Hugging Face's logo

Autobrik
/
SO-ARM100-dump-pocket-cleaning2-diffusion

Robotics
LeRobot
Safetensors
imitation-learning
diffusion
Model card Files
xet
Community
Autobrik commited on
Commit
092c126
·
verified ·
1 Parent(s): 1de7a72

Upload folder using huggingface_hub

Browse files
Files changed (12) hide show
  1. checkpoints/last/pretrained_model/config.json +91 -0
  2. checkpoints/last/pretrained_model/model.safetensors +3 -0
  3. checkpoints/last/pretrained_model/policy_postprocessor.json +32 -0
  4. checkpoints/last/pretrained_model/policy_postprocessor_step_0_unnormalizer_processor.safetensors +3 -0
  5. checkpoints/last/pretrained_model/policy_preprocessor.json +64 -0
  6. checkpoints/last/pretrained_model/policy_preprocessor_step_3_normalizer_processor.safetensors +3 -0
  7. checkpoints/last/pretrained_model/train_config.json +396 -0
  8. checkpoints/last/training_state/optimizer_param_groups.json +233 -0
  9. checkpoints/last/training_state/optimizer_state.safetensors +3 -0
  10. checkpoints/last/training_state/rng_state.safetensors +3 -0
  11. checkpoints/last/training_state/scheduler_state.json +14 -0
  12. checkpoints/last/training_state/training_step.json +3 -0
checkpoints/last/pretrained_model/config.json ADDED
@@ -0,0 +1,91 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "diffusion",
3
+ "n_obs_steps": 2,
4
+ "input_features": {
5
+ "observation.state": {
6
+ "type": "STATE",
7
+ "shape": [
8
+ 6
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
+ 6
33
+ ]
34
+ }
35
+ },
36
+ "device": "cuda",
37
+ "use_amp": false,
38
+ "use_peft": false,
39
+ "push_to_hub": false,
40
+ "repo_id": null,
41
+ "private": null,
42
+ "tags": null,
43
+ "license": null,
44
+ "pretrained_path": null,
45
+ "horizon": 16,
46
+ "n_action_steps": 8,
47
+ "normalization_mapping": {
48
+ "VISUAL": "MEAN_STD",
49
+ "STATE": "MIN_MAX",
50
+ "ACTION": "MIN_MAX"
51
+ },
52
+ "drop_n_last_frames": 7,
53
+ "vision_backbone": "resnet18",
54
+ "crop_shape": [
55
+ 84,
56
+ 84
57
+ ],
58
+ "crop_is_random": true,
59
+ "pretrained_backbone_weights": null,
60
+ "use_group_norm": true,
61
+ "spatial_softmax_num_keypoints": 32,
62
+ "use_separate_rgb_encoder_per_camera": false,
63
+ "down_dims": [
64
+ 512,
65
+ 1024,
66
+ 2048
67
+ ],
68
+ "kernel_size": 5,
69
+ "n_groups": 8,
70
+ "diffusion_step_embed_dim": 128,
71
+ "use_film_scale_modulation": true,
72
+ "noise_scheduler_type": "DDPM",
73
+ "num_train_timesteps": 100,
74
+ "beta_schedule": "squaredcos_cap_v2",
75
+ "beta_start": 0.0001,
76
+ "beta_end": 0.02,
77
+ "prediction_type": "epsilon",
78
+ "clip_sample": true,
79
+ "clip_sample_range": 1.0,
80
+ "num_inference_steps": null,
81
+ "do_mask_loss_for_padding": false,
82
+ "optimizer_lr": 0.0001,
83
+ "optimizer_betas": [
84
+ 0.95,
85
+ 0.999
86
+ ],
87
+ "optimizer_eps": 1e-08,
88
+ "optimizer_weight_decay": 1e-06,
89
+ "scheduler_name": "cosine",
90
+ "scheduler_warmup_steps": 500
91
+ }
checkpoints/last/pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac94ddcc6b60e7ae7a8ceb1e711efcdc3cf1a78db67a67dfc7ddbc4aba67859d
3
+ size 1066516384
checkpoints/last/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
+ }
checkpoints/last/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 sha256:2636adf897cda0071bde2ef865e92f2bdd9b6fc7e7ebd8203a45d55225abe39c
3
+ size 7536
checkpoints/last/pretrained_model/policy_preprocessor.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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.top": {
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
+ "action": {
49
+ "type": "ACTION",
50
+ "shape": [
51
+ 6
52
+ ]
53
+ }
54
+ },
55
+ "norm_map": {
56
+ "VISUAL": "MEAN_STD",
57
+ "STATE": "MIN_MAX",
58
+ "ACTION": "MIN_MAX"
59
+ }
60
+ },
61
+ "state_file": "policy_preprocessor_step_3_normalizer_processor.safetensors"
62
+ }
63
+ ]
64
+ }
checkpoints/last/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 sha256:2636adf897cda0071bde2ef865e92f2bdd9b6fc7e7ebd8203a45d55225abe39c
3
+ size 7536
checkpoints/last/pretrained_model/train_config.json ADDED
@@ -0,0 +1,396 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "Autobrik/SO-ARM100-dump-pocket-cleaning2",
4
+ "root": null,
5
+ "episodes": [
6
+ 1,
7
+ 3,
8
+ 4,
9
+ 5,
10
+ 6,
11
+ 7,
12
+ 8,
13
+ 9,
14
+ 10,
15
+ 11,
16
+ 12,
17
+ 13,
18
+ 14,
19
+ 15,
20
+ 16,
21
+ 17,
22
+ 18,
23
+ 21,
24
+ 23,
25
+ 24,
26
+ 27,
27
+ 29,
28
+ 31,
29
+ 32,
30
+ 33,
31
+ 34,
32
+ 35,
33
+ 36,
34
+ 37,
35
+ 38,
36
+ 39,
37
+ 40,
38
+ 41,
39
+ 42,
40
+ 43,
41
+ 44,
42
+ 45,
43
+ 46,
44
+ 47,
45
+ 48,
46
+ 49,
47
+ 50,
48
+ 51,
49
+ 52,
50
+ 54,
51
+ 55,
52
+ 56,
53
+ 58,
54
+ 59,
55
+ 60,
56
+ 62,
57
+ 63,
58
+ 65,
59
+ 66,
60
+ 67,
61
+ 68,
62
+ 69,
63
+ 70,
64
+ 71,
65
+ 72,
66
+ 74,
67
+ 75,
68
+ 76,
69
+ 77,
70
+ 78,
71
+ 79,
72
+ 82,
73
+ 83,
74
+ 84,
75
+ 85,
76
+ 86,
77
+ 88,
78
+ 90,
79
+ 92,
80
+ 93,
81
+ 94,
82
+ 95,
83
+ 97,
84
+ 98,
85
+ 99,
86
+ 100,
87
+ 102,
88
+ 103,
89
+ 104,
90
+ 105,
91
+ 106,
92
+ 108,
93
+ 109,
94
+ 110,
95
+ 111,
96
+ 113,
97
+ 114,
98
+ 116,
99
+ 117,
100
+ 118,
101
+ 119,
102
+ 120,
103
+ 121,
104
+ 122,
105
+ 123,
106
+ 124,
107
+ 126,
108
+ 127,
109
+ 129,
110
+ 130,
111
+ 132,
112
+ 133,
113
+ 134,
114
+ 135,
115
+ 136,
116
+ 137,
117
+ 138,
118
+ 139,
119
+ 141,
120
+ 143,
121
+ 144,
122
+ 145,
123
+ 147,
124
+ 148,
125
+ 149,
126
+ 151,
127
+ 152,
128
+ 154,
129
+ 155,
130
+ 156,
131
+ 157,
132
+ 159,
133
+ 160,
134
+ 161
135
+ ],
136
+ "image_transforms": {
137
+ "enable": false,
138
+ "max_num_transforms": 3,
139
+ "random_order": false,
140
+ "tfs": {
141
+ "brightness": {
142
+ "weight": 1.0,
143
+ "type": "ColorJitter",
144
+ "kwargs": {
145
+ "brightness": [
146
+ 0.8,
147
+ 1.2
148
+ ]
149
+ }
150
+ },
151
+ "contrast": {
152
+ "weight": 1.0,
153
+ "type": "ColorJitter",
154
+ "kwargs": {
155
+ "contrast": [
156
+ 0.8,
157
+ 1.2
158
+ ]
159
+ }
160
+ },
161
+ "saturation": {
162
+ "weight": 1.0,
163
+ "type": "ColorJitter",
164
+ "kwargs": {
165
+ "saturation": [
166
+ 0.5,
167
+ 1.5
168
+ ]
169
+ }
170
+ },
171
+ "hue": {
172
+ "weight": 1.0,
173
+ "type": "ColorJitter",
174
+ "kwargs": {
175
+ "hue": [
176
+ -0.05,
177
+ 0.05
178
+ ]
179
+ }
180
+ },
181
+ "sharpness": {
182
+ "weight": 1.0,
183
+ "type": "SharpnessJitter",
184
+ "kwargs": {
185
+ "sharpness": [
186
+ 0.5,
187
+ 1.5
188
+ ]
189
+ }
190
+ },
191
+ "affine": {
192
+ "weight": 1.0,
193
+ "type": "RandomAffine",
194
+ "kwargs": {
195
+ "degrees": [
196
+ -5.0,
197
+ 5.0
198
+ ],
199
+ "translate": [
200
+ 0.05,
201
+ 0.05
202
+ ]
203
+ }
204
+ }
205
+ }
206
+ },
207
+ "revision": null,
208
+ "use_imagenet_stats": true,
209
+ "video_backend": "torchcodec",
210
+ "streaming": false
211
+ },
212
+ "env": null,
213
+ "policy": {
214
+ "type": "diffusion",
215
+ "n_obs_steps": 2,
216
+ "input_features": {
217
+ "observation.state": {
218
+ "type": "STATE",
219
+ "shape": [
220
+ 6
221
+ ]
222
+ },
223
+ "observation.images.top": {
224
+ "type": "VISUAL",
225
+ "shape": [
226
+ 3,
227
+ 480,
228
+ 640
229
+ ]
230
+ },
231
+ "observation.images.wrist": {
232
+ "type": "VISUAL",
233
+ "shape": [
234
+ 3,
235
+ 480,
236
+ 640
237
+ ]
238
+ }
239
+ },
240
+ "output_features": {
241
+ "action": {
242
+ "type": "ACTION",
243
+ "shape": [
244
+ 6
245
+ ]
246
+ }
247
+ },
248
+ "device": "cuda",
249
+ "use_amp": false,
250
+ "use_peft": false,
251
+ "push_to_hub": false,
252
+ "repo_id": null,
253
+ "private": null,
254
+ "tags": null,
255
+ "license": null,
256
+ "pretrained_path": null,
257
+ "horizon": 16,
258
+ "n_action_steps": 8,
259
+ "normalization_mapping": {
260
+ "VISUAL": "MEAN_STD",
261
+ "STATE": "MIN_MAX",
262
+ "ACTION": "MIN_MAX"
263
+ },
264
+ "drop_n_last_frames": 7,
265
+ "vision_backbone": "resnet18",
266
+ "crop_shape": [
267
+ 84,
268
+ 84
269
+ ],
270
+ "crop_is_random": true,
271
+ "pretrained_backbone_weights": null,
272
+ "use_group_norm": true,
273
+ "spatial_softmax_num_keypoints": 32,
274
+ "use_separate_rgb_encoder_per_camera": false,
275
+ "down_dims": [
276
+ 512,
277
+ 1024,
278
+ 2048
279
+ ],
280
+ "kernel_size": 5,
281
+ "n_groups": 8,
282
+ "diffusion_step_embed_dim": 128,
283
+ "use_film_scale_modulation": true,
284
+ "noise_scheduler_type": "DDPM",
285
+ "num_train_timesteps": 100,
286
+ "beta_schedule": "squaredcos_cap_v2",
287
+ "beta_start": 0.0001,
288
+ "beta_end": 0.02,
289
+ "prediction_type": "epsilon",
290
+ "clip_sample": true,
291
+ "clip_sample_range": 1.0,
292
+ "num_inference_steps": null,
293
+ "do_mask_loss_for_padding": false,
294
+ "optimizer_lr": 0.0001,
295
+ "optimizer_betas": [
296
+ 0.95,
297
+ 0.999
298
+ ],
299
+ "optimizer_eps": 1e-08,
300
+ "optimizer_weight_decay": 1e-06,
301
+ "scheduler_name": "cosine",
302
+ "scheduler_warmup_steps": 500
303
+ },
304
+ "output_dir": "outputs/train/benchmark/20260216_022628_benchmark_diffusion",
305
+ "job_name": "benchmark_diffusion",
306
+ "resume": false,
307
+ "seed": 1000,
308
+ "num_workers": 4,
309
+ "batch_size": 32,
310
+ "steps": 7252,
311
+ "eval_freq": -1,
312
+ "log_freq": 100,
313
+ "tolerance_s": 0.0001,
314
+ "save_checkpoint": true,
315
+ "save_freq": 1813,
316
+ "use_policy_training_preset": true,
317
+ "optimizer": {
318
+ "type": "adam",
319
+ "lr": 0.0001,
320
+ "weight_decay": 1e-06,
321
+ "grad_clip_norm": 10.0,
322
+ "betas": [
323
+ 0.95,
324
+ 0.999
325
+ ],
326
+ "eps": 1e-08
327
+ },
328
+ "scheduler": {
329
+ "type": "diffuser",
330
+ "num_warmup_steps": 500,
331
+ "name": "cosine"
332
+ },
333
+ "eval": {
334
+ "n_episodes": 50,
335
+ "batch_size": 50,
336
+ "use_async_envs": false
337
+ },
338
+ "offline_val": {
339
+ "enable": true,
340
+ "episodes": [
341
+ 0,
342
+ 2,
343
+ 19,
344
+ 20,
345
+ 22,
346
+ 25,
347
+ 26,
348
+ 28,
349
+ 30,
350
+ 53,
351
+ 57,
352
+ 61,
353
+ 64,
354
+ 73,
355
+ 80,
356
+ 81,
357
+ 87,
358
+ 89,
359
+ 91,
360
+ 96,
361
+ 101,
362
+ 107,
363
+ 112,
364
+ 115,
365
+ 125,
366
+ 128,
367
+ 131,
368
+ 140,
369
+ 142,
370
+ 146,
371
+ 150,
372
+ 153,
373
+ 158
374
+ ],
375
+ "freq": 907,
376
+ "max_batches": null,
377
+ "track_best_checkpoint": true
378
+ },
379
+ "wandb": {
380
+ "enable": true,
381
+ "disable_artifact": false,
382
+ "project": "dump-pocket-benchmark",
383
+ "entity": null,
384
+ "notes": null,
385
+ "run_id": "w69epy0a",
386
+ "mode": null
387
+ },
388
+ "peft": null,
389
+ "use_rabc": false,
390
+ "rabc_progress_path": null,
391
+ "rabc_kappa": 0.01,
392
+ "rabc_epsilon": 1e-06,
393
+ "rabc_head_mode": "sparse",
394
+ "rename_map": {},
395
+ "checkpoint_path": null
396
+ }
checkpoints/last/training_state/optimizer_param_groups.json ADDED
@@ -0,0 +1,233 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ ]
232
+ }
233
+ ]
checkpoints/last/training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e93cf91956a70f13553b7d666238d0d0595320520f0826e65c5fdc38ad40fdda
3
+ size 2133039080
checkpoints/last/training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:043fae3990afc260bb45c636026bd1da79f3de2049f9bf6d3c8da2a8e3b94c12
3
+ size 15708
checkpoints/last/training_state/scheduler_state.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_lrs": [
3
+ 0.0001
4
+ ],
5
+ "last_epoch": 7252,
6
+ "_step_count": 7253,
7
+ "_get_lr_called_within_step": false,
8
+ "_last_lr": [
9
+ 0.0
10
+ ],
11
+ "lr_lambdas": [
12
+ null
13
+ ]
14
+ }
checkpoints/last/training_state/training_step.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "step": 7252
3
+ }