dmcdono7 commited on
Commit
d573644
·
verified ·
1 Parent(s): 5e7b18f

checkpoint

Browse files
config.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "act",
3
+ "n_obs_steps": 1,
4
+ "input_features": {
5
+ "observation.state": {
6
+ "type": "STATE",
7
+ "shape": [
8
+ 6
9
+ ]
10
+ },
11
+ "observation.images.wrist": {
12
+ "type": "VISUAL",
13
+ "shape": [
14
+ 3,
15
+ 480,
16
+ 640
17
+ ]
18
+ }
19
+ },
20
+ "output_features": {
21
+ "action": {
22
+ "type": "ACTION",
23
+ "shape": [
24
+ 6
25
+ ]
26
+ }
27
+ },
28
+ "device": "cuda",
29
+ "dtype": null,
30
+ "use_amp": false,
31
+ "use_peft": false,
32
+ "push_to_hub": false,
33
+ "repo_id": null,
34
+ "private": null,
35
+ "tags": null,
36
+ "license": null,
37
+ "pretrained_path": "outputs/train/act_stack_v3/checkpoints/060000/pretrained_model",
38
+ "pretrained_revision": null,
39
+ "chunk_size": 100,
40
+ "n_action_steps": 100,
41
+ "normalization_mapping": {
42
+ "VISUAL": "MEAN_STD",
43
+ "STATE": "MEAN_STD",
44
+ "ACTION": "MEAN_STD"
45
+ },
46
+ "vision_backbone": "resnet18",
47
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
48
+ "replace_final_stride_with_dilation": 0,
49
+ "pre_norm": false,
50
+ "dim_model": 512,
51
+ "n_heads": 8,
52
+ "dim_feedforward": 3200,
53
+ "feedforward_activation": "relu",
54
+ "n_encoder_layers": 4,
55
+ "n_decoder_layers": 1,
56
+ "use_vae": true,
57
+ "latent_dim": 32,
58
+ "n_vae_encoder_layers": 4,
59
+ "temporal_ensemble_coeff": null,
60
+ "dropout": 0.1,
61
+ "kl_weight": 10.0,
62
+ "optimizer_lr": 1e-05,
63
+ "optimizer_weight_decay": 0.0001,
64
+ "optimizer_lr_backbone": 1e-05,
65
+ "optimizer_fused": null
66
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:720f1c8e6a0b6007f0f8e998968e1c1ac1063eb140f150cc71606e99ae870470
3
+ size 206699768
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": "MEAN_STD",
19
+ "ACTION": "MEAN_STD"
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
+ }
policy_postprocessor_step_0_unnormalizer_processor.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7071ab498ecf3582173e661d2c84aad207d487b1967570bd2b077ff71590dca
3
+ size 6560
policy_preprocessor.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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.wrist": {
33
+ "type": "VISUAL",
34
+ "shape": [
35
+ 3,
36
+ 480,
37
+ 640
38
+ ]
39
+ },
40
+ "action": {
41
+ "type": "ACTION",
42
+ "shape": [
43
+ 6
44
+ ]
45
+ }
46
+ },
47
+ "norm_map": {
48
+ "VISUAL": "MEAN_STD",
49
+ "STATE": "MEAN_STD",
50
+ "ACTION": "MEAN_STD"
51
+ }
52
+ },
53
+ "state_file": "policy_preprocessor_step_3_normalizer_processor.safetensors"
54
+ }
55
+ ]
56
+ }
policy_preprocessor_step_3_normalizer_processor.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f25687cdc0b372beb38156d13ffbe4cf75648ccf92ab39bb4202249f9e3761eb
3
+ size 6568
train_config.json ADDED
@@ -0,0 +1,288 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "local/so101_block_stack_v3_dag60k_r2",
4
+ "repo_type": "dataset",
5
+ "root": "/home/douglasmcdonough12/hrl_2/hrl_imerse/assignment2/task2_v3/data/so101_block_stack_v3_dag60k_r2",
6
+ "episodes": null,
7
+ "exclude_episodes": null,
8
+ "image_transforms": {
9
+ "enable": true,
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": 0.032
99
+ },
100
+ "env": null,
101
+ "policy": {
102
+ "type": "act",
103
+ "n_obs_steps": 1,
104
+ "input_features": {
105
+ "observation.state": {
106
+ "type": "STATE",
107
+ "shape": [
108
+ 6
109
+ ]
110
+ },
111
+ "observation.images.wrist": {
112
+ "type": "VISUAL",
113
+ "shape": [
114
+ 3,
115
+ 480,
116
+ 640
117
+ ]
118
+ }
119
+ },
120
+ "output_features": {
121
+ "action": {
122
+ "type": "ACTION",
123
+ "shape": [
124
+ 6
125
+ ]
126
+ }
127
+ },
128
+ "device": "cuda",
129
+ "dtype": null,
130
+ "use_amp": false,
131
+ "use_peft": false,
132
+ "push_to_hub": false,
133
+ "repo_id": null,
134
+ "private": null,
135
+ "tags": null,
136
+ "license": null,
137
+ "pretrained_path": "outputs/train/act_stack_v3/checkpoints/060000/pretrained_model",
138
+ "pretrained_revision": null,
139
+ "chunk_size": 100,
140
+ "n_action_steps": 100,
141
+ "normalization_mapping": {
142
+ "VISUAL": "MEAN_STD",
143
+ "STATE": "MEAN_STD",
144
+ "ACTION": "MEAN_STD"
145
+ },
146
+ "vision_backbone": "resnet18",
147
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
148
+ "replace_final_stride_with_dilation": 0,
149
+ "pre_norm": false,
150
+ "dim_model": 512,
151
+ "n_heads": 8,
152
+ "dim_feedforward": 3200,
153
+ "feedforward_activation": "relu",
154
+ "n_encoder_layers": 4,
155
+ "n_decoder_layers": 1,
156
+ "use_vae": true,
157
+ "latent_dim": 32,
158
+ "n_vae_encoder_layers": 4,
159
+ "temporal_ensemble_coeff": null,
160
+ "dropout": 0.1,
161
+ "kl_weight": 10.0,
162
+ "optimizer_lr": 1e-05,
163
+ "optimizer_weight_decay": 0.0001,
164
+ "optimizer_lr_backbone": 1e-05,
165
+ "optimizer_fused": null
166
+ },
167
+ "reward_model": null,
168
+ "output_dir": "/home/douglasmcdonough12/hrl_2/hrl_imerse/assignment2/task2_v3/outputs/train/act_stack_v3_dag60k_r2",
169
+ "job_name": "act_stack_v3_dag60k_r2",
170
+ "resume": false,
171
+ "seed": 1000,
172
+ "cudnn_deterministic": false,
173
+ "tf32": true,
174
+ "num_workers": 4,
175
+ "batch_size": 8,
176
+ "prefetch_factor": 4,
177
+ "persistent_workers": true,
178
+ "dataloader_multiprocessing_context": "spawn",
179
+ "steps": 10000,
180
+ "env_eval_freq": 20000,
181
+ "log_freq": 200,
182
+ "eval_steps": 2500,
183
+ "max_eval_samples": 3000,
184
+ "tolerance_s": 0.0001,
185
+ "save_checkpoint": true,
186
+ "save_freq": 2500,
187
+ "checkpoint_format": "safetensors",
188
+ "use_policy_training_preset": true,
189
+ "optimizer": {
190
+ "type": "adamw",
191
+ "lr": 1e-05,
192
+ "weight_decay": 0.0001,
193
+ "grad_clip_norm": 10.0,
194
+ "betas": [
195
+ 0.9,
196
+ 0.999
197
+ ],
198
+ "eps": 1e-08,
199
+ "fused": null
200
+ },
201
+ "scheduler": null,
202
+ "parallelism": {
203
+ "dp_replicate": 1,
204
+ "dp_shard": 1,
205
+ "context_parallel": {
206
+ "ring_degree": 1,
207
+ "ulysses_degree": 1
208
+ },
209
+ "cfg_parallel": 1
210
+ },
211
+ "accelerator": {
212
+ "mixed_precision": "bf16",
213
+ "gradient_accumulation": {
214
+ "steps": 1,
215
+ "sync_each_batch": false
216
+ },
217
+ "grad_scaler": {
218
+ "init_scale": 65536.0,
219
+ "growth_factor": 2.0,
220
+ "backoff_factor": 0.5,
221
+ "growth_interval": 2000
222
+ },
223
+ "fsdp": {
224
+ "reshard_after_forward": true,
225
+ "wrap_modules": null,
226
+ "min_num_params": null,
227
+ "cpu_offload": false,
228
+ "ignored_modules": null,
229
+ "mixed_precision_policy": {
230
+ "param_dtype": null,
231
+ "reduce_dtype": null,
232
+ "output_dtype": null,
233
+ "cast_forward_inputs": true
234
+ }
235
+ },
236
+ "ddp": {
237
+ "find_unused_parameters": true,
238
+ "gradient_as_bucket_view": false,
239
+ "static_graph": false
240
+ },
241
+ "init_process_group": {
242
+ "backend": "nccl",
243
+ "init_method": null,
244
+ "timeout": null
245
+ },
246
+ "compile": {
247
+ "enabled": false,
248
+ "backend": "inductor",
249
+ "mode": null,
250
+ "regional": true
251
+ },
252
+ "activation_checkpointing": {
253
+ "mode": "none"
254
+ }
255
+ },
256
+ "eval": {
257
+ "n_episodes": 50,
258
+ "batch_size": 22,
259
+ "use_async_envs": true,
260
+ "recording": false,
261
+ "recording_repo_id": null,
262
+ "recording_private": false,
263
+ "max_episode_steps": null
264
+ },
265
+ "ema": null,
266
+ "trackio": {
267
+ "enable": false,
268
+ "disable_artifact": true,
269
+ "project": "lerobot",
270
+ "space_id": null,
271
+ "private": null,
272
+ "run_name": null,
273
+ "resume": null,
274
+ "capture_console": true
275
+ },
276
+ "peft": null,
277
+ "job": {
278
+ "target": null,
279
+ "image": "huggingface/lerobot-gpu:latest",
280
+ "timeout": "2d",
281
+ "detach": false,
282
+ "tags": []
283
+ },
284
+ "save_checkpoint_to_hub": false,
285
+ "sample_weighting": null,
286
+ "rename_map": {},
287
+ "checkpoint_path": null
288
+ }