thanhkt commited on
Commit
4cd5468
·
verified ·
1 Parent(s): 7ee272d

Upload train_planbind_s1002

Browse files
train_planbind_s1002/checkpoints/060000/pretrained_model/config.json ADDED
@@ -0,0 +1,124 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "bspline",
3
+ "n_obs_steps": 2,
4
+ "input_features": {
5
+ "observation.state": {
6
+ "type": "STATE",
7
+ "shape": [
8
+ 6
9
+ ]
10
+ },
11
+ "observation.images.front": {
12
+ "type": "VISUAL",
13
+ "shape": [
14
+ 3,
15
+ 480,
16
+ 640
17
+ ]
18
+ },
19
+ "observation.images.wrist": {
20
+ "type": "VISUAL",
21
+ "shape": [
22
+ 3,
23
+ 480,
24
+ 640
25
+ ]
26
+ },
27
+ "observation.images.top": {
28
+ "type": "VISUAL",
29
+ "shape": [
30
+ 3,
31
+ 480,
32
+ 640
33
+ ]
34
+ }
35
+ },
36
+ "output_features": {
37
+ "action": {
38
+ "type": "ACTION",
39
+ "shape": [
40
+ 6
41
+ ]
42
+ }
43
+ },
44
+ "device": "cuda",
45
+ "dtype": null,
46
+ "use_amp": false,
47
+ "use_peft": false,
48
+ "push_to_hub": false,
49
+ "repo_id": null,
50
+ "private": null,
51
+ "tags": null,
52
+ "license": null,
53
+ "pretrained_path": null,
54
+ "pretrained_revision": null,
55
+ "horizon": 16,
56
+ "n_action_steps": 32,
57
+ "normalization_mapping": {
58
+ "VISUAL": "MEAN_STD",
59
+ "STATE": "MIN_MAX",
60
+ "ACTION": "MIN_MAX"
61
+ },
62
+ "drop_n_last_frames": 0,
63
+ "vision_backbone": "resnet18",
64
+ "resize_shape": [
65
+ 120,
66
+ 160
67
+ ],
68
+ "crop_ratio": 1.0,
69
+ "crop_shape": null,
70
+ "crop_is_random": true,
71
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
72
+ "use_group_norm": false,
73
+ "spatial_softmax_num_keypoints": 32,
74
+ "use_separate_rgb_encoder_per_camera": true,
75
+ "down_dims": [
76
+ 512,
77
+ 1024,
78
+ 2048
79
+ ],
80
+ "kernel_size": 5,
81
+ "n_groups": 8,
82
+ "diffusion_step_embed_dim": 128,
83
+ "use_film_scale_modulation": true,
84
+ "gradient_checkpointing": false,
85
+ "noise_scheduler_type": "DDPM",
86
+ "num_train_timesteps": 100,
87
+ "beta_schedule": "squaredcos_cap_v2",
88
+ "beta_start": 0.0001,
89
+ "beta_end": 0.02,
90
+ "prediction_type": "epsilon",
91
+ "clip_sample": true,
92
+ "clip_sample_range": 1.5,
93
+ "num_inference_steps": null,
94
+ "compile_model": false,
95
+ "compile_mode": "reduce-overhead",
96
+ "do_mask_loss_for_padding": false,
97
+ "optimizer_lr": 0.0001,
98
+ "optimizer_betas": [
99
+ 0.95,
100
+ 0.999
101
+ ],
102
+ "optimizer_eps": 1e-08,
103
+ "optimizer_weight_decay": 1e-06,
104
+ "scheduler_name": "cosine",
105
+ "scheduler_warmup_steps": 500,
106
+ "bspline_degree": 3,
107
+ "bspline_chunk_size": 10,
108
+ "bspline_window": 64,
109
+ "bspline_max_error": 0.01,
110
+ "bspline_speed_up": 1.0,
111
+ "bspline_fit_workers": 0,
112
+ "bspline_mode": "planbind",
113
+ "planbind_fine_spacing": 4,
114
+ "planbind_subdivision": 4,
115
+ "planbind_max_plan_age": 32,
116
+ "planbind_plan_noise": 0.02,
117
+ "planbind_replan_threshold": 0.0,
118
+ "planbind_latency": 0,
119
+ "planbind_commit": "latency",
120
+ "planbind_position_limit": 0.0,
121
+ "planbind_velocity_limit": 0.0,
122
+ "planbind_call_every": 0,
123
+ "bspline_runtime": false
124
+ }
train_planbind_s1002/checkpoints/060000/pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cee38058b977eb3072895200f4f00503b26d1bfbe4059a749f9065d33c9822bf
3
+ size 1170926200
train_planbind_s1002/checkpoints/060000/pretrained_model/policy_postprocessor.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "policy_postprocessor",
3
+ "steps": [
4
+ {
5
+ "registry_name": "unnormalizer_processor",
6
+ "config": {
7
+ "eps": 1e-08,
8
+ "features": {
9
+ "action": {
10
+ "type": "ACTION",
11
+ "shape": [
12
+ 6
13
+ ]
14
+ }
15
+ },
16
+ "norm_map": {
17
+ "VISUAL": "MEAN_STD",
18
+ "STATE": "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
+ }
train_planbind_s1002/checkpoints/060000/pretrained_model/policy_postprocessor_step_0_unnormalizer_processor.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f8634f9b5a9ed02d6d82d3ce943ae8072f8754f5c8b127c499524a7d4bbdd6a
3
+ size 8528
train_planbind_s1002/checkpoints/060000/pretrained_model/policy_preprocessor.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "policy_preprocessor",
3
+ "steps": [
4
+ {
5
+ "registry_name": "rename_observations_processor",
6
+ "config": {
7
+ "rename_map": {}
8
+ }
9
+ },
10
+ {
11
+ "registry_name": "to_batch_processor",
12
+ "config": {}
13
+ },
14
+ {
15
+ "registry_name": "device_processor",
16
+ "config": {
17
+ "device": "cuda",
18
+ "float_dtype": null
19
+ }
20
+ },
21
+ {
22
+ "registry_name": "normalizer_processor",
23
+ "config": {
24
+ "eps": 1e-08,
25
+ "features": {
26
+ "observation.state": {
27
+ "type": "STATE",
28
+ "shape": [
29
+ 6
30
+ ]
31
+ },
32
+ "observation.images.front": {
33
+ "type": "VISUAL",
34
+ "shape": [
35
+ 3,
36
+ 480,
37
+ 640
38
+ ]
39
+ },
40
+ "observation.images.wrist": {
41
+ "type": "VISUAL",
42
+ "shape": [
43
+ 3,
44
+ 480,
45
+ 640
46
+ ]
47
+ },
48
+ "observation.images.top": {
49
+ "type": "VISUAL",
50
+ "shape": [
51
+ 3,
52
+ 480,
53
+ 640
54
+ ]
55
+ },
56
+ "action": {
57
+ "type": "ACTION",
58
+ "shape": [
59
+ 6
60
+ ]
61
+ }
62
+ },
63
+ "norm_map": {
64
+ "VISUAL": "MEAN_STD",
65
+ "STATE": "MIN_MAX",
66
+ "ACTION": "MIN_MAX"
67
+ }
68
+ },
69
+ "state_file": "policy_preprocessor_step_3_normalizer_processor.safetensors"
70
+ }
71
+ ]
72
+ }
train_planbind_s1002/checkpoints/060000/pretrained_model/policy_preprocessor_step_3_normalizer_processor.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7c0e3938605a37c6c4b8552405350548eae796642add139ce37596cc17c2e10
3
+ size 8536
train_planbind_s1002/checkpoints/060000/pretrained_model/train_config.json ADDED
@@ -0,0 +1,349 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "local/nexarm_stack_bowls",
4
+ "repo_type": "dataset",
5
+ "root": "/home/25thanh.tk/lerobot-nexarm/outputs/datasets/nexarm_stack_bowls_red_blue_black_1k",
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": false,
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
+ "streaming_sidecar_lock_timeout_s": 1800,
97
+ "video_decoder_cache_size": null,
98
+ "eval_split": 0.0
99
+ },
100
+ "env": null,
101
+ "policy": {
102
+ "type": "bspline",
103
+ "n_obs_steps": 2,
104
+ "input_features": {
105
+ "observation.state": {
106
+ "type": "STATE",
107
+ "shape": [
108
+ 6
109
+ ]
110
+ },
111
+ "observation.images.front": {
112
+ "type": "VISUAL",
113
+ "shape": [
114
+ 3,
115
+ 480,
116
+ 640
117
+ ]
118
+ },
119
+ "observation.images.wrist": {
120
+ "type": "VISUAL",
121
+ "shape": [
122
+ 3,
123
+ 480,
124
+ 640
125
+ ]
126
+ },
127
+ "observation.images.top": {
128
+ "type": "VISUAL",
129
+ "shape": [
130
+ 3,
131
+ 480,
132
+ 640
133
+ ]
134
+ }
135
+ },
136
+ "output_features": {
137
+ "action": {
138
+ "type": "ACTION",
139
+ "shape": [
140
+ 6
141
+ ]
142
+ }
143
+ },
144
+ "device": "cuda",
145
+ "dtype": null,
146
+ "use_amp": false,
147
+ "use_peft": false,
148
+ "push_to_hub": false,
149
+ "repo_id": null,
150
+ "private": null,
151
+ "tags": null,
152
+ "license": null,
153
+ "pretrained_path": null,
154
+ "pretrained_revision": null,
155
+ "horizon": 16,
156
+ "n_action_steps": 32,
157
+ "normalization_mapping": {
158
+ "VISUAL": "MEAN_STD",
159
+ "STATE": "MIN_MAX",
160
+ "ACTION": "MIN_MAX"
161
+ },
162
+ "drop_n_last_frames": 0,
163
+ "vision_backbone": "resnet18",
164
+ "resize_shape": [
165
+ 120,
166
+ 160
167
+ ],
168
+ "crop_ratio": 1.0,
169
+ "crop_shape": null,
170
+ "crop_is_random": true,
171
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
172
+ "use_group_norm": false,
173
+ "spatial_softmax_num_keypoints": 32,
174
+ "use_separate_rgb_encoder_per_camera": true,
175
+ "down_dims": [
176
+ 512,
177
+ 1024,
178
+ 2048
179
+ ],
180
+ "kernel_size": 5,
181
+ "n_groups": 8,
182
+ "diffusion_step_embed_dim": 128,
183
+ "use_film_scale_modulation": true,
184
+ "gradient_checkpointing": false,
185
+ "noise_scheduler_type": "DDPM",
186
+ "num_train_timesteps": 100,
187
+ "beta_schedule": "squaredcos_cap_v2",
188
+ "beta_start": 0.0001,
189
+ "beta_end": 0.02,
190
+ "prediction_type": "epsilon",
191
+ "clip_sample": true,
192
+ "clip_sample_range": 1.5,
193
+ "num_inference_steps": null,
194
+ "compile_model": false,
195
+ "compile_mode": "reduce-overhead",
196
+ "do_mask_loss_for_padding": false,
197
+ "optimizer_lr": 0.0001,
198
+ "optimizer_betas": [
199
+ 0.95,
200
+ 0.999
201
+ ],
202
+ "optimizer_eps": 1e-08,
203
+ "optimizer_weight_decay": 1e-06,
204
+ "scheduler_name": "cosine",
205
+ "scheduler_warmup_steps": 500,
206
+ "bspline_degree": 3,
207
+ "bspline_chunk_size": 10,
208
+ "bspline_window": 64,
209
+ "bspline_max_error": 0.01,
210
+ "bspline_speed_up": 1.0,
211
+ "bspline_fit_workers": 0,
212
+ "bspline_mode": "planbind",
213
+ "planbind_fine_spacing": 4,
214
+ "planbind_subdivision": 4,
215
+ "planbind_max_plan_age": 32,
216
+ "planbind_plan_noise": 0.02,
217
+ "planbind_replan_threshold": 0.0,
218
+ "planbind_latency": 0,
219
+ "planbind_commit": "latency",
220
+ "planbind_position_limit": 0.0,
221
+ "planbind_velocity_limit": 0.0,
222
+ "planbind_call_every": 0,
223
+ "bspline_runtime": false
224
+ },
225
+ "reward_model": null,
226
+ "output_dir": "/home/25thanh.tk/lerobot-nexarm/experiments/261029-plan-bind-d1b-seeds/outputs/full/train_planbind_s1002",
227
+ "job_name": "plan-bind-d1b-planbind-s1002",
228
+ "resume": false,
229
+ "seed": 1002,
230
+ "cudnn_deterministic": false,
231
+ "num_workers": 2,
232
+ "batch_size": 32,
233
+ "prefetch_factor": 4,
234
+ "persistent_workers": true,
235
+ "dataloader_multiprocessing_context": "spawn",
236
+ "steps": 60000,
237
+ "env_eval_freq": 0,
238
+ "log_freq": 100,
239
+ "eval_steps": 0,
240
+ "max_eval_samples": 0,
241
+ "tolerance_s": 0.0001,
242
+ "save_checkpoint": true,
243
+ "save_freq": 10000,
244
+ "checkpoint_format": "safetensors",
245
+ "use_policy_training_preset": true,
246
+ "optimizer": {
247
+ "type": "adam",
248
+ "lr": 0.0001,
249
+ "weight_decay": 1e-06,
250
+ "grad_clip_norm": 10.0,
251
+ "betas": [
252
+ 0.95,
253
+ 0.999
254
+ ],
255
+ "eps": 1e-08,
256
+ "fused": null
257
+ },
258
+ "scheduler": {
259
+ "type": "diffuser",
260
+ "num_warmup_steps": 500,
261
+ "name": "cosine"
262
+ },
263
+ "parallelism": {
264
+ "dp_replicate": 1,
265
+ "dp_shard": 1,
266
+ "context_parallel": {
267
+ "ring_degree": 1,
268
+ "ulysses_degree": 1
269
+ },
270
+ "cfg_parallel": 1
271
+ },
272
+ "accelerator": {
273
+ "mixed_precision": "no",
274
+ "gradient_accumulation": {
275
+ "steps": 1
276
+ },
277
+ "grad_scaler": {
278
+ "init_scale": 65536.0,
279
+ "growth_factor": 2.0,
280
+ "backoff_factor": 0.5,
281
+ "growth_interval": 2000
282
+ },
283
+ "fsdp": {
284
+ "reshard_after_forward": true,
285
+ "wrap_modules": null,
286
+ "min_num_params": null,
287
+ "cpu_offload": false,
288
+ "ignored_modules": null
289
+ },
290
+ "ddp": {
291
+ "find_unused_parameters": true,
292
+ "gradient_as_bucket_view": false,
293
+ "static_graph": false
294
+ },
295
+ "compile": {
296
+ "enabled": false,
297
+ "backend": "inductor",
298
+ "mode": null,
299
+ "regional": true
300
+ },
301
+ "activation_checkpointing": {
302
+ "mode": "none"
303
+ }
304
+ },
305
+ "eval": {
306
+ "n_episodes": 50,
307
+ "batch_size": 44,
308
+ "use_async_envs": true,
309
+ "recording": false,
310
+ "recording_repo_id": null,
311
+ "recording_private": false
312
+ },
313
+ "ema": {
314
+ "enable": false,
315
+ "decay": null,
316
+ "update_after_step": 0,
317
+ "inv_gamma": 1.0,
318
+ "power": 0.75,
319
+ "min_decay": 0.0,
320
+ "max_decay": 0.9999,
321
+ "use_for_eval": true
322
+ },
323
+ "wandb": {
324
+ "enable": false,
325
+ "disable_artifact": false,
326
+ "project": "lerobot-nexarm",
327
+ "entity": null,
328
+ "notes": null,
329
+ "run_id": null,
330
+ "resume": null,
331
+ "mode": null,
332
+ "console": "wrap",
333
+ "console_multipart": false,
334
+ "console_chunk_max_seconds": 0,
335
+ "add_tags": true
336
+ },
337
+ "peft": null,
338
+ "job": {
339
+ "target": null,
340
+ "image": "huggingface/lerobot-gpu:latest",
341
+ "timeout": "2d",
342
+ "detach": false,
343
+ "tags": []
344
+ },
345
+ "save_checkpoint_to_hub": false,
346
+ "sample_weighting": null,
347
+ "rename_map": {},
348
+ "checkpoint_path": null
349
+ }
train_planbind_s1002/checkpoints/060000/training_state/optimizer_param_groups.json ADDED
@@ -0,0 +1,361 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "lr": 0.0,
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": 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
+ 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
+ 212,
232
+ 213,
233
+ 214,
234
+ 215,
235
+ 216,
236
+ 217,
237
+ 218,
238
+ 219,
239
+ 220,
240
+ 221,
241
+ 222,
242
+ 223,
243
+ 224,
244
+ 225,
245
+ 226,
246
+ 227,
247
+ 228,
248
+ 229,
249
+ 230,
250
+ 231,
251
+ 232,
252
+ 233,
253
+ 234,
254
+ 235,
255
+ 236,
256
+ 237,
257
+ 238,
258
+ 239,
259
+ 240,
260
+ 241,
261
+ 242,
262
+ 243,
263
+ 244,
264
+ 245,
265
+ 246,
266
+ 247,
267
+ 248,
268
+ 249,
269
+ 250,
270
+ 251,
271
+ 252,
272
+ 253,
273
+ 254,
274
+ 255,
275
+ 256,
276
+ 257,
277
+ 258,
278
+ 259,
279
+ 260,
280
+ 261,
281
+ 262,
282
+ 263,
283
+ 264,
284
+ 265,
285
+ 266,
286
+ 267,
287
+ 268,
288
+ 269,
289
+ 270,
290
+ 271,
291
+ 272,
292
+ 273,
293
+ 274,
294
+ 275,
295
+ 276,
296
+ 277,
297
+ 278,
298
+ 279,
299
+ 280,
300
+ 281,
301
+ 282,
302
+ 283,
303
+ 284,
304
+ 285,
305
+ 286,
306
+ 287,
307
+ 288,
308
+ 289,
309
+ 290,
310
+ 291,
311
+ 292,
312
+ 293,
313
+ 294,
314
+ 295,
315
+ 296,
316
+ 297,
317
+ 298,
318
+ 299,
319
+ 300,
320
+ 301,
321
+ 302,
322
+ 303,
323
+ 304,
324
+ 305,
325
+ 306,
326
+ 307,
327
+ 308,
328
+ 309,
329
+ 310,
330
+ 311,
331
+ 312,
332
+ 313,
333
+ 314,
334
+ 315,
335
+ 316,
336
+ 317,
337
+ 318,
338
+ 319,
339
+ 320,
340
+ 321,
341
+ 322,
342
+ 323,
343
+ 324,
344
+ 325,
345
+ 326,
346
+ 327,
347
+ 328,
348
+ 329,
349
+ 330,
350
+ 331,
351
+ 332,
352
+ 333,
353
+ 334,
354
+ 335,
355
+ 336,
356
+ 337,
357
+ 338,
358
+ 339
359
+ ]
360
+ }
361
+ ]
train_planbind_s1002/checkpoints/060000/training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43c846ff0d7beb3900648cea38c1bd0606b0d183ac2dcd202c1f850139274849
3
+ size 2341586312
train_planbind_s1002/checkpoints/060000/training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f001216310b53e0b85df7dd168b0c52518ffde8f0dcf27e4cf00935c44fb4ed
3
+ size 15712
train_planbind_s1002/checkpoints/060000/training_state/scheduler_state.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_lrs": [
3
+ 0.0001
4
+ ],
5
+ "last_epoch": 60000,
6
+ "_step_count": 60001,
7
+ "_is_initial": false,
8
+ "_get_lr_called_within_step": false,
9
+ "_last_lr": [
10
+ 0.0
11
+ ],
12
+ "lr_lambdas": [
13
+ null
14
+ ]
15
+ }
train_planbind_s1002/checkpoints/060000/training_state/training_step.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "step": 60000,
3
+ "dp_world_size": 1,
4
+ "batch_size": 32,
5
+ "grad_accum_steps": 1,
6
+ "mixed_precision": "no",
7
+ "parallelism": {
8
+ "dp_replicate": 1,
9
+ "dp_shard": 1,
10
+ "ring_degree": 1,
11
+ "ulysses_degree": 1
12
+ }
13
+ }