Hugging Face's logo

SieloRobotics
/
dit_3tasks_2nd_trial

Robotics
LeRobot
Safetensors
multi_task_dit
Model card Files
xet
 Community
SieloRobotics commited on
Commit
74c12e7
·
verified ·
1 Parent(s): 54d6fec

checkpoint 027000 (full, resumable)

Browse files
Files changed (12) hide show
  1. checkpoints/027000/pretrained_model/config.json +106 -0
  2. checkpoints/027000/pretrained_model/model.safetensors +3 -0
  3. checkpoints/027000/pretrained_model/policy_postprocessor.json +32 -0
  4. checkpoints/027000/pretrained_model/policy_postprocessor_step_0_unnormalizer_processor.safetensors +3 -0
  5. checkpoints/027000/pretrained_model/policy_preprocessor.json +75 -0
  6. checkpoints/027000/pretrained_model/policy_preprocessor_step_4_normalizer_processor.safetensors +3 -0
  7. checkpoints/027000/pretrained_model/train_config.json +257 -0
  8. checkpoints/027000/training_state/optimizer_param_groups.json +508 -0
  9. checkpoints/027000/training_state/optimizer_state.safetensors +3 -0
  10. checkpoints/027000/training_state/rng_state.safetensors +3 -0
  11. checkpoints/027000/training_state/scheduler_state.json +18 -0
  12. checkpoints/027000/training_state/training_step.json +5 -0
checkpoints/027000/pretrained_model/config.json ADDED
@@ -0,0 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "multi_task_dit",
3
+ "n_obs_steps": 2,
4
+ "input_features": {
5
+ "observation.state": {
6
+ "type": "STATE",
7
+ "shape": [
8
+ 7
9
+ ]
10
+ },
11
+ "observation.images.top": {
12
+ "type": "VISUAL",
13
+ "shape": [
14
+ 3,
15
+ 480,
16
+ 640
17
+ ]
18
+ },
19
+ "observation.images.wrist": {
20
+ "type": "VISUAL",
21
+ "shape": [
22
+ 3,
23
+ 480,
24
+ 640
25
+ ]
26
+ }
27
+ },
28
+ "output_features": {
29
+ "action": {
30
+ "type": "ACTION",
31
+ "shape": [
32
+ 7
33
+ ]
34
+ }
35
+ },
36
+ "device": "cuda",
37
+ "use_amp": false,
38
+ "use_peft": false,
39
+ "push_to_hub": true,
40
+ "repo_id": "SieloRobotics/dit_3tasks_2",
41
+ "private": null,
42
+ "tags": null,
43
+ "license": null,
44
+ "pretrained_path": "/content/outputs/dit_3tasks_resumed/checkpoints/021000/pretrained_model",
45
+ "pretrained_revision": null,
46
+ "horizon": 32,
47
+ "n_action_steps": 24,
48
+ "objective": "diffusion",
49
+ "noise_scheduler_type": "DDPM",
50
+ "num_train_timesteps": 100,
51
+ "beta_schedule": "squaredcos_cap_v2",
52
+ "beta_start": 0.0001,
53
+ "beta_end": 0.02,
54
+ "prediction_type": "epsilon",
55
+ "clip_sample": true,
56
+ "clip_sample_range": 1.0,
57
+ "num_inference_steps": null,
58
+ "sigma_min": 0.0,
59
+ "num_integration_steps": 100,
60
+ "integration_method": "euler",
61
+ "timestep_sampling_strategy": "beta",
62
+ "timestep_sampling_s": 0.999,
63
+ "timestep_sampling_alpha": 1.5,
64
+ "timestep_sampling_beta": 1.0,
65
+ "hidden_dim": 512,
66
+ "num_layers": 6,
67
+ "num_heads": 8,
68
+ "dropout": 0.1,
69
+ "use_positional_encoding": false,
70
+ "timestep_embed_dim": 256,
71
+ "use_rope": true,
72
+ "rope_base": 10000.0,
73
+ "vision_encoder_name": "openai/clip-vit-base-patch16",
74
+ "use_separate_rgb_encoder_per_camera": true,
75
+ "vision_encoder_lr_multiplier": 0.1,
76
+ "image_resize_shape": [
77
+ 224,
78
+ 224
79
+ ],
80
+ "image_crop_shape": [
81
+ 224,
82
+ 224
83
+ ],
84
+ "image_crop_is_random": false,
85
+ "text_encoder_name": "openai/clip-vit-base-patch16",
86
+ "tokenizer_max_length": 77,
87
+ "tokenizer_padding": "max_length",
88
+ "tokenizer_padding_side": "right",
89
+ "tokenizer_truncation": true,
90
+ "normalization_mapping": {
91
+ "VISUAL": "MEAN_STD",
92
+ "STATE": "MIN_MAX",
93
+ "ACTION": "MIN_MAX"
94
+ },
95
+ "optimizer_lr": 2e-05,
96
+ "optimizer_betas": [
97
+ 0.95,
98
+ 0.999
99
+ ],
100
+ "optimizer_eps": 1e-08,
101
+ "optimizer_weight_decay": 0.0,
102
+ "scheduler_name": "cosine",
103
+ "scheduler_warmup_steps": 500,
104
+ "do_mask_loss_for_padding": false,
105
+ "drop_n_last_frames": 7
106
+ }
checkpoints/027000/pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:855e0f995f794fc21830314679c0f2f535151600e1c13ffb26644b0affa099c2
3
+ size 1338869684
checkpoints/027000/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
+ 7
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
+ }
checkpoints/027000/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 sha256:502f81eb5be9039a8846af35055057d9da8084c5c3e0140fcfa494e196dcf8c8
3
+ size 9824
checkpoints/027000/pretrained_model/policy_preprocessor.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "tokenizer_processor",
16
+ "config": {
17
+ "max_length": 77,
18
+ "task_key": "task",
19
+ "padding_side": "right",
20
+ "padding": "max_length",
21
+ "truncation": true,
22
+ "tokenizer_name": "openai/clip-vit-base-patch16"
23
+ }
24
+ },
25
+ {
26
+ "registry_name": "device_processor",
27
+ "config": {
28
+ "device": "cuda",
29
+ "float_dtype": null
30
+ }
31
+ },
32
+ {
33
+ "registry_name": "normalizer_processor",
34
+ "config": {
35
+ "eps": 1e-08,
36
+ "features": {
37
+ "observation.state": {
38
+ "type": "STATE",
39
+ "shape": [
40
+ 7
41
+ ]
42
+ },
43
+ "observation.images.top": {
44
+ "type": "VISUAL",
45
+ "shape": [
46
+ 3,
47
+ 480,
48
+ 640
49
+ ]
50
+ },
51
+ "observation.images.wrist": {
52
+ "type": "VISUAL",
53
+ "shape": [
54
+ 3,
55
+ 480,
56
+ 640
57
+ ]
58
+ },
59
+ "action": {
60
+ "type": "ACTION",
61
+ "shape": [
62
+ 7
63
+ ]
64
+ }
65
+ },
66
+ "norm_map": {
67
+ "VISUAL": "MEAN_STD",
68
+ "STATE": "MIN_MAX",
69
+ "ACTION": "MIN_MAX"
70
+ }
71
+ },
72
+ "state_file": "policy_preprocessor_step_4_normalizer_processor.safetensors"
73
+ }
74
+ ]
75
+ }
checkpoints/027000/pretrained_model/policy_preprocessor_step_4_normalizer_processor.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:118752880f4a65b75660c4874aabc19ad296f9f43d5266da51bed3a4fe336f77
3
+ size 9832
checkpoints/027000/pretrained_model/train_config.json ADDED
@@ -0,0 +1,257 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "SieloRobotics/3tasks_combined2_short",
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
+ "affine": {
62
+ "weight": 1.0,
63
+ "type": "RandomAffine",
64
+ "kwargs": {
65
+ "degrees": [
66
+ -5.0,
67
+ 5.0
68
+ ],
69
+ "translate": [
70
+ 0.05,
71
+ 0.05
72
+ ]
73
+ }
74
+ }
75
+ }
76
+ },
77
+ "revision": null,
78
+ "use_imagenet_stats": true,
79
+ "video_backend": "torchcodec",
80
+ "return_uint8": false,
81
+ "depth_output_unit": "mm",
82
+ "streaming": false,
83
+ "eval_split": 0.0
84
+ },
85
+ "env": null,
86
+ "policy": {
87
+ "type": "multi_task_dit",
88
+ "n_obs_steps": 2,
89
+ "input_features": {
90
+ "observation.state": {
91
+ "type": "STATE",
92
+ "shape": [
93
+ 7
94
+ ]
95
+ },
96
+ "observation.images.top": {
97
+ "type": "VISUAL",
98
+ "shape": [
99
+ 3,
100
+ 480,
101
+ 640
102
+ ]
103
+ },
104
+ "observation.images.wrist": {
105
+ "type": "VISUAL",
106
+ "shape": [
107
+ 3,
108
+ 480,
109
+ 640
110
+ ]
111
+ }
112
+ },
113
+ "output_features": {
114
+ "action": {
115
+ "type": "ACTION",
116
+ "shape": [
117
+ 7
118
+ ]
119
+ }
120
+ },
121
+ "device": "cuda",
122
+ "use_amp": false,
123
+ "use_peft": false,
124
+ "push_to_hub": true,
125
+ "repo_id": "SieloRobotics/dit_3tasks_2",
126
+ "private": null,
127
+ "tags": null,
128
+ "license": null,
129
+ "pretrained_path": "/content/outputs/dit_3tasks_resumed/checkpoints/021000/pretrained_model",
130
+ "pretrained_revision": null,
131
+ "horizon": 32,
132
+ "n_action_steps": 24,
133
+ "objective": "diffusion",
134
+ "noise_scheduler_type": "DDPM",
135
+ "num_train_timesteps": 100,
136
+ "beta_schedule": "squaredcos_cap_v2",
137
+ "beta_start": 0.0001,
138
+ "beta_end": 0.02,
139
+ "prediction_type": "epsilon",
140
+ "clip_sample": true,
141
+ "clip_sample_range": 1.0,
142
+ "num_inference_steps": null,
143
+ "sigma_min": 0.0,
144
+ "num_integration_steps": 100,
145
+ "integration_method": "euler",
146
+ "timestep_sampling_strategy": "beta",
147
+ "timestep_sampling_s": 0.999,
148
+ "timestep_sampling_alpha": 1.5,
149
+ "timestep_sampling_beta": 1.0,
150
+ "hidden_dim": 512,
151
+ "num_layers": 6,
152
+ "num_heads": 8,
153
+ "dropout": 0.1,
154
+ "use_positional_encoding": false,
155
+ "timestep_embed_dim": 256,
156
+ "use_rope": true,
157
+ "rope_base": 10000.0,
158
+ "vision_encoder_name": "openai/clip-vit-base-patch16",
159
+ "use_separate_rgb_encoder_per_camera": true,
160
+ "vision_encoder_lr_multiplier": 0.1,
161
+ "image_resize_shape": [
162
+ 224,
163
+ 224
164
+ ],
165
+ "image_crop_shape": [
166
+ 224,
167
+ 224
168
+ ],
169
+ "image_crop_is_random": false,
170
+ "text_encoder_name": "openai/clip-vit-base-patch16",
171
+ "tokenizer_max_length": 77,
172
+ "tokenizer_padding": "max_length",
173
+ "tokenizer_padding_side": "right",
174
+ "tokenizer_truncation": true,
175
+ "normalization_mapping": {
176
+ "VISUAL": "MEAN_STD",
177
+ "STATE": "MIN_MAX",
178
+ "ACTION": "MIN_MAX"
179
+ },
180
+ "optimizer_lr": 2e-05,
181
+ "optimizer_betas": [
182
+ 0.95,
183
+ 0.999
184
+ ],
185
+ "optimizer_eps": 1e-08,
186
+ "optimizer_weight_decay": 0.0,
187
+ "scheduler_name": "cosine",
188
+ "scheduler_warmup_steps": 500,
189
+ "do_mask_loss_for_padding": false,
190
+ "drop_n_last_frames": 7
191
+ },
192
+ "reward_model": null,
193
+ "output_dir": "outputs/dit_3tasks_resumed",
194
+ "job_name": "dit_3tasks",
195
+ "resume": true,
196
+ "seed": 1000,
197
+ "cudnn_deterministic": false,
198
+ "num_workers": 4,
199
+ "batch_size": 96,
200
+ "prefetch_factor": 4,
201
+ "persistent_workers": true,
202
+ "steps": 50000,
203
+ "env_eval_freq": 20000,
204
+ "log_freq": 200,
205
+ "eval_steps": 0,
206
+ "max_eval_samples": 0,
207
+ "tolerance_s": 0.0001,
208
+ "save_checkpoint": true,
209
+ "save_freq": 3000,
210
+ "use_policy_training_preset": true,
211
+ "optimizer": {
212
+ "type": "adam",
213
+ "lr": 2e-05,
214
+ "weight_decay": 0.0,
215
+ "grad_clip_norm": 10.0,
216
+ "betas": [
217
+ 0.95,
218
+ 0.999
219
+ ],
220
+ "eps": 1e-08
221
+ },
222
+ "scheduler": {
223
+ "type": "diffuser",
224
+ "num_warmup_steps": 500,
225
+ "name": "cosine"
226
+ },
227
+ "eval": {
228
+ "n_episodes": 50,
229
+ "batch_size": 8,
230
+ "use_async_envs": true,
231
+ "recording": false,
232
+ "recording_repo_id": null,
233
+ "recording_private": false
234
+ },
235
+ "wandb": {
236
+ "enable": true,
237
+ "disable_artifact": false,
238
+ "project": "dit_3tasks",
239
+ "entity": null,
240
+ "notes": null,
241
+ "run_id": "f0kgg913",
242
+ "mode": null,
243
+ "add_tags": true
244
+ },
245
+ "peft": null,
246
+ "job": {
247
+ "target": null,
248
+ "image": "huggingface/lerobot-gpu:latest",
249
+ "timeout": "2d",
250
+ "detach": false,
251
+ "tags": []
252
+ },
253
+ "save_checkpoint_to_hub": false,
254
+ "sample_weighting": null,
255
+ "rename_map": {},
256
+ "checkpoint_path": "/content/outputs/dit_3tasks_resumed/checkpoints/021000"
257
+ }
checkpoints/027000/training_state/optimizer_param_groups.json ADDED
@@ -0,0 +1,508 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "lr": 8.89161800098989e-06,
4
+ "betas": [
5
+ 0.95,
6
+ 0.999
7
+ ],
8
+ "eps": 1e-08,
9
+ "weight_decay": 0.0,
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": 2e-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
+ ]
90
+ },
91
+ {
92
+ "lr": 8.891618000989892e-07,
93
+ "betas": [
94
+ 0.95,
95
+ 0.999
96
+ ],
97
+ "eps": 1e-08,
98
+ "weight_decay": 0.0,
99
+ "amsgrad": false,
100
+ "maximize": false,
101
+ "foreach": null,
102
+ "capturable": false,
103
+ "differentiable": false,
104
+ "fused": null,
105
+ "decoupled_weight_decay": false,
106
+ "initial_lr": 2.0000000000000003e-06,
107
+ "params": [
108
+ 70,
109
+ 71,
110
+ 72,
111
+ 73,
112
+ 74,
113
+ 75,
114
+ 76,
115
+ 77,
116
+ 78,
117
+ 79,
118
+ 80,
119
+ 81,
120
+ 82,
121
+ 83,
122
+ 84,
123
+ 85,
124
+ 86,
125
+ 87,
126
+ 88,
127
+ 89,
128
+ 90,
129
+ 91,
130
+ 92,
131
+ 93,
132
+ 94,
133
+ 95,
134
+ 96,
135
+ 97,
136
+ 98,
137
+ 99,
138
+ 100,
139
+ 101,
140
+ 102,
141
+ 103,
142
+ 104,
143
+ 105,
144
+ 106,
145
+ 107,
146
+ 108,
147
+ 109,
148
+ 110,
149
+ 111,
150
+ 112,
151
+ 113,
152
+ 114,
153
+ 115,
154
+ 116,
155
+ 117,
156
+ 118,
157
+ 119,
158
+ 120,
159
+ 121,
160
+ 122,
161
+ 123,
162
+ 124,
163
+ 125,
164
+ 126,
165
+ 127,
166
+ 128,
167
+ 129,
168
+ 130,
169
+ 131,
170
+ 132,
171
+ 133,
172
+ 134,
173
+ 135,
174
+ 136,
175
+ 137,
176
+ 138,
177
+ 139,
178
+ 140,
179
+ 141,
180
+ 142,
181
+ 143,
182
+ 144,
183
+ 145,
184
+ 146,
185
+ 147,
186
+ 148,
187
+ 149,
188
+ 150,
189
+ 151,
190
+ 152,
191
+ 153,
192
+ 154,
193
+ 155,
194
+ 156,
195
+ 157,
196
+ 158,
197
+ 159,
198
+ 160,
199
+ 161,
200
+ 162,
201
+ 163,
202
+ 164,
203
+ 165,
204
+ 166,
205
+ 167,
206
+ 168,
207
+ 169,
208
+ 170,
209
+ 171,
210
+ 172,
211
+ 173,
212
+ 174,
213
+ 175,
214
+ 176,
215
+ 177,
216
+ 178,
217
+ 179,
218
+ 180,
219
+ 181,
220
+ 182,
221
+ 183,
222
+ 184,
223
+ 185,
224
+ 186,
225
+ 187,
226
+ 188,
227
+ 189,
228
+ 190,
229
+ 191,
230
+ 192,
231
+ 193,
232
+ 194,
233
+ 195,
234
+ 196,
235
+ 197,
236
+ 198,
237
+ 199,
238
+ 200,
239
+ 201,
240
+ 202,
241
+ 203,
242
+ 204,
243
+ 205,
244
+ 206,
245
+ 207,
246
+ 208,
247
+ 209,
248
+ 210,
249
+ 211,
250
+ 212,
251
+ 213,
252
+ 214,
253
+ 215,
254
+ 216,
255
+ 217,
256
+ 218,
257
+ 219,
258
+ 220,
259
+ 221,
260
+ 222,
261
+ 223,
262
+ 224,
263
+ 225,
264
+ 226,
265
+ 227,
266
+ 228,
267
+ 229,
268
+ 230,
269
+ 231,
270
+ 232,
271
+ 233,
272
+ 234,
273
+ 235,
274
+ 236,
275
+ 237,
276
+ 238,
277
+ 239,
278
+ 240,
279
+ 241,
280
+ 242,
281
+ 243,
282
+ 244,
283
+ 245,
284
+ 246,
285
+ 247,
286
+ 248,
287
+ 249,
288
+ 250,
289
+ 251,
290
+ 252,
291
+ 253,
292
+ 254,
293
+ 255,
294
+ 256,
295
+ 257,
296
+ 258,
297
+ 259,
298
+ 260,
299
+ 261,
300
+ 262,
301
+ 263,
302
+ 264,
303
+ 265,
304
+ 266,
305
+ 267,
306
+ 268,
307
+ 269,
308
+ 270,
309
+ 271,
310
+ 272,
311
+ 273,
312
+ 274,
313
+ 275,
314
+ 276,
315
+ 277,
316
+ 278,
317
+ 279,
318
+ 280,
319
+ 281,
320
+ 282,
321
+ 283,
322
+ 284,
323
+ 285,
324
+ 286,
325
+ 287,
326
+ 288,
327
+ 289,
328
+ 290,
329
+ 291,
330
+ 292,
331
+ 293,
332
+ 294,
333
+ 295,
334
+ 296,
335
+ 297,
336
+ 298,
337
+ 299,
338
+ 300,
339
+ 301,
340
+ 302,
341
+ 303,
342
+ 304,
343
+ 305,
344
+ 306,
345
+ 307,
346
+ 308,
347
+ 309,
348
+ 310,
349
+ 311,
350
+ 312,
351
+ 313,
352
+ 314,
353
+ 315,
354
+ 316,
355
+ 317,
356
+ 318,
357
+ 319,
358
+ 320,
359
+ 321,
360
+ 322,
361
+ 323,
362
+ 324,
363
+ 325,
364
+ 326,
365
+ 327,
366
+ 328,
367
+ 329,
368
+ 330,
369
+ 331,
370
+ 332,
371
+ 333,
372
+ 334,
373
+ 335,
374
+ 336,
375
+ 337,
376
+ 338,
377
+ 339,
378
+ 340,
379
+ 341,
380
+ 342,
381
+ 343,
382
+ 344,
383
+ 345,
384
+ 346,
385
+ 347,
386
+ 348,
387
+ 349,
388
+ 350,
389
+ 351,
390
+ 352,
391
+ 353,
392
+ 354,
393
+ 355,
394
+ 356,
395
+ 357,
396
+ 358,
397
+ 359,
398
+ 360,
399
+ 361,
400
+ 362,
401
+ 363,
402
+ 364,
403
+ 365,
404
+ 366,
405
+ 367,
406
+ 368,
407
+ 369,
408
+ 370,
409
+ 371,
410
+ 372,
411
+ 373,
412
+ 374,
413
+ 375,
414
+ 376,
415
+ 377,
416
+ 378,
417
+ 379,
418
+ 380,
419
+ 381,
420
+ 382,
421
+ 383,
422
+ 384,
423
+ 385,
424
+ 386,
425
+ 387,
426
+ 388,
427
+ 389,
428
+ 390,
429
+ 391,
430
+ 392,
431
+ 393,
432
+ 394,
433
+ 395,
434
+ 396,
435
+ 397,
436
+ 398,
437
+ 399,
438
+ 400,
439
+ 401,
440
+ 402,
441
+ 403,
442
+ 404,
443
+ 405,
444
+ 406,
445
+ 407,
446
+ 408,
447
+ 409,
448
+ 410,
449
+ 411,
450
+ 412,
451
+ 413,
452
+ 414,
453
+ 415,
454
+ 416,
455
+ 417,
456
+ 418,
457
+ 419,
458
+ 420,
459
+ 421,
460
+ 422,
461
+ 423,
462
+ 424,
463
+ 425,
464
+ 426,
465
+ 427,
466
+ 428,
467
+ 429,
468
+ 430,
469
+ 431,
470
+ 432,
471
+ 433,
472
+ 434,
473
+ 435,
474
+ 436,
475
+ 437,
476
+ 438,
477
+ 439,
478
+ 440,
479
+ 441,
480
+ 442,
481
+ 443,
482
+ 444,
483
+ 445,
484
+ 446,
485
+ 447,
486
+ 448,
487
+ 449,
488
+ 450,
489
+ 451,
490
+ 452,
491
+ 453,
492
+ 454,
493
+ 455,
494
+ 456,
495
+ 457,
496
+ 458,
497
+ 459,
498
+ 460,
499
+ 461,
500
+ 462,
501
+ 463,
502
+ 464,
503
+ 465,
504
+ 466,
505
+ 467
506
+ ]
507
+ }
508
+ ]
checkpoints/027000/training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b28ea7090140497cc599bbb5d298eea2c7910b3e30a6bd890983c0e4f49e0afd
3
+ size 2172312904
checkpoints/027000/training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:855d7a61ea3e90bb5a1cb7ec362c9b795b7ec1f5f9154f6576522737cad8ee52
3
+ size 15708
checkpoints/027000/training_state/scheduler_state.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_lrs": [
3
+ 2e-05,
4
+ 2.0000000000000003e-06
5
+ ],
6
+ "last_epoch": 27000,
7
+ "_step_count": 27001,
8
+ "_is_initial": false,
9
+ "_get_lr_called_within_step": false,
10
+ "_last_lr": [
11
+ 8.89161800098989e-06,
12
+ 8.891618000989892e-07
13
+ ],
14
+ "lr_lambdas": [
15
+ null,
16
+ null
17
+ ]
18
+ }
checkpoints/027000/training_state/training_step.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "step": 27000,
3
+ "num_processes": 1,
4
+ "batch_size": 96
5
+ }