jadechoghari commited on
Commit
1d325e7
·
verified ·
1 Parent(s): 68069cc

Upload folder using huggingface_hub

Browse files
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
+ 20
14
+ ]
15
+ },
16
+ "observation.images.laptop": {
17
+ "type": "VISUAL",
18
+ "shape": [
19
+ 3,
20
+ 960,
21
+ 1280
22
+ ]
23
+ }
24
+ },
25
+ "output_features": {
26
+ "action": {
27
+ "type": "ACTION",
28
+ "shape": [
29
+ 9
30
+ ]
31
+ }
32
+ },
33
+ "device": "cuda",
34
+ "use_amp": false,
35
+ "chunk_size": 100,
36
+ "n_action_steps": 100,
37
+ "vision_backbone": "resnet18",
38
+ "pretrained_backbone_weights": "ResNet18_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
+ }
005000/pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69a758abfcd5ce3039328193b7d24f4569b16bd695054f8298c88fb696e583a0
3
+ size 206770604
005000/pretrained_model/train_config.json ADDED
@@ -0,0 +1,197 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "jadechoghari/pick-cube-genesis",
4
+ "root": null,
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
+ }
62
+ },
63
+ "revision": null,
64
+ "use_imagenet_stats": true,
65
+ "video_backend": "torchcodec"
66
+ },
67
+ "env": {
68
+ "type": "aloha",
69
+ "task": "AlohaInsertion-v0",
70
+ "fps": 50,
71
+ "features": {
72
+ "action": {
73
+ "type": "ACTION",
74
+ "shape": [
75
+ 14
76
+ ]
77
+ },
78
+ "agent_pos": {
79
+ "type": "STATE",
80
+ "shape": [
81
+ 14
82
+ ]
83
+ },
84
+ "pixels/top": {
85
+ "type": "VISUAL",
86
+ "shape": [
87
+ 480,
88
+ 640,
89
+ 3
90
+ ]
91
+ }
92
+ },
93
+ "features_map": {
94
+ "action": "action",
95
+ "agent_pos": "observation.state",
96
+ "top": "observation.image.top",
97
+ "pixels/top": "observation.images.top"
98
+ },
99
+ "episode_length": 400,
100
+ "obs_type": "pixels_agent_pos",
101
+ "render_mode": "rgb_array"
102
+ },
103
+ "policy": {
104
+ "type": "act",
105
+ "n_obs_steps": 1,
106
+ "normalization_mapping": {
107
+ "VISUAL": "MEAN_STD",
108
+ "STATE": "MEAN_STD",
109
+ "ACTION": "MEAN_STD"
110
+ },
111
+ "input_features": {
112
+ "observation.state": {
113
+ "type": "STATE",
114
+ "shape": [
115
+ 20
116
+ ]
117
+ },
118
+ "observation.images.laptop": {
119
+ "type": "VISUAL",
120
+ "shape": [
121
+ 3,
122
+ 960,
123
+ 1280
124
+ ]
125
+ }
126
+ },
127
+ "output_features": {
128
+ "action": {
129
+ "type": "ACTION",
130
+ "shape": [
131
+ 9
132
+ ]
133
+ }
134
+ },
135
+ "device": "cuda",
136
+ "use_amp": false,
137
+ "chunk_size": 100,
138
+ "n_action_steps": 100,
139
+ "vision_backbone": "resnet18",
140
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
141
+ "replace_final_stride_with_dilation": false,
142
+ "pre_norm": false,
143
+ "dim_model": 512,
144
+ "n_heads": 8,
145
+ "dim_feedforward": 3200,
146
+ "feedforward_activation": "relu",
147
+ "n_encoder_layers": 4,
148
+ "n_decoder_layers": 1,
149
+ "use_vae": true,
150
+ "latent_dim": 32,
151
+ "n_vae_encoder_layers": 4,
152
+ "temporal_ensemble_coeff": null,
153
+ "dropout": 0.1,
154
+ "kl_weight": 10.0,
155
+ "optimizer_lr": 1e-05,
156
+ "optimizer_weight_decay": 0.0001,
157
+ "optimizer_lr_backbone": 1e-05
158
+ },
159
+ "output_dir": "outputs/train/act_pick_cube",
160
+ "job_name": "aloha_act",
161
+ "resume": false,
162
+ "seed": 100000,
163
+ "num_workers": 4,
164
+ "batch_size": 8,
165
+ "steps": 10000,
166
+ "eval_freq": 10000000,
167
+ "log_freq": 200,
168
+ "save_checkpoint": true,
169
+ "save_freq": 5000,
170
+ "use_policy_training_preset": true,
171
+ "optimizer": {
172
+ "type": "adamw",
173
+ "lr": 1e-05,
174
+ "weight_decay": 0.0001,
175
+ "grad_clip_norm": 10.0,
176
+ "betas": [
177
+ 0.9,
178
+ 0.999
179
+ ],
180
+ "eps": 1e-08
181
+ },
182
+ "scheduler": null,
183
+ "eval": {
184
+ "n_episodes": 50,
185
+ "batch_size": 50,
186
+ "use_async_envs": false
187
+ },
188
+ "wandb": {
189
+ "enable": true,
190
+ "disable_artifact": false,
191
+ "project": "lerobot",
192
+ "entity": null,
193
+ "notes": null,
194
+ "run_id": null,
195
+ "mode": null
196
+ }
197
+ }
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
+ ]
005000/training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a41c6cab2921cdee22cd62980ad4d3d7eacba627184a5450f287ac178321093
3
+ size 412956948
005000/training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d15ddd095960f81c45aacf8382636ba8d32be92835e1594f1eeec4e1eadd411
3
+ size 15708
005000/training_state/training_step.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "step": 5000
3
+ }
010000/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
+ 20
14
+ ]
15
+ },
16
+ "observation.images.laptop": {
17
+ "type": "VISUAL",
18
+ "shape": [
19
+ 3,
20
+ 960,
21
+ 1280
22
+ ]
23
+ }
24
+ },
25
+ "output_features": {
26
+ "action": {
27
+ "type": "ACTION",
28
+ "shape": [
29
+ 9
30
+ ]
31
+ }
32
+ },
33
+ "device": "cuda",
34
+ "use_amp": false,
35
+ "chunk_size": 100,
36
+ "n_action_steps": 100,
37
+ "vision_backbone": "resnet18",
38
+ "pretrained_backbone_weights": "ResNet18_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
+ }
010000/pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8895ebe2780ef2d231ceb3e0777a86241046608377811c01deb95d7adc05f03
3
+ size 206770604
010000/pretrained_model/train_config.json ADDED
@@ -0,0 +1,197 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "jadechoghari/pick-cube-genesis",
4
+ "root": null,
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
+ }
62
+ },
63
+ "revision": null,
64
+ "use_imagenet_stats": true,
65
+ "video_backend": "torchcodec"
66
+ },
67
+ "env": {
68
+ "type": "aloha",
69
+ "task": "AlohaInsertion-v0",
70
+ "fps": 50,
71
+ "features": {
72
+ "action": {
73
+ "type": "ACTION",
74
+ "shape": [
75
+ 14
76
+ ]
77
+ },
78
+ "agent_pos": {
79
+ "type": "STATE",
80
+ "shape": [
81
+ 14
82
+ ]
83
+ },
84
+ "pixels/top": {
85
+ "type": "VISUAL",
86
+ "shape": [
87
+ 480,
88
+ 640,
89
+ 3
90
+ ]
91
+ }
92
+ },
93
+ "features_map": {
94
+ "action": "action",
95
+ "agent_pos": "observation.state",
96
+ "top": "observation.image.top",
97
+ "pixels/top": "observation.images.top"
98
+ },
99
+ "episode_length": 400,
100
+ "obs_type": "pixels_agent_pos",
101
+ "render_mode": "rgb_array"
102
+ },
103
+ "policy": {
104
+ "type": "act",
105
+ "n_obs_steps": 1,
106
+ "normalization_mapping": {
107
+ "VISUAL": "MEAN_STD",
108
+ "STATE": "MEAN_STD",
109
+ "ACTION": "MEAN_STD"
110
+ },
111
+ "input_features": {
112
+ "observation.state": {
113
+ "type": "STATE",
114
+ "shape": [
115
+ 20
116
+ ]
117
+ },
118
+ "observation.images.laptop": {
119
+ "type": "VISUAL",
120
+ "shape": [
121
+ 3,
122
+ 960,
123
+ 1280
124
+ ]
125
+ }
126
+ },
127
+ "output_features": {
128
+ "action": {
129
+ "type": "ACTION",
130
+ "shape": [
131
+ 9
132
+ ]
133
+ }
134
+ },
135
+ "device": "cuda",
136
+ "use_amp": false,
137
+ "chunk_size": 100,
138
+ "n_action_steps": 100,
139
+ "vision_backbone": "resnet18",
140
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
141
+ "replace_final_stride_with_dilation": false,
142
+ "pre_norm": false,
143
+ "dim_model": 512,
144
+ "n_heads": 8,
145
+ "dim_feedforward": 3200,
146
+ "feedforward_activation": "relu",
147
+ "n_encoder_layers": 4,
148
+ "n_decoder_layers": 1,
149
+ "use_vae": true,
150
+ "latent_dim": 32,
151
+ "n_vae_encoder_layers": 4,
152
+ "temporal_ensemble_coeff": null,
153
+ "dropout": 0.1,
154
+ "kl_weight": 10.0,
155
+ "optimizer_lr": 1e-05,
156
+ "optimizer_weight_decay": 0.0001,
157
+ "optimizer_lr_backbone": 1e-05
158
+ },
159
+ "output_dir": "outputs/train/act_pick_cube",
160
+ "job_name": "aloha_act",
161
+ "resume": false,
162
+ "seed": 100000,
163
+ "num_workers": 4,
164
+ "batch_size": 8,
165
+ "steps": 10000,
166
+ "eval_freq": 10000000,
167
+ "log_freq": 200,
168
+ "save_checkpoint": true,
169
+ "save_freq": 5000,
170
+ "use_policy_training_preset": true,
171
+ "optimizer": {
172
+ "type": "adamw",
173
+ "lr": 1e-05,
174
+ "weight_decay": 0.0001,
175
+ "grad_clip_norm": 10.0,
176
+ "betas": [
177
+ 0.9,
178
+ 0.999
179
+ ],
180
+ "eps": 1e-08
181
+ },
182
+ "scheduler": null,
183
+ "eval": {
184
+ "n_episodes": 50,
185
+ "batch_size": 50,
186
+ "use_async_envs": false
187
+ },
188
+ "wandb": {
189
+ "enable": true,
190
+ "disable_artifact": false,
191
+ "project": "lerobot",
192
+ "entity": null,
193
+ "notes": null,
194
+ "run_id": null,
195
+ "mode": null
196
+ }
197
+ }
010000/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
+ ]
010000/training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e0b0ca69eb3bcca5d647883d83ea19738f14a159e7ab4a4c28b4c281d875758
3
+ size 412956948
010000/training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09afeb3b3f8cf8d7a7d3c221659ef92fb327c5649c09f1c7c8119391eda7b4b7
3
+ size 15708
010000/training_state/training_step.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "step": 10000
3
+ }