Hugging Face's logo

SieloRobotics
/
dit_ee_cubes

Robotics
LeRobot
Safetensors
multi_task_dit
Model card Files
xet
 Community
SieloRobotics commited on
Commit
41ff48a
·
verified ·
1 Parent(s): bdff189

checkpoint 028000

Browse files
Files changed (20) hide show
  1. checkpoints/028000/pretrained_model/config.json +124 -0
  2. checkpoints/028000/pretrained_model/model.safetensors +3 -0
  3. checkpoints/028000/pretrained_model/policy_postprocessor.json +38 -0
  4. checkpoints/028000/pretrained_model/policy_postprocessor_step_0_unnormalizer_processor.safetensors +3 -0
  5. checkpoints/028000/pretrained_model/policy_preprocessor.json +73 -0
  6. checkpoints/028000/pretrained_model/policy_preprocessor_step_4_normalizer_processor.safetensors +3 -0
  7. checkpoints/028000/pretrained_model/train_config.json +347 -0
  8. checkpoints/028000/pretrained_model_ema/config.json +124 -0
  9. checkpoints/028000/pretrained_model_ema/model.safetensors +3 -0
  10. checkpoints/028000/pretrained_model_ema/policy_postprocessor.json +38 -0
  11. checkpoints/028000/pretrained_model_ema/policy_postprocessor_step_0_unnormalizer_processor.safetensors +3 -0
  12. checkpoints/028000/pretrained_model_ema/policy_preprocessor.json +73 -0
  13. checkpoints/028000/pretrained_model_ema/policy_preprocessor_step_4_normalizer_processor.safetensors +3 -0
  14. checkpoints/028000/pretrained_model_ema/train_config.json +347 -0
  15. checkpoints/028000/training_state/ema_state.pt +3 -0
  16. checkpoints/028000/training_state/optimizer_param_groups.json +506 -0
  17. checkpoints/028000/training_state/optimizer_state.safetensors +3 -0
  18. checkpoints/028000/training_state/rng_state.safetensors +3 -0
  19. checkpoints/028000/training_state/scheduler_state.json +18 -0
  20. checkpoints/028000/training_state/training_step.json +13 -0
checkpoints/028000/pretrained_model/config.json ADDED
@@ -0,0 +1,124 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "multi_task_dit",
3
+ "n_obs_steps": 2,
4
+ "input_features": {
5
+ "observation.images.wrist": {
6
+ "type": "VISUAL",
7
+ "shape": [
8
+ 3,
9
+ 480,
10
+ 640
11
+ ]
12
+ },
13
+ "observation.images.top": {
14
+ "type": "VISUAL",
15
+ "shape": [
16
+ 3,
17
+ 480,
18
+ 640
19
+ ]
20
+ },
21
+ "observation.state": {
22
+ "type": "STATE",
23
+ "shape": [
24
+ 10
25
+ ]
26
+ }
27
+ },
28
+ "output_features": {
29
+ "action": {
30
+ "type": "ACTION",
31
+ "shape": [
32
+ 10
33
+ ]
34
+ }
35
+ },
36
+ "device": "cuda",
37
+ "dtype": null,
38
+ "use_amp": false,
39
+ "use_peft": false,
40
+ "push_to_hub": true,
41
+ "repo_id": "SieloRobotics/dit_ee_cubes",
42
+ "private": false,
43
+ "tags": null,
44
+ "license": null,
45
+ "pretrained_path": null,
46
+ "pretrained_revision": null,
47
+ "horizon": 32,
48
+ "n_action_steps": 8,
49
+ "objective": "flow_matching",
50
+ "noise_scheduler_type": "DDPM",
51
+ "num_train_timesteps": 100,
52
+ "beta_schedule": "squaredcos_cap_v2",
53
+ "beta_start": 0.0001,
54
+ "beta_end": 0.02,
55
+ "prediction_type": "epsilon",
56
+ "clip_sample": true,
57
+ "clip_sample_range": 1.0,
58
+ "num_inference_steps": null,
59
+ "sigma_min": 0.0,
60
+ "num_integration_steps": 10,
61
+ "integration_method": "euler",
62
+ "timestep_sampling_strategy": "beta",
63
+ "timestep_sampling_s": 0.999,
64
+ "timestep_sampling_alpha": 1.5,
65
+ "timestep_sampling_beta": 1.0,
66
+ "hidden_dim": 512,
67
+ "num_layers": 6,
68
+ "num_heads": 8,
69
+ "dropout": 0.1,
70
+ "use_positional_encoding": false,
71
+ "timestep_embed_dim": 256,
72
+ "use_rope": true,
73
+ "rope_base": 10000.0,
74
+ "vision_encoder_name": "openai/clip-vit-base-patch16",
75
+ "use_separate_rgb_encoder_per_camera": true,
76
+ "vision_encoder_lr_multiplier": 0.1,
77
+ "image_resize_shape": [
78
+ 240,
79
+ 240
80
+ ],
81
+ "image_crop_shape": [
82
+ 224,
83
+ 224
84
+ ],
85
+ "image_crop_is_random": true,
86
+ "compile_model": true,
87
+ "compile_mode": null,
88
+ "use_text_conditioning": false,
89
+ "text_encoder_name": "openai/clip-vit-base-patch16",
90
+ "tokenizer_max_length": 77,
91
+ "tokenizer_padding": "max_length",
92
+ "tokenizer_padding_side": "right",
93
+ "tokenizer_truncation": true,
94
+ "normalization_mapping": {
95
+ "VISUAL": "MEAN_STD",
96
+ "STATE": "QUANTILES",
97
+ "ACTION": "QUANTILES"
98
+ },
99
+ "use_relative_ee_actions": true,
100
+ "action_feature_names": [
101
+ "ee.x",
102
+ "ee.y",
103
+ "ee.z",
104
+ "ee.r6d_0",
105
+ "ee.r6d_1",
106
+ "ee.r6d_2",
107
+ "ee.r6d_3",
108
+ "ee.r6d_4",
109
+ "ee.r6d_5",
110
+ "gripper.pos"
111
+ ],
112
+ "optimizer_lr": 0.0001,
113
+ "optimizer_betas": [
114
+ 0.95,
115
+ 0.999
116
+ ],
117
+ "optimizer_eps": 1e-08,
118
+ "optimizer_weight_decay": 0.0,
119
+ "optimizer_grad_clip_norm": 1.0,
120
+ "scheduler_name": "cosine",
121
+ "scheduler_warmup_steps": 800,
122
+ "do_mask_loss_for_padding": false,
123
+ "drop_n_last_frames": 23
124
+ }
checkpoints/028000/pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b52231f8c9e9e85f91b8aa49a96e17d1a7f1e5dd36d5766eed47a0ce8a5a4ffa
3
+ size 1010086976
checkpoints/028000/pretrained_model/policy_postprocessor.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ 10
13
+ ]
14
+ }
15
+ },
16
+ "norm_map": {
17
+ "VISUAL": "MEAN_STD",
18
+ "STATE": "QUANTILES",
19
+ "ACTION": "QUANTILES"
20
+ }
21
+ },
22
+ "state_file": "policy_postprocessor_step_0_unnormalizer_processor.safetensors"
23
+ },
24
+ {
25
+ "registry_name": "absolute_ee_actions_processor",
26
+ "config": {
27
+ "enabled": true
28
+ }
29
+ },
30
+ {
31
+ "registry_name": "device_processor",
32
+ "config": {
33
+ "device": "cpu",
34
+ "float_dtype": null
35
+ }
36
+ }
37
+ ]
38
+ }
checkpoints/028000/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:be1e4c4b011808b824c52e23f647269b1cee8124ccdda17265cc0b4885950da4
3
+ size 9888
checkpoints/028000/pretrained_model/policy_preprocessor.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "relative_ee_actions_processor",
23
+ "config": {
24
+ "enabled": true,
25
+ "pos_index": 0,
26
+ "rot6d_index": 3,
27
+ "anchor_obs_index": -1
28
+ }
29
+ },
30
+ {
31
+ "registry_name": "normalizer_processor",
32
+ "config": {
33
+ "eps": 1e-08,
34
+ "features": {
35
+ "observation.images.wrist": {
36
+ "type": "VISUAL",
37
+ "shape": [
38
+ 3,
39
+ 480,
40
+ 640
41
+ ]
42
+ },
43
+ "observation.images.top": {
44
+ "type": "VISUAL",
45
+ "shape": [
46
+ 3,
47
+ 480,
48
+ 640
49
+ ]
50
+ },
51
+ "observation.state": {
52
+ "type": "STATE",
53
+ "shape": [
54
+ 10
55
+ ]
56
+ },
57
+ "action": {
58
+ "type": "ACTION",
59
+ "shape": [
60
+ 10
61
+ ]
62
+ }
63
+ },
64
+ "norm_map": {
65
+ "VISUAL": "MEAN_STD",
66
+ "STATE": "QUANTILES",
67
+ "ACTION": "QUANTILES"
68
+ }
69
+ },
70
+ "state_file": "policy_preprocessor_step_4_normalizer_processor.safetensors"
71
+ }
72
+ ]
73
+ }
checkpoints/028000/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 sha256:3e004b0582c25c39c12fa6ddde74db10824a5fb64c948de676f92949dcbd44a1
3
+ size 9896
checkpoints/028000/pretrained_model/train_config.json ADDED
@@ -0,0 +1,347 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "SieloRobotics/rebot_pick_place_ee",
4
+ "repo_type": "dataset",
5
+ "root": null,
6
+ "episodes": null,
7
+ "exclude_episodes": null,
8
+ "image_transforms": {
9
+ "enable": false,
10
+ "backend": "dataloader",
11
+ "gpu_compile": true,
12
+ "gpu_chunk_size": 32,
13
+ "max_num_transforms": 3,
14
+ "random_order": false,
15
+ "tfs": {
16
+ "brightness": {
17
+ "weight": 1.0,
18
+ "type": "ColorJitter",
19
+ "kwargs": {
20
+ "brightness": [
21
+ 0.8,
22
+ 1.2
23
+ ]
24
+ }
25
+ },
26
+ "contrast": {
27
+ "weight": 1.0,
28
+ "type": "ColorJitter",
29
+ "kwargs": {
30
+ "contrast": [
31
+ 0.8,
32
+ 1.2
33
+ ]
34
+ }
35
+ },
36
+ "saturation": {
37
+ "weight": 1.0,
38
+ "type": "ColorJitter",
39
+ "kwargs": {
40
+ "saturation": [
41
+ 0.5,
42
+ 1.5
43
+ ]
44
+ }
45
+ },
46
+ "hue": {
47
+ "weight": 1.0,
48
+ "type": "ColorJitter",
49
+ "kwargs": {
50
+ "hue": [
51
+ -0.05,
52
+ 0.05
53
+ ]
54
+ }
55
+ },
56
+ "sharpness": {
57
+ "weight": 1.0,
58
+ "type": "SharpnessJitter",
59
+ "kwargs": {
60
+ "sharpness": [
61
+ 0.5,
62
+ 1.5
63
+ ]
64
+ }
65
+ },
66
+ "affine": {
67
+ "weight": 1.0,
68
+ "type": "RandomAffine",
69
+ "kwargs": {
70
+ "degrees": [
71
+ -5.0,
72
+ 5.0
73
+ ],
74
+ "translate": [
75
+ 0.05,
76
+ 0.05
77
+ ]
78
+ }
79
+ }
80
+ }
81
+ },
82
+ "revision": null,
83
+ "use_imagenet_stats": true,
84
+ "video_backend": "torchcodec",
85
+ "return_uint8": true,
86
+ "depth_output_unit": "mm",
87
+ "streaming": false,
88
+ "streaming_episode_pool_size": null,
89
+ "streaming_sampling_strategy": "remaining",
90
+ "streaming_prefetch_episodes": 8,
91
+ "streaming_byte_budget_gb": 8.0,
92
+ "streaming_decode_threads": 2,
93
+ "streaming_decoded_queue_size": 8,
94
+ "streaming_native_http_connections": null,
95
+ "streaming_native_http_subranges": 1,
96
+ "video_decoder_cache_size": null,
97
+ "eval_split": 0.02
98
+ },
99
+ "env": null,
100
+ "policy": {
101
+ "type": "multi_task_dit",
102
+ "n_obs_steps": 2,
103
+ "input_features": {
104
+ "observation.images.wrist": {
105
+ "type": "VISUAL",
106
+ "shape": [
107
+ 3,
108
+ 480,
109
+ 640
110
+ ]
111
+ },
112
+ "observation.images.top": {
113
+ "type": "VISUAL",
114
+ "shape": [
115
+ 3,
116
+ 480,
117
+ 640
118
+ ]
119
+ },
120
+ "observation.state": {
121
+ "type": "STATE",
122
+ "shape": [
123
+ 10
124
+ ]
125
+ }
126
+ },
127
+ "output_features": {
128
+ "action": {
129
+ "type": "ACTION",
130
+ "shape": [
131
+ 10
132
+ ]
133
+ }
134
+ },
135
+ "device": "cuda",
136
+ "dtype": null,
137
+ "use_amp": false,
138
+ "use_peft": false,
139
+ "push_to_hub": true,
140
+ "repo_id": "SieloRobotics/dit_ee_cubes",
141
+ "private": false,
142
+ "tags": null,
143
+ "license": null,
144
+ "pretrained_path": null,
145
+ "pretrained_revision": null,
146
+ "horizon": 32,
147
+ "n_action_steps": 8,
148
+ "objective": "flow_matching",
149
+ "noise_scheduler_type": "DDPM",
150
+ "num_train_timesteps": 100,
151
+ "beta_schedule": "squaredcos_cap_v2",
152
+ "beta_start": 0.0001,
153
+ "beta_end": 0.02,
154
+ "prediction_type": "epsilon",
155
+ "clip_sample": true,
156
+ "clip_sample_range": 1.0,
157
+ "num_inference_steps": null,
158
+ "sigma_min": 0.0,
159
+ "num_integration_steps": 10,
160
+ "integration_method": "euler",
161
+ "timestep_sampling_strategy": "beta",
162
+ "timestep_sampling_s": 0.999,
163
+ "timestep_sampling_alpha": 1.5,
164
+ "timestep_sampling_beta": 1.0,
165
+ "hidden_dim": 512,
166
+ "num_layers": 6,
167
+ "num_heads": 8,
168
+ "dropout": 0.1,
169
+ "use_positional_encoding": false,
170
+ "timestep_embed_dim": 256,
171
+ "use_rope": true,
172
+ "rope_base": 10000.0,
173
+ "vision_encoder_name": "openai/clip-vit-base-patch16",
174
+ "use_separate_rgb_encoder_per_camera": true,
175
+ "vision_encoder_lr_multiplier": 0.1,
176
+ "image_resize_shape": [
177
+ 240,
178
+ 240
179
+ ],
180
+ "image_crop_shape": [
181
+ 224,
182
+ 224
183
+ ],
184
+ "image_crop_is_random": true,
185
+ "compile_model": true,
186
+ "compile_mode": null,
187
+ "use_text_conditioning": false,
188
+ "text_encoder_name": "openai/clip-vit-base-patch16",
189
+ "tokenizer_max_length": 77,
190
+ "tokenizer_padding": "max_length",
191
+ "tokenizer_padding_side": "right",
192
+ "tokenizer_truncation": true,
193
+ "normalization_mapping": {
194
+ "VISUAL": "MEAN_STD",
195
+ "STATE": "QUANTILES",
196
+ "ACTION": "QUANTILES"
197
+ },
198
+ "use_relative_ee_actions": true,
199
+ "action_feature_names": [
200
+ "ee.x",
201
+ "ee.y",
202
+ "ee.z",
203
+ "ee.r6d_0",
204
+ "ee.r6d_1",
205
+ "ee.r6d_2",
206
+ "ee.r6d_3",
207
+ "ee.r6d_4",
208
+ "ee.r6d_5",
209
+ "gripper.pos"
210
+ ],
211
+ "optimizer_lr": 0.0001,
212
+ "optimizer_betas": [
213
+ 0.95,
214
+ 0.999
215
+ ],
216
+ "optimizer_eps": 1e-08,
217
+ "optimizer_weight_decay": 0.0,
218
+ "optimizer_grad_clip_norm": 1.0,
219
+ "scheduler_name": "cosine",
220
+ "scheduler_warmup_steps": 800,
221
+ "do_mask_loss_for_padding": false,
222
+ "drop_n_last_frames": 23
223
+ },
224
+ "reward_model": null,
225
+ "output_dir": "/content/outputs/dit_ee_cubes_run_20261020_202835",
226
+ "job_name": "dit_ee_cubes",
227
+ "resume": false,
228
+ "seed": 1000,
229
+ "cudnn_deterministic": false,
230
+ "num_workers": 12,
231
+ "batch_size": 256,
232
+ "prefetch_factor": 2,
233
+ "persistent_workers": true,
234
+ "dataloader_multiprocessing_context": "spawn",
235
+ "steps": 40000,
236
+ "env_eval_freq": 20000,
237
+ "log_freq": 100,
238
+ "eval_steps": 2000,
239
+ "max_eval_samples": 0,
240
+ "tolerance_s": 0.0001,
241
+ "save_checkpoint": true,
242
+ "save_freq": 2000,
243
+ "checkpoint_format": "safetensors",
244
+ "use_policy_training_preset": true,
245
+ "optimizer": {
246
+ "type": "adam",
247
+ "lr": 0.0001,
248
+ "weight_decay": 0.0,
249
+ "grad_clip_norm": 1.0,
250
+ "betas": [
251
+ 0.95,
252
+ 0.999
253
+ ],
254
+ "eps": 1e-08
255
+ },
256
+ "scheduler": {
257
+ "type": "diffuser",
258
+ "num_warmup_steps": 800,
259
+ "name": "cosine"
260
+ },
261
+ "parallelism": {
262
+ "dp_replicate": 1,
263
+ "dp_shard": 1,
264
+ "context_parallel": {
265
+ "ring_degree": 1,
266
+ "ulysses_degree": 1
267
+ },
268
+ "cfg_parallel": 1
269
+ },
270
+ "accelerator": {
271
+ "mixed_precision": "bf16",
272
+ "gradient_accumulation": {
273
+ "steps": 1
274
+ },
275
+ "grad_scaler": {
276
+ "init_scale": 65536.0,
277
+ "growth_factor": 2.0,
278
+ "backoff_factor": 0.5,
279
+ "growth_interval": 2000
280
+ },
281
+ "fsdp": {
282
+ "reshard_after_forward": true,
283
+ "wrap_modules": null,
284
+ "min_num_params": null,
285
+ "cpu_offload": false,
286
+ "ignored_modules": null
287
+ },
288
+ "ddp": {
289
+ "find_unused_parameters": true,
290
+ "gradient_as_bucket_view": false,
291
+ "static_graph": false
292
+ },
293
+ "compile": {
294
+ "enabled": false,
295
+ "backend": "inductor",
296
+ "mode": null,
297
+ "regional": true
298
+ },
299
+ "activation_checkpointing": {
300
+ "mode": "none"
301
+ }
302
+ },
303
+ "eval": {
304
+ "n_episodes": 50,
305
+ "batch_size": 33,
306
+ "use_async_envs": true,
307
+ "recording": false,
308
+ "recording_repo_id": null,
309
+ "recording_private": false
310
+ },
311
+ "ema": {
312
+ "enable": true,
313
+ "decay": null,
314
+ "update_after_step": 0,
315
+ "inv_gamma": 1.0,
316
+ "power": 0.75,
317
+ "min_decay": 0.0,
318
+ "max_decay": 0.9999,
319
+ "use_for_eval": true
320
+ },
321
+ "wandb": {
322
+ "enable": true,
323
+ "disable_artifact": true,
324
+ "project": "dit_ee_cubes",
325
+ "entity": null,
326
+ "notes": null,
327
+ "run_id": "igo5cik4",
328
+ "resume": null,
329
+ "mode": null,
330
+ "console": "wrap",
331
+ "console_multipart": false,
332
+ "console_chunk_max_seconds": 0,
333
+ "add_tags": true
334
+ },
335
+ "peft": null,
336
+ "job": {
337
+ "target": null,
338
+ "image": "huggingface/lerobot-gpu:latest",
339
+ "timeout": "2d",
340
+ "detach": false,
341
+ "tags": []
342
+ },
343
+ "save_checkpoint_to_hub": false,
344
+ "sample_weighting": null,
345
+ "rename_map": {},
346
+ "checkpoint_path": null
347
+ }
checkpoints/028000/pretrained_model_ema/config.json ADDED
@@ -0,0 +1,124 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "multi_task_dit",
3
+ "n_obs_steps": 2,
4
+ "input_features": {
5
+ "observation.images.wrist": {
6
+ "type": "VISUAL",
7
+ "shape": [
8
+ 3,
9
+ 480,
10
+ 640
11
+ ]
12
+ },
13
+ "observation.images.top": {
14
+ "type": "VISUAL",
15
+ "shape": [
16
+ 3,
17
+ 480,
18
+ 640
19
+ ]
20
+ },
21
+ "observation.state": {
22
+ "type": "STATE",
23
+ "shape": [
24
+ 10
25
+ ]
26
+ }
27
+ },
28
+ "output_features": {
29
+ "action": {
30
+ "type": "ACTION",
31
+ "shape": [
32
+ 10
33
+ ]
34
+ }
35
+ },
36
+ "device": "cuda",
37
+ "dtype": null,
38
+ "use_amp": false,
39
+ "use_peft": false,
40
+ "push_to_hub": true,
41
+ "repo_id": "SieloRobotics/dit_ee_cubes",
42
+ "private": false,
43
+ "tags": null,
44
+ "license": null,
45
+ "pretrained_path": null,
46
+ "pretrained_revision": null,
47
+ "horizon": 32,
48
+ "n_action_steps": 8,
49
+ "objective": "flow_matching",
50
+ "noise_scheduler_type": "DDPM",
51
+ "num_train_timesteps": 100,
52
+ "beta_schedule": "squaredcos_cap_v2",
53
+ "beta_start": 0.0001,
54
+ "beta_end": 0.02,
55
+ "prediction_type": "epsilon",
56
+ "clip_sample": true,
57
+ "clip_sample_range": 1.0,
58
+ "num_inference_steps": null,
59
+ "sigma_min": 0.0,
60
+ "num_integration_steps": 10,
61
+ "integration_method": "euler",
62
+ "timestep_sampling_strategy": "beta",
63
+ "timestep_sampling_s": 0.999,
64
+ "timestep_sampling_alpha": 1.5,
65
+ "timestep_sampling_beta": 1.0,
66
+ "hidden_dim": 512,
67
+ "num_layers": 6,
68
+ "num_heads": 8,
69
+ "dropout": 0.1,
70
+ "use_positional_encoding": false,
71
+ "timestep_embed_dim": 256,
72
+ "use_rope": true,
73
+ "rope_base": 10000.0,
74
+ "vision_encoder_name": "openai/clip-vit-base-patch16",
75
+ "use_separate_rgb_encoder_per_camera": true,
76
+ "vision_encoder_lr_multiplier": 0.1,
77
+ "image_resize_shape": [
78
+ 240,
79
+ 240
80
+ ],
81
+ "image_crop_shape": [
82
+ 224,
83
+ 224
84
+ ],
85
+ "image_crop_is_random": true,
86
+ "compile_model": true,
87
+ "compile_mode": null,
88
+ "use_text_conditioning": false,
89
+ "text_encoder_name": "openai/clip-vit-base-patch16",
90
+ "tokenizer_max_length": 77,
91
+ "tokenizer_padding": "max_length",
92
+ "tokenizer_padding_side": "right",
93
+ "tokenizer_truncation": true,
94
+ "normalization_mapping": {
95
+ "VISUAL": "MEAN_STD",
96
+ "STATE": "QUANTILES",
97
+ "ACTION": "QUANTILES"
98
+ },
99
+ "use_relative_ee_actions": true,
100
+ "action_feature_names": [
101
+ "ee.x",
102
+ "ee.y",
103
+ "ee.z",
104
+ "ee.r6d_0",
105
+ "ee.r6d_1",
106
+ "ee.r6d_2",
107
+ "ee.r6d_3",
108
+ "ee.r6d_4",
109
+ "ee.r6d_5",
110
+ "gripper.pos"
111
+ ],
112
+ "optimizer_lr": 0.0001,
113
+ "optimizer_betas": [
114
+ 0.95,
115
+ 0.999
116
+ ],
117
+ "optimizer_eps": 1e-08,
118
+ "optimizer_weight_decay": 0.0,
119
+ "optimizer_grad_clip_norm": 1.0,
120
+ "scheduler_name": "cosine",
121
+ "scheduler_warmup_steps": 800,
122
+ "do_mask_loss_for_padding": false,
123
+ "drop_n_last_frames": 23
124
+ }
checkpoints/028000/pretrained_model_ema/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a9f136ddfd54d89d363c4fd4d09db467c393ca915811597aa63679b32f336f4
3
+ size 1010086976
checkpoints/028000/pretrained_model_ema/policy_postprocessor.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ 10
13
+ ]
14
+ }
15
+ },
16
+ "norm_map": {
17
+ "VISUAL": "MEAN_STD",
18
+ "STATE": "QUANTILES",
19
+ "ACTION": "QUANTILES"
20
+ }
21
+ },
22
+ "state_file": "policy_postprocessor_step_0_unnormalizer_processor.safetensors"
23
+ },
24
+ {
25
+ "registry_name": "absolute_ee_actions_processor",
26
+ "config": {
27
+ "enabled": true
28
+ }
29
+ },
30
+ {
31
+ "registry_name": "device_processor",
32
+ "config": {
33
+ "device": "cpu",
34
+ "float_dtype": null
35
+ }
36
+ }
37
+ ]
38
+ }
checkpoints/028000/pretrained_model_ema/policy_postprocessor_step_0_unnormalizer_processor.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be1e4c4b011808b824c52e23f647269b1cee8124ccdda17265cc0b4885950da4
3
+ size 9888
checkpoints/028000/pretrained_model_ema/policy_preprocessor.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "relative_ee_actions_processor",
23
+ "config": {
24
+ "enabled": true,
25
+ "pos_index": 0,
26
+ "rot6d_index": 3,
27
+ "anchor_obs_index": -1
28
+ }
29
+ },
30
+ {
31
+ "registry_name": "normalizer_processor",
32
+ "config": {
33
+ "eps": 1e-08,
34
+ "features": {
35
+ "observation.images.wrist": {
36
+ "type": "VISUAL",
37
+ "shape": [
38
+ 3,
39
+ 480,
40
+ 640
41
+ ]
42
+ },
43
+ "observation.images.top": {
44
+ "type": "VISUAL",
45
+ "shape": [
46
+ 3,
47
+ 480,
48
+ 640
49
+ ]
50
+ },
51
+ "observation.state": {
52
+ "type": "STATE",
53
+ "shape": [
54
+ 10
55
+ ]
56
+ },
57
+ "action": {
58
+ "type": "ACTION",
59
+ "shape": [
60
+ 10
61
+ ]
62
+ }
63
+ },
64
+ "norm_map": {
65
+ "VISUAL": "MEAN_STD",
66
+ "STATE": "QUANTILES",
67
+ "ACTION": "QUANTILES"
68
+ }
69
+ },
70
+ "state_file": "policy_preprocessor_step_4_normalizer_processor.safetensors"
71
+ }
72
+ ]
73
+ }
checkpoints/028000/pretrained_model_ema/policy_preprocessor_step_4_normalizer_processor.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e004b0582c25c39c12fa6ddde74db10824a5fb64c948de676f92949dcbd44a1
3
+ size 9896
checkpoints/028000/pretrained_model_ema/train_config.json ADDED
@@ -0,0 +1,347 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "SieloRobotics/rebot_pick_place_ee",
4
+ "repo_type": "dataset",
5
+ "root": null,
6
+ "episodes": null,
7
+ "exclude_episodes": null,
8
+ "image_transforms": {
9
+ "enable": false,
10
+ "backend": "dataloader",
11
+ "gpu_compile": true,
12
+ "gpu_chunk_size": 32,
13
+ "max_num_transforms": 3,
14
+ "random_order": false,
15
+ "tfs": {
16
+ "brightness": {
17
+ "weight": 1.0,
18
+ "type": "ColorJitter",
19
+ "kwargs": {
20
+ "brightness": [
21
+ 0.8,
22
+ 1.2
23
+ ]
24
+ }
25
+ },
26
+ "contrast": {
27
+ "weight": 1.0,
28
+ "type": "ColorJitter",
29
+ "kwargs": {
30
+ "contrast": [
31
+ 0.8,
32
+ 1.2
33
+ ]
34
+ }
35
+ },
36
+ "saturation": {
37
+ "weight": 1.0,
38
+ "type": "ColorJitter",
39
+ "kwargs": {
40
+ "saturation": [
41
+ 0.5,
42
+ 1.5
43
+ ]
44
+ }
45
+ },
46
+ "hue": {
47
+ "weight": 1.0,
48
+ "type": "ColorJitter",
49
+ "kwargs": {
50
+ "hue": [
51
+ -0.05,
52
+ 0.05
53
+ ]
54
+ }
55
+ },
56
+ "sharpness": {
57
+ "weight": 1.0,
58
+ "type": "SharpnessJitter",
59
+ "kwargs": {
60
+ "sharpness": [
61
+ 0.5,
62
+ 1.5
63
+ ]
64
+ }
65
+ },
66
+ "affine": {
67
+ "weight": 1.0,
68
+ "type": "RandomAffine",
69
+ "kwargs": {
70
+ "degrees": [
71
+ -5.0,
72
+ 5.0
73
+ ],
74
+ "translate": [
75
+ 0.05,
76
+ 0.05
77
+ ]
78
+ }
79
+ }
80
+ }
81
+ },
82
+ "revision": null,
83
+ "use_imagenet_stats": true,
84
+ "video_backend": "torchcodec",
85
+ "return_uint8": true,
86
+ "depth_output_unit": "mm",
87
+ "streaming": false,
88
+ "streaming_episode_pool_size": null,
89
+ "streaming_sampling_strategy": "remaining",
90
+ "streaming_prefetch_episodes": 8,
91
+ "streaming_byte_budget_gb": 8.0,
92
+ "streaming_decode_threads": 2,
93
+ "streaming_decoded_queue_size": 8,
94
+ "streaming_native_http_connections": null,
95
+ "streaming_native_http_subranges": 1,
96
+ "video_decoder_cache_size": null,
97
+ "eval_split": 0.02
98
+ },
99
+ "env": null,
100
+ "policy": {
101
+ "type": "multi_task_dit",
102
+ "n_obs_steps": 2,
103
+ "input_features": {
104
+ "observation.images.wrist": {
105
+ "type": "VISUAL",
106
+ "shape": [
107
+ 3,
108
+ 480,
109
+ 640
110
+ ]
111
+ },
112
+ "observation.images.top": {
113
+ "type": "VISUAL",
114
+ "shape": [
115
+ 3,
116
+ 480,
117
+ 640
118
+ ]
119
+ },
120
+ "observation.state": {
121
+ "type": "STATE",
122
+ "shape": [
123
+ 10
124
+ ]
125
+ }
126
+ },
127
+ "output_features": {
128
+ "action": {
129
+ "type": "ACTION",
130
+ "shape": [
131
+ 10
132
+ ]
133
+ }
134
+ },
135
+ "device": "cuda",
136
+ "dtype": null,
137
+ "use_amp": false,
138
+ "use_peft": false,
139
+ "push_to_hub": true,
140
+ "repo_id": "SieloRobotics/dit_ee_cubes",
141
+ "private": false,
142
+ "tags": null,
143
+ "license": null,
144
+ "pretrained_path": null,
145
+ "pretrained_revision": null,
146
+ "horizon": 32,
147
+ "n_action_steps": 8,
148
+ "objective": "flow_matching",
149
+ "noise_scheduler_type": "DDPM",
150
+ "num_train_timesteps": 100,
151
+ "beta_schedule": "squaredcos_cap_v2",
152
+ "beta_start": 0.0001,
153
+ "beta_end": 0.02,
154
+ "prediction_type": "epsilon",
155
+ "clip_sample": true,
156
+ "clip_sample_range": 1.0,
157
+ "num_inference_steps": null,
158
+ "sigma_min": 0.0,
159
+ "num_integration_steps": 10,
160
+ "integration_method": "euler",
161
+ "timestep_sampling_strategy": "beta",
162
+ "timestep_sampling_s": 0.999,
163
+ "timestep_sampling_alpha": 1.5,
164
+ "timestep_sampling_beta": 1.0,
165
+ "hidden_dim": 512,
166
+ "num_layers": 6,
167
+ "num_heads": 8,
168
+ "dropout": 0.1,
169
+ "use_positional_encoding": false,
170
+ "timestep_embed_dim": 256,
171
+ "use_rope": true,
172
+ "rope_base": 10000.0,
173
+ "vision_encoder_name": "openai/clip-vit-base-patch16",
174
+ "use_separate_rgb_encoder_per_camera": true,
175
+ "vision_encoder_lr_multiplier": 0.1,
176
+ "image_resize_shape": [
177
+ 240,
178
+ 240
179
+ ],
180
+ "image_crop_shape": [
181
+ 224,
182
+ 224
183
+ ],
184
+ "image_crop_is_random": true,
185
+ "compile_model": true,
186
+ "compile_mode": null,
187
+ "use_text_conditioning": false,
188
+ "text_encoder_name": "openai/clip-vit-base-patch16",
189
+ "tokenizer_max_length": 77,
190
+ "tokenizer_padding": "max_length",
191
+ "tokenizer_padding_side": "right",
192
+ "tokenizer_truncation": true,
193
+ "normalization_mapping": {
194
+ "VISUAL": "MEAN_STD",
195
+ "STATE": "QUANTILES",
196
+ "ACTION": "QUANTILES"
197
+ },
198
+ "use_relative_ee_actions": true,
199
+ "action_feature_names": [
200
+ "ee.x",
201
+ "ee.y",
202
+ "ee.z",
203
+ "ee.r6d_0",
204
+ "ee.r6d_1",
205
+ "ee.r6d_2",
206
+ "ee.r6d_3",
207
+ "ee.r6d_4",
208
+ "ee.r6d_5",
209
+ "gripper.pos"
210
+ ],
211
+ "optimizer_lr": 0.0001,
212
+ "optimizer_betas": [
213
+ 0.95,
214
+ 0.999
215
+ ],
216
+ "optimizer_eps": 1e-08,
217
+ "optimizer_weight_decay": 0.0,
218
+ "optimizer_grad_clip_norm": 1.0,
219
+ "scheduler_name": "cosine",
220
+ "scheduler_warmup_steps": 800,
221
+ "do_mask_loss_for_padding": false,
222
+ "drop_n_last_frames": 23
223
+ },
224
+ "reward_model": null,
225
+ "output_dir": "/content/outputs/dit_ee_cubes_run_20261020_202835",
226
+ "job_name": "dit_ee_cubes",
227
+ "resume": false,
228
+ "seed": 1000,
229
+ "cudnn_deterministic": false,
230
+ "num_workers": 12,
231
+ "batch_size": 256,
232
+ "prefetch_factor": 2,
233
+ "persistent_workers": true,
234
+ "dataloader_multiprocessing_context": "spawn",
235
+ "steps": 40000,
236
+ "env_eval_freq": 20000,
237
+ "log_freq": 100,
238
+ "eval_steps": 2000,
239
+ "max_eval_samples": 0,
240
+ "tolerance_s": 0.0001,
241
+ "save_checkpoint": true,
242
+ "save_freq": 2000,
243
+ "checkpoint_format": "safetensors",
244
+ "use_policy_training_preset": true,
245
+ "optimizer": {
246
+ "type": "adam",
247
+ "lr": 0.0001,
248
+ "weight_decay": 0.0,
249
+ "grad_clip_norm": 1.0,
250
+ "betas": [
251
+ 0.95,
252
+ 0.999
253
+ ],
254
+ "eps": 1e-08
255
+ },
256
+ "scheduler": {
257
+ "type": "diffuser",
258
+ "num_warmup_steps": 800,
259
+ "name": "cosine"
260
+ },
261
+ "parallelism": {
262
+ "dp_replicate": 1,
263
+ "dp_shard": 1,
264
+ "context_parallel": {
265
+ "ring_degree": 1,
266
+ "ulysses_degree": 1
267
+ },
268
+ "cfg_parallel": 1
269
+ },
270
+ "accelerator": {
271
+ "mixed_precision": "bf16",
272
+ "gradient_accumulation": {
273
+ "steps": 1
274
+ },
275
+ "grad_scaler": {
276
+ "init_scale": 65536.0,
277
+ "growth_factor": 2.0,
278
+ "backoff_factor": 0.5,
279
+ "growth_interval": 2000
280
+ },
281
+ "fsdp": {
282
+ "reshard_after_forward": true,
283
+ "wrap_modules": null,
284
+ "min_num_params": null,
285
+ "cpu_offload": false,
286
+ "ignored_modules": null
287
+ },
288
+ "ddp": {
289
+ "find_unused_parameters": true,
290
+ "gradient_as_bucket_view": false,
291
+ "static_graph": false
292
+ },
293
+ "compile": {
294
+ "enabled": false,
295
+ "backend": "inductor",
296
+ "mode": null,
297
+ "regional": true
298
+ },
299
+ "activation_checkpointing": {
300
+ "mode": "none"
301
+ }
302
+ },
303
+ "eval": {
304
+ "n_episodes": 50,
305
+ "batch_size": 33,
306
+ "use_async_envs": true,
307
+ "recording": false,
308
+ "recording_repo_id": null,
309
+ "recording_private": false
310
+ },
311
+ "ema": {
312
+ "enable": true,
313
+ "decay": null,
314
+ "update_after_step": 0,
315
+ "inv_gamma": 1.0,
316
+ "power": 0.75,
317
+ "min_decay": 0.0,
318
+ "max_decay": 0.9999,
319
+ "use_for_eval": true
320
+ },
321
+ "wandb": {
322
+ "enable": true,
323
+ "disable_artifact": true,
324
+ "project": "dit_ee_cubes",
325
+ "entity": null,
326
+ "notes": null,
327
+ "run_id": "igo5cik4",
328
+ "resume": null,
329
+ "mode": null,
330
+ "console": "wrap",
331
+ "console_multipart": false,
332
+ "console_chunk_max_seconds": 0,
333
+ "add_tags": true
334
+ },
335
+ "peft": null,
336
+ "job": {
337
+ "target": null,
338
+ "image": "huggingface/lerobot-gpu:latest",
339
+ "timeout": "2d",
340
+ "detach": false,
341
+ "tags": []
342
+ },
343
+ "save_checkpoint_to_hub": false,
344
+ "sample_weighting": null,
345
+ "rename_map": {},
346
+ "checkpoint_path": null
347
+ }
checkpoints/028000/training_state/ema_state.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c78e51c4d9faba92bc7d10e4246d4539fe4dde8b26fce97fa19fc3e7aa180ba5
3
+ size 1010145739
checkpoints/028000/training_state/optimizer_param_groups.json ADDED
@@ -0,0 +1,506 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "lr": 2.139416699389153e-05,
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": 0.0001,
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
+ ]
88
+ },
89
+ {
90
+ "lr": 2.139416699389153e-06,
91
+ "betas": [
92
+ 0.95,
93
+ 0.999
94
+ ],
95
+ "eps": 1e-08,
96
+ "weight_decay": 0.0,
97
+ "amsgrad": false,
98
+ "maximize": false,
99
+ "foreach": null,
100
+ "capturable": false,
101
+ "differentiable": false,
102
+ "fused": null,
103
+ "decoupled_weight_decay": false,
104
+ "initial_lr": 1e-05,
105
+ "params": [
106
+ 68,
107
+ 69,
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
+ ]
505
+ }
506
+ ]
checkpoints/028000/training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5dafc0b76db7311611d3f89a68fbaf5239bc18cc84ebce579114b6f58db9617
3
+ size 2020125400
checkpoints/028000/training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90f19702d54344037917b4c5a4700a7d4e502320720e7078dee69548551772a8
3
+ size 15708
checkpoints/028000/training_state/scheduler_state.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_lrs": [
3
+ 0.0001,
4
+ 1e-05
5
+ ],
6
+ "last_epoch": 28000,
7
+ "_step_count": 28001,
8
+ "_is_initial": false,
9
+ "_get_lr_called_within_step": false,
10
+ "_last_lr": [
11
+ 2.139416699389153e-05,
12
+ 2.139416699389153e-06
13
+ ],
14
+ "lr_lambdas": [
15
+ null,
16
+ null
17
+ ]
18
+ }
checkpoints/028000/training_state/training_step.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "step": 28000,
3
+ "dp_world_size": 1,
4
+ "batch_size": 256,
5
+ "grad_accum_steps": 1,
6
+ "mixed_precision": "bf16",
7
+ "parallelism": {
8
+ "dp_replicate": 1,
9
+ "dp_shard": 1,
10
+ "ring_degree": 1,
11
+ "ulysses_degree": 1
12
+ }
13
+ }