Hugging Face's logo

ranegray
/
act_drawing_final_safe

Safetensors
Model card Files
xet
Community
ranegray commited on
Commit
c612709
·
verified ·
1 Parent(s): 9690561

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. .gitattributes +1 -0
  2. checkpoints/001000/pretrained_model/config.json +56 -0
  3. checkpoints/001000/pretrained_model/model.safetensors +3 -0
  4. checkpoints/001000/pretrained_model/train_config.json +162 -0
  5. checkpoints/001000/training_state/optimizer_param_groups.json +191 -0
  6. checkpoints/001000/training_state/optimizer_state.safetensors +3 -0
  7. checkpoints/001000/training_state/rng_state.safetensors +3 -0
  8. checkpoints/001000/training_state/training_step.json +3 -0
  9. checkpoints/002000/pretrained_model/config.json +56 -0
  10. checkpoints/002000/pretrained_model/model.safetensors +3 -0
  11. checkpoints/002000/pretrained_model/train_config.json +162 -0
  12. checkpoints/002000/training_state/optimizer_param_groups.json +191 -0
  13. checkpoints/002000/training_state/optimizer_state.safetensors +3 -0
  14. checkpoints/002000/training_state/rng_state.safetensors +3 -0
  15. checkpoints/002000/training_state/training_step.json +3 -0
  16. checkpoints/003000/pretrained_model/config.json +56 -0
  17. checkpoints/003000/pretrained_model/model.safetensors +3 -0
  18. checkpoints/003000/pretrained_model/train_config.json +162 -0
  19. checkpoints/003000/training_state/optimizer_param_groups.json +191 -0
  20. checkpoints/003000/training_state/optimizer_state.safetensors +3 -0
  21. checkpoints/003000/training_state/rng_state.safetensors +3 -0
  22. checkpoints/003000/training_state/training_step.json +3 -0
  23. checkpoints/004000/pretrained_model/config.json +56 -0
  24. checkpoints/004000/pretrained_model/model.safetensors +3 -0
  25. checkpoints/004000/pretrained_model/train_config.json +162 -0
  26. checkpoints/004000/training_state/optimizer_param_groups.json +191 -0
  27. checkpoints/004000/training_state/optimizer_state.safetensors +3 -0
  28. checkpoints/004000/training_state/rng_state.safetensors +3 -0
  29. checkpoints/004000/training_state/training_step.json +3 -0
  30. checkpoints/005000/pretrained_model/config.json +56 -0
  31. checkpoints/005000/pretrained_model/model.safetensors +3 -0
  32. checkpoints/005000/pretrained_model/train_config.json +162 -0
  33. checkpoints/005000/training_state/optimizer_param_groups.json +191 -0
  34. checkpoints/005000/training_state/optimizer_state.safetensors +3 -0
  35. checkpoints/005000/training_state/rng_state.safetensors +3 -0
  36. checkpoints/005000/training_state/training_step.json +3 -0
  37. checkpoints/006000/pretrained_model/config.json +56 -0
  38. checkpoints/006000/pretrained_model/model.safetensors +3 -0
  39. checkpoints/006000/pretrained_model/train_config.json +162 -0
  40. checkpoints/006000/training_state/optimizer_param_groups.json +191 -0
  41. checkpoints/006000/training_state/optimizer_state.safetensors +3 -0
  42. checkpoints/006000/training_state/rng_state.safetensors +3 -0
  43. checkpoints/006000/training_state/training_step.json +3 -0
  44. checkpoints/007000/pretrained_model/config.json +56 -0
  45. checkpoints/007000/pretrained_model/model.safetensors +3 -0
  46. checkpoints/007000/pretrained_model/train_config.json +162 -0
  47. checkpoints/007000/training_state/optimizer_param_groups.json +191 -0
  48. checkpoints/007000/training_state/optimizer_state.safetensors +3 -0
  49. checkpoints/007000/training_state/rng_state.safetensors +3 -0
  50. checkpoints/007000/training_state/training_step.json +3 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ wandb/run-20250615_121800-2ags28sq/run-2ags28sq.wandb filter=lfs diff=lfs merge=lfs -text
checkpoints/001000/pretrained_model/config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "act",
3
+ "n_obs_steps": 1,
4
+ "normalization_mapping": {
5
+ "VISUAL": "MEAN_STD",
6
+ "STATE": "MEAN_STD",
7
+ "ACTION": "MEAN_STD"
8
+ },
9
+ "input_features": {
10
+ "observation.state": {
11
+ "type": "STATE",
12
+ "shape": [
13
+ 6
14
+ ]
15
+ },
16
+ "observation.images.front": {
17
+ "type": "VISUAL",
18
+ "shape": [
19
+ 3,
20
+ 1080,
21
+ 1920
22
+ ]
23
+ }
24
+ },
25
+ "output_features": {
26
+ "action": {
27
+ "type": "ACTION",
28
+ "shape": [
29
+ 6
30
+ ]
31
+ }
32
+ },
33
+ "device": "cuda",
34
+ "use_amp": true,
35
+ "chunk_size": 100,
36
+ "n_action_steps": 100,
37
+ "vision_backbone": "resnet18",
38
+ "pretrained_backbone_weights": "IMAGENET1K_V1",
39
+ "replace_final_stride_with_dilation": false,
40
+ "pre_norm": false,
41
+ "dim_model": 512,
42
+ "n_heads": 8,
43
+ "dim_feedforward": 3200,
44
+ "feedforward_activation": "relu",
45
+ "n_encoder_layers": 4,
46
+ "n_decoder_layers": 1,
47
+ "use_vae": true,
48
+ "latent_dim": 32,
49
+ "n_vae_encoder_layers": 4,
50
+ "temporal_ensemble_coeff": null,
51
+ "dropout": 0.1,
52
+ "kl_weight": 10.0,
53
+ "optimizer_lr": 1e-05,
54
+ "optimizer_weight_decay": 0.0001,
55
+ "optimizer_lr_backbone": 1e-05
56
+ }
checkpoints/001000/pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8afb082a5093ba156691fd664694bcfe0dbc1acda4280d41112d4db97d1cf7e6
3
+ size 206700792
checkpoints/001000/pretrained_model/train_config.json ADDED
@@ -0,0 +1,162 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "ranegray/so101-drawing-dataset",
4
+ "root": null,
5
+ "episodes": null,
6
+ "image_transforms": {
7
+ "enable": true,
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
+ }
62
+ },
63
+ "revision": null,
64
+ "use_imagenet_stats": true,
65
+ "video_backend": "torchcodec"
66
+ },
67
+ "env": null,
68
+ "policy": {
69
+ "type": "act",
70
+ "n_obs_steps": 1,
71
+ "normalization_mapping": {
72
+ "VISUAL": "MEAN_STD",
73
+ "STATE": "MEAN_STD",
74
+ "ACTION": "MEAN_STD"
75
+ },
76
+ "input_features": {
77
+ "observation.state": {
78
+ "type": "STATE",
79
+ "shape": [
80
+ 6
81
+ ]
82
+ },
83
+ "observation.images.front": {
84
+ "type": "VISUAL",
85
+ "shape": [
86
+ 3,
87
+ 1080,
88
+ 1920
89
+ ]
90
+ }
91
+ },
92
+ "output_features": {
93
+ "action": {
94
+ "type": "ACTION",
95
+ "shape": [
96
+ 6
97
+ ]
98
+ }
99
+ },
100
+ "device": "cuda",
101
+ "use_amp": true,
102
+ "chunk_size": 100,
103
+ "n_action_steps": 100,
104
+ "vision_backbone": "resnet18",
105
+ "pretrained_backbone_weights": "IMAGENET1K_V1",
106
+ "replace_final_stride_with_dilation": false,
107
+ "pre_norm": false,
108
+ "dim_model": 512,
109
+ "n_heads": 8,
110
+ "dim_feedforward": 3200,
111
+ "feedforward_activation": "relu",
112
+ "n_encoder_layers": 4,
113
+ "n_decoder_layers": 1,
114
+ "use_vae": true,
115
+ "latent_dim": 32,
116
+ "n_vae_encoder_layers": 4,
117
+ "temporal_ensemble_coeff": null,
118
+ "dropout": 0.1,
119
+ "kl_weight": 10.0,
120
+ "optimizer_lr": 1e-05,
121
+ "optimizer_weight_decay": 0.0001,
122
+ "optimizer_lr_backbone": 1e-05
123
+ },
124
+ "output_dir": "outputs/train/act_drawing_final_safe",
125
+ "job_name": "act_drawing_final_safe",
126
+ "resume": false,
127
+ "seed": 1000,
128
+ "num_workers": 4,
129
+ "batch_size": 4,
130
+ "steps": 10000,
131
+ "eval_freq": 20000,
132
+ "log_freq": 200,
133
+ "save_checkpoint": true,
134
+ "save_freq": 1000,
135
+ "use_policy_training_preset": true,
136
+ "optimizer": {
137
+ "type": "adamw",
138
+ "lr": 1e-05,
139
+ "weight_decay": 0.0001,
140
+ "grad_clip_norm": 10.0,
141
+ "betas": [
142
+ 0.9,
143
+ 0.999
144
+ ],
145
+ "eps": 1e-08
146
+ },
147
+ "scheduler": null,
148
+ "eval": {
149
+ "n_episodes": 50,
150
+ "batch_size": 50,
151
+ "use_async_envs": false
152
+ },
153
+ "wandb": {
154
+ "enable": true,
155
+ "disable_artifact": false,
156
+ "project": "lerobot",
157
+ "entity": null,
158
+ "notes": null,
159
+ "run_id": "2ags28sq",
160
+ "mode": null
161
+ }
162
+ }
checkpoints/001000/training_state/optimizer_param_groups.json ADDED
@@ -0,0 +1,191 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "lr": 1e-05,
4
+ "betas": [
5
+ 0.9,
6
+ 0.999
7
+ ],
8
+ "eps": 1e-08,
9
+ "weight_decay": 0.0001,
10
+ "amsgrad": false,
11
+ "maximize": false,
12
+ "foreach": null,
13
+ "capturable": false,
14
+ "differentiable": false,
15
+ "fused": null,
16
+ "decoupled_weight_decay": true,
17
+ "params": [
18
+ 0,
19
+ 1,
20
+ 2,
21
+ 3,
22
+ 4,
23
+ 5,
24
+ 6,
25
+ 7,
26
+ 8,
27
+ 9,
28
+ 10,
29
+ 11,
30
+ 12,
31
+ 13,
32
+ 14,
33
+ 15,
34
+ 16,
35
+ 17,
36
+ 18,
37
+ 19,
38
+ 20,
39
+ 21,
40
+ 22,
41
+ 23,
42
+ 24,
43
+ 25,
44
+ 26,
45
+ 27,
46
+ 28,
47
+ 29,
48
+ 30,
49
+ 31,
50
+ 32,
51
+ 33,
52
+ 34,
53
+ 35,
54
+ 36,
55
+ 37,
56
+ 38,
57
+ 39,
58
+ 40,
59
+ 41,
60
+ 42,
61
+ 43,
62
+ 44,
63
+ 45,
64
+ 46,
65
+ 47,
66
+ 48,
67
+ 49,
68
+ 50,
69
+ 51,
70
+ 52,
71
+ 53,
72
+ 54,
73
+ 55,
74
+ 56,
75
+ 57,
76
+ 58,
77
+ 59,
78
+ 60,
79
+ 61,
80
+ 62,
81
+ 63,
82
+ 64,
83
+ 65,
84
+ 66,
85
+ 67,
86
+ 68,
87
+ 69,
88
+ 70,
89
+ 71,
90
+ 72,
91
+ 73,
92
+ 74,
93
+ 75,
94
+ 76,
95
+ 77,
96
+ 78,
97
+ 79,
98
+ 80,
99
+ 81,
100
+ 82,
101
+ 83,
102
+ 84,
103
+ 85,
104
+ 86,
105
+ 87,
106
+ 88,
107
+ 89,
108
+ 90,
109
+ 91,
110
+ 92,
111
+ 93,
112
+ 94,
113
+ 95,
114
+ 96,
115
+ 97,
116
+ 98,
117
+ 99,
118
+ 100,
119
+ 101,
120
+ 102,
121
+ 103,
122
+ 104,
123
+ 105,
124
+ 106,
125
+ 107,
126
+ 108,
127
+ 109,
128
+ 110,
129
+ 111,
130
+ 112,
131
+ 113,
132
+ 114,
133
+ 115,
134
+ 116,
135
+ 117,
136
+ 118,
137
+ 119,
138
+ 120,
139
+ 121,
140
+ 122,
141
+ 123,
142
+ 124,
143
+ 125,
144
+ 126,
145
+ 127,
146
+ 128,
147
+ 129,
148
+ 130,
149
+ 131,
150
+ 132
151
+ ]
152
+ },
153
+ {
154
+ "lr": 1e-05,
155
+ "betas": [
156
+ 0.9,
157
+ 0.999
158
+ ],
159
+ "eps": 1e-08,
160
+ "weight_decay": 0.0001,
161
+ "amsgrad": false,
162
+ "maximize": false,
163
+ "foreach": null,
164
+ "capturable": false,
165
+ "differentiable": false,
166
+ "fused": null,
167
+ "decoupled_weight_decay": true,
168
+ "params": [
169
+ 133,
170
+ 134,
171
+ 135,
172
+ 136,
173
+ 137,
174
+ 138,
175
+ 139,
176
+ 140,
177
+ 141,
178
+ 142,
179
+ 143,
180
+ 144,
181
+ 145,
182
+ 146,
183
+ 147,
184
+ 148,
185
+ 149,
186
+ 150,
187
+ 151,
188
+ 152
189
+ ]
190
+ }
191
+ ]
checkpoints/001000/training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bb98b9d2ce39067d12dcfdfa461feb6f529a70f3f0059b3c66cae2b5c5cd376
3
+ size 412817652
checkpoints/001000/training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a440034fb4ed24000db5820f396e7ac4fc7e63268de053cfb8c495e5b815524
3
+ size 15708
checkpoints/001000/training_state/training_step.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "step": 1000
3
+ }
checkpoints/002000/pretrained_model/config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "act",
3
+ "n_obs_steps": 1,
4
+ "normalization_mapping": {
5
+ "VISUAL": "MEAN_STD",
6
+ "STATE": "MEAN_STD",
7
+ "ACTION": "MEAN_STD"
8
+ },
9
+ "input_features": {
10
+ "observation.state": {
11
+ "type": "STATE",
12
+ "shape": [
13
+ 6
14
+ ]
15
+ },
16
+ "observation.images.front": {
17
+ "type": "VISUAL",
18
+ "shape": [
19
+ 3,
20
+ 1080,
21
+ 1920
22
+ ]
23
+ }
24
+ },
25
+ "output_features": {
26
+ "action": {
27
+ "type": "ACTION",
28
+ "shape": [
29
+ 6
30
+ ]
31
+ }
32
+ },
33
+ "device": "cuda",
34
+ "use_amp": true,
35
+ "chunk_size": 100,
36
+ "n_action_steps": 100,
37
+ "vision_backbone": "resnet18",
38
+ "pretrained_backbone_weights": "IMAGENET1K_V1",
39
+ "replace_final_stride_with_dilation": false,
40
+ "pre_norm": false,
41
+ "dim_model": 512,
42
+ "n_heads": 8,
43
+ "dim_feedforward": 3200,
44
+ "feedforward_activation": "relu",
45
+ "n_encoder_layers": 4,
46
+ "n_decoder_layers": 1,
47
+ "use_vae": true,
48
+ "latent_dim": 32,
49
+ "n_vae_encoder_layers": 4,
50
+ "temporal_ensemble_coeff": null,
51
+ "dropout": 0.1,
52
+ "kl_weight": 10.0,
53
+ "optimizer_lr": 1e-05,
54
+ "optimizer_weight_decay": 0.0001,
55
+ "optimizer_lr_backbone": 1e-05
56
+ }
checkpoints/002000/pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f01a3304e2d22168a03e06df85f9f51178ecb4597478b66ff76e023a16e089a2
3
+ size 206700792
checkpoints/002000/pretrained_model/train_config.json ADDED
@@ -0,0 +1,162 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "ranegray/so101-drawing-dataset",
4
+ "root": null,
5
+ "episodes": null,
6
+ "image_transforms": {
7
+ "enable": true,
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
+ }
62
+ },
63
+ "revision": null,
64
+ "use_imagenet_stats": true,
65
+ "video_backend": "torchcodec"
66
+ },
67
+ "env": null,
68
+ "policy": {
69
+ "type": "act",
70
+ "n_obs_steps": 1,
71
+ "normalization_mapping": {
72
+ "VISUAL": "MEAN_STD",
73
+ "STATE": "MEAN_STD",
74
+ "ACTION": "MEAN_STD"
75
+ },
76
+ "input_features": {
77
+ "observation.state": {
78
+ "type": "STATE",
79
+ "shape": [
80
+ 6
81
+ ]
82
+ },
83
+ "observation.images.front": {
84
+ "type": "VISUAL",
85
+ "shape": [
86
+ 3,
87
+ 1080,
88
+ 1920
89
+ ]
90
+ }
91
+ },
92
+ "output_features": {
93
+ "action": {
94
+ "type": "ACTION",
95
+ "shape": [
96
+ 6
97
+ ]
98
+ }
99
+ },
100
+ "device": "cuda",
101
+ "use_amp": true,
102
+ "chunk_size": 100,
103
+ "n_action_steps": 100,
104
+ "vision_backbone": "resnet18",
105
+ "pretrained_backbone_weights": "IMAGENET1K_V1",
106
+ "replace_final_stride_with_dilation": false,
107
+ "pre_norm": false,
108
+ "dim_model": 512,
109
+ "n_heads": 8,
110
+ "dim_feedforward": 3200,
111
+ "feedforward_activation": "relu",
112
+ "n_encoder_layers": 4,
113
+ "n_decoder_layers": 1,
114
+ "use_vae": true,
115
+ "latent_dim": 32,
116
+ "n_vae_encoder_layers": 4,
117
+ "temporal_ensemble_coeff": null,
118
+ "dropout": 0.1,
119
+ "kl_weight": 10.0,
120
+ "optimizer_lr": 1e-05,
121
+ "optimizer_weight_decay": 0.0001,
122
+ "optimizer_lr_backbone": 1e-05
123
+ },
124
+ "output_dir": "outputs/train/act_drawing_final_safe",
125
+ "job_name": "act_drawing_final_safe",
126
+ "resume": false,
127
+ "seed": 1000,
128
+ "num_workers": 4,
129
+ "batch_size": 4,
130
+ "steps": 10000,
131
+ "eval_freq": 20000,
132
+ "log_freq": 200,
133
+ "save_checkpoint": true,
134
+ "save_freq": 1000,
135
+ "use_policy_training_preset": true,
136
+ "optimizer": {
137
+ "type": "adamw",
138
+ "lr": 1e-05,
139
+ "weight_decay": 0.0001,
140
+ "grad_clip_norm": 10.0,
141
+ "betas": [
142
+ 0.9,
143
+ 0.999
144
+ ],
145
+ "eps": 1e-08
146
+ },
147
+ "scheduler": null,
148
+ "eval": {
149
+ "n_episodes": 50,
150
+ "batch_size": 50,
151
+ "use_async_envs": false
152
+ },
153
+ "wandb": {
154
+ "enable": true,
155
+ "disable_artifact": false,
156
+ "project": "lerobot",
157
+ "entity": null,
158
+ "notes": null,
159
+ "run_id": "2ags28sq",
160
+ "mode": null
161
+ }
162
+ }
checkpoints/002000/training_state/optimizer_param_groups.json ADDED
@@ -0,0 +1,191 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "lr": 1e-05,
4
+ "betas": [
5
+ 0.9,
6
+ 0.999
7
+ ],
8
+ "eps": 1e-08,
9
+ "weight_decay": 0.0001,
10
+ "amsgrad": false,
11
+ "maximize": false,
12
+ "foreach": null,
13
+ "capturable": false,
14
+ "differentiable": false,
15
+ "fused": null,
16
+ "decoupled_weight_decay": true,
17
+ "params": [
18
+ 0,
19
+ 1,
20
+ 2,
21
+ 3,
22
+ 4,
23
+ 5,
24
+ 6,
25
+ 7,
26
+ 8,
27
+ 9,
28
+ 10,
29
+ 11,
30
+ 12,
31
+ 13,
32
+ 14,
33
+ 15,
34
+ 16,
35
+ 17,
36
+ 18,
37
+ 19,
38
+ 20,
39
+ 21,
40
+ 22,
41
+ 23,
42
+ 24,
43
+ 25,
44
+ 26,
45
+ 27,
46
+ 28,
47
+ 29,
48
+ 30,
49
+ 31,
50
+ 32,
51
+ 33,
52
+ 34,
53
+ 35,
54
+ 36,
55
+ 37,
56
+ 38,
57
+ 39,
58
+ 40,
59
+ 41,
60
+ 42,
61
+ 43,
62
+ 44,
63
+ 45,
64
+ 46,
65
+ 47,
66
+ 48,
67
+ 49,
68
+ 50,
69
+ 51,
70
+ 52,
71
+ 53,
72
+ 54,
73
+ 55,
74
+ 56,
75
+ 57,
76
+ 58,
77
+ 59,
78
+ 60,
79
+ 61,
80
+ 62,
81
+ 63,
82
+ 64,
83
+ 65,
84
+ 66,
85
+ 67,
86
+ 68,
87
+ 69,
88
+ 70,
89
+ 71,
90
+ 72,
91
+ 73,
92
+ 74,
93
+ 75,
94
+ 76,
95
+ 77,
96
+ 78,
97
+ 79,
98
+ 80,
99
+ 81,
100
+ 82,
101
+ 83,
102
+ 84,
103
+ 85,
104
+ 86,
105
+ 87,
106
+ 88,
107
+ 89,
108
+ 90,
109
+ 91,
110
+ 92,
111
+ 93,
112
+ 94,
113
+ 95,
114
+ 96,
115
+ 97,
116
+ 98,
117
+ 99,
118
+ 100,
119
+ 101,
120
+ 102,
121
+ 103,
122
+ 104,
123
+ 105,
124
+ 106,
125
+ 107,
126
+ 108,
127
+ 109,
128
+ 110,
129
+ 111,
130
+ 112,
131
+ 113,
132
+ 114,
133
+ 115,
134
+ 116,
135
+ 117,
136
+ 118,
137
+ 119,
138
+ 120,
139
+ 121,
140
+ 122,
141
+ 123,
142
+ 124,
143
+ 125,
144
+ 126,
145
+ 127,
146
+ 128,
147
+ 129,
148
+ 130,
149
+ 131,
150
+ 132
151
+ ]
152
+ },
153
+ {
154
+ "lr": 1e-05,
155
+ "betas": [
156
+ 0.9,
157
+ 0.999
158
+ ],
159
+ "eps": 1e-08,
160
+ "weight_decay": 0.0001,
161
+ "amsgrad": false,
162
+ "maximize": false,
163
+ "foreach": null,
164
+ "capturable": false,
165
+ "differentiable": false,
166
+ "fused": null,
167
+ "decoupled_weight_decay": true,
168
+ "params": [
169
+ 133,
170
+ 134,
171
+ 135,
172
+ 136,
173
+ 137,
174
+ 138,
175
+ 139,
176
+ 140,
177
+ 141,
178
+ 142,
179
+ 143,
180
+ 144,
181
+ 145,
182
+ 146,
183
+ 147,
184
+ 148,
185
+ 149,
186
+ 150,
187
+ 151,
188
+ 152
189
+ ]
190
+ }
191
+ ]
checkpoints/002000/training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e544029fa0a12252f5e08e7af9f597de135a9753dc7a38e9aff435dd4d2e7e1
3
+ size 412817652
checkpoints/002000/training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c205c43e2b29d33c212438dcc76b13bdf557bd985dba7d6e00ef681069d8a95b
3
+ size 15708
checkpoints/002000/training_state/training_step.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "step": 2000
3
+ }
checkpoints/003000/pretrained_model/config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "act",
3
+ "n_obs_steps": 1,
4
+ "normalization_mapping": {
5
+ "VISUAL": "MEAN_STD",
6
+ "STATE": "MEAN_STD",
7
+ "ACTION": "MEAN_STD"
8
+ },
9
+ "input_features": {
10
+ "observation.state": {
11
+ "type": "STATE",
12
+ "shape": [
13
+ 6
14
+ ]
15
+ },
16
+ "observation.images.front": {
17
+ "type": "VISUAL",
18
+ "shape": [
19
+ 3,
20
+ 1080,
21
+ 1920
22
+ ]
23
+ }
24
+ },
25
+ "output_features": {
26
+ "action": {
27
+ "type": "ACTION",
28
+ "shape": [
29
+ 6
30
+ ]
31
+ }
32
+ },
33
+ "device": "cuda",
34
+ "use_amp": true,
35
+ "chunk_size": 100,
36
+ "n_action_steps": 100,
37
+ "vision_backbone": "resnet18",
38
+ "pretrained_backbone_weights": "IMAGENET1K_V1",
39
+ "replace_final_stride_with_dilation": false,
40
+ "pre_norm": false,
41
+ "dim_model": 512,
42
+ "n_heads": 8,
43
+ "dim_feedforward": 3200,
44
+ "feedforward_activation": "relu",
45
+ "n_encoder_layers": 4,
46
+ "n_decoder_layers": 1,
47
+ "use_vae": true,
48
+ "latent_dim": 32,
49
+ "n_vae_encoder_layers": 4,
50
+ "temporal_ensemble_coeff": null,
51
+ "dropout": 0.1,
52
+ "kl_weight": 10.0,
53
+ "optimizer_lr": 1e-05,
54
+ "optimizer_weight_decay": 0.0001,
55
+ "optimizer_lr_backbone": 1e-05
56
+ }
checkpoints/003000/pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aad697dcc5aef74a7399512408c6e4aebb7fe01b24128865b4ad11b1d768bdd4
3
+ size 206700792
checkpoints/003000/pretrained_model/train_config.json ADDED
@@ -0,0 +1,162 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "ranegray/so101-drawing-dataset",
4
+ "root": null,
5
+ "episodes": null,
6
+ "image_transforms": {
7
+ "enable": true,
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
+ }
62
+ },
63
+ "revision": null,
64
+ "use_imagenet_stats": true,
65
+ "video_backend": "torchcodec"
66
+ },
67
+ "env": null,
68
+ "policy": {
69
+ "type": "act",
70
+ "n_obs_steps": 1,
71
+ "normalization_mapping": {
72
+ "VISUAL": "MEAN_STD",
73
+ "STATE": "MEAN_STD",
74
+ "ACTION": "MEAN_STD"
75
+ },
76
+ "input_features": {
77
+ "observation.state": {
78
+ "type": "STATE",
79
+ "shape": [
80
+ 6
81
+ ]
82
+ },
83
+ "observation.images.front": {
84
+ "type": "VISUAL",
85
+ "shape": [
86
+ 3,
87
+ 1080,
88
+ 1920
89
+ ]
90
+ }
91
+ },
92
+ "output_features": {
93
+ "action": {
94
+ "type": "ACTION",
95
+ "shape": [
96
+ 6
97
+ ]
98
+ }
99
+ },
100
+ "device": "cuda",
101
+ "use_amp": true,
102
+ "chunk_size": 100,
103
+ "n_action_steps": 100,
104
+ "vision_backbone": "resnet18",
105
+ "pretrained_backbone_weights": "IMAGENET1K_V1",
106
+ "replace_final_stride_with_dilation": false,
107
+ "pre_norm": false,
108
+ "dim_model": 512,
109
+ "n_heads": 8,
110
+ "dim_feedforward": 3200,
111
+ "feedforward_activation": "relu",
112
+ "n_encoder_layers": 4,
113
+ "n_decoder_layers": 1,
114
+ "use_vae": true,
115
+ "latent_dim": 32,
116
+ "n_vae_encoder_layers": 4,
117
+ "temporal_ensemble_coeff": null,
118
+ "dropout": 0.1,
119
+ "kl_weight": 10.0,
120
+ "optimizer_lr": 1e-05,
121
+ "optimizer_weight_decay": 0.0001,
122
+ "optimizer_lr_backbone": 1e-05
123
+ },
124
+ "output_dir": "outputs/train/act_drawing_final_safe",
125
+ "job_name": "act_drawing_final_safe",
126
+ "resume": false,
127
+ "seed": 1000,
128
+ "num_workers": 4,
129
+ "batch_size": 4,
130
+ "steps": 10000,
131
+ "eval_freq": 20000,
132
+ "log_freq": 200,
133
+ "save_checkpoint": true,
134
+ "save_freq": 1000,
135
+ "use_policy_training_preset": true,
136
+ "optimizer": {
137
+ "type": "adamw",
138
+ "lr": 1e-05,
139
+ "weight_decay": 0.0001,
140
+ "grad_clip_norm": 10.0,
141
+ "betas": [
142
+ 0.9,
143
+ 0.999
144
+ ],
145
+ "eps": 1e-08
146
+ },
147
+ "scheduler": null,
148
+ "eval": {
149
+ "n_episodes": 50,
150
+ "batch_size": 50,
151
+ "use_async_envs": false
152
+ },
153
+ "wandb": {
154
+ "enable": true,
155
+ "disable_artifact": false,
156
+ "project": "lerobot",
157
+ "entity": null,
158
+ "notes": null,
159
+ "run_id": "2ags28sq",
160
+ "mode": null
161
+ }
162
+ }
checkpoints/003000/training_state/optimizer_param_groups.json ADDED
@@ -0,0 +1,191 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "lr": 1e-05,
4
+ "betas": [
5
+ 0.9,
6
+ 0.999
7
+ ],
8
+ "eps": 1e-08,
9
+ "weight_decay": 0.0001,
10
+ "amsgrad": false,
11
+ "maximize": false,
12
+ "foreach": null,
13
+ "capturable": false,
14
+ "differentiable": false,
15
+ "fused": null,
16
+ "decoupled_weight_decay": true,
17
+ "params": [
18
+ 0,
19
+ 1,
20
+ 2,
21
+ 3,
22
+ 4,
23
+ 5,
24
+ 6,
25
+ 7,
26
+ 8,
27
+ 9,
28
+ 10,
29
+ 11,
30
+ 12,
31
+ 13,
32
+ 14,
33
+ 15,
34
+ 16,
35
+ 17,
36
+ 18,
37
+ 19,
38
+ 20,
39
+ 21,
40
+ 22,
41
+ 23,
42
+ 24,
43
+ 25,
44
+ 26,
45
+ 27,
46
+ 28,
47
+ 29,
48
+ 30,
49
+ 31,
50
+ 32,
51
+ 33,
52
+ 34,
53
+ 35,
54
+ 36,
55
+ 37,
56
+ 38,
57
+ 39,
58
+ 40,
59
+ 41,
60
+ 42,
61
+ 43,
62
+ 44,
63
+ 45,
64
+ 46,
65
+ 47,
66
+ 48,
67
+ 49,
68
+ 50,
69
+ 51,
70
+ 52,
71
+ 53,
72
+ 54,
73
+ 55,
74
+ 56,
75
+ 57,
76
+ 58,
77
+ 59,
78
+ 60,
79
+ 61,
80
+ 62,
81
+ 63,
82
+ 64,
83
+ 65,
84
+ 66,
85
+ 67,
86
+ 68,
87
+ 69,
88
+ 70,
89
+ 71,
90
+ 72,
91
+ 73,
92
+ 74,
93
+ 75,
94
+ 76,
95
+ 77,
96
+ 78,
97
+ 79,
98
+ 80,
99
+ 81,
100
+ 82,
101
+ 83,
102
+ 84,
103
+ 85,
104
+ 86,
105
+ 87,
106
+ 88,
107
+ 89,
108
+ 90,
109
+ 91,
110
+ 92,
111
+ 93,
112
+ 94,
113
+ 95,
114
+ 96,
115
+ 97,
116
+ 98,
117
+ 99,
118
+ 100,
119
+ 101,
120
+ 102,
121
+ 103,
122
+ 104,
123
+ 105,
124
+ 106,
125
+ 107,
126
+ 108,
127
+ 109,
128
+ 110,
129
+ 111,
130
+ 112,
131
+ 113,
132
+ 114,
133
+ 115,
134
+ 116,
135
+ 117,
136
+ 118,
137
+ 119,
138
+ 120,
139
+ 121,
140
+ 122,
141
+ 123,
142
+ 124,
143
+ 125,
144
+ 126,
145
+ 127,
146
+ 128,
147
+ 129,
148
+ 130,
149
+ 131,
150
+ 132
151
+ ]
152
+ },
153
+ {
154
+ "lr": 1e-05,
155
+ "betas": [
156
+ 0.9,
157
+ 0.999
158
+ ],
159
+ "eps": 1e-08,
160
+ "weight_decay": 0.0001,
161
+ "amsgrad": false,
162
+ "maximize": false,
163
+ "foreach": null,
164
+ "capturable": false,
165
+ "differentiable": false,
166
+ "fused": null,
167
+ "decoupled_weight_decay": true,
168
+ "params": [
169
+ 133,
170
+ 134,
171
+ 135,
172
+ 136,
173
+ 137,
174
+ 138,
175
+ 139,
176
+ 140,
177
+ 141,
178
+ 142,
179
+ 143,
180
+ 144,
181
+ 145,
182
+ 146,
183
+ 147,
184
+ 148,
185
+ 149,
186
+ 150,
187
+ 151,
188
+ 152
189
+ ]
190
+ }
191
+ ]
checkpoints/003000/training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e46a8b97500ac79a0954cc031537cd2f06bbc628dfb1bad5873a698eac65ee5
3
+ size 412817652
checkpoints/003000/training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:009a1eb76cddaab29f780b62361827f9b21c7f965d18e760ec8dbe46a8ec63e6
3
+ size 15708
checkpoints/003000/training_state/training_step.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "step": 3000
3
+ }
checkpoints/004000/pretrained_model/config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "act",
3
+ "n_obs_steps": 1,
4
+ "normalization_mapping": {
5
+ "VISUAL": "MEAN_STD",
6
+ "STATE": "MEAN_STD",
7
+ "ACTION": "MEAN_STD"
8
+ },
9
+ "input_features": {
10
+ "observation.state": {
11
+ "type": "STATE",
12
+ "shape": [
13
+ 6
14
+ ]
15
+ },
16
+ "observation.images.front": {
17
+ "type": "VISUAL",
18
+ "shape": [
19
+ 3,
20
+ 1080,
21
+ 1920
22
+ ]
23
+ }
24
+ },
25
+ "output_features": {
26
+ "action": {
27
+ "type": "ACTION",
28
+ "shape": [
29
+ 6
30
+ ]
31
+ }
32
+ },
33
+ "device": "cuda",
34
+ "use_amp": true,
35
+ "chunk_size": 100,
36
+ "n_action_steps": 100,
37
+ "vision_backbone": "resnet18",
38
+ "pretrained_backbone_weights": "IMAGENET1K_V1",
39
+ "replace_final_stride_with_dilation": false,
40
+ "pre_norm": false,
41
+ "dim_model": 512,
42
+ "n_heads": 8,
43
+ "dim_feedforward": 3200,
44
+ "feedforward_activation": "relu",
45
+ "n_encoder_layers": 4,
46
+ "n_decoder_layers": 1,
47
+ "use_vae": true,
48
+ "latent_dim": 32,
49
+ "n_vae_encoder_layers": 4,
50
+ "temporal_ensemble_coeff": null,
51
+ "dropout": 0.1,
52
+ "kl_weight": 10.0,
53
+ "optimizer_lr": 1e-05,
54
+ "optimizer_weight_decay": 0.0001,
55
+ "optimizer_lr_backbone": 1e-05
56
+ }
checkpoints/004000/pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:473f6eac738513e13fbe8a893d735c99cb858b1790f6f277dae99186ef6c603b
3
+ size 206700792
checkpoints/004000/pretrained_model/train_config.json ADDED
@@ -0,0 +1,162 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "ranegray/so101-drawing-dataset",
4
+ "root": null,
5
+ "episodes": null,
6
+ "image_transforms": {
7
+ "enable": true,
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
+ }
62
+ },
63
+ "revision": null,
64
+ "use_imagenet_stats": true,
65
+ "video_backend": "torchcodec"
66
+ },
67
+ "env": null,
68
+ "policy": {
69
+ "type": "act",
70
+ "n_obs_steps": 1,
71
+ "normalization_mapping": {
72
+ "VISUAL": "MEAN_STD",
73
+ "STATE": "MEAN_STD",
74
+ "ACTION": "MEAN_STD"
75
+ },
76
+ "input_features": {
77
+ "observation.state": {
78
+ "type": "STATE",
79
+ "shape": [
80
+ 6
81
+ ]
82
+ },
83
+ "observation.images.front": {
84
+ "type": "VISUAL",
85
+ "shape": [
86
+ 3,
87
+ 1080,
88
+ 1920
89
+ ]
90
+ }
91
+ },
92
+ "output_features": {
93
+ "action": {
94
+ "type": "ACTION",
95
+ "shape": [
96
+ 6
97
+ ]
98
+ }
99
+ },
100
+ "device": "cuda",
101
+ "use_amp": true,
102
+ "chunk_size": 100,
103
+ "n_action_steps": 100,
104
+ "vision_backbone": "resnet18",
105
+ "pretrained_backbone_weights": "IMAGENET1K_V1",
106
+ "replace_final_stride_with_dilation": false,
107
+ "pre_norm": false,
108
+ "dim_model": 512,
109
+ "n_heads": 8,
110
+ "dim_feedforward": 3200,
111
+ "feedforward_activation": "relu",
112
+ "n_encoder_layers": 4,
113
+ "n_decoder_layers": 1,
114
+ "use_vae": true,
115
+ "latent_dim": 32,
116
+ "n_vae_encoder_layers": 4,
117
+ "temporal_ensemble_coeff": null,
118
+ "dropout": 0.1,
119
+ "kl_weight": 10.0,
120
+ "optimizer_lr": 1e-05,
121
+ "optimizer_weight_decay": 0.0001,
122
+ "optimizer_lr_backbone": 1e-05
123
+ },
124
+ "output_dir": "outputs/train/act_drawing_final_safe",
125
+ "job_name": "act_drawing_final_safe",
126
+ "resume": false,
127
+ "seed": 1000,
128
+ "num_workers": 4,
129
+ "batch_size": 4,
130
+ "steps": 10000,
131
+ "eval_freq": 20000,
132
+ "log_freq": 200,
133
+ "save_checkpoint": true,
134
+ "save_freq": 1000,
135
+ "use_policy_training_preset": true,
136
+ "optimizer": {
137
+ "type": "adamw",
138
+ "lr": 1e-05,
139
+ "weight_decay": 0.0001,
140
+ "grad_clip_norm": 10.0,
141
+ "betas": [
142
+ 0.9,
143
+ 0.999
144
+ ],
145
+ "eps": 1e-08
146
+ },
147
+ "scheduler": null,
148
+ "eval": {
149
+ "n_episodes": 50,
150
+ "batch_size": 50,
151
+ "use_async_envs": false
152
+ },
153
+ "wandb": {
154
+ "enable": true,
155
+ "disable_artifact": false,
156
+ "project": "lerobot",
157
+ "entity": null,
158
+ "notes": null,
159
+ "run_id": "2ags28sq",
160
+ "mode": null
161
+ }
162
+ }
checkpoints/004000/training_state/optimizer_param_groups.json ADDED
@@ -0,0 +1,191 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "lr": 1e-05,
4
+ "betas": [
5
+ 0.9,
6
+ 0.999
7
+ ],
8
+ "eps": 1e-08,
9
+ "weight_decay": 0.0001,
10
+ "amsgrad": false,
11
+ "maximize": false,
12
+ "foreach": null,
13
+ "capturable": false,
14
+ "differentiable": false,
15
+ "fused": null,
16
+ "decoupled_weight_decay": true,
17
+ "params": [
18
+ 0,
19
+ 1,
20
+ 2,
21
+ 3,
22
+ 4,
23
+ 5,
24
+ 6,
25
+ 7,
26
+ 8,
27
+ 9,
28
+ 10,
29
+ 11,
30
+ 12,
31
+ 13,
32
+ 14,
33
+ 15,
34
+ 16,
35
+ 17,
36
+ 18,
37
+ 19,
38
+ 20,
39
+ 21,
40
+ 22,
41
+ 23,
42
+ 24,
43
+ 25,
44
+ 26,
45
+ 27,
46
+ 28,
47
+ 29,
48
+ 30,
49
+ 31,
50
+ 32,
51
+ 33,
52
+ 34,
53
+ 35,
54
+ 36,
55
+ 37,
56
+ 38,
57
+ 39,
58
+ 40,
59
+ 41,
60
+ 42,
61
+ 43,
62
+ 44,
63
+ 45,
64
+ 46,
65
+ 47,
66
+ 48,
67
+ 49,
68
+ 50,
69
+ 51,
70
+ 52,
71
+ 53,
72
+ 54,
73
+ 55,
74
+ 56,
75
+ 57,
76
+ 58,
77
+ 59,
78
+ 60,
79
+ 61,
80
+ 62,
81
+ 63,
82
+ 64,
83
+ 65,
84
+ 66,
85
+ 67,
86
+ 68,
87
+ 69,
88
+ 70,
89
+ 71,
90
+ 72,
91
+ 73,
92
+ 74,
93
+ 75,
94
+ 76,
95
+ 77,
96
+ 78,
97
+ 79,
98
+ 80,
99
+ 81,
100
+ 82,
101
+ 83,
102
+ 84,
103
+ 85,
104
+ 86,
105
+ 87,
106
+ 88,
107
+ 89,
108
+ 90,
109
+ 91,
110
+ 92,
111
+ 93,
112
+ 94,
113
+ 95,
114
+ 96,
115
+ 97,
116
+ 98,
117
+ 99,
118
+ 100,
119
+ 101,
120
+ 102,
121
+ 103,
122
+ 104,
123
+ 105,
124
+ 106,
125
+ 107,
126
+ 108,
127
+ 109,
128
+ 110,
129
+ 111,
130
+ 112,
131
+ 113,
132
+ 114,
133
+ 115,
134
+ 116,
135
+ 117,
136
+ 118,
137
+ 119,
138
+ 120,
139
+ 121,
140
+ 122,
141
+ 123,
142
+ 124,
143
+ 125,
144
+ 126,
145
+ 127,
146
+ 128,
147
+ 129,
148
+ 130,
149
+ 131,
150
+ 132
151
+ ]
152
+ },
153
+ {
154
+ "lr": 1e-05,
155
+ "betas": [
156
+ 0.9,
157
+ 0.999
158
+ ],
159
+ "eps": 1e-08,
160
+ "weight_decay": 0.0001,
161
+ "amsgrad": false,
162
+ "maximize": false,
163
+ "foreach": null,
164
+ "capturable": false,
165
+ "differentiable": false,
166
+ "fused": null,
167
+ "decoupled_weight_decay": true,
168
+ "params": [
169
+ 133,
170
+ 134,
171
+ 135,
172
+ 136,
173
+ 137,
174
+ 138,
175
+ 139,
176
+ 140,
177
+ 141,
178
+ 142,
179
+ 143,
180
+ 144,
181
+ 145,
182
+ 146,
183
+ 147,
184
+ 148,
185
+ 149,
186
+ 150,
187
+ 151,
188
+ 152
189
+ ]
190
+ }
191
+ ]
checkpoints/004000/training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:689b2db5eb3adbeb4f5d3b54e1d765814ecd2d5e8cf90ee98a7777865b06c37b
3
+ size 412817652
checkpoints/004000/training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca5244981fc3c83244a6954f2540d0980e49cafdb8eff6ec315c401b6ff74596
3
+ size 15708
checkpoints/004000/training_state/training_step.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "step": 4000
3
+ }
checkpoints/005000/pretrained_model/config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "act",
3
+ "n_obs_steps": 1,
4
+ "normalization_mapping": {
5
+ "VISUAL": "MEAN_STD",
6
+ "STATE": "MEAN_STD",
7
+ "ACTION": "MEAN_STD"
8
+ },
9
+ "input_features": {
10
+ "observation.state": {
11
+ "type": "STATE",
12
+ "shape": [
13
+ 6
14
+ ]
15
+ },
16
+ "observation.images.front": {
17
+ "type": "VISUAL",
18
+ "shape": [
19
+ 3,
20
+ 1080,
21
+ 1920
22
+ ]
23
+ }
24
+ },
25
+ "output_features": {
26
+ "action": {
27
+ "type": "ACTION",
28
+ "shape": [
29
+ 6
30
+ ]
31
+ }
32
+ },
33
+ "device": "cuda",
34
+ "use_amp": true,
35
+ "chunk_size": 100,
36
+ "n_action_steps": 100,
37
+ "vision_backbone": "resnet18",
38
+ "pretrained_backbone_weights": "IMAGENET1K_V1",
39
+ "replace_final_stride_with_dilation": false,
40
+ "pre_norm": false,
41
+ "dim_model": 512,
42
+ "n_heads": 8,
43
+ "dim_feedforward": 3200,
44
+ "feedforward_activation": "relu",
45
+ "n_encoder_layers": 4,
46
+ "n_decoder_layers": 1,
47
+ "use_vae": true,
48
+ "latent_dim": 32,
49
+ "n_vae_encoder_layers": 4,
50
+ "temporal_ensemble_coeff": null,
51
+ "dropout": 0.1,
52
+ "kl_weight": 10.0,
53
+ "optimizer_lr": 1e-05,
54
+ "optimizer_weight_decay": 0.0001,
55
+ "optimizer_lr_backbone": 1e-05
56
+ }
checkpoints/005000/pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8837d19e5e3e465df6bf06a7d6bf618768f0ec96db3d2f40a52ca35827c37c5
3
+ size 206700792
checkpoints/005000/pretrained_model/train_config.json ADDED
@@ -0,0 +1,162 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "ranegray/so101-drawing-dataset",
4
+ "root": null,
5
+ "episodes": null,
6
+ "image_transforms": {
7
+ "enable": true,
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
+ }
62
+ },
63
+ "revision": null,
64
+ "use_imagenet_stats": true,
65
+ "video_backend": "torchcodec"
66
+ },
67
+ "env": null,
68
+ "policy": {
69
+ "type": "act",
70
+ "n_obs_steps": 1,
71
+ "normalization_mapping": {
72
+ "VISUAL": "MEAN_STD",
73
+ "STATE": "MEAN_STD",
74
+ "ACTION": "MEAN_STD"
75
+ },
76
+ "input_features": {
77
+ "observation.state": {
78
+ "type": "STATE",
79
+ "shape": [
80
+ 6
81
+ ]
82
+ },
83
+ "observation.images.front": {
84
+ "type": "VISUAL",
85
+ "shape": [
86
+ 3,
87
+ 1080,
88
+ 1920
89
+ ]
90
+ }
91
+ },
92
+ "output_features": {
93
+ "action": {
94
+ "type": "ACTION",
95
+ "shape": [
96
+ 6
97
+ ]
98
+ }
99
+ },
100
+ "device": "cuda",
101
+ "use_amp": true,
102
+ "chunk_size": 100,
103
+ "n_action_steps": 100,
104
+ "vision_backbone": "resnet18",
105
+ "pretrained_backbone_weights": "IMAGENET1K_V1",
106
+ "replace_final_stride_with_dilation": false,
107
+ "pre_norm": false,
108
+ "dim_model": 512,
109
+ "n_heads": 8,
110
+ "dim_feedforward": 3200,
111
+ "feedforward_activation": "relu",
112
+ "n_encoder_layers": 4,
113
+ "n_decoder_layers": 1,
114
+ "use_vae": true,
115
+ "latent_dim": 32,
116
+ "n_vae_encoder_layers": 4,
117
+ "temporal_ensemble_coeff": null,
118
+ "dropout": 0.1,
119
+ "kl_weight": 10.0,
120
+ "optimizer_lr": 1e-05,
121
+ "optimizer_weight_decay": 0.0001,
122
+ "optimizer_lr_backbone": 1e-05
123
+ },
124
+ "output_dir": "outputs/train/act_drawing_final_safe",
125
+ "job_name": "act_drawing_final_safe",
126
+ "resume": false,
127
+ "seed": 1000,
128
+ "num_workers": 4,
129
+ "batch_size": 4,
130
+ "steps": 10000,
131
+ "eval_freq": 20000,
132
+ "log_freq": 200,
133
+ "save_checkpoint": true,
134
+ "save_freq": 1000,
135
+ "use_policy_training_preset": true,
136
+ "optimizer": {
137
+ "type": "adamw",
138
+ "lr": 1e-05,
139
+ "weight_decay": 0.0001,
140
+ "grad_clip_norm": 10.0,
141
+ "betas": [
142
+ 0.9,
143
+ 0.999
144
+ ],
145
+ "eps": 1e-08
146
+ },
147
+ "scheduler": null,
148
+ "eval": {
149
+ "n_episodes": 50,
150
+ "batch_size": 50,
151
+ "use_async_envs": false
152
+ },
153
+ "wandb": {
154
+ "enable": true,
155
+ "disable_artifact": false,
156
+ "project": "lerobot",
157
+ "entity": null,
158
+ "notes": null,
159
+ "run_id": "2ags28sq",
160
+ "mode": null
161
+ }
162
+ }
checkpoints/005000/training_state/optimizer_param_groups.json ADDED
@@ -0,0 +1,191 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "lr": 1e-05,
4
+ "betas": [
5
+ 0.9,
6
+ 0.999
7
+ ],
8
+ "eps": 1e-08,
9
+ "weight_decay": 0.0001,
10
+ "amsgrad": false,
11
+ "maximize": false,
12
+ "foreach": null,
13
+ "capturable": false,
14
+ "differentiable": false,
15
+ "fused": null,
16
+ "decoupled_weight_decay": true,
17
+ "params": [
18
+ 0,
19
+ 1,
20
+ 2,
21
+ 3,
22
+ 4,
23
+ 5,
24
+ 6,
25
+ 7,
26
+ 8,
27
+ 9,
28
+ 10,
29
+ 11,
30
+ 12,
31
+ 13,
32
+ 14,
33
+ 15,
34
+ 16,
35
+ 17,
36
+ 18,
37
+ 19,
38
+ 20,
39
+ 21,
40
+ 22,
41
+ 23,
42
+ 24,
43
+ 25,
44
+ 26,
45
+ 27,
46
+ 28,
47
+ 29,
48
+ 30,
49
+ 31,
50
+ 32,
51
+ 33,
52
+ 34,
53
+ 35,
54
+ 36,
55
+ 37,
56
+ 38,
57
+ 39,
58
+ 40,
59
+ 41,
60
+ 42,
61
+ 43,
62
+ 44,
63
+ 45,
64
+ 46,
65
+ 47,
66
+ 48,
67
+ 49,
68
+ 50,
69
+ 51,
70
+ 52,
71
+ 53,
72
+ 54,
73
+ 55,
74
+ 56,
75
+ 57,
76
+ 58,
77
+ 59,
78
+ 60,
79
+ 61,
80
+ 62,
81
+ 63,
82
+ 64,
83
+ 65,
84
+ 66,
85
+ 67,
86
+ 68,
87
+ 69,
88
+ 70,
89
+ 71,
90
+ 72,
91
+ 73,
92
+ 74,
93
+ 75,
94
+ 76,
95
+ 77,
96
+ 78,
97
+ 79,
98
+ 80,
99
+ 81,
100
+ 82,
101
+ 83,
102
+ 84,
103
+ 85,
104
+ 86,
105
+ 87,
106
+ 88,
107
+ 89,
108
+ 90,
109
+ 91,
110
+ 92,
111
+ 93,
112
+ 94,
113
+ 95,
114
+ 96,
115
+ 97,
116
+ 98,
117
+ 99,
118
+ 100,
119
+ 101,
120
+ 102,
121
+ 103,
122
+ 104,
123
+ 105,
124
+ 106,
125
+ 107,
126
+ 108,
127
+ 109,
128
+ 110,
129
+ 111,
130
+ 112,
131
+ 113,
132
+ 114,
133
+ 115,
134
+ 116,
135
+ 117,
136
+ 118,
137
+ 119,
138
+ 120,
139
+ 121,
140
+ 122,
141
+ 123,
142
+ 124,
143
+ 125,
144
+ 126,
145
+ 127,
146
+ 128,
147
+ 129,
148
+ 130,
149
+ 131,
150
+ 132
151
+ ]
152
+ },
153
+ {
154
+ "lr": 1e-05,
155
+ "betas": [
156
+ 0.9,
157
+ 0.999
158
+ ],
159
+ "eps": 1e-08,
160
+ "weight_decay": 0.0001,
161
+ "amsgrad": false,
162
+ "maximize": false,
163
+ "foreach": null,
164
+ "capturable": false,
165
+ "differentiable": false,
166
+ "fused": null,
167
+ "decoupled_weight_decay": true,
168
+ "params": [
169
+ 133,
170
+ 134,
171
+ 135,
172
+ 136,
173
+ 137,
174
+ 138,
175
+ 139,
176
+ 140,
177
+ 141,
178
+ 142,
179
+ 143,
180
+ 144,
181
+ 145,
182
+ 146,
183
+ 147,
184
+ 148,
185
+ 149,
186
+ 150,
187
+ 151,
188
+ 152
189
+ ]
190
+ }
191
+ ]
checkpoints/005000/training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:377708cb1e04614fd17374c0b68d27ecd28da518f4cfc6a027c17c94a50b0d12
3
+ size 412817652
checkpoints/005000/training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7ed3274308ea5f96e79a0a0ad3c48451bfb62995281621dee1e6e807e063e76
3
+ size 15708
checkpoints/005000/training_state/training_step.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "step": 5000
3
+ }
checkpoints/006000/pretrained_model/config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "act",
3
+ "n_obs_steps": 1,
4
+ "normalization_mapping": {
5
+ "VISUAL": "MEAN_STD",
6
+ "STATE": "MEAN_STD",
7
+ "ACTION": "MEAN_STD"
8
+ },
9
+ "input_features": {
10
+ "observation.state": {
11
+ "type": "STATE",
12
+ "shape": [
13
+ 6
14
+ ]
15
+ },
16
+ "observation.images.front": {
17
+ "type": "VISUAL",
18
+ "shape": [
19
+ 3,
20
+ 1080,
21
+ 1920
22
+ ]
23
+ }
24
+ },
25
+ "output_features": {
26
+ "action": {
27
+ "type": "ACTION",
28
+ "shape": [
29
+ 6
30
+ ]
31
+ }
32
+ },
33
+ "device": "cuda",
34
+ "use_amp": true,
35
+ "chunk_size": 100,
36
+ "n_action_steps": 100,
37
+ "vision_backbone": "resnet18",
38
+ "pretrained_backbone_weights": "IMAGENET1K_V1",
39
+ "replace_final_stride_with_dilation": false,
40
+ "pre_norm": false,
41
+ "dim_model": 512,
42
+ "n_heads": 8,
43
+ "dim_feedforward": 3200,
44
+ "feedforward_activation": "relu",
45
+ "n_encoder_layers": 4,
46
+ "n_decoder_layers": 1,
47
+ "use_vae": true,
48
+ "latent_dim": 32,
49
+ "n_vae_encoder_layers": 4,
50
+ "temporal_ensemble_coeff": null,
51
+ "dropout": 0.1,
52
+ "kl_weight": 10.0,
53
+ "optimizer_lr": 1e-05,
54
+ "optimizer_weight_decay": 0.0001,
55
+ "optimizer_lr_backbone": 1e-05
56
+ }
checkpoints/006000/pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48161e051a55c52065d5ef177e1866e41cbdd5477bb3dcdb6ea0f4a70624cc00
3
+ size 206700792
checkpoints/006000/pretrained_model/train_config.json ADDED
@@ -0,0 +1,162 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "ranegray/so101-drawing-dataset",
4
+ "root": null,
5
+ "episodes": null,
6
+ "image_transforms": {
7
+ "enable": true,
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
+ }
62
+ },
63
+ "revision": null,
64
+ "use_imagenet_stats": true,
65
+ "video_backend": "torchcodec"
66
+ },
67
+ "env": null,
68
+ "policy": {
69
+ "type": "act",
70
+ "n_obs_steps": 1,
71
+ "normalization_mapping": {
72
+ "VISUAL": "MEAN_STD",
73
+ "STATE": "MEAN_STD",
74
+ "ACTION": "MEAN_STD"
75
+ },
76
+ "input_features": {
77
+ "observation.state": {
78
+ "type": "STATE",
79
+ "shape": [
80
+ 6
81
+ ]
82
+ },
83
+ "observation.images.front": {
84
+ "type": "VISUAL",
85
+ "shape": [
86
+ 3,
87
+ 1080,
88
+ 1920
89
+ ]
90
+ }
91
+ },
92
+ "output_features": {
93
+ "action": {
94
+ "type": "ACTION",
95
+ "shape": [
96
+ 6
97
+ ]
98
+ }
99
+ },
100
+ "device": "cuda",
101
+ "use_amp": true,
102
+ "chunk_size": 100,
103
+ "n_action_steps": 100,
104
+ "vision_backbone": "resnet18",
105
+ "pretrained_backbone_weights": "IMAGENET1K_V1",
106
+ "replace_final_stride_with_dilation": false,
107
+ "pre_norm": false,
108
+ "dim_model": 512,
109
+ "n_heads": 8,
110
+ "dim_feedforward": 3200,
111
+ "feedforward_activation": "relu",
112
+ "n_encoder_layers": 4,
113
+ "n_decoder_layers": 1,
114
+ "use_vae": true,
115
+ "latent_dim": 32,
116
+ "n_vae_encoder_layers": 4,
117
+ "temporal_ensemble_coeff": null,
118
+ "dropout": 0.1,
119
+ "kl_weight": 10.0,
120
+ "optimizer_lr": 1e-05,
121
+ "optimizer_weight_decay": 0.0001,
122
+ "optimizer_lr_backbone": 1e-05
123
+ },
124
+ "output_dir": "outputs/train/act_drawing_final_safe",
125
+ "job_name": "act_drawing_final_safe",
126
+ "resume": false,
127
+ "seed": 1000,
128
+ "num_workers": 4,
129
+ "batch_size": 4,
130
+ "steps": 10000,
131
+ "eval_freq": 20000,
132
+ "log_freq": 200,
133
+ "save_checkpoint": true,
134
+ "save_freq": 1000,
135
+ "use_policy_training_preset": true,
136
+ "optimizer": {
137
+ "type": "adamw",
138
+ "lr": 1e-05,
139
+ "weight_decay": 0.0001,
140
+ "grad_clip_norm": 10.0,
141
+ "betas": [
142
+ 0.9,
143
+ 0.999
144
+ ],
145
+ "eps": 1e-08
146
+ },
147
+ "scheduler": null,
148
+ "eval": {
149
+ "n_episodes": 50,
150
+ "batch_size": 50,
151
+ "use_async_envs": false
152
+ },
153
+ "wandb": {
154
+ "enable": true,
155
+ "disable_artifact": false,
156
+ "project": "lerobot",
157
+ "entity": null,
158
+ "notes": null,
159
+ "run_id": "2ags28sq",
160
+ "mode": null
161
+ }
162
+ }
checkpoints/006000/training_state/optimizer_param_groups.json ADDED
@@ -0,0 +1,191 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "lr": 1e-05,
4
+ "betas": [
5
+ 0.9,
6
+ 0.999
7
+ ],
8
+ "eps": 1e-08,
9
+ "weight_decay": 0.0001,
10
+ "amsgrad": false,
11
+ "maximize": false,
12
+ "foreach": null,
13
+ "capturable": false,
14
+ "differentiable": false,
15
+ "fused": null,
16
+ "decoupled_weight_decay": true,
17
+ "params": [
18
+ 0,
19
+ 1,
20
+ 2,
21
+ 3,
22
+ 4,
23
+ 5,
24
+ 6,
25
+ 7,
26
+ 8,
27
+ 9,
28
+ 10,
29
+ 11,
30
+ 12,
31
+ 13,
32
+ 14,
33
+ 15,
34
+ 16,
35
+ 17,
36
+ 18,
37
+ 19,
38
+ 20,
39
+ 21,
40
+ 22,
41
+ 23,
42
+ 24,
43
+ 25,
44
+ 26,
45
+ 27,
46
+ 28,
47
+ 29,
48
+ 30,
49
+ 31,
50
+ 32,
51
+ 33,
52
+ 34,
53
+ 35,
54
+ 36,
55
+ 37,
56
+ 38,
57
+ 39,
58
+ 40,
59
+ 41,
60
+ 42,
61
+ 43,
62
+ 44,
63
+ 45,
64
+ 46,
65
+ 47,
66
+ 48,
67
+ 49,
68
+ 50,
69
+ 51,
70
+ 52,
71
+ 53,
72
+ 54,
73
+ 55,
74
+ 56,
75
+ 57,
76
+ 58,
77
+ 59,
78
+ 60,
79
+ 61,
80
+ 62,
81
+ 63,
82
+ 64,
83
+ 65,
84
+ 66,
85
+ 67,
86
+ 68,
87
+ 69,
88
+ 70,
89
+ 71,
90
+ 72,
91
+ 73,
92
+ 74,
93
+ 75,
94
+ 76,
95
+ 77,
96
+ 78,
97
+ 79,
98
+ 80,
99
+ 81,
100
+ 82,
101
+ 83,
102
+ 84,
103
+ 85,
104
+ 86,
105
+ 87,
106
+ 88,
107
+ 89,
108
+ 90,
109
+ 91,
110
+ 92,
111
+ 93,
112
+ 94,
113
+ 95,
114
+ 96,
115
+ 97,
116
+ 98,
117
+ 99,
118
+ 100,
119
+ 101,
120
+ 102,
121
+ 103,
122
+ 104,
123
+ 105,
124
+ 106,
125
+ 107,
126
+ 108,
127
+ 109,
128
+ 110,
129
+ 111,
130
+ 112,
131
+ 113,
132
+ 114,
133
+ 115,
134
+ 116,
135
+ 117,
136
+ 118,
137
+ 119,
138
+ 120,
139
+ 121,
140
+ 122,
141
+ 123,
142
+ 124,
143
+ 125,
144
+ 126,
145
+ 127,
146
+ 128,
147
+ 129,
148
+ 130,
149
+ 131,
150
+ 132
151
+ ]
152
+ },
153
+ {
154
+ "lr": 1e-05,
155
+ "betas": [
156
+ 0.9,
157
+ 0.999
158
+ ],
159
+ "eps": 1e-08,
160
+ "weight_decay": 0.0001,
161
+ "amsgrad": false,
162
+ "maximize": false,
163
+ "foreach": null,
164
+ "capturable": false,
165
+ "differentiable": false,
166
+ "fused": null,
167
+ "decoupled_weight_decay": true,
168
+ "params": [
169
+ 133,
170
+ 134,
171
+ 135,
172
+ 136,
173
+ 137,
174
+ 138,
175
+ 139,
176
+ 140,
177
+ 141,
178
+ 142,
179
+ 143,
180
+ 144,
181
+ 145,
182
+ 146,
183
+ 147,
184
+ 148,
185
+ 149,
186
+ 150,
187
+ 151,
188
+ 152
189
+ ]
190
+ }
191
+ ]
checkpoints/006000/training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da20bebd4852511164309013694246e83359797f43ee70e63d319866c76f9d57
3
+ size 412817652
checkpoints/006000/training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb62d91879613f00e57ecd05b975e0c8391f00c8d1dbc1801d6a11581fd5e507
3
+ size 15708
checkpoints/006000/training_state/training_step.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "step": 6000
3
+ }
checkpoints/007000/pretrained_model/config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "act",
3
+ "n_obs_steps": 1,
4
+ "normalization_mapping": {
5
+ "VISUAL": "MEAN_STD",
6
+ "STATE": "MEAN_STD",
7
+ "ACTION": "MEAN_STD"
8
+ },
9
+ "input_features": {
10
+ "observation.state": {
11
+ "type": "STATE",
12
+ "shape": [
13
+ 6
14
+ ]
15
+ },
16
+ "observation.images.front": {
17
+ "type": "VISUAL",
18
+ "shape": [
19
+ 3,
20
+ 1080,
21
+ 1920
22
+ ]
23
+ }
24
+ },
25
+ "output_features": {
26
+ "action": {
27
+ "type": "ACTION",
28
+ "shape": [
29
+ 6
30
+ ]
31
+ }
32
+ },
33
+ "device": "cuda",
34
+ "use_amp": true,
35
+ "chunk_size": 100,
36
+ "n_action_steps": 100,
37
+ "vision_backbone": "resnet18",
38
+ "pretrained_backbone_weights": "IMAGENET1K_V1",
39
+ "replace_final_stride_with_dilation": false,
40
+ "pre_norm": false,
41
+ "dim_model": 512,
42
+ "n_heads": 8,
43
+ "dim_feedforward": 3200,
44
+ "feedforward_activation": "relu",
45
+ "n_encoder_layers": 4,
46
+ "n_decoder_layers": 1,
47
+ "use_vae": true,
48
+ "latent_dim": 32,
49
+ "n_vae_encoder_layers": 4,
50
+ "temporal_ensemble_coeff": null,
51
+ "dropout": 0.1,
52
+ "kl_weight": 10.0,
53
+ "optimizer_lr": 1e-05,
54
+ "optimizer_weight_decay": 0.0001,
55
+ "optimizer_lr_backbone": 1e-05
56
+ }
checkpoints/007000/pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28b150a8fadd5d623a61f10ff593f8de5d3924a2e1a49bd143d7a6ce961c1391
3
+ size 206700792
checkpoints/007000/pretrained_model/train_config.json ADDED
@@ -0,0 +1,162 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "ranegray/so101-drawing-dataset",
4
+ "root": null,
5
+ "episodes": null,
6
+ "image_transforms": {
7
+ "enable": true,
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
+ }
62
+ },
63
+ "revision": null,
64
+ "use_imagenet_stats": true,
65
+ "video_backend": "torchcodec"
66
+ },
67
+ "env": null,
68
+ "policy": {
69
+ "type": "act",
70
+ "n_obs_steps": 1,
71
+ "normalization_mapping": {
72
+ "VISUAL": "MEAN_STD",
73
+ "STATE": "MEAN_STD",
74
+ "ACTION": "MEAN_STD"
75
+ },
76
+ "input_features": {
77
+ "observation.state": {
78
+ "type": "STATE",
79
+ "shape": [
80
+ 6
81
+ ]
82
+ },
83
+ "observation.images.front": {
84
+ "type": "VISUAL",
85
+ "shape": [
86
+ 3,
87
+ 1080,
88
+ 1920
89
+ ]
90
+ }
91
+ },
92
+ "output_features": {
93
+ "action": {
94
+ "type": "ACTION",
95
+ "shape": [
96
+ 6
97
+ ]
98
+ }
99
+ },
100
+ "device": "cuda",
101
+ "use_amp": true,
102
+ "chunk_size": 100,
103
+ "n_action_steps": 100,
104
+ "vision_backbone": "resnet18",
105
+ "pretrained_backbone_weights": "IMAGENET1K_V1",
106
+ "replace_final_stride_with_dilation": false,
107
+ "pre_norm": false,
108
+ "dim_model": 512,
109
+ "n_heads": 8,
110
+ "dim_feedforward": 3200,
111
+ "feedforward_activation": "relu",
112
+ "n_encoder_layers": 4,
113
+ "n_decoder_layers": 1,
114
+ "use_vae": true,
115
+ "latent_dim": 32,
116
+ "n_vae_encoder_layers": 4,
117
+ "temporal_ensemble_coeff": null,
118
+ "dropout": 0.1,
119
+ "kl_weight": 10.0,
120
+ "optimizer_lr": 1e-05,
121
+ "optimizer_weight_decay": 0.0001,
122
+ "optimizer_lr_backbone": 1e-05
123
+ },
124
+ "output_dir": "outputs/train/act_drawing_final_safe",
125
+ "job_name": "act_drawing_final_safe",
126
+ "resume": false,
127
+ "seed": 1000,
128
+ "num_workers": 4,
129
+ "batch_size": 4,
130
+ "steps": 10000,
131
+ "eval_freq": 20000,
132
+ "log_freq": 200,
133
+ "save_checkpoint": true,
134
+ "save_freq": 1000,
135
+ "use_policy_training_preset": true,
136
+ "optimizer": {
137
+ "type": "adamw",
138
+ "lr": 1e-05,
139
+ "weight_decay": 0.0001,
140
+ "grad_clip_norm": 10.0,
141
+ "betas": [
142
+ 0.9,
143
+ 0.999
144
+ ],
145
+ "eps": 1e-08
146
+ },
147
+ "scheduler": null,
148
+ "eval": {
149
+ "n_episodes": 50,
150
+ "batch_size": 50,
151
+ "use_async_envs": false
152
+ },
153
+ "wandb": {
154
+ "enable": true,
155
+ "disable_artifact": false,
156
+ "project": "lerobot",
157
+ "entity": null,
158
+ "notes": null,
159
+ "run_id": "2ags28sq",
160
+ "mode": null
161
+ }
162
+ }
checkpoints/007000/training_state/optimizer_param_groups.json ADDED
@@ -0,0 +1,191 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "lr": 1e-05,
4
+ "betas": [
5
+ 0.9,
6
+ 0.999
7
+ ],
8
+ "eps": 1e-08,
9
+ "weight_decay": 0.0001,
10
+ "amsgrad": false,
11
+ "maximize": false,
12
+ "foreach": null,
13
+ "capturable": false,
14
+ "differentiable": false,
15
+ "fused": null,
16
+ "decoupled_weight_decay": true,
17
+ "params": [
18
+ 0,
19
+ 1,
20
+ 2,
21
+ 3,
22
+ 4,
23
+ 5,
24
+ 6,
25
+ 7,
26
+ 8,
27
+ 9,
28
+ 10,
29
+ 11,
30
+ 12,
31
+ 13,
32
+ 14,
33
+ 15,
34
+ 16,
35
+ 17,
36
+ 18,
37
+ 19,
38
+ 20,
39
+ 21,
40
+ 22,
41
+ 23,
42
+ 24,
43
+ 25,
44
+ 26,
45
+ 27,
46
+ 28,
47
+ 29,
48
+ 30,
49
+ 31,
50
+ 32,
51
+ 33,
52
+ 34,
53
+ 35,
54
+ 36,
55
+ 37,
56
+ 38,
57
+ 39,
58
+ 40,
59
+ 41,
60
+ 42,
61
+ 43,
62
+ 44,
63
+ 45,
64
+ 46,
65
+ 47,
66
+ 48,
67
+ 49,
68
+ 50,
69
+ 51,
70
+ 52,
71
+ 53,
72
+ 54,
73
+ 55,
74
+ 56,
75
+ 57,
76
+ 58,
77
+ 59,
78
+ 60,
79
+ 61,
80
+ 62,
81
+ 63,
82
+ 64,
83
+ 65,
84
+ 66,
85
+ 67,
86
+ 68,
87
+ 69,
88
+ 70,
89
+ 71,
90
+ 72,
91
+ 73,
92
+ 74,
93
+ 75,
94
+ 76,
95
+ 77,
96
+ 78,
97
+ 79,
98
+ 80,
99
+ 81,
100
+ 82,
101
+ 83,
102
+ 84,
103
+ 85,
104
+ 86,
105
+ 87,
106
+ 88,
107
+ 89,
108
+ 90,
109
+ 91,
110
+ 92,
111
+ 93,
112
+ 94,
113
+ 95,
114
+ 96,
115
+ 97,
116
+ 98,
117
+ 99,
118
+ 100,
119
+ 101,
120
+ 102,
121
+ 103,
122
+ 104,
123
+ 105,
124
+ 106,
125
+ 107,
126
+ 108,
127
+ 109,
128
+ 110,
129
+ 111,
130
+ 112,
131
+ 113,
132
+ 114,
133
+ 115,
134
+ 116,
135
+ 117,
136
+ 118,
137
+ 119,
138
+ 120,
139
+ 121,
140
+ 122,
141
+ 123,
142
+ 124,
143
+ 125,
144
+ 126,
145
+ 127,
146
+ 128,
147
+ 129,
148
+ 130,
149
+ 131,
150
+ 132
151
+ ]
152
+ },
153
+ {
154
+ "lr": 1e-05,
155
+ "betas": [
156
+ 0.9,
157
+ 0.999
158
+ ],
159
+ "eps": 1e-08,
160
+ "weight_decay": 0.0001,
161
+ "amsgrad": false,
162
+ "maximize": false,
163
+ "foreach": null,
164
+ "capturable": false,
165
+ "differentiable": false,
166
+ "fused": null,
167
+ "decoupled_weight_decay": true,
168
+ "params": [
169
+ 133,
170
+ 134,
171
+ 135,
172
+ 136,
173
+ 137,
174
+ 138,
175
+ 139,
176
+ 140,
177
+ 141,
178
+ 142,
179
+ 143,
180
+ 144,
181
+ 145,
182
+ 146,
183
+ 147,
184
+ 148,
185
+ 149,
186
+ 150,
187
+ 151,
188
+ 152
189
+ ]
190
+ }
191
+ ]
checkpoints/007000/training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0a3375953a8e6d5d3e8d003fb5659929cb5a19f4a16db17141bef7dfbbf3ee7
3
+ size 412817652
checkpoints/007000/training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5097b919aa111ff3c48b46e1258fd23961434d53575bb652d1f696cda8cebd9b
3
+ size 15708
checkpoints/007000/training_state/training_step.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "step": 7000
3
+ }