AriRyo commited on
Commit
35c19b5
·
verified ·
1 Parent(s): 0276e13

upload blockpick_gray_pi0_48 step 001000

Browse files
checkpoints/001000/pretrained_model/config.json ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "pi0",
3
+ "n_obs_steps": 1,
4
+ "input_features": {
5
+ "observation.state": {
6
+ "type": "STATE",
7
+ "shape": [
8
+ 6
9
+ ]
10
+ },
11
+ "observation.images.above": {
12
+ "type": "VISUAL",
13
+ "shape": [
14
+ 3,
15
+ 480,
16
+ 640
17
+ ]
18
+ },
19
+ "observation.images.side": {
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": true,
40
+ "repo_id": "AriRyo/blockpick_gray_pi0_48",
41
+ "private": null,
42
+ "tags": null,
43
+ "license": null,
44
+ "pretrained_path": "lerobot/pi0_base",
45
+ "paligemma_variant": "gemma_2b",
46
+ "action_expert_variant": "gemma_300m",
47
+ "dtype": "bfloat16",
48
+ "chunk_size": 50,
49
+ "n_action_steps": 50,
50
+ "max_state_dim": 32,
51
+ "max_action_dim": 32,
52
+ "num_inference_steps": 10,
53
+ "time_sampling_beta_alpha": 1.5,
54
+ "time_sampling_beta_beta": 1.0,
55
+ "time_sampling_scale": 0.999,
56
+ "time_sampling_offset": 0.001,
57
+ "min_period": 0.004,
58
+ "max_period": 4.0,
59
+ "rtc_config": null,
60
+ "image_resolution": [
61
+ 224,
62
+ 224
63
+ ],
64
+ "empty_cameras": 0,
65
+ "normalization_mapping": {
66
+ "VISUAL": "IDENTITY",
67
+ "STATE": "MEAN_STD",
68
+ "ACTION": "MEAN_STD"
69
+ },
70
+ "gradient_checkpointing": true,
71
+ "compile_model": true,
72
+ "compile_mode": "max-autotune",
73
+ "freeze_vision_encoder": false,
74
+ "train_expert_only": false,
75
+ "optimizer_lr": 2.5e-05,
76
+ "optimizer_betas": [
77
+ 0.9,
78
+ 0.95
79
+ ],
80
+ "optimizer_eps": 1e-08,
81
+ "optimizer_weight_decay": 0.01,
82
+ "optimizer_grad_clip_norm": 1.0,
83
+ "scheduler_warmup_steps": 1000,
84
+ "scheduler_decay_steps": 30000,
85
+ "scheduler_decay_lr": 2.5e-06,
86
+ "tokenizer_max_length": 48
87
+ }
checkpoints/001000/pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e31440e68c49fefb085eee9f980f83bf3ffe17d0720a162f809563a4e9532898
3
+ size 8892502944
checkpoints/001000/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": "IDENTITY",
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
+ }
checkpoints/001000/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 sha256:77bed77ed2328fbe8bcb6be874e13da7cb8d179312d0a6a70ee9e72ad1db4360
3
+ size 7544
checkpoints/001000/pretrained_model/policy_preprocessor.json ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "pi0_new_line_processor",
16
+ "config": {}
17
+ },
18
+ {
19
+ "registry_name": "tokenizer_processor",
20
+ "config": {
21
+ "max_length": 48,
22
+ "task_key": "task",
23
+ "padding_side": "right",
24
+ "padding": "max_length",
25
+ "truncation": true,
26
+ "tokenizer_name": "google/paligemma-3b-pt-224"
27
+ }
28
+ },
29
+ {
30
+ "registry_name": "device_processor",
31
+ "config": {
32
+ "device": "cuda",
33
+ "float_dtype": null
34
+ }
35
+ },
36
+ {
37
+ "registry_name": "normalizer_processor",
38
+ "config": {
39
+ "eps": 1e-08,
40
+ "features": {
41
+ "observation.state": {
42
+ "type": "STATE",
43
+ "shape": [
44
+ 6
45
+ ]
46
+ },
47
+ "observation.images.above": {
48
+ "type": "VISUAL",
49
+ "shape": [
50
+ 3,
51
+ 480,
52
+ 640
53
+ ]
54
+ },
55
+ "observation.images.side": {
56
+ "type": "VISUAL",
57
+ "shape": [
58
+ 3,
59
+ 480,
60
+ 640
61
+ ]
62
+ },
63
+ "action": {
64
+ "type": "ACTION",
65
+ "shape": [
66
+ 6
67
+ ]
68
+ }
69
+ },
70
+ "norm_map": {
71
+ "VISUAL": "IDENTITY",
72
+ "STATE": "MEAN_STD",
73
+ "ACTION": "MEAN_STD"
74
+ }
75
+ },
76
+ "state_file": "policy_preprocessor_step_5_normalizer_processor.safetensors"
77
+ }
78
+ ]
79
+ }
checkpoints/001000/pretrained_model/policy_preprocessor_step_5_normalizer_processor.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77bed77ed2328fbe8bcb6be874e13da7cb8d179312d0a6a70ee9e72ad1db4360
3
+ size 7544
checkpoints/001000/pretrained_model/train_config.json ADDED
@@ -0,0 +1,274 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "AriRyo/blockpick_gray_03",
4
+ "root": null,
5
+ "episodes": [
6
+ 0,
7
+ 1,
8
+ 2,
9
+ 3,
10
+ 4,
11
+ 5,
12
+ 6,
13
+ 7,
14
+ 8,
15
+ 9,
16
+ 10,
17
+ 11,
18
+ 12,
19
+ 13,
20
+ 14,
21
+ 15,
22
+ 16,
23
+ 17,
24
+ 18,
25
+ 19,
26
+ 20,
27
+ 21,
28
+ 22,
29
+ 23,
30
+ 24,
31
+ 25,
32
+ 26,
33
+ 27,
34
+ 28,
35
+ 29,
36
+ 30,
37
+ 31,
38
+ 32,
39
+ 33,
40
+ 34,
41
+ 35,
42
+ 36,
43
+ 37,
44
+ 38,
45
+ 39,
46
+ 40,
47
+ 41,
48
+ 42,
49
+ 43,
50
+ 44,
51
+ 45,
52
+ 46,
53
+ 47
54
+ ],
55
+ "image_transforms": {
56
+ "enable": false,
57
+ "max_num_transforms": 3,
58
+ "random_order": false,
59
+ "tfs": {
60
+ "brightness": {
61
+ "weight": 1.0,
62
+ "type": "ColorJitter",
63
+ "kwargs": {
64
+ "brightness": [
65
+ 0.8,
66
+ 1.2
67
+ ]
68
+ }
69
+ },
70
+ "contrast": {
71
+ "weight": 1.0,
72
+ "type": "ColorJitter",
73
+ "kwargs": {
74
+ "contrast": [
75
+ 0.8,
76
+ 1.2
77
+ ]
78
+ }
79
+ },
80
+ "saturation": {
81
+ "weight": 1.0,
82
+ "type": "ColorJitter",
83
+ "kwargs": {
84
+ "saturation": [
85
+ 0.5,
86
+ 1.5
87
+ ]
88
+ }
89
+ },
90
+ "hue": {
91
+ "weight": 1.0,
92
+ "type": "ColorJitter",
93
+ "kwargs": {
94
+ "hue": [
95
+ -0.05,
96
+ 0.05
97
+ ]
98
+ }
99
+ },
100
+ "sharpness": {
101
+ "weight": 1.0,
102
+ "type": "SharpnessJitter",
103
+ "kwargs": {
104
+ "sharpness": [
105
+ 0.5,
106
+ 1.5
107
+ ]
108
+ }
109
+ },
110
+ "affine": {
111
+ "weight": 1.0,
112
+ "type": "RandomAffine",
113
+ "kwargs": {
114
+ "degrees": [
115
+ -5.0,
116
+ 5.0
117
+ ],
118
+ "translate": [
119
+ 0.05,
120
+ 0.05
121
+ ]
122
+ }
123
+ }
124
+ }
125
+ },
126
+ "revision": null,
127
+ "use_imagenet_stats": true,
128
+ "video_backend": "torchcodec",
129
+ "streaming": false
130
+ },
131
+ "env": null,
132
+ "policy": {
133
+ "type": "pi0",
134
+ "n_obs_steps": 1,
135
+ "input_features": {
136
+ "observation.state": {
137
+ "type": "STATE",
138
+ "shape": [
139
+ 6
140
+ ]
141
+ },
142
+ "observation.images.above": {
143
+ "type": "VISUAL",
144
+ "shape": [
145
+ 3,
146
+ 480,
147
+ 640
148
+ ]
149
+ },
150
+ "observation.images.side": {
151
+ "type": "VISUAL",
152
+ "shape": [
153
+ 3,
154
+ 480,
155
+ 640
156
+ ]
157
+ }
158
+ },
159
+ "output_features": {
160
+ "action": {
161
+ "type": "ACTION",
162
+ "shape": [
163
+ 6
164
+ ]
165
+ }
166
+ },
167
+ "device": "cuda",
168
+ "use_amp": false,
169
+ "use_peft": false,
170
+ "push_to_hub": true,
171
+ "repo_id": "AriRyo/blockpick_gray_pi0_48",
172
+ "private": null,
173
+ "tags": null,
174
+ "license": null,
175
+ "pretrained_path": "lerobot/pi0_base",
176
+ "paligemma_variant": "gemma_2b",
177
+ "action_expert_variant": "gemma_300m",
178
+ "dtype": "bfloat16",
179
+ "chunk_size": 50,
180
+ "n_action_steps": 50,
181
+ "max_state_dim": 32,
182
+ "max_action_dim": 32,
183
+ "num_inference_steps": 10,
184
+ "time_sampling_beta_alpha": 1.5,
185
+ "time_sampling_beta_beta": 1.0,
186
+ "time_sampling_scale": 0.999,
187
+ "time_sampling_offset": 0.001,
188
+ "min_period": 0.004,
189
+ "max_period": 4.0,
190
+ "rtc_config": null,
191
+ "image_resolution": [
192
+ 224,
193
+ 224
194
+ ],
195
+ "empty_cameras": 0,
196
+ "normalization_mapping": {
197
+ "VISUAL": "IDENTITY",
198
+ "STATE": "MEAN_STD",
199
+ "ACTION": "MEAN_STD"
200
+ },
201
+ "gradient_checkpointing": true,
202
+ "compile_model": true,
203
+ "compile_mode": "max-autotune",
204
+ "freeze_vision_encoder": false,
205
+ "train_expert_only": false,
206
+ "optimizer_lr": 2.5e-05,
207
+ "optimizer_betas": [
208
+ 0.9,
209
+ 0.95
210
+ ],
211
+ "optimizer_eps": 1e-08,
212
+ "optimizer_weight_decay": 0.01,
213
+ "optimizer_grad_clip_norm": 1.0,
214
+ "scheduler_warmup_steps": 1000,
215
+ "scheduler_decay_steps": 30000,
216
+ "scheduler_decay_lr": 2.5e-06,
217
+ "tokenizer_max_length": 48
218
+ },
219
+ "output_dir": "outputs/train/blockpick_gray_pi0_48",
220
+ "job_name": "blockpick_gray_pi0_48",
221
+ "resume": false,
222
+ "seed": 1000,
223
+ "cudnn_deterministic": false,
224
+ "num_workers": 4,
225
+ "batch_size": 16,
226
+ "steps": 5000,
227
+ "eval_freq": 20000,
228
+ "log_freq": 200,
229
+ "tolerance_s": 0.0001,
230
+ "save_checkpoint": true,
231
+ "save_freq": 1000,
232
+ "use_policy_training_preset": true,
233
+ "optimizer": {
234
+ "type": "adamw",
235
+ "lr": 2.5e-05,
236
+ "weight_decay": 0.01,
237
+ "grad_clip_norm": 1.0,
238
+ "betas": [
239
+ 0.9,
240
+ 0.95
241
+ ],
242
+ "eps": 1e-08
243
+ },
244
+ "scheduler": {
245
+ "type": "cosine_decay_with_warmup",
246
+ "num_warmup_steps": 1000,
247
+ "num_decay_steps": 30000,
248
+ "peak_lr": 2.5e-05,
249
+ "decay_lr": 2.5e-06
250
+ },
251
+ "eval": {
252
+ "n_episodes": 50,
253
+ "batch_size": 50,
254
+ "use_async_envs": false
255
+ },
256
+ "wandb": {
257
+ "enable": true,
258
+ "disable_artifact": true,
259
+ "project": "lerobot",
260
+ "entity": null,
261
+ "notes": null,
262
+ "run_id": "hnsgxqbg",
263
+ "mode": null,
264
+ "add_tags": true
265
+ },
266
+ "peft": null,
267
+ "use_rabc": false,
268
+ "rabc_progress_path": null,
269
+ "rabc_kappa": 0.01,
270
+ "rabc_epsilon": 1e-06,
271
+ "rabc_head_mode": "sparse",
272
+ "rename_map": {},
273
+ "checkpoint_path": null
274
+ }
checkpoints/001000/training_state/optimizer_param_groups.json ADDED
@@ -0,0 +1,799 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "lr": 2.285144118671816e-05,
4
+ "betas": [
5
+ 0.9,
6
+ 0.95
7
+ ],
8
+ "eps": 1e-08,
9
+ "weight_decay": 0.01,
10
+ "amsgrad": false,
11
+ "maximize": false,
12
+ "foreach": null,
13
+ "capturable": false,
14
+ "differentiable": false,
15
+ "fused": null,
16
+ "decoupled_weight_decay": true,
17
+ "initial_lr": 2.5e-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
+ 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
+ 340,
360
+ 341,
361
+ 342,
362
+ 343,
363
+ 344,
364
+ 345,
365
+ 346,
366
+ 347,
367
+ 348,
368
+ 349,
369
+ 350,
370
+ 351,
371
+ 352,
372
+ 353,
373
+ 354,
374
+ 355,
375
+ 356,
376
+ 357,
377
+ 358,
378
+ 359,
379
+ 360,
380
+ 361,
381
+ 362,
382
+ 363,
383
+ 364,
384
+ 365,
385
+ 366,
386
+ 367,
387
+ 368,
388
+ 369,
389
+ 370,
390
+ 371,
391
+ 372,
392
+ 373,
393
+ 374,
394
+ 375,
395
+ 376,
396
+ 377,
397
+ 378,
398
+ 379,
399
+ 380,
400
+ 381,
401
+ 382,
402
+ 383,
403
+ 384,
404
+ 385,
405
+ 386,
406
+ 387,
407
+ 388,
408
+ 389,
409
+ 390,
410
+ 391,
411
+ 392,
412
+ 393,
413
+ 394,
414
+ 395,
415
+ 396,
416
+ 397,
417
+ 398,
418
+ 399,
419
+ 400,
420
+ 401,
421
+ 402,
422
+ 403,
423
+ 404,
424
+ 405,
425
+ 406,
426
+ 407,
427
+ 408,
428
+ 409,
429
+ 410,
430
+ 411,
431
+ 412,
432
+ 413,
433
+ 414,
434
+ 415,
435
+ 416,
436
+ 417,
437
+ 418,
438
+ 419,
439
+ 420,
440
+ 421,
441
+ 422,
442
+ 423,
443
+ 424,
444
+ 425,
445
+ 426,
446
+ 427,
447
+ 428,
448
+ 429,
449
+ 430,
450
+ 431,
451
+ 432,
452
+ 433,
453
+ 434,
454
+ 435,
455
+ 436,
456
+ 437,
457
+ 438,
458
+ 439,
459
+ 440,
460
+ 441,
461
+ 442,
462
+ 443,
463
+ 444,
464
+ 445,
465
+ 446,
466
+ 447,
467
+ 448,
468
+ 449,
469
+ 450,
470
+ 451,
471
+ 452,
472
+ 453,
473
+ 454,
474
+ 455,
475
+ 456,
476
+ 457,
477
+ 458,
478
+ 459,
479
+ 460,
480
+ 461,
481
+ 462,
482
+ 463,
483
+ 464,
484
+ 465,
485
+ 466,
486
+ 467,
487
+ 468,
488
+ 469,
489
+ 470,
490
+ 471,
491
+ 472,
492
+ 473,
493
+ 474,
494
+ 475,
495
+ 476,
496
+ 477,
497
+ 478,
498
+ 479,
499
+ 480,
500
+ 481,
501
+ 482,
502
+ 483,
503
+ 484,
504
+ 485,
505
+ 486,
506
+ 487,
507
+ 488,
508
+ 489,
509
+ 490,
510
+ 491,
511
+ 492,
512
+ 493,
513
+ 494,
514
+ 495,
515
+ 496,
516
+ 497,
517
+ 498,
518
+ 499,
519
+ 500,
520
+ 501,
521
+ 502,
522
+ 503,
523
+ 504,
524
+ 505,
525
+ 506,
526
+ 507,
527
+ 508,
528
+ 509,
529
+ 510,
530
+ 511,
531
+ 512,
532
+ 513,
533
+ 514,
534
+ 515,
535
+ 516,
536
+ 517,
537
+ 518,
538
+ 519,
539
+ 520,
540
+ 521,
541
+ 522,
542
+ 523,
543
+ 524,
544
+ 525,
545
+ 526,
546
+ 527,
547
+ 528,
548
+ 529,
549
+ 530,
550
+ 531,
551
+ 532,
552
+ 533,
553
+ 534,
554
+ 535,
555
+ 536,
556
+ 537,
557
+ 538,
558
+ 539,
559
+ 540,
560
+ 541,
561
+ 542,
562
+ 543,
563
+ 544,
564
+ 545,
565
+ 546,
566
+ 547,
567
+ 548,
568
+ 549,
569
+ 550,
570
+ 551,
571
+ 552,
572
+ 553,
573
+ 554,
574
+ 555,
575
+ 556,
576
+ 557,
577
+ 558,
578
+ 559,
579
+ 560,
580
+ 561,
581
+ 562,
582
+ 563,
583
+ 564,
584
+ 565,
585
+ 566,
586
+ 567,
587
+ 568,
588
+ 569,
589
+ 570,
590
+ 571,
591
+ 572,
592
+ 573,
593
+ 574,
594
+ 575,
595
+ 576,
596
+ 577,
597
+ 578,
598
+ 579,
599
+ 580,
600
+ 581,
601
+ 582,
602
+ 583,
603
+ 584,
604
+ 585,
605
+ 586,
606
+ 587,
607
+ 588,
608
+ 589,
609
+ 590,
610
+ 591,
611
+ 592,
612
+ 593,
613
+ 594,
614
+ 595,
615
+ 596,
616
+ 597,
617
+ 598,
618
+ 599,
619
+ 600,
620
+ 601,
621
+ 602,
622
+ 603,
623
+ 604,
624
+ 605,
625
+ 606,
626
+ 607,
627
+ 608,
628
+ 609,
629
+ 610,
630
+ 611,
631
+ 612,
632
+ 613,
633
+ 614,
634
+ 615,
635
+ 616,
636
+ 617,
637
+ 618,
638
+ 619,
639
+ 620,
640
+ 621,
641
+ 622,
642
+ 623,
643
+ 624,
644
+ 625,
645
+ 626,
646
+ 627,
647
+ 628,
648
+ 629,
649
+ 630,
650
+ 631,
651
+ 632,
652
+ 633,
653
+ 634,
654
+ 635,
655
+ 636,
656
+ 637,
657
+ 638,
658
+ 639,
659
+ 640,
660
+ 641,
661
+ 642,
662
+ 643,
663
+ 644,
664
+ 645,
665
+ 646,
666
+ 647,
667
+ 648,
668
+ 649,
669
+ 650,
670
+ 651,
671
+ 652,
672
+ 653,
673
+ 654,
674
+ 655,
675
+ 656,
676
+ 657,
677
+ 658,
678
+ 659,
679
+ 660,
680
+ 661,
681
+ 662,
682
+ 663,
683
+ 664,
684
+ 665,
685
+ 666,
686
+ 667,
687
+ 668,
688
+ 669,
689
+ 670,
690
+ 671,
691
+ 672,
692
+ 673,
693
+ 674,
694
+ 675,
695
+ 676,
696
+ 677,
697
+ 678,
698
+ 679,
699
+ 680,
700
+ 681,
701
+ 682,
702
+ 683,
703
+ 684,
704
+ 685,
705
+ 686,
706
+ 687,
707
+ 688,
708
+ 689,
709
+ 690,
710
+ 691,
711
+ 692,
712
+ 693,
713
+ 694,
714
+ 695,
715
+ 696,
716
+ 697,
717
+ 698,
718
+ 699,
719
+ 700,
720
+ 701,
721
+ 702,
722
+ 703,
723
+ 704,
724
+ 705,
725
+ 706,
726
+ 707,
727
+ 708,
728
+ 709,
729
+ 710,
730
+ 711,
731
+ 712,
732
+ 713,
733
+ 714,
734
+ 715,
735
+ 716,
736
+ 717,
737
+ 718,
738
+ 719,
739
+ 720,
740
+ 721,
741
+ 722,
742
+ 723,
743
+ 724,
744
+ 725,
745
+ 726,
746
+ 727,
747
+ 728,
748
+ 729,
749
+ 730,
750
+ 731,
751
+ 732,
752
+ 733,
753
+ 734,
754
+ 735,
755
+ 736,
756
+ 737,
757
+ 738,
758
+ 739,
759
+ 740,
760
+ 741,
761
+ 742,
762
+ 743,
763
+ 744,
764
+ 745,
765
+ 746,
766
+ 747,
767
+ 748,
768
+ 749,
769
+ 750,
770
+ 751,
771
+ 752,
772
+ 753,
773
+ 754,
774
+ 755,
775
+ 756,
776
+ 757,
777
+ 758,
778
+ 759,
779
+ 760,
780
+ 761,
781
+ 762,
782
+ 763,
783
+ 764,
784
+ 765,
785
+ 766,
786
+ 767,
787
+ 768,
788
+ 769,
789
+ 770,
790
+ 771,
791
+ 772,
792
+ 773,
793
+ 774,
794
+ 775,
795
+ 776,
796
+ 777
797
+ ]
798
+ }
799
+ ]
checkpoints/001000/training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:842734331dd355e9f8ac9e377f127b7dc890564888e5056a66d55a768ba0d202
3
+ size 14205605000
checkpoints/001000/training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8b06d41c9dbff79e5a1f9e1208bb47d0cf62b41847c949d355c50865d46f987
3
+ size 15708
checkpoints/001000/training_state/scheduler_state.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_lrs": [
3
+ 2.5e-05
4
+ ],
5
+ "last_epoch": 1000,
6
+ "_step_count": 1001,
7
+ "_is_initial": false,
8
+ "_get_lr_called_within_step": false,
9
+ "_last_lr": [
10
+ 2.285144118671816e-05
11
+ ],
12
+ "lr_lambdas": [
13
+ null
14
+ ]
15
+ }
checkpoints/001000/training_state/training_step.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "step": 1000
3
+ }