Hugging Face's logo

Dimios45
/
act1

Robotics
LeRobot
Safetensors
act
Model card Files
xet
Community
5usu2806 commited on
Commit
23311d8
·
1 Parent(s): 666b47b

Upload full ACT training checkpoints (20K–100K)

Browse files
Files changed (46) hide show
  1. checkpoints/020000/pretrained_model/config.json +63 -0
  2. checkpoints/020000/pretrained_model/model.safetensors +3 -0
  3. checkpoints/020000/pretrained_model/policy_postprocessor.json +32 -0
  4. checkpoints/020000/pretrained_model/policy_postprocessor_step_0_unnormalizer_processor.safetensors +3 -0
  5. checkpoints/020000/pretrained_model/policy_preprocessor.json +56 -0
  6. checkpoints/020000/pretrained_model/policy_preprocessor_step_3_normalizer_processor.safetensors +3 -0
  7. checkpoints/020000/pretrained_model/train_config.json +186 -0
  8. checkpoints/020000/training_state/optimizer_param_groups.json +189 -0
  9. checkpoints/020000/training_state/optimizer_state.safetensors +3 -0
  10. checkpoints/020000/training_state/rng_state.safetensors +3 -0
  11. checkpoints/020000/training_state/training_step.json +3 -0
  12. checkpoints/040000/pretrained_model/config.json +63 -0
  13. checkpoints/040000/pretrained_model/model.safetensors +3 -0
  14. checkpoints/040000/pretrained_model/policy_postprocessor.json +32 -0
  15. checkpoints/040000/pretrained_model/policy_postprocessor_step_0_unnormalizer_processor.safetensors +3 -0
  16. checkpoints/040000/pretrained_model/policy_preprocessor.json +56 -0
  17. checkpoints/040000/pretrained_model/policy_preprocessor_step_3_normalizer_processor.safetensors +3 -0
  18. checkpoints/040000/pretrained_model/train_config.json +186 -0
  19. checkpoints/040000/training_state/optimizer_param_groups.json +189 -0
  20. checkpoints/040000/training_state/optimizer_state.safetensors +3 -0
  21. checkpoints/040000/training_state/rng_state.safetensors +3 -0
  22. checkpoints/040000/training_state/training_step.json +3 -0
  23. checkpoints/060000/pretrained_model/config.json +63 -0
  24. checkpoints/060000/pretrained_model/model.safetensors +3 -0
  25. checkpoints/060000/pretrained_model/policy_postprocessor.json +32 -0
  26. checkpoints/060000/pretrained_model/policy_postprocessor_step_0_unnormalizer_processor.safetensors +3 -0
  27. checkpoints/060000/pretrained_model/policy_preprocessor.json +56 -0
  28. checkpoints/060000/pretrained_model/policy_preprocessor_step_3_normalizer_processor.safetensors +3 -0
  29. checkpoints/060000/pretrained_model/train_config.json +186 -0
  30. checkpoints/060000/training_state/optimizer_param_groups.json +189 -0
  31. checkpoints/060000/training_state/optimizer_state.safetensors +3 -0
  32. checkpoints/060000/training_state/rng_state.safetensors +3 -0
  33. checkpoints/060000/training_state/training_step.json +3 -0
  34. checkpoints/080000/pretrained_model/config.json +63 -0
  35. checkpoints/080000/pretrained_model/model.safetensors +3 -0
  36. checkpoints/080000/pretrained_model/policy_postprocessor.json +32 -0
  37. checkpoints/080000/pretrained_model/policy_postprocessor_step_0_unnormalizer_processor.safetensors +3 -0
  38. checkpoints/080000/pretrained_model/policy_preprocessor.json +56 -0
  39. checkpoints/080000/pretrained_model/policy_preprocessor_step_3_normalizer_processor.safetensors +3 -0
  40. checkpoints/080000/pretrained_model/train_config.json +186 -0
  41. checkpoints/080000/training_state/optimizer_param_groups.json +189 -0
  42. checkpoints/080000/training_state/optimizer_state.safetensors +3 -0
  43. checkpoints/080000/training_state/rng_state.safetensors +3 -0
  44. checkpoints/080000/training_state/training_step.json +3 -0
  45. checkpoints/100000 +1 -0
  46. checkpoints/last +1 -0
checkpoints/020000/pretrained_model/config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "act",
3
+ "n_obs_steps": 1,
4
+ "input_features": {
5
+ "observation.state": {
6
+ "type": "STATE",
7
+ "shape": [
8
+ 6
9
+ ]
10
+ },
11
+ "observation.images.front": {
12
+ "type": "VISUAL",
13
+ "shape": [
14
+ 3,
15
+ 480,
16
+ 640
17
+ ]
18
+ }
19
+ },
20
+ "output_features": {
21
+ "action": {
22
+ "type": "ACTION",
23
+ "shape": [
24
+ 6
25
+ ]
26
+ }
27
+ },
28
+ "device": "cuda",
29
+ "use_amp": false,
30
+ "push_to_hub": true,
31
+ "repo_id": "Dimios45/act1",
32
+ "private": null,
33
+ "tags": null,
34
+ "license": null,
35
+ "pretrained_path": null,
36
+ "chunk_size": 100,
37
+ "n_action_steps": 100,
38
+ "normalization_mapping": {
39
+ "VISUAL": "MEAN_STD",
40
+ "STATE": "MEAN_STD",
41
+ "ACTION": "MEAN_STD"
42
+ },
43
+ "vision_backbone": "resnet18",
44
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
45
+ "replace_final_stride_with_dilation": false,
46
+ "pre_norm": false,
47
+ "dim_model": 512,
48
+ "n_heads": 8,
49
+ "dim_feedforward": 3200,
50
+ "feedforward_activation": "relu",
51
+ "n_encoder_layers": 4,
52
+ "n_decoder_layers": 1,
53
+ "use_vae": true,
54
+ "latent_dim": 32,
55
+ "n_vae_encoder_layers": 4,
56
+ "temporal_ensemble_coeff": null,
57
+ "dropout": 0.1,
58
+ "kl_weight": 10.0,
59
+ "use_torch_compile": false,
60
+ "optimizer_lr": 1e-05,
61
+ "optimizer_weight_decay": 0.0001,
62
+ "optimizer_lr_backbone": 1e-05
63
+ }
checkpoints/020000/pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4cdf56d1159d9f3a80be3744e1f2f9aa53c2d03235b130508dd2210c284a145
3
+ size 206699736
checkpoints/020000/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": "MEAN_STD",
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/020000/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 sha256:93e38dbbaf8f561886dfc5aa9497d5cd263387d20cab724c84b5be152b85dea2
3
+ size 6560
checkpoints/020000/pretrained_model/policy_preprocessor.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "policy_preprocessor",
3
+ "steps": [
4
+ {
5
+ "registry_name": "rename_observations_processor",
6
+ "config": {
7
+ "rename_map": {}
8
+ }
9
+ },
10
+ {
11
+ "registry_name": "to_batch_processor",
12
+ "config": {}
13
+ },
14
+ {
15
+ "registry_name": "device_processor",
16
+ "config": {
17
+ "device": "cuda",
18
+ "float_dtype": null
19
+ }
20
+ },
21
+ {
22
+ "registry_name": "normalizer_processor",
23
+ "config": {
24
+ "eps": 1e-08,
25
+ "features": {
26
+ "observation.state": {
27
+ "type": "STATE",
28
+ "shape": [
29
+ 6
30
+ ]
31
+ },
32
+ "observation.images.front": {
33
+ "type": "VISUAL",
34
+ "shape": [
35
+ 3,
36
+ 480,
37
+ 640
38
+ ]
39
+ },
40
+ "action": {
41
+ "type": "ACTION",
42
+ "shape": [
43
+ 6
44
+ ]
45
+ }
46
+ },
47
+ "norm_map": {
48
+ "VISUAL": "MEAN_STD",
49
+ "STATE": "MEAN_STD",
50
+ "ACTION": "MEAN_STD"
51
+ }
52
+ },
53
+ "state_file": "policy_preprocessor_step_3_normalizer_processor.safetensors"
54
+ }
55
+ ]
56
+ }
checkpoints/020000/pretrained_model/policy_preprocessor_step_3_normalizer_processor.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93e38dbbaf8f561886dfc5aa9497d5cd263387d20cab724c84b5be152b85dea2
3
+ size 6560
checkpoints/020000/pretrained_model/train_config.json ADDED
@@ -0,0 +1,186 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "Dimios45/santra",
4
+ "root": "santra/santra_demo_20251108_102726",
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": "pyav",
80
+ "streaming": false
81
+ },
82
+ "env": null,
83
+ "policy": {
84
+ "type": "act",
85
+ "n_obs_steps": 1,
86
+ "input_features": {
87
+ "observation.state": {
88
+ "type": "STATE",
89
+ "shape": [
90
+ 6
91
+ ]
92
+ },
93
+ "observation.images.front": {
94
+ "type": "VISUAL",
95
+ "shape": [
96
+ 3,
97
+ 480,
98
+ 640
99
+ ]
100
+ }
101
+ },
102
+ "output_features": {
103
+ "action": {
104
+ "type": "ACTION",
105
+ "shape": [
106
+ 6
107
+ ]
108
+ }
109
+ },
110
+ "device": "cuda",
111
+ "use_amp": false,
112
+ "push_to_hub": true,
113
+ "repo_id": "Dimios45/act1",
114
+ "private": null,
115
+ "tags": null,
116
+ "license": null,
117
+ "pretrained_path": null,
118
+ "chunk_size": 100,
119
+ "n_action_steps": 100,
120
+ "normalization_mapping": {
121
+ "VISUAL": "MEAN_STD",
122
+ "STATE": "MEAN_STD",
123
+ "ACTION": "MEAN_STD"
124
+ },
125
+ "vision_backbone": "resnet18",
126
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
127
+ "replace_final_stride_with_dilation": false,
128
+ "pre_norm": false,
129
+ "dim_model": 512,
130
+ "n_heads": 8,
131
+ "dim_feedforward": 3200,
132
+ "feedforward_activation": "relu",
133
+ "n_encoder_layers": 4,
134
+ "n_decoder_layers": 1,
135
+ "use_vae": true,
136
+ "latent_dim": 32,
137
+ "n_vae_encoder_layers": 4,
138
+ "temporal_ensemble_coeff": null,
139
+ "dropout": 0.1,
140
+ "kl_weight": 10.0,
141
+ "use_torch_compile": false,
142
+ "optimizer_lr": 1e-05,
143
+ "optimizer_weight_decay": 0.0001,
144
+ "optimizer_lr_backbone": 1e-05
145
+ },
146
+ "output_dir": "outputs/train/act_santra_cuda",
147
+ "job_name": "act_santra_cuda",
148
+ "resume": false,
149
+ "seed": 1000,
150
+ "num_workers": 4,
151
+ "batch_size": 8,
152
+ "steps": 100000,
153
+ "eval_freq": 20000,
154
+ "log_freq": 200,
155
+ "save_checkpoint": true,
156
+ "save_freq": 20000,
157
+ "use_policy_training_preset": true,
158
+ "optimizer": {
159
+ "type": "adamw",
160
+ "lr": 1e-05,
161
+ "weight_decay": 0.0001,
162
+ "grad_clip_norm": 10.0,
163
+ "betas": [
164
+ 0.9,
165
+ 0.999
166
+ ],
167
+ "eps": 1e-08
168
+ },
169
+ "scheduler": null,
170
+ "eval": {
171
+ "n_episodes": 50,
172
+ "batch_size": 50,
173
+ "use_async_envs": false
174
+ },
175
+ "wandb": {
176
+ "enable": true,
177
+ "disable_artifact": false,
178
+ "project": "lerobot",
179
+ "entity": null,
180
+ "notes": null,
181
+ "run_id": "t8w1ifju",
182
+ "mode": null
183
+ },
184
+ "checkpoint_path": null,
185
+ "rename_map": {}
186
+ }
checkpoints/020000/training_state/optimizer_param_groups.json ADDED
@@ -0,0 +1,189 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "foreach": null,
12
+ "maximize": false,
13
+ "capturable": false,
14
+ "differentiable": false,
15
+ "fused": null,
16
+ "params": [
17
+ 0,
18
+ 1,
19
+ 2,
20
+ 3,
21
+ 4,
22
+ 5,
23
+ 6,
24
+ 7,
25
+ 8,
26
+ 9,
27
+ 10,
28
+ 11,
29
+ 12,
30
+ 13,
31
+ 14,
32
+ 15,
33
+ 16,
34
+ 17,
35
+ 18,
36
+ 19,
37
+ 20,
38
+ 21,
39
+ 22,
40
+ 23,
41
+ 24,
42
+ 25,
43
+ 26,
44
+ 27,
45
+ 28,
46
+ 29,
47
+ 30,
48
+ 31,
49
+ 32,
50
+ 33,
51
+ 34,
52
+ 35,
53
+ 36,
54
+ 37,
55
+ 38,
56
+ 39,
57
+ 40,
58
+ 41,
59
+ 42,
60
+ 43,
61
+ 44,
62
+ 45,
63
+ 46,
64
+ 47,
65
+ 48,
66
+ 49,
67
+ 50,
68
+ 51,
69
+ 52,
70
+ 53,
71
+ 54,
72
+ 55,
73
+ 56,
74
+ 57,
75
+ 58,
76
+ 59,
77
+ 60,
78
+ 61,
79
+ 62,
80
+ 63,
81
+ 64,
82
+ 65,
83
+ 66,
84
+ 67,
85
+ 68,
86
+ 69,
87
+ 70,
88
+ 71,
89
+ 72,
90
+ 73,
91
+ 74,
92
+ 75,
93
+ 76,
94
+ 77,
95
+ 78,
96
+ 79,
97
+ 80,
98
+ 81,
99
+ 82,
100
+ 83,
101
+ 84,
102
+ 85,
103
+ 86,
104
+ 87,
105
+ 88,
106
+ 89,
107
+ 90,
108
+ 91,
109
+ 92,
110
+ 93,
111
+ 94,
112
+ 95,
113
+ 96,
114
+ 97,
115
+ 98,
116
+ 99,
117
+ 100,
118
+ 101,
119
+ 102,
120
+ 103,
121
+ 104,
122
+ 105,
123
+ 106,
124
+ 107,
125
+ 108,
126
+ 109,
127
+ 110,
128
+ 111,
129
+ 112,
130
+ 113,
131
+ 114,
132
+ 115,
133
+ 116,
134
+ 117,
135
+ 118,
136
+ 119,
137
+ 120,
138
+ 121,
139
+ 122,
140
+ 123,
141
+ 124,
142
+ 125,
143
+ 126,
144
+ 127,
145
+ 128,
146
+ 129,
147
+ 130,
148
+ 131,
149
+ 132
150
+ ]
151
+ },
152
+ {
153
+ "lr": 1e-05,
154
+ "betas": [
155
+ 0.9,
156
+ 0.999
157
+ ],
158
+ "eps": 1e-08,
159
+ "weight_decay": 0.0001,
160
+ "amsgrad": false,
161
+ "foreach": null,
162
+ "maximize": false,
163
+ "capturable": false,
164
+ "differentiable": false,
165
+ "fused": null,
166
+ "params": [
167
+ 133,
168
+ 134,
169
+ 135,
170
+ 136,
171
+ 137,
172
+ 138,
173
+ 139,
174
+ 140,
175
+ 141,
176
+ 142,
177
+ 143,
178
+ 144,
179
+ 145,
180
+ 146,
181
+ 147,
182
+ 148,
183
+ 149,
184
+ 150,
185
+ 151,
186
+ 152
187
+ ]
188
+ }
189
+ ]
checkpoints/020000/training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0b16c8f4ad5319a26fa0d894ae0e22a866ebfb5ed841ded7a0d3c54af1b8543
3
+ size 412817652
checkpoints/020000/training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30e0586bd3297bd14d282ace0c161c92ee9af18ae66fe715aebeceb7ec62d83e
3
+ size 15708
checkpoints/020000/training_state/training_step.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "step": 20000
3
+ }
checkpoints/040000/pretrained_model/config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "act",
3
+ "n_obs_steps": 1,
4
+ "input_features": {
5
+ "observation.state": {
6
+ "type": "STATE",
7
+ "shape": [
8
+ 6
9
+ ]
10
+ },
11
+ "observation.images.front": {
12
+ "type": "VISUAL",
13
+ "shape": [
14
+ 3,
15
+ 480,
16
+ 640
17
+ ]
18
+ }
19
+ },
20
+ "output_features": {
21
+ "action": {
22
+ "type": "ACTION",
23
+ "shape": [
24
+ 6
25
+ ]
26
+ }
27
+ },
28
+ "device": "cuda",
29
+ "use_amp": false,
30
+ "push_to_hub": true,
31
+ "repo_id": "Dimios45/act1",
32
+ "private": null,
33
+ "tags": null,
34
+ "license": null,
35
+ "pretrained_path": null,
36
+ "chunk_size": 100,
37
+ "n_action_steps": 100,
38
+ "normalization_mapping": {
39
+ "VISUAL": "MEAN_STD",
40
+ "STATE": "MEAN_STD",
41
+ "ACTION": "MEAN_STD"
42
+ },
43
+ "vision_backbone": "resnet18",
44
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
45
+ "replace_final_stride_with_dilation": false,
46
+ "pre_norm": false,
47
+ "dim_model": 512,
48
+ "n_heads": 8,
49
+ "dim_feedforward": 3200,
50
+ "feedforward_activation": "relu",
51
+ "n_encoder_layers": 4,
52
+ "n_decoder_layers": 1,
53
+ "use_vae": true,
54
+ "latent_dim": 32,
55
+ "n_vae_encoder_layers": 4,
56
+ "temporal_ensemble_coeff": null,
57
+ "dropout": 0.1,
58
+ "kl_weight": 10.0,
59
+ "use_torch_compile": false,
60
+ "optimizer_lr": 1e-05,
61
+ "optimizer_weight_decay": 0.0001,
62
+ "optimizer_lr_backbone": 1e-05
63
+ }
checkpoints/040000/pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69415c9448075ee73bf7005f2c7044c65706e0cc1fbe6a6b9a72555c4f03efe4
3
+ size 206699736
checkpoints/040000/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": "MEAN_STD",
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/040000/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 sha256:93e38dbbaf8f561886dfc5aa9497d5cd263387d20cab724c84b5be152b85dea2
3
+ size 6560
checkpoints/040000/pretrained_model/policy_preprocessor.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "policy_preprocessor",
3
+ "steps": [
4
+ {
5
+ "registry_name": "rename_observations_processor",
6
+ "config": {
7
+ "rename_map": {}
8
+ }
9
+ },
10
+ {
11
+ "registry_name": "to_batch_processor",
12
+ "config": {}
13
+ },
14
+ {
15
+ "registry_name": "device_processor",
16
+ "config": {
17
+ "device": "cuda",
18
+ "float_dtype": null
19
+ }
20
+ },
21
+ {
22
+ "registry_name": "normalizer_processor",
23
+ "config": {
24
+ "eps": 1e-08,
25
+ "features": {
26
+ "observation.state": {
27
+ "type": "STATE",
28
+ "shape": [
29
+ 6
30
+ ]
31
+ },
32
+ "observation.images.front": {
33
+ "type": "VISUAL",
34
+ "shape": [
35
+ 3,
36
+ 480,
37
+ 640
38
+ ]
39
+ },
40
+ "action": {
41
+ "type": "ACTION",
42
+ "shape": [
43
+ 6
44
+ ]
45
+ }
46
+ },
47
+ "norm_map": {
48
+ "VISUAL": "MEAN_STD",
49
+ "STATE": "MEAN_STD",
50
+ "ACTION": "MEAN_STD"
51
+ }
52
+ },
53
+ "state_file": "policy_preprocessor_step_3_normalizer_processor.safetensors"
54
+ }
55
+ ]
56
+ }
checkpoints/040000/pretrained_model/policy_preprocessor_step_3_normalizer_processor.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93e38dbbaf8f561886dfc5aa9497d5cd263387d20cab724c84b5be152b85dea2
3
+ size 6560
checkpoints/040000/pretrained_model/train_config.json ADDED
@@ -0,0 +1,186 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "Dimios45/santra",
4
+ "root": "santra/santra_demo_20251108_102726",
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": "pyav",
80
+ "streaming": false
81
+ },
82
+ "env": null,
83
+ "policy": {
84
+ "type": "act",
85
+ "n_obs_steps": 1,
86
+ "input_features": {
87
+ "observation.state": {
88
+ "type": "STATE",
89
+ "shape": [
90
+ 6
91
+ ]
92
+ },
93
+ "observation.images.front": {
94
+ "type": "VISUAL",
95
+ "shape": [
96
+ 3,
97
+ 480,
98
+ 640
99
+ ]
100
+ }
101
+ },
102
+ "output_features": {
103
+ "action": {
104
+ "type": "ACTION",
105
+ "shape": [
106
+ 6
107
+ ]
108
+ }
109
+ },
110
+ "device": "cuda",
111
+ "use_amp": false,
112
+ "push_to_hub": true,
113
+ "repo_id": "Dimios45/act1",
114
+ "private": null,
115
+ "tags": null,
116
+ "license": null,
117
+ "pretrained_path": null,
118
+ "chunk_size": 100,
119
+ "n_action_steps": 100,
120
+ "normalization_mapping": {
121
+ "VISUAL": "MEAN_STD",
122
+ "STATE": "MEAN_STD",
123
+ "ACTION": "MEAN_STD"
124
+ },
125
+ "vision_backbone": "resnet18",
126
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
127
+ "replace_final_stride_with_dilation": false,
128
+ "pre_norm": false,
129
+ "dim_model": 512,
130
+ "n_heads": 8,
131
+ "dim_feedforward": 3200,
132
+ "feedforward_activation": "relu",
133
+ "n_encoder_layers": 4,
134
+ "n_decoder_layers": 1,
135
+ "use_vae": true,
136
+ "latent_dim": 32,
137
+ "n_vae_encoder_layers": 4,
138
+ "temporal_ensemble_coeff": null,
139
+ "dropout": 0.1,
140
+ "kl_weight": 10.0,
141
+ "use_torch_compile": false,
142
+ "optimizer_lr": 1e-05,
143
+ "optimizer_weight_decay": 0.0001,
144
+ "optimizer_lr_backbone": 1e-05
145
+ },
146
+ "output_dir": "outputs/train/act_santra_cuda",
147
+ "job_name": "act_santra_cuda",
148
+ "resume": false,
149
+ "seed": 1000,
150
+ "num_workers": 4,
151
+ "batch_size": 8,
152
+ "steps": 100000,
153
+ "eval_freq": 20000,
154
+ "log_freq": 200,
155
+ "save_checkpoint": true,
156
+ "save_freq": 20000,
157
+ "use_policy_training_preset": true,
158
+ "optimizer": {
159
+ "type": "adamw",
160
+ "lr": 1e-05,
161
+ "weight_decay": 0.0001,
162
+ "grad_clip_norm": 10.0,
163
+ "betas": [
164
+ 0.9,
165
+ 0.999
166
+ ],
167
+ "eps": 1e-08
168
+ },
169
+ "scheduler": null,
170
+ "eval": {
171
+ "n_episodes": 50,
172
+ "batch_size": 50,
173
+ "use_async_envs": false
174
+ },
175
+ "wandb": {
176
+ "enable": true,
177
+ "disable_artifact": false,
178
+ "project": "lerobot",
179
+ "entity": null,
180
+ "notes": null,
181
+ "run_id": "t8w1ifju",
182
+ "mode": null
183
+ },
184
+ "checkpoint_path": null,
185
+ "rename_map": {}
186
+ }
checkpoints/040000/training_state/optimizer_param_groups.json ADDED
@@ -0,0 +1,189 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "foreach": null,
12
+ "maximize": false,
13
+ "capturable": false,
14
+ "differentiable": false,
15
+ "fused": null,
16
+ "params": [
17
+ 0,
18
+ 1,
19
+ 2,
20
+ 3,
21
+ 4,
22
+ 5,
23
+ 6,
24
+ 7,
25
+ 8,
26
+ 9,
27
+ 10,
28
+ 11,
29
+ 12,
30
+ 13,
31
+ 14,
32
+ 15,
33
+ 16,
34
+ 17,
35
+ 18,
36
+ 19,
37
+ 20,
38
+ 21,
39
+ 22,
40
+ 23,
41
+ 24,
42
+ 25,
43
+ 26,
44
+ 27,
45
+ 28,
46
+ 29,
47
+ 30,
48
+ 31,
49
+ 32,
50
+ 33,
51
+ 34,
52
+ 35,
53
+ 36,
54
+ 37,
55
+ 38,
56
+ 39,
57
+ 40,
58
+ 41,
59
+ 42,
60
+ 43,
61
+ 44,
62
+ 45,
63
+ 46,
64
+ 47,
65
+ 48,
66
+ 49,
67
+ 50,
68
+ 51,
69
+ 52,
70
+ 53,
71
+ 54,
72
+ 55,
73
+ 56,
74
+ 57,
75
+ 58,
76
+ 59,
77
+ 60,
78
+ 61,
79
+ 62,
80
+ 63,
81
+ 64,
82
+ 65,
83
+ 66,
84
+ 67,
85
+ 68,
86
+ 69,
87
+ 70,
88
+ 71,
89
+ 72,
90
+ 73,
91
+ 74,
92
+ 75,
93
+ 76,
94
+ 77,
95
+ 78,
96
+ 79,
97
+ 80,
98
+ 81,
99
+ 82,
100
+ 83,
101
+ 84,
102
+ 85,
103
+ 86,
104
+ 87,
105
+ 88,
106
+ 89,
107
+ 90,
108
+ 91,
109
+ 92,
110
+ 93,
111
+ 94,
112
+ 95,
113
+ 96,
114
+ 97,
115
+ 98,
116
+ 99,
117
+ 100,
118
+ 101,
119
+ 102,
120
+ 103,
121
+ 104,
122
+ 105,
123
+ 106,
124
+ 107,
125
+ 108,
126
+ 109,
127
+ 110,
128
+ 111,
129
+ 112,
130
+ 113,
131
+ 114,
132
+ 115,
133
+ 116,
134
+ 117,
135
+ 118,
136
+ 119,
137
+ 120,
138
+ 121,
139
+ 122,
140
+ 123,
141
+ 124,
142
+ 125,
143
+ 126,
144
+ 127,
145
+ 128,
146
+ 129,
147
+ 130,
148
+ 131,
149
+ 132
150
+ ]
151
+ },
152
+ {
153
+ "lr": 1e-05,
154
+ "betas": [
155
+ 0.9,
156
+ 0.999
157
+ ],
158
+ "eps": 1e-08,
159
+ "weight_decay": 0.0001,
160
+ "amsgrad": false,
161
+ "foreach": null,
162
+ "maximize": false,
163
+ "capturable": false,
164
+ "differentiable": false,
165
+ "fused": null,
166
+ "params": [
167
+ 133,
168
+ 134,
169
+ 135,
170
+ 136,
171
+ 137,
172
+ 138,
173
+ 139,
174
+ 140,
175
+ 141,
176
+ 142,
177
+ 143,
178
+ 144,
179
+ 145,
180
+ 146,
181
+ 147,
182
+ 148,
183
+ 149,
184
+ 150,
185
+ 151,
186
+ 152
187
+ ]
188
+ }
189
+ ]
checkpoints/040000/training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf859a4d75e5221b8c441db9e8a0f36555cb7252a25e1c42703e3fcf8f15129e
3
+ size 412817652
checkpoints/040000/training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6684ed5c5e13bb0e1c373cf7a94a0e4830e04942b1718f50a5db2cf60837eb0
3
+ size 15708
checkpoints/040000/training_state/training_step.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "step": 40000
3
+ }
checkpoints/060000/pretrained_model/config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "act",
3
+ "n_obs_steps": 1,
4
+ "input_features": {
5
+ "observation.state": {
6
+ "type": "STATE",
7
+ "shape": [
8
+ 6
9
+ ]
10
+ },
11
+ "observation.images.front": {
12
+ "type": "VISUAL",
13
+ "shape": [
14
+ 3,
15
+ 480,
16
+ 640
17
+ ]
18
+ }
19
+ },
20
+ "output_features": {
21
+ "action": {
22
+ "type": "ACTION",
23
+ "shape": [
24
+ 6
25
+ ]
26
+ }
27
+ },
28
+ "device": "cuda",
29
+ "use_amp": false,
30
+ "push_to_hub": true,
31
+ "repo_id": "Dimios45/act1",
32
+ "private": null,
33
+ "tags": null,
34
+ "license": null,
35
+ "pretrained_path": null,
36
+ "chunk_size": 100,
37
+ "n_action_steps": 100,
38
+ "normalization_mapping": {
39
+ "VISUAL": "MEAN_STD",
40
+ "STATE": "MEAN_STD",
41
+ "ACTION": "MEAN_STD"
42
+ },
43
+ "vision_backbone": "resnet18",
44
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
45
+ "replace_final_stride_with_dilation": false,
46
+ "pre_norm": false,
47
+ "dim_model": 512,
48
+ "n_heads": 8,
49
+ "dim_feedforward": 3200,
50
+ "feedforward_activation": "relu",
51
+ "n_encoder_layers": 4,
52
+ "n_decoder_layers": 1,
53
+ "use_vae": true,
54
+ "latent_dim": 32,
55
+ "n_vae_encoder_layers": 4,
56
+ "temporal_ensemble_coeff": null,
57
+ "dropout": 0.1,
58
+ "kl_weight": 10.0,
59
+ "use_torch_compile": false,
60
+ "optimizer_lr": 1e-05,
61
+ "optimizer_weight_decay": 0.0001,
62
+ "optimizer_lr_backbone": 1e-05
63
+ }
checkpoints/060000/pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe60295b4402b9c9b5b20748831da8a928bcc070dfd5bd6d9378f238caddb153
3
+ size 206699736
checkpoints/060000/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": "MEAN_STD",
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/060000/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 sha256:93e38dbbaf8f561886dfc5aa9497d5cd263387d20cab724c84b5be152b85dea2
3
+ size 6560
checkpoints/060000/pretrained_model/policy_preprocessor.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "policy_preprocessor",
3
+ "steps": [
4
+ {
5
+ "registry_name": "rename_observations_processor",
6
+ "config": {
7
+ "rename_map": {}
8
+ }
9
+ },
10
+ {
11
+ "registry_name": "to_batch_processor",
12
+ "config": {}
13
+ },
14
+ {
15
+ "registry_name": "device_processor",
16
+ "config": {
17
+ "device": "cuda",
18
+ "float_dtype": null
19
+ }
20
+ },
21
+ {
22
+ "registry_name": "normalizer_processor",
23
+ "config": {
24
+ "eps": 1e-08,
25
+ "features": {
26
+ "observation.state": {
27
+ "type": "STATE",
28
+ "shape": [
29
+ 6
30
+ ]
31
+ },
32
+ "observation.images.front": {
33
+ "type": "VISUAL",
34
+ "shape": [
35
+ 3,
36
+ 480,
37
+ 640
38
+ ]
39
+ },
40
+ "action": {
41
+ "type": "ACTION",
42
+ "shape": [
43
+ 6
44
+ ]
45
+ }
46
+ },
47
+ "norm_map": {
48
+ "VISUAL": "MEAN_STD",
49
+ "STATE": "MEAN_STD",
50
+ "ACTION": "MEAN_STD"
51
+ }
52
+ },
53
+ "state_file": "policy_preprocessor_step_3_normalizer_processor.safetensors"
54
+ }
55
+ ]
56
+ }
checkpoints/060000/pretrained_model/policy_preprocessor_step_3_normalizer_processor.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93e38dbbaf8f561886dfc5aa9497d5cd263387d20cab724c84b5be152b85dea2
3
+ size 6560
checkpoints/060000/pretrained_model/train_config.json ADDED
@@ -0,0 +1,186 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "Dimios45/santra",
4
+ "root": "santra/santra_demo_20251108_102726",
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": "pyav",
80
+ "streaming": false
81
+ },
82
+ "env": null,
83
+ "policy": {
84
+ "type": "act",
85
+ "n_obs_steps": 1,
86
+ "input_features": {
87
+ "observation.state": {
88
+ "type": "STATE",
89
+ "shape": [
90
+ 6
91
+ ]
92
+ },
93
+ "observation.images.front": {
94
+ "type": "VISUAL",
95
+ "shape": [
96
+ 3,
97
+ 480,
98
+ 640
99
+ ]
100
+ }
101
+ },
102
+ "output_features": {
103
+ "action": {
104
+ "type": "ACTION",
105
+ "shape": [
106
+ 6
107
+ ]
108
+ }
109
+ },
110
+ "device": "cuda",
111
+ "use_amp": false,
112
+ "push_to_hub": true,
113
+ "repo_id": "Dimios45/act1",
114
+ "private": null,
115
+ "tags": null,
116
+ "license": null,
117
+ "pretrained_path": null,
118
+ "chunk_size": 100,
119
+ "n_action_steps": 100,
120
+ "normalization_mapping": {
121
+ "VISUAL": "MEAN_STD",
122
+ "STATE": "MEAN_STD",
123
+ "ACTION": "MEAN_STD"
124
+ },
125
+ "vision_backbone": "resnet18",
126
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
127
+ "replace_final_stride_with_dilation": false,
128
+ "pre_norm": false,
129
+ "dim_model": 512,
130
+ "n_heads": 8,
131
+ "dim_feedforward": 3200,
132
+ "feedforward_activation": "relu",
133
+ "n_encoder_layers": 4,
134
+ "n_decoder_layers": 1,
135
+ "use_vae": true,
136
+ "latent_dim": 32,
137
+ "n_vae_encoder_layers": 4,
138
+ "temporal_ensemble_coeff": null,
139
+ "dropout": 0.1,
140
+ "kl_weight": 10.0,
141
+ "use_torch_compile": false,
142
+ "optimizer_lr": 1e-05,
143
+ "optimizer_weight_decay": 0.0001,
144
+ "optimizer_lr_backbone": 1e-05
145
+ },
146
+ "output_dir": "outputs/train/act_santra_cuda",
147
+ "job_name": "act_santra_cuda",
148
+ "resume": false,
149
+ "seed": 1000,
150
+ "num_workers": 4,
151
+ "batch_size": 8,
152
+ "steps": 100000,
153
+ "eval_freq": 20000,
154
+ "log_freq": 200,
155
+ "save_checkpoint": true,
156
+ "save_freq": 20000,
157
+ "use_policy_training_preset": true,
158
+ "optimizer": {
159
+ "type": "adamw",
160
+ "lr": 1e-05,
161
+ "weight_decay": 0.0001,
162
+ "grad_clip_norm": 10.0,
163
+ "betas": [
164
+ 0.9,
165
+ 0.999
166
+ ],
167
+ "eps": 1e-08
168
+ },
169
+ "scheduler": null,
170
+ "eval": {
171
+ "n_episodes": 50,
172
+ "batch_size": 50,
173
+ "use_async_envs": false
174
+ },
175
+ "wandb": {
176
+ "enable": true,
177
+ "disable_artifact": false,
178
+ "project": "lerobot",
179
+ "entity": null,
180
+ "notes": null,
181
+ "run_id": "t8w1ifju",
182
+ "mode": null
183
+ },
184
+ "checkpoint_path": null,
185
+ "rename_map": {}
186
+ }
checkpoints/060000/training_state/optimizer_param_groups.json ADDED
@@ -0,0 +1,189 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "foreach": null,
12
+ "maximize": false,
13
+ "capturable": false,
14
+ "differentiable": false,
15
+ "fused": null,
16
+ "params": [
17
+ 0,
18
+ 1,
19
+ 2,
20
+ 3,
21
+ 4,
22
+ 5,
23
+ 6,
24
+ 7,
25
+ 8,
26
+ 9,
27
+ 10,
28
+ 11,
29
+ 12,
30
+ 13,
31
+ 14,
32
+ 15,
33
+ 16,
34
+ 17,
35
+ 18,
36
+ 19,
37
+ 20,
38
+ 21,
39
+ 22,
40
+ 23,
41
+ 24,
42
+ 25,
43
+ 26,
44
+ 27,
45
+ 28,
46
+ 29,
47
+ 30,
48
+ 31,
49
+ 32,
50
+ 33,
51
+ 34,
52
+ 35,
53
+ 36,
54
+ 37,
55
+ 38,
56
+ 39,
57
+ 40,
58
+ 41,
59
+ 42,
60
+ 43,
61
+ 44,
62
+ 45,
63
+ 46,
64
+ 47,
65
+ 48,
66
+ 49,
67
+ 50,
68
+ 51,
69
+ 52,
70
+ 53,
71
+ 54,
72
+ 55,
73
+ 56,
74
+ 57,
75
+ 58,
76
+ 59,
77
+ 60,
78
+ 61,
79
+ 62,
80
+ 63,
81
+ 64,
82
+ 65,
83
+ 66,
84
+ 67,
85
+ 68,
86
+ 69,
87
+ 70,
88
+ 71,
89
+ 72,
90
+ 73,
91
+ 74,
92
+ 75,
93
+ 76,
94
+ 77,
95
+ 78,
96
+ 79,
97
+ 80,
98
+ 81,
99
+ 82,
100
+ 83,
101
+ 84,
102
+ 85,
103
+ 86,
104
+ 87,
105
+ 88,
106
+ 89,
107
+ 90,
108
+ 91,
109
+ 92,
110
+ 93,
111
+ 94,
112
+ 95,
113
+ 96,
114
+ 97,
115
+ 98,
116
+ 99,
117
+ 100,
118
+ 101,
119
+ 102,
120
+ 103,
121
+ 104,
122
+ 105,
123
+ 106,
124
+ 107,
125
+ 108,
126
+ 109,
127
+ 110,
128
+ 111,
129
+ 112,
130
+ 113,
131
+ 114,
132
+ 115,
133
+ 116,
134
+ 117,
135
+ 118,
136
+ 119,
137
+ 120,
138
+ 121,
139
+ 122,
140
+ 123,
141
+ 124,
142
+ 125,
143
+ 126,
144
+ 127,
145
+ 128,
146
+ 129,
147
+ 130,
148
+ 131,
149
+ 132
150
+ ]
151
+ },
152
+ {
153
+ "lr": 1e-05,
154
+ "betas": [
155
+ 0.9,
156
+ 0.999
157
+ ],
158
+ "eps": 1e-08,
159
+ "weight_decay": 0.0001,
160
+ "amsgrad": false,
161
+ "foreach": null,
162
+ "maximize": false,
163
+ "capturable": false,
164
+ "differentiable": false,
165
+ "fused": null,
166
+ "params": [
167
+ 133,
168
+ 134,
169
+ 135,
170
+ 136,
171
+ 137,
172
+ 138,
173
+ 139,
174
+ 140,
175
+ 141,
176
+ 142,
177
+ 143,
178
+ 144,
179
+ 145,
180
+ 146,
181
+ 147,
182
+ 148,
183
+ 149,
184
+ 150,
185
+ 151,
186
+ 152
187
+ ]
188
+ }
189
+ ]
checkpoints/060000/training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:754a0f6e242bafe377b72afa0ded09179d180a3628fc5881f21fb35e3cecd940
3
+ size 412817652
checkpoints/060000/training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63b545a9385521287560a8235611820286094a7866dc23662a04d0458f5a5934
3
+ size 15708
checkpoints/060000/training_state/training_step.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "step": 60000
3
+ }
checkpoints/080000/pretrained_model/config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "act",
3
+ "n_obs_steps": 1,
4
+ "input_features": {
5
+ "observation.state": {
6
+ "type": "STATE",
7
+ "shape": [
8
+ 6
9
+ ]
10
+ },
11
+ "observation.images.front": {
12
+ "type": "VISUAL",
13
+ "shape": [
14
+ 3,
15
+ 480,
16
+ 640
17
+ ]
18
+ }
19
+ },
20
+ "output_features": {
21
+ "action": {
22
+ "type": "ACTION",
23
+ "shape": [
24
+ 6
25
+ ]
26
+ }
27
+ },
28
+ "device": "cuda",
29
+ "use_amp": false,
30
+ "push_to_hub": true,
31
+ "repo_id": "Dimios45/act1",
32
+ "private": null,
33
+ "tags": null,
34
+ "license": null,
35
+ "pretrained_path": null,
36
+ "chunk_size": 100,
37
+ "n_action_steps": 100,
38
+ "normalization_mapping": {
39
+ "VISUAL": "MEAN_STD",
40
+ "STATE": "MEAN_STD",
41
+ "ACTION": "MEAN_STD"
42
+ },
43
+ "vision_backbone": "resnet18",
44
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
45
+ "replace_final_stride_with_dilation": false,
46
+ "pre_norm": false,
47
+ "dim_model": 512,
48
+ "n_heads": 8,
49
+ "dim_feedforward": 3200,
50
+ "feedforward_activation": "relu",
51
+ "n_encoder_layers": 4,
52
+ "n_decoder_layers": 1,
53
+ "use_vae": true,
54
+ "latent_dim": 32,
55
+ "n_vae_encoder_layers": 4,
56
+ "temporal_ensemble_coeff": null,
57
+ "dropout": 0.1,
58
+ "kl_weight": 10.0,
59
+ "use_torch_compile": false,
60
+ "optimizer_lr": 1e-05,
61
+ "optimizer_weight_decay": 0.0001,
62
+ "optimizer_lr_backbone": 1e-05
63
+ }
checkpoints/080000/pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b48ea29089d1d0d1d9f66c612b2280b44bdcdbdb8ed129ecbb4a3c23fb13eae
3
+ size 206699736
checkpoints/080000/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": "MEAN_STD",
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/080000/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 sha256:93e38dbbaf8f561886dfc5aa9497d5cd263387d20cab724c84b5be152b85dea2
3
+ size 6560
checkpoints/080000/pretrained_model/policy_preprocessor.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "policy_preprocessor",
3
+ "steps": [
4
+ {
5
+ "registry_name": "rename_observations_processor",
6
+ "config": {
7
+ "rename_map": {}
8
+ }
9
+ },
10
+ {
11
+ "registry_name": "to_batch_processor",
12
+ "config": {}
13
+ },
14
+ {
15
+ "registry_name": "device_processor",
16
+ "config": {
17
+ "device": "cuda",
18
+ "float_dtype": null
19
+ }
20
+ },
21
+ {
22
+ "registry_name": "normalizer_processor",
23
+ "config": {
24
+ "eps": 1e-08,
25
+ "features": {
26
+ "observation.state": {
27
+ "type": "STATE",
28
+ "shape": [
29
+ 6
30
+ ]
31
+ },
32
+ "observation.images.front": {
33
+ "type": "VISUAL",
34
+ "shape": [
35
+ 3,
36
+ 480,
37
+ 640
38
+ ]
39
+ },
40
+ "action": {
41
+ "type": "ACTION",
42
+ "shape": [
43
+ 6
44
+ ]
45
+ }
46
+ },
47
+ "norm_map": {
48
+ "VISUAL": "MEAN_STD",
49
+ "STATE": "MEAN_STD",
50
+ "ACTION": "MEAN_STD"
51
+ }
52
+ },
53
+ "state_file": "policy_preprocessor_step_3_normalizer_processor.safetensors"
54
+ }
55
+ ]
56
+ }
checkpoints/080000/pretrained_model/policy_preprocessor_step_3_normalizer_processor.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93e38dbbaf8f561886dfc5aa9497d5cd263387d20cab724c84b5be152b85dea2
3
+ size 6560
checkpoints/080000/pretrained_model/train_config.json ADDED
@@ -0,0 +1,186 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "Dimios45/santra",
4
+ "root": "santra/santra_demo_20251108_102726",
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": "pyav",
80
+ "streaming": false
81
+ },
82
+ "env": null,
83
+ "policy": {
84
+ "type": "act",
85
+ "n_obs_steps": 1,
86
+ "input_features": {
87
+ "observation.state": {
88
+ "type": "STATE",
89
+ "shape": [
90
+ 6
91
+ ]
92
+ },
93
+ "observation.images.front": {
94
+ "type": "VISUAL",
95
+ "shape": [
96
+ 3,
97
+ 480,
98
+ 640
99
+ ]
100
+ }
101
+ },
102
+ "output_features": {
103
+ "action": {
104
+ "type": "ACTION",
105
+ "shape": [
106
+ 6
107
+ ]
108
+ }
109
+ },
110
+ "device": "cuda",
111
+ "use_amp": false,
112
+ "push_to_hub": true,
113
+ "repo_id": "Dimios45/act1",
114
+ "private": null,
115
+ "tags": null,
116
+ "license": null,
117
+ "pretrained_path": null,
118
+ "chunk_size": 100,
119
+ "n_action_steps": 100,
120
+ "normalization_mapping": {
121
+ "VISUAL": "MEAN_STD",
122
+ "STATE": "MEAN_STD",
123
+ "ACTION": "MEAN_STD"
124
+ },
125
+ "vision_backbone": "resnet18",
126
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
127
+ "replace_final_stride_with_dilation": false,
128
+ "pre_norm": false,
129
+ "dim_model": 512,
130
+ "n_heads": 8,
131
+ "dim_feedforward": 3200,
132
+ "feedforward_activation": "relu",
133
+ "n_encoder_layers": 4,
134
+ "n_decoder_layers": 1,
135
+ "use_vae": true,
136
+ "latent_dim": 32,
137
+ "n_vae_encoder_layers": 4,
138
+ "temporal_ensemble_coeff": null,
139
+ "dropout": 0.1,
140
+ "kl_weight": 10.0,
141
+ "use_torch_compile": false,
142
+ "optimizer_lr": 1e-05,
143
+ "optimizer_weight_decay": 0.0001,
144
+ "optimizer_lr_backbone": 1e-05
145
+ },
146
+ "output_dir": "outputs/train/act_santra_cuda",
147
+ "job_name": "act_santra_cuda",
148
+ "resume": false,
149
+ "seed": 1000,
150
+ "num_workers": 4,
151
+ "batch_size": 8,
152
+ "steps": 100000,
153
+ "eval_freq": 20000,
154
+ "log_freq": 200,
155
+ "save_checkpoint": true,
156
+ "save_freq": 20000,
157
+ "use_policy_training_preset": true,
158
+ "optimizer": {
159
+ "type": "adamw",
160
+ "lr": 1e-05,
161
+ "weight_decay": 0.0001,
162
+ "grad_clip_norm": 10.0,
163
+ "betas": [
164
+ 0.9,
165
+ 0.999
166
+ ],
167
+ "eps": 1e-08
168
+ },
169
+ "scheduler": null,
170
+ "eval": {
171
+ "n_episodes": 50,
172
+ "batch_size": 50,
173
+ "use_async_envs": false
174
+ },
175
+ "wandb": {
176
+ "enable": true,
177
+ "disable_artifact": false,
178
+ "project": "lerobot",
179
+ "entity": null,
180
+ "notes": null,
181
+ "run_id": "t8w1ifju",
182
+ "mode": null
183
+ },
184
+ "checkpoint_path": null,
185
+ "rename_map": {}
186
+ }
checkpoints/080000/training_state/optimizer_param_groups.json ADDED
@@ -0,0 +1,189 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "foreach": null,
12
+ "maximize": false,
13
+ "capturable": false,
14
+ "differentiable": false,
15
+ "fused": null,
16
+ "params": [
17
+ 0,
18
+ 1,
19
+ 2,
20
+ 3,
21
+ 4,
22
+ 5,
23
+ 6,
24
+ 7,
25
+ 8,
26
+ 9,
27
+ 10,
28
+ 11,
29
+ 12,
30
+ 13,
31
+ 14,
32
+ 15,
33
+ 16,
34
+ 17,
35
+ 18,
36
+ 19,
37
+ 20,
38
+ 21,
39
+ 22,
40
+ 23,
41
+ 24,
42
+ 25,
43
+ 26,
44
+ 27,
45
+ 28,
46
+ 29,
47
+ 30,
48
+ 31,
49
+ 32,
50
+ 33,
51
+ 34,
52
+ 35,
53
+ 36,
54
+ 37,
55
+ 38,
56
+ 39,
57
+ 40,
58
+ 41,
59
+ 42,
60
+ 43,
61
+ 44,
62
+ 45,
63
+ 46,
64
+ 47,
65
+ 48,
66
+ 49,
67
+ 50,
68
+ 51,
69
+ 52,
70
+ 53,
71
+ 54,
72
+ 55,
73
+ 56,
74
+ 57,
75
+ 58,
76
+ 59,
77
+ 60,
78
+ 61,
79
+ 62,
80
+ 63,
81
+ 64,
82
+ 65,
83
+ 66,
84
+ 67,
85
+ 68,
86
+ 69,
87
+ 70,
88
+ 71,
89
+ 72,
90
+ 73,
91
+ 74,
92
+ 75,
93
+ 76,
94
+ 77,
95
+ 78,
96
+ 79,
97
+ 80,
98
+ 81,
99
+ 82,
100
+ 83,
101
+ 84,
102
+ 85,
103
+ 86,
104
+ 87,
105
+ 88,
106
+ 89,
107
+ 90,
108
+ 91,
109
+ 92,
110
+ 93,
111
+ 94,
112
+ 95,
113
+ 96,
114
+ 97,
115
+ 98,
116
+ 99,
117
+ 100,
118
+ 101,
119
+ 102,
120
+ 103,
121
+ 104,
122
+ 105,
123
+ 106,
124
+ 107,
125
+ 108,
126
+ 109,
127
+ 110,
128
+ 111,
129
+ 112,
130
+ 113,
131
+ 114,
132
+ 115,
133
+ 116,
134
+ 117,
135
+ 118,
136
+ 119,
137
+ 120,
138
+ 121,
139
+ 122,
140
+ 123,
141
+ 124,
142
+ 125,
143
+ 126,
144
+ 127,
145
+ 128,
146
+ 129,
147
+ 130,
148
+ 131,
149
+ 132
150
+ ]
151
+ },
152
+ {
153
+ "lr": 1e-05,
154
+ "betas": [
155
+ 0.9,
156
+ 0.999
157
+ ],
158
+ "eps": 1e-08,
159
+ "weight_decay": 0.0001,
160
+ "amsgrad": false,
161
+ "foreach": null,
162
+ "maximize": false,
163
+ "capturable": false,
164
+ "differentiable": false,
165
+ "fused": null,
166
+ "params": [
167
+ 133,
168
+ 134,
169
+ 135,
170
+ 136,
171
+ 137,
172
+ 138,
173
+ 139,
174
+ 140,
175
+ 141,
176
+ 142,
177
+ 143,
178
+ 144,
179
+ 145,
180
+ 146,
181
+ 147,
182
+ 148,
183
+ 149,
184
+ 150,
185
+ 151,
186
+ 152
187
+ ]
188
+ }
189
+ ]
checkpoints/080000/training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:971e5b4181f345fa39c9a801f05d1e042907b182ab3b4226da36cfd65d2aba6a
3
+ size 412817652
checkpoints/080000/training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c33e46c4006e3a0161f3dc3b00b8dd2dbd3a7fb2801fd61dd65d80bb52e4d354
3
+ size 15708
checkpoints/080000/training_state/training_step.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "step": 80000
3
+ }
checkpoints/100000 ADDED
@@ -0,0 +1 @@
 
 
1
+ Subproject commit 666b47bb019a19032e44c122362b1be1a599e39d
checkpoints/last ADDED
@@ -0,0 +1 @@
 
 
1
+ 100000