Hugging Face's logo

QRP123
/
day3_25

Safetensors
Model card Files
xet
 Community
QRP123 commited on
Commit
1965bbd
·
verified ·
1 Parent(s): 65f7eb5

Upload checkpoint 130000 (DP-ACT-100-WHOLE-V30-fixed-base-torque)

Browse files
Files changed (12) hide show
  1. pretrained_model/config.json +130 -0
  2. pretrained_model/model.safetensors +3 -0
  3. pretrained_model/policy_postprocessor.json +32 -0
  4. pretrained_model/policy_postprocessor_step_0_unnormalizer_processor.safetensors +3 -0
  5. pretrained_model/policy_preprocessor.json +98 -0
  6. pretrained_model/policy_preprocessor_step_3_normalizer_processor.safetensors +3 -0
  7. pretrained_model/train_config.json +257 -0
  8. training_state/optimizer_param_groups.json +233 -0
  9. training_state/optimizer_state.safetensors +3 -0
  10. training_state/rng_state.safetensors +3 -0
  11. training_state/scheduler_state.json +14 -0
  12. training_state/training_step.json +3 -0
pretrained_model/config.json ADDED
@@ -0,0 +1,130 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "diffusion",
3
+ "n_obs_steps": 2,
4
+ "input_features": {
5
+ "observation.state": {
6
+ "type": "STATE",
7
+ "shape": [
8
+ 14
9
+ ]
10
+ },
11
+ "observation.velocity": {
12
+ "type": "STATE",
13
+ "shape": [
14
+ 14
15
+ ]
16
+ },
17
+ "observation.effort": {
18
+ "type": "STATE",
19
+ "shape": [
20
+ 14
21
+ ]
22
+ },
23
+ "observation.base_velocity": {
24
+ "type": "STATE",
25
+ "shape": [
26
+ 3
27
+ ]
28
+ },
29
+ "observation.images.main": {
30
+ "type": "VISUAL",
31
+ "shape": [
32
+ 3,
33
+ 224,
34
+ 224
35
+ ]
36
+ },
37
+ "observation.images.secondary_0": {
38
+ "type": "VISUAL",
39
+ "shape": [
40
+ 3,
41
+ 224,
42
+ 224
43
+ ]
44
+ },
45
+ "observation.images.secondary_1": {
46
+ "type": "VISUAL",
47
+ "shape": [
48
+ 3,
49
+ 224,
50
+ 224
51
+ ]
52
+ },
53
+ "observation.images.secondary_2": {
54
+ "type": "VISUAL",
55
+ "shape": [
56
+ 3,
57
+ 224,
58
+ 224
59
+ ]
60
+ }
61
+ },
62
+ "output_features": {
63
+ "action": {
64
+ "type": "ACTION",
65
+ "shape": [
66
+ 17
67
+ ]
68
+ }
69
+ },
70
+ "device": "cuda",
71
+ "use_amp": true,
72
+ "push_to_hub": false,
73
+ "repo_id": "local/DP-ACT-100-WHOLE-V30-fixed-base-torque",
74
+ "private": null,
75
+ "tags": null,
76
+ "license": null,
77
+ "pretrained_path": null,
78
+ "horizon": 16,
79
+ "n_action_steps": 8,
80
+ "normalization_mapping": {
81
+ "VISUAL": "MEAN_STD",
82
+ "STATE": "MIN_MAX",
83
+ "ACTION": "MIN_MAX"
84
+ },
85
+ "drop_n_last_frames": 7,
86
+ "vision_backbone": "resnet18",
87
+ "resize_shape": [
88
+ 224,
89
+ 224
90
+ ],
91
+ "crop_ratio": 1.0,
92
+ "crop_shape": null,
93
+ "crop_is_random": true,
94
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
95
+ "use_group_norm": false,
96
+ "spatial_softmax_num_keypoints": 32,
97
+ "use_separate_rgb_encoder_per_camera": false,
98
+ "down_dims": [
99
+ 512,
100
+ 1024,
101
+ 2048
102
+ ],
103
+ "kernel_size": 5,
104
+ "n_groups": 8,
105
+ "diffusion_step_embed_dim": 128,
106
+ "use_film_scale_modulation": true,
107
+ "noise_scheduler_type": "DDPM",
108
+ "num_train_timesteps": 100,
109
+ "beta_schedule": "squaredcos_cap_v2",
110
+ "beta_start": 0.0001,
111
+ "beta_end": 0.02,
112
+ "prediction_type": "epsilon",
113
+ "clip_sample": true,
114
+ "clip_sample_range": 1.0,
115
+ "num_inference_steps": null,
116
+ "compile_model": false,
117
+ "compile_mode": "reduce-overhead",
118
+ "do_mask_loss_for_padding": false,
119
+ "use_base": true,
120
+ "use_torque": true,
121
+ "optimizer_lr": 8e-05,
122
+ "optimizer_betas": [
123
+ 0.95,
124
+ 0.999
125
+ ],
126
+ "optimizer_eps": 1e-08,
127
+ "optimizer_weight_decay": 1e-06,
128
+ "scheduler_name": "cosine",
129
+ "scheduler_warmup_steps": 2000
130
+ }
pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:812dd0f9ed92d6c9d79bf7e7cc50f89c8450669394f4e2566884c2b6ca822dbd
3
+ size 1101814476
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
+ 17
13
+ ]
14
+ }
15
+ },
16
+ "norm_map": {
17
+ "VISUAL": "MEAN_STD",
18
+ "STATE": "MIN_MAX",
19
+ "ACTION": "MIN_MAX"
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
+ }
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:cc81a12ac3f3eee527e3b12670a5af38c4df434c1186f901e1cd6b5664176325
3
+ size 14172
pretrained_model/policy_preprocessor.json ADDED
@@ -0,0 +1,98 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ 14
30
+ ]
31
+ },
32
+ "observation.velocity": {
33
+ "type": "STATE",
34
+ "shape": [
35
+ 14
36
+ ]
37
+ },
38
+ "observation.effort": {
39
+ "type": "STATE",
40
+ "shape": [
41
+ 14
42
+ ]
43
+ },
44
+ "observation.base_velocity": {
45
+ "type": "STATE",
46
+ "shape": [
47
+ 3
48
+ ]
49
+ },
50
+ "observation.images.main": {
51
+ "type": "VISUAL",
52
+ "shape": [
53
+ 3,
54
+ 224,
55
+ 224
56
+ ]
57
+ },
58
+ "observation.images.secondary_0": {
59
+ "type": "VISUAL",
60
+ "shape": [
61
+ 3,
62
+ 224,
63
+ 224
64
+ ]
65
+ },
66
+ "observation.images.secondary_1": {
67
+ "type": "VISUAL",
68
+ "shape": [
69
+ 3,
70
+ 224,
71
+ 224
72
+ ]
73
+ },
74
+ "observation.images.secondary_2": {
75
+ "type": "VISUAL",
76
+ "shape": [
77
+ 3,
78
+ 224,
79
+ 224
80
+ ]
81
+ },
82
+ "action": {
83
+ "type": "ACTION",
84
+ "shape": [
85
+ 17
86
+ ]
87
+ }
88
+ },
89
+ "norm_map": {
90
+ "VISUAL": "MEAN_STD",
91
+ "STATE": "MIN_MAX",
92
+ "ACTION": "MIN_MAX"
93
+ }
94
+ },
95
+ "state_file": "policy_preprocessor_step_3_normalizer_processor.safetensors"
96
+ }
97
+ ]
98
+ }
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:cc81a12ac3f3eee527e3b12670a5af38c4df434c1186f901e1cd6b5664176325
3
+ size 14172
pretrained_model/train_config.json ADDED
@@ -0,0 +1,257 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "ACT-100-WHOLE-V30-fixed",
4
+ "root": "/workspace/RSS/RSS-Hanger/data/ACT-100-WHOLE-V30-fixed",
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": "diffusion",
85
+ "n_obs_steps": 2,
86
+ "input_features": {
87
+ "observation.state": {
88
+ "type": "STATE",
89
+ "shape": [
90
+ 14
91
+ ]
92
+ },
93
+ "observation.velocity": {
94
+ "type": "STATE",
95
+ "shape": [
96
+ 14
97
+ ]
98
+ },
99
+ "observation.effort": {
100
+ "type": "STATE",
101
+ "shape": [
102
+ 14
103
+ ]
104
+ },
105
+ "observation.base_velocity": {
106
+ "type": "STATE",
107
+ "shape": [
108
+ 3
109
+ ]
110
+ },
111
+ "observation.images.main": {
112
+ "type": "VISUAL",
113
+ "shape": [
114
+ 3,
115
+ 224,
116
+ 224
117
+ ]
118
+ },
119
+ "observation.images.secondary_0": {
120
+ "type": "VISUAL",
121
+ "shape": [
122
+ 3,
123
+ 224,
124
+ 224
125
+ ]
126
+ },
127
+ "observation.images.secondary_1": {
128
+ "type": "VISUAL",
129
+ "shape": [
130
+ 3,
131
+ 224,
132
+ 224
133
+ ]
134
+ },
135
+ "observation.images.secondary_2": {
136
+ "type": "VISUAL",
137
+ "shape": [
138
+ 3,
139
+ 224,
140
+ 224
141
+ ]
142
+ }
143
+ },
144
+ "output_features": {
145
+ "action": {
146
+ "type": "ACTION",
147
+ "shape": [
148
+ 17
149
+ ]
150
+ }
151
+ },
152
+ "device": "cuda",
153
+ "use_amp": true,
154
+ "push_to_hub": false,
155
+ "repo_id": "local/DP-ACT-100-WHOLE-V30-fixed-base-torque",
156
+ "private": null,
157
+ "tags": null,
158
+ "license": null,
159
+ "pretrained_path": null,
160
+ "horizon": 16,
161
+ "n_action_steps": 8,
162
+ "normalization_mapping": {
163
+ "VISUAL": "MEAN_STD",
164
+ "STATE": "MIN_MAX",
165
+ "ACTION": "MIN_MAX"
166
+ },
167
+ "drop_n_last_frames": 7,
168
+ "vision_backbone": "resnet18",
169
+ "resize_shape": [
170
+ 224,
171
+ 224
172
+ ],
173
+ "crop_ratio": 1.0,
174
+ "crop_shape": null,
175
+ "crop_is_random": true,
176
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
177
+ "use_group_norm": false,
178
+ "spatial_softmax_num_keypoints": 32,
179
+ "use_separate_rgb_encoder_per_camera": false,
180
+ "down_dims": [
181
+ 512,
182
+ 1024,
183
+ 2048
184
+ ],
185
+ "kernel_size": 5,
186
+ "n_groups": 8,
187
+ "diffusion_step_embed_dim": 128,
188
+ "use_film_scale_modulation": true,
189
+ "noise_scheduler_type": "DDPM",
190
+ "num_train_timesteps": 100,
191
+ "beta_schedule": "squaredcos_cap_v2",
192
+ "beta_start": 0.0001,
193
+ "beta_end": 0.02,
194
+ "prediction_type": "epsilon",
195
+ "clip_sample": true,
196
+ "clip_sample_range": 1.0,
197
+ "num_inference_steps": null,
198
+ "compile_model": false,
199
+ "compile_mode": "reduce-overhead",
200
+ "do_mask_loss_for_padding": false,
201
+ "use_base": true,
202
+ "use_torque": true,
203
+ "optimizer_lr": 8e-05,
204
+ "optimizer_betas": [
205
+ 0.95,
206
+ 0.999
207
+ ],
208
+ "optimizer_eps": 1e-08,
209
+ "optimizer_weight_decay": 1e-06,
210
+ "scheduler_name": "cosine",
211
+ "scheduler_warmup_steps": 2000
212
+ },
213
+ "output_dir": "/workspace/RSS/RSS-Hanger/models/DP-ACT-100-WHOLE-V30-fixed-base-torque",
214
+ "job_name": "DP-ACT-100-WHOLE-V30-fixed-base-torque",
215
+ "resume": false,
216
+ "seed": 1000,
217
+ "num_workers": 16,
218
+ "batch_size": 64,
219
+ "steps": 200000,
220
+ "eval_freq": 0,
221
+ "log_freq": 100,
222
+ "save_checkpoint": true,
223
+ "save_freq": 10000,
224
+ "use_policy_training_preset": true,
225
+ "optimizer": {
226
+ "type": "adam",
227
+ "lr": 8e-05,
228
+ "weight_decay": 1e-06,
229
+ "grad_clip_norm": 10.0,
230
+ "betas": [
231
+ 0.95,
232
+ 0.999
233
+ ],
234
+ "eps": 1e-08
235
+ },
236
+ "scheduler": {
237
+ "type": "diffuser",
238
+ "num_warmup_steps": 2000,
239
+ "name": "cosine"
240
+ },
241
+ "eval": {
242
+ "n_episodes": 50,
243
+ "batch_size": 50,
244
+ "use_async_envs": false
245
+ },
246
+ "wandb": {
247
+ "enable": false,
248
+ "disable_artifact": false,
249
+ "project": "DP-ACT-100-WHOLE-V30-fixed",
250
+ "entity": null,
251
+ "notes": null,
252
+ "run_id": null,
253
+ "mode": null
254
+ },
255
+ "checkpoint_path": null,
256
+ "rename_map": {}
257
+ }
training_state/optimizer_param_groups.json ADDED
@@ -0,0 +1,233 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "lr": 2.2237335495769035e-05,
4
+ "betas": [
5
+ 0.95,
6
+ 0.999
7
+ ],
8
+ "eps": 1e-08,
9
+ "weight_decay": 1e-06,
10
+ "amsgrad": false,
11
+ "maximize": false,
12
+ "foreach": null,
13
+ "capturable": false,
14
+ "differentiable": false,
15
+ "fused": null,
16
+ "decoupled_weight_decay": false,
17
+ "initial_lr": 8e-05,
18
+ "params": [
19
+ 0,
20
+ 1,
21
+ 2,
22
+ 3,
23
+ 4,
24
+ 5,
25
+ 6,
26
+ 7,
27
+ 8,
28
+ 9,
29
+ 10,
30
+ 11,
31
+ 12,
32
+ 13,
33
+ 14,
34
+ 15,
35
+ 16,
36
+ 17,
37
+ 18,
38
+ 19,
39
+ 20,
40
+ 21,
41
+ 22,
42
+ 23,
43
+ 24,
44
+ 25,
45
+ 26,
46
+ 27,
47
+ 28,
48
+ 29,
49
+ 30,
50
+ 31,
51
+ 32,
52
+ 33,
53
+ 34,
54
+ 35,
55
+ 36,
56
+ 37,
57
+ 38,
58
+ 39,
59
+ 40,
60
+ 41,
61
+ 42,
62
+ 43,
63
+ 44,
64
+ 45,
65
+ 46,
66
+ 47,
67
+ 48,
68
+ 49,
69
+ 50,
70
+ 51,
71
+ 52,
72
+ 53,
73
+ 54,
74
+ 55,
75
+ 56,
76
+ 57,
77
+ 58,
78
+ 59,
79
+ 60,
80
+ 61,
81
+ 62,
82
+ 63,
83
+ 64,
84
+ 65,
85
+ 66,
86
+ 67,
87
+ 68,
88
+ 69,
89
+ 70,
90
+ 71,
91
+ 72,
92
+ 73,
93
+ 74,
94
+ 75,
95
+ 76,
96
+ 77,
97
+ 78,
98
+ 79,
99
+ 80,
100
+ 81,
101
+ 82,
102
+ 83,
103
+ 84,
104
+ 85,
105
+ 86,
106
+ 87,
107
+ 88,
108
+ 89,
109
+ 90,
110
+ 91,
111
+ 92,
112
+ 93,
113
+ 94,
114
+ 95,
115
+ 96,
116
+ 97,
117
+ 98,
118
+ 99,
119
+ 100,
120
+ 101,
121
+ 102,
122
+ 103,
123
+ 104,
124
+ 105,
125
+ 106,
126
+ 107,
127
+ 108,
128
+ 109,
129
+ 110,
130
+ 111,
131
+ 112,
132
+ 113,
133
+ 114,
134
+ 115,
135
+ 116,
136
+ 117,
137
+ 118,
138
+ 119,
139
+ 120,
140
+ 121,
141
+ 122,
142
+ 123,
143
+ 124,
144
+ 125,
145
+ 126,
146
+ 127,
147
+ 128,
148
+ 129,
149
+ 130,
150
+ 131,
151
+ 132,
152
+ 133,
153
+ 134,
154
+ 135,
155
+ 136,
156
+ 137,
157
+ 138,
158
+ 139,
159
+ 140,
160
+ 141,
161
+ 142,
162
+ 143,
163
+ 144,
164
+ 145,
165
+ 146,
166
+ 147,
167
+ 148,
168
+ 149,
169
+ 150,
170
+ 151,
171
+ 152,
172
+ 153,
173
+ 154,
174
+ 155,
175
+ 156,
176
+ 157,
177
+ 158,
178
+ 159,
179
+ 160,
180
+ 161,
181
+ 162,
182
+ 163,
183
+ 164,
184
+ 165,
185
+ 166,
186
+ 167,
187
+ 168,
188
+ 169,
189
+ 170,
190
+ 171,
191
+ 172,
192
+ 173,
193
+ 174,
194
+ 175,
195
+ 176,
196
+ 177,
197
+ 178,
198
+ 179,
199
+ 180,
200
+ 181,
201
+ 182,
202
+ 183,
203
+ 184,
204
+ 185,
205
+ 186,
206
+ 187,
207
+ 188,
208
+ 189,
209
+ 190,
210
+ 191,
211
+ 192,
212
+ 193,
213
+ 194,
214
+ 195,
215
+ 196,
216
+ 197,
217
+ 198,
218
+ 199,
219
+ 200,
220
+ 201,
221
+ 202,
222
+ 203,
223
+ 204,
224
+ 205,
225
+ 206,
226
+ 207,
227
+ 208,
228
+ 209,
229
+ 210,
230
+ 211
231
+ ]
232
+ }
233
+ ]
training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65311f131578694798b9e6bbde34702d47fb3a4c799f330d28bdc46179c2118f
3
+ size 2203543624
training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad714a2bcac9778f438d0897b3c0851a4617ffdc1dad4dc7d1de8c44585a83e9
3
+ size 15708
training_state/scheduler_state.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_lrs": [
3
+ 8e-05
4
+ ],
5
+ "last_epoch": 130000,
6
+ "_step_count": 130001,
7
+ "_get_lr_called_within_step": false,
8
+ "_last_lr": [
9
+ 2.2237335495769035e-05
10
+ ],
11
+ "lr_lambdas": [
12
+ null
13
+ ]
14
+ }
training_state/training_step.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "step": 130000
3
+ }