_STD",
58
+ "ACTION": "MEAN_STD"
59
+ },
60
+ "max_state_dim": 32,
61
+ "max_action_dim": 32,
62
+ "resize_imgs_with_padding": [
63
+ 512,
64
+ 512
65
+ ],
66
+ "empty_cameras": 0,
67
+ "adapt_to_pi_aloha": false,
68
+ "use_delta_joint_actions_aloha": false,
69
+ "tokenizer_max_length": 48,
70
+ "num_steps": 10,
71
+ "use_cache": true,
72
+ "freeze_vision_encoder": true,
73
+ "train_expert_only": true,
74
+ "train_state_proj": true,
75
+ "optimizer_lr": 0.0001,
76
+ "optimizer_betas": [
77
+ 0.9,
78
+ 0.95
79
+ ],
80
+ "optimizer_eps": 1e-08,
81
+ "optimizer_weight_decay": 1e-10,
82
+ "optimizer_grad_clip_norm": 10.0,
83
+ "scheduler_warmup_steps": 1000,
84
+ "scheduler_decay_steps": 30000,
85
+ "scheduler_decay_lr": 2.5e-06,
86
+ "vlm_model_name": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct",
87
+ "load_vlm_weights": true,
88
+ "add_image_special_tokens": false,
89
+ "attention_mode": "cross_attn",
90
+ "prefix_length": 0,
91
+ "pad_language_to": "max_length",
92
+ "num_expert_layers": 0,
93
+ "num_vlm_layers": 16,
94
+ "self_attn_every_n_layers": 2,
95
+ "expert_width_multiplier": 0.75,
96
+ "min_period": 0.004,
97
+ "max_period": 4.0,
98
+ "rtc_config": null,
99
+ "compile_model": false,
100
+ "compile_mode": "max-autotune"
101
+ }
checkpoints/006000/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
+ }
checkpoints/006000/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 sha256:95b1027d071458ea98ce5cad20f02497ee126ffb777eaba0854f405c81181c94
3
+ size 6560
checkpoints/006000/pretrained_model/policy_preprocessor.json ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct"
29
+ }
30
+ },
31
+ {
32
+ "registry_name": "device_processor",
33
+ "config": {
34
+ "device": "cuda",
35
+ "float_dtype": null
36
+ }
37
+ },
38
+ {
39
+ "registry_name": "normalizer_processor",
40
+ "config": {
41
+ "eps": 1e-08,
42
+ "features": {
43
+ "observation.state": {
44
+ "type": "STATE",
45
+ "shape": [
46
+ 6
47
+ ]
48
+ },
49
+ "observation.images.camera1": {
50
+ "type": "VISUAL",
51
+ "shape": [
52
+ 3,
53
+ 256,
54
+ 256
55
+ ]
56
+ },
57
+ "observation.images.camera2": {
58
+ "type": "VISUAL",
59
+ "shape": [
60
+ 3,
61
+ 256,
62
+ 256
63
+ ]
64
+ },
65
+ "observation.images.camera3": {
66
+ "type": "VISUAL",
67
+ "shape": [
68
+ 3,
69
+ 256,
70
+ 256
71
+ ]
72
+ },
73
+ "action": {
74
+ "type": "ACTION",
75
+ "shape": [
76
+ 6
77
+ ]
78
+ }
79
+ },
80
+ "norm_map": {
81
+ "VISUAL": "IDENTITY",
82
+ "STATE": "MEAN_STD",
83
+ "ACTION": "MEAN_STD"
84
+ }
85
+ },
86
+ "state_file": "policy_preprocessor_step_5_normalizer_processor.safetensors"
87
+ }
88
+ ]
89
+ }
checkpoints/006000/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 sha256:95b1027d071458ea98ce5cad20f02497ee126ffb777eaba0854f405c81181c94
3
+ size 6560
checkpoints/006000/pretrained_model/train_config.json ADDED
@@ -0,0 +1,250 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "robot-learning-group47/eval3_toy_video",
4
+ "root": "./data/eval3_toy_video",
5
+ "episodes": null,
6
+ "image_transforms": {
7
+ "enable": false,
8
+ "max_num_transforms": 3,
9
+ "random_order": false,
10
+ "tfs": {
11
+ "brightness": {
12
+ "weight": 1.0,
13
+ "type": "ColorJitter",
14
+ "kwargs": {
15
+ "brightness": [
16
+ 0.8,
17
+ 1.2
18
+ ]
19
+ }
20
+ },
21
+ "contrast": {
22
+ "weight": 1.0,
23
+ "type": "ColorJitter",
24
+ "kwargs": {
25
+ "contrast": [
26
+ 0.8,
27
+ 1.2
28
+ ]
29
+ }
30
+ },
31
+ "saturation": {
32
+ "weight": 1.0,
33
+ "type": "ColorJitter",
34
+ "kwargs": {
35
+ "saturation": [
36
+ 0.5,
37
+ 1.5
38
+ ]
39
+ }
40
+ },
41
+ "hue": {
42
+ "weight": 1.0,
43
+ "type": "ColorJitter",
44
+ "kwargs": {
45
+ "hue": [
46
+ -0.05,
47
+ 0.05
48
+ ]
49
+ }
50
+ },
51
+ "sharpness": {
52
+ "weight": 1.0,
53
+ "type": "SharpnessJitter",
54
+ "kwargs": {
55
+ "sharpness": [
56
+ 0.5,
57
+ 1.5
58
+ ]
59
+ }
60
+ },
61
+ "affine": {
62
+ "weight": 1.0,
63
+ "type": "RandomAffine",
64
+ "kwargs": {
65
+ "degrees": [
66
+ -5.0,
67
+ 5.0
68
+ ],
69
+ "translate": [
70
+ 0.05,
71
+ 0.05
72
+ ]
73
+ }
74
+ }
75
+ }
76
+ },
77
+ "revision": null,
78
+ "use_imagenet_stats": true,
79
+ "video_backend": "torchcodec",
80
+ "streaming": false
81
+ },
82
+ "env": null,
83
+ "policy": {
84
+ "type": "smolvla",
85
+ "n_obs_steps": 1,
86
+ "input_features": {
87
+ "observation.state": {
88
+ "type": "STATE",
89
+ "shape": [
90
+ 6
91
+ ]
92
+ },
93
+ "observation.images.camera1": {
94
+ "type": "VISUAL",
95
+ "shape": [
96
+ 3,
97
+ 256,
98
+ 256
99
+ ]
100
+ },
101
+ "observation.images.camera2": {
102
+ "type": "VISUAL",
103
+ "shape": [
104
+ 3,
105
+ 256,
106
+ 256
107
+ ]
108
+ },
109
+ "observation.images.camera3": {
110
+ "type": "VISUAL",
111
+ "shape": [
112
+ 3,
113
+ 256,
114
+ 256
115
+ ]
116
+ }
117
+ },
118
+ "output_features": {
119
+ "action": {
120
+ "type": "ACTION",
121
+ "shape": [
122
+ 6
123
+ ]
124
+ }
125
+ },
126
+ "device": "cuda",
127
+ "use_amp": false,
128
+ "use_peft": true,
129
+ "push_to_hub": true,
130
+ "repo_id": "robot_learning_group47/eval3_test",
131
+ "private": null,
132
+ "tags": null,
133
+ "license": null,
134
+ "pretrained_path": "outputs/train/2026-05-19/16-29-49_smolvla/checkpoints/last/pretrained_model",
135
+ "chunk_size": 50,
136
+ "n_action_steps": 50,
137
+ "normalization_mapping": {
138
+ "VISUAL": "IDENTITY",
139
+ "STATE": "MEAN_STD",
140
+ "ACTION": "MEAN_STD"
141
+ },
142
+ "max_state_dim": 32,
143
+ "max_action_dim": 32,
144
+ "resize_imgs_with_padding": [
145
+ 512,
146
+ 512
147
+ ],
148
+ "empty_cameras": 0,
149
+ "adapt_to_pi_aloha": false,
150
+ "use_delta_joint_actions_aloha": false,
151
+ "tokenizer_max_length": 48,
152
+ "num_steps": 10,
153
+ "use_cache": true,
154
+ "freeze_vision_encoder": true,
155
+ "train_expert_only": true,
156
+ "train_state_proj": true,
157
+ "optimizer_lr": 0.0001,
158
+ "optimizer_betas": [
159
+ 0.9,
160
+ 0.95
161
+ ],
162
+ "optimizer_eps": 1e-08,
163
+ "optimizer_weight_decay": 1e-10,
164
+ "optimizer_grad_clip_norm": 10.0,
165
+ "scheduler_warmup_steps": 1000,
166
+ "scheduler_decay_steps": 30000,
167
+ "scheduler_decay_lr": 2.5e-06,
168
+ "vlm_model_name": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct",
169
+ "load_vlm_weights": true,
170
+ "add_image_special_tokens": false,
171
+ "attention_mode": "cross_attn",
172
+ "prefix_length": 0,
173
+ "pad_language_to": "max_length",
174
+ "num_expert_layers": 0,
175
+ "num_vlm_layers": 16,
176
+ "self_attn_every_n_layers": 2,
177
+ "expert_width_multiplier": 0.75,
178
+ "min_period": 0.004,
179
+ "max_period": 4.0,
180
+ "rtc_config": null,
181
+ "compile_model": false,
182
+ "compile_mode": "max-autotune"
183
+ },
184
+ "output_dir": "outputs/train/2026-05-19/17-12-35_smolvla",
185
+ "job_name": "smolvla",
186
+ "resume": false,
187
+ "seed": 1000,
188
+ "cudnn_deterministic": false,
189
+ "num_workers": 4,
190
+ "batch_size": 32,
191
+ "steps": 30000,
192
+ "eval_freq": 20000,
193
+ "log_freq": 200,
194
+ "tolerance_s": 0.0001,
195
+ "save_checkpoint": true,
196
+ "save_freq": 2000,
197
+ "use_policy_training_preset": true,
198
+ "optimizer": {
199
+ "type": "adamw",
200
+ "lr": 0.0001,
201
+ "weight_decay": 1e-10,
202
+ "grad_clip_norm": 10.0,
203
+ "betas": [
204
+ 0.9,
205
+ 0.95
206
+ ],
207
+ "eps": 1e-08
208
+ },
209
+ "scheduler": {
210
+ "type": "cosine_decay_with_warmup",
211
+ "num_warmup_steps": 1000,
212
+ "num_decay_steps": 30000,
213
+ "peak_lr": 0.0001,
214
+ "decay_lr": 2.5e-06
215
+ },
216
+ "eval": {
217
+ "n_episodes": 50,
218
+ "batch_size": 50,
219
+ "use_async_envs": false
220
+ },
221
+ "wandb": {
222
+ "enable": false,
223
+ "disable_artifact": false,
224
+ "project": "lerobot",
225
+ "entity": null,
226
+ "notes": null,
227
+ "run_id": null,
228
+ "mode": null,
229
+ "add_tags": true
230
+ },
231
+ "peft": {
232
+ "target_modules": [
233
+ "q_proj",
234
+ "v_proj"
235
+ ],
236
+ "full_training_modules": null,
237
+ "method_type": "LORA",
238
+ "init_type": null,
239
+ "r": 64
240
+ },
241
+ "use_rabc": false,
242
+ "rabc_progress_path": null,
243
+ "rabc_kappa": 0.01,
244
+ "rabc_epsilon": 1e-06,
245
+ "rabc_head_mode": "sparse",
246
+ "rename_map": {
247
+ "observation.images.front": "observation.images.camera1"
248
+ },
249
+ "checkpoint_path": null
250
+ }
checkpoints/006000/training_state/optimizer_param_groups.json ADDED
@@ -0,0 +1,697 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "lr": 9.06895784757787e-05,
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": 0.0001,
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
+ 572,
592
+ 573,
593
+ 574,
594
+ 575,
595
+ 576,
596
+ 577,
597
+ 578,
598
+ 579,
599
+ 580,
600
+ 581,
601
+ 582,
602
+ 583,
603
+ 584,
604
+ 585,
605
+ 586,
606
+ 587,
607
+ 588,
608
+ 589,
609
+ 590,
610
+ 591,
611
+ 592,
612
+ 593,
613
+ 594,
614
+ 595,
615
+ 596,
616
+ 597,
617
+ 598,
618
+ 599,
619
+ 600,
620
+ 601,
621
+ 602,
622
+ 603,
623
+ 604,
624
+ 605,
625
+ 606,
626
+ 607,
627
+ 608,
628
+ 609,
629
+ 610,
630
+ 611,
631
+ 612,
632
+ 613,
633
+ 614,
634
+ 615,
635
+ 616,
636
+ 617,
637
+ 618,
638
+ 619,
639
+ 620,
640
+ 621,
641
+ 622,
642
+ 623,
643
+ 624,
644
+ 625,
645
+ 626,
646
+ 627,
647
+ 628,
648
+ 629,
649
+ 630,
650
+ 631,
651
+ 632,
652
+ 633,
653
+ 634,
654
+ 635,
655
+ 636,
656
+ 637,
657
+ 638,
658
+ 639,
659
+ 640,
660
+ 641,
661
+ 642,
662
+ 643,
663
+ 644,
664
+ 645,
665
+ 646,
666
+ 647,
667
+ 648,
668
+ 649,
669
+ 650,
670
+ 651,
671
+ 652,
672
+ 653,
673
+ 654,
674
+ 655,
675
+ 656,
676
+ 657,
677
+ 658,
678
+ 659,
679
+ 660,
680
+ 661,
681
+ 662,
682
+ 663,
683
+ 664,
684
+ 665,
685
+ 666,
686
+ 667,
687
+ 668,
688
+ 669,
689
+ 670,
690
+ 671,
691
+ 672,
692
+ 673,
693
+ 674,
694
+ 675
695
+ ]
696
+ }
697
+ ]
checkpoints/006000/training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed399ff0680247088adcd4bbd32bb52119c4bf8579336e31be71a7bd09b6fada
3
+ size 64794928
checkpoints/006000/training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e504b1cadc949107457f41af8ce5fae2e67acf7990a803afcf949b8809ceb7be
3
+ size 15708
checkpoints/006000/training_state/scheduler_state.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_lrs": [
3
+ 0.0001
4
+ ],
5
+ "last_epoch": 6000,
6
+ "_step_count": 6001,
7
+ "_is_initial": false,
8
+ "_get_lr_called_within_step": false,
9
+ "_last_lr": [
10
+ 9.06895784757787e-05
11
+ ],
12
+ "lr_lambdas": [
13
+ null
14
+ ]
15
+ }
checkpoints/006000/training_state/training_step.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "step": 6000
3
+ }
checkpoints/008000/pretrained_model/README.md ADDED
@@ -0,0 +1,204 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ tags:
4
+ - base_model:adapter:outputs/train/2026-05-19/16-29-49_smolvla/checkpoints/last/pretrained_model
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 0.19.1
checkpoints/008000/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": "outputs/train/2026-05-19/16-29-49_smolvla/checkpoints/last/pretrained_model",
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
+ "layer_replication": null,
19
+ "layers_pattern": null,
20
+ "layers_to_transform": null,
21
+ "loftq_config": {},
22
+ "lora_alpha": 8,
23
+ "lora_bias": false,
24
+ "lora_dropout": 0.0,
25
+ "lora_ga_config": null,
26
+ "megatron_config": null,
27
+ "megatron_core": "megatron.core",
28
+ "modules_to_save": [],
29
+ "peft_type": "LORA",
30
+ "peft_version": "0.19.1",
31
+ "qalora_group_size": 16,
32
+ "r": 64,
33
+ "rank_pattern": {},
34
+ "revision": null,
35
+ "target_modules": [
36
+ "q_proj",
37
+ "v_proj"
38
+ ],
39
+ "target_parameters": null,
40
+ "task_type": null,
41
+ "trainable_token_indices": null,
42
+ "use_bdlora": null,
43
+ "use_dora": false,
44
+ "use_qalora": false,
45
+ "use_rslora": false
46
+ }
checkpoints/008000/pretrained_model/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07cf9e77a3abf1e190a1c5063d685b1318616da745e382e897e43e7598f22404
3
+ size 32895960
checkpoints/008000/pretrained_model/config.json ADDED
@@ -0,0 +1,101 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true,
48
+ "repo_id": "robot_learning_group47/eval3_test",
49
+ "private": null,
50
+ "tags": null,
51
+ "license": null,
52
+ "pretrained_path": "outputs/train/2026-05-19/16-29-49_smolvla/checkpoints/last/pretrained_model",
53
+ "chunk_size": 50,
54
+ "n_action_steps": 50,
55
+ "normalization_mapping": {
56
+ "VISUAL": "IDENTITY",
57
+ "STATE": "MEAN_STD",
58
+ "ACTION": "MEAN_STD"
59
+ },
60
+ "max_state_dim": 32,
61
+ "max_action_dim": 32,
62
+ "resize_imgs_with_padding": [
63
+ 512,
64
+ 512
65
+ ],
66
+ "empty_cameras": 0,
67
+ "adapt_to_pi_aloha": false,
68
+ "use_delta_joint_actions_aloha": false,
69
+ "tokenizer_max_length": 48,
70
+ "num_steps": 10,
71
+ "use_cache": true,
72
+ "freeze_vision_encoder": true,
73
+ "train_expert_only": true,
74
+ "train_state_proj": true,
75
+ "optimizer_lr": 0.0001,
76
+ "optimizer_betas": [
77
+ 0.9,
78
+ 0.95
79
+ ],
80
+ "optimizer_eps": 1e-08,
81
+ "optimizer_weight_decay": 1e-10,
82
+ "optimizer_grad_clip_norm": 10.0,
83
+ "scheduler_warmup_steps": 1000,
84
+ "scheduler_decay_steps": 30000,
85
+ "scheduler_decay_lr": 2.5e-06,
86
+ "vlm_model_name": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct",
87
+ "load_vlm_weights": true,
88
+ "add_image_special_tokens": false,
89
+ "attention_mode": "cross_attn",
90
+ "prefix_length": 0,
91
+ "pad_language_to": "max_length",
92
+ "num_expert_layers": 0,
93
+ "num_vlm_layers": 16,
94
+ "self_attn_every_n_layers": 2,
95
+ "expert_width_multiplier": 0.75,
96
+ "min_period": 0.004,
97
+ "max_period": 4.0,
98
+ "rtc_config": null,
99
+ "compile_model": false,
100
+ "compile_mode": "max-autotune"
101
+ }
checkpoints/008000/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
+ }
checkpoints/008000/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 sha256:95b1027d071458ea98ce5cad20f02497ee126ffb777eaba0854f405c81181c94
3
+ size 6560
checkpoints/008000/pretrained_model/policy_preprocessor.json ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct"
29
+ }
30
+ },
31
+ {
32
+ "registry_name": "device_processor",
33
+ "config": {
34
+ "device": "cuda",
35
+ "float_dtype": null
36
+ }
37
+ },
38
+ {
39
+ "registry_name": "normalizer_processor",
40
+ "config": {
41
+ "eps": 1e-08,
42
+ "features": {
43
+ "observation.state": {
44
+ "type": "STATE",
45
+ "shape": [
46
+ 6
47
+ ]
48
+ },
49
+ "observation.images.camera1": {
50
+ "type": "VISUAL",
51
+ "shape": [
52
+ 3,
53
+ 256,
54
+ 256
55
+ ]
56
+ },
57
+ "observation.images.camera2": {
58
+ "type": "VISUAL",
59
+ "shape": [
60
+ 3,
61
+ 256,
62
+ 256
63
+ ]
64
+ },
65
+ "observation.images.camera3": {
66
+ "type": "VISUAL",
67
+ "shape": [
68
+ 3,
69
+ 256,
70
+ 256
71
+ ]
72
+ },
73
+ "action": {
74
+ "type": "ACTION",
75
+ "shape": [
76
+ 6
77
+ ]
78
+ }
79
+ },
80
+ "norm_map": {
81
+ "VISUAL": "IDENTITY",
82
+ "STATE": "MEAN_STD",
83
+ "ACTION": "MEAN_STD"
84
+ }
85
+ },
86
+ "state_file": "policy_preprocessor_step_5_normalizer_processor.safetensors"
87
+ }
88
+ ]
89
+ }
checkpoints/008000/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 sha256:95b1027d071458ea98ce5cad20f02497ee126ffb777eaba0854f405c81181c94
3
+ size 6560