Hugging Face's logo

Spring14th
/
hybrid_050k

Safetensors
Model card Files
xet
Community
Spring14th commited on
Commit
cbc1b6f
·
verified ·
1 Parent(s): de329ae

Upload folder using huggingface_hub

Browse files
Files changed (8) hide show
  1. pretrained_model/config.json +165 -0
  2. pretrained_model/model.safetensors +3 -0
  3. pretrained_model/train_config.json +309 -0
  4. training_state/optimizer_param_groups.json +393 -0
  5. training_state/optimizer_state.safetensors +3 -0
  6. training_state/rng_state.safetensors +3 -0
  7. training_state/scheduler_state.json +15 -0
  8. training_state/training_step.json +3 -0
pretrained_model/config.json ADDED
@@ -0,0 +1,165 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "hybrid",
3
+ "n_obs_steps": 1,
4
+ "normalization_mapping": {},
5
+ "input_features": {
6
+ "observation.images.top": {
7
+ "type": "VISUAL",
8
+ "shape": [
9
+ 3,
10
+ 480,
11
+ 640
12
+ ]
13
+ },
14
+ "observation.state": {
15
+ "type": "STATE",
16
+ "shape": [
17
+ 14
18
+ ]
19
+ }
20
+ },
21
+ "output_features": {
22
+ "action": {
23
+ "type": "ACTION",
24
+ "shape": [
25
+ 14
26
+ ]
27
+ }
28
+ },
29
+ "device": "cuda",
30
+ "use_amp": false,
31
+ "act_config": {
32
+ "type": "act",
33
+ "n_obs_steps": 2,
34
+ "normalization_mapping": {
35
+ "VISUAL": "MEAN_STD",
36
+ "STATE": "MEAN_STD",
37
+ "ACTION": "MEAN_STD"
38
+ },
39
+ "input_features": {
40
+ "observation.state": {
41
+ "type": "STATE",
42
+ "shape": [
43
+ 14
44
+ ]
45
+ },
46
+ "observation.images.top": {
47
+ "type": "VISUAL",
48
+ "shape": [
49
+ 3,
50
+ 480,
51
+ 640
52
+ ]
53
+ }
54
+ },
55
+ "output_features": {
56
+ "action": {
57
+ "type": "ACTION",
58
+ "shape": [
59
+ 14
60
+ ]
61
+ }
62
+ },
63
+ "device": "cuda",
64
+ "use_amp": false,
65
+ "chunk_size": 400,
66
+ "n_action_steps": 400,
67
+ "vision_backbone": "resnet18",
68
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
69
+ "replace_final_stride_with_dilation": false,
70
+ "pre_norm": false,
71
+ "dim_model": 512,
72
+ "n_heads": 8,
73
+ "dim_feedforward": 3200,
74
+ "feedforward_activation": "relu",
75
+ "n_encoder_layers": 4,
76
+ "n_decoder_layers": 1,
77
+ "use_vae": true,
78
+ "latent_dim": 32,
79
+ "n_vae_encoder_layers": 4,
80
+ "temporal_ensemble_coeff": null,
81
+ "dropout": 0.1,
82
+ "kl_weight": 10.0,
83
+ "smoothness_weight": 0.0,
84
+ "smoothness_type": "velocity",
85
+ "optimizer_lr": 1e-05,
86
+ "optimizer_weight_decay": 0.0001,
87
+ "optimizer_lr_backbone": 1e-05
88
+ },
89
+ "diffusion_config": {
90
+ "type": "diffusion",
91
+ "n_obs_steps": 2,
92
+ "normalization_mapping": {
93
+ "VISUAL": "MEAN_STD",
94
+ "STATE": "MEAN_STD",
95
+ "ACTION": "MEAN_STD"
96
+ },
97
+ "input_features": {
98
+ "observation.state": {
99
+ "type": "STATE",
100
+ "shape": [
101
+ 14
102
+ ]
103
+ },
104
+ "observation.images.top": {
105
+ "type": "VISUAL",
106
+ "shape": [
107
+ 3,
108
+ 480,
109
+ 640
110
+ ]
111
+ }
112
+ },
113
+ "output_features": {
114
+ "action": {
115
+ "type": "ACTION",
116
+ "shape": [
117
+ 14
118
+ ]
119
+ }
120
+ },
121
+ "device": "cuda",
122
+ "use_amp": false,
123
+ "horizon": 16,
124
+ "n_action_steps": 1,
125
+ "drop_n_last_frames": 7,
126
+ "vision_backbone": "resnet18",
127
+ "crop_shape": null,
128
+ "crop_is_random": true,
129
+ "pretrained_backbone_weights": null,
130
+ "use_group_norm": true,
131
+ "spatial_softmax_num_keypoints": 32,
132
+ "use_separate_rgb_encoder_per_camera": false,
133
+ "down_dims": [
134
+ 128,
135
+ 256,
136
+ 512
137
+ ],
138
+ "kernel_size": 5,
139
+ "n_groups": 8,
140
+ "diffusion_step_embed_dim": 128,
141
+ "use_film_scale_modulation": true,
142
+ "noise_scheduler_type": "DDIM",
143
+ "num_train_timesteps": 100,
144
+ "beta_schedule": "squaredcos_cap_v2",
145
+ "beta_start": 0.0001,
146
+ "beta_end": 0.02,
147
+ "prediction_type": "epsilon",
148
+ "clip_sample": true,
149
+ "clip_sample_range": 1.0,
150
+ "num_inference_steps": 80,
151
+ "do_mask_loss_for_padding": false,
152
+ "optimizer_lr": 0.0001,
153
+ "optimizer_betas": [
154
+ 0.95,
155
+ 0.999
156
+ ],
157
+ "optimizer_eps": 1e-08,
158
+ "optimizer_weight_decay": 1e-06,
159
+ "scheduler_name": "cosine",
160
+ "scheduler_warmup_steps": 500
161
+ },
162
+ "act_loss_weight": 1.0,
163
+ "diffusion_loss_weight": 4.0,
164
+ "action_blend_alpha": 0.7
165
+ }
pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44e5cd4d3ced5152086cfe155ae093f89e25fa7ee5b33f426621c625a4673e4f
3
+ size 322278544
pretrained_model/train_config.json ADDED
@@ -0,0 +1,309 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "lerobot/aloha_sim_insertion_human",
4
+ "root": null,
5
+ "episodes": null,
6
+ "image_transforms": {
7
+ "enable": false,
8
+ "max_num_transforms": 3,
9
+ "random_order": false,
10
+ "tfs": {
11
+ "brightness": {
12
+ "weight": 1.0,
13
+ "type": "ColorJitter",
14
+ "kwargs": {
15
+ "brightness": [
16
+ 0.8,
17
+ 1.2
18
+ ]
19
+ }
20
+ },
21
+ "contrast": {
22
+ "weight": 1.0,
23
+ "type": "ColorJitter",
24
+ "kwargs": {
25
+ "contrast": [
26
+ 0.8,
27
+ 1.2
28
+ ]
29
+ }
30
+ },
31
+ "saturation": {
32
+ "weight": 1.0,
33
+ "type": "ColorJitter",
34
+ "kwargs": {
35
+ "saturation": [
36
+ 0.5,
37
+ 1.5
38
+ ]
39
+ }
40
+ },
41
+ "hue": {
42
+ "weight": 1.0,
43
+ "type": "ColorJitter",
44
+ "kwargs": {
45
+ "hue": [
46
+ -0.05,
47
+ 0.05
48
+ ]
49
+ }
50
+ },
51
+ "sharpness": {
52
+ "weight": 1.0,
53
+ "type": "SharpnessJitter",
54
+ "kwargs": {
55
+ "sharpness": [
56
+ 0.5,
57
+ 1.5
58
+ ]
59
+ }
60
+ }
61
+ }
62
+ },
63
+ "revision": null,
64
+ "use_imagenet_stats": true,
65
+ "video_backend": "pyav"
66
+ },
67
+ "env": {
68
+ "type": "aloha",
69
+ "task": "AlohaInsertion-v0",
70
+ "fps": 50,
71
+ "features": {
72
+ "action": {
73
+ "type": "ACTION",
74
+ "shape": [
75
+ 14
76
+ ]
77
+ },
78
+ "agent_pos": {
79
+ "type": "STATE",
80
+ "shape": [
81
+ 14
82
+ ]
83
+ },
84
+ "pixels/top": {
85
+ "type": "VISUAL",
86
+ "shape": [
87
+ 480,
88
+ 640,
89
+ 3
90
+ ]
91
+ }
92
+ },
93
+ "features_map": {
94
+ "action": "action",
95
+ "agent_pos": "observation.state",
96
+ "top": "observation.image.top",
97
+ "pixels/top": "observation.images.top"
98
+ },
99
+ "episode_length": 400,
100
+ "obs_type": "pixels_agent_pos",
101
+ "render_mode": "rgb_array"
102
+ },
103
+ "policy": {
104
+ "type": "hybrid",
105
+ "n_obs_steps": 1,
106
+ "normalization_mapping": {},
107
+ "input_features": {
108
+ "observation.images.top": {
109
+ "type": "VISUAL",
110
+ "shape": [
111
+ 3,
112
+ 480,
113
+ 640
114
+ ]
115
+ },
116
+ "observation.state": {
117
+ "type": "STATE",
118
+ "shape": [
119
+ 14
120
+ ]
121
+ }
122
+ },
123
+ "output_features": {
124
+ "action": {
125
+ "type": "ACTION",
126
+ "shape": [
127
+ 14
128
+ ]
129
+ }
130
+ },
131
+ "device": "cuda",
132
+ "use_amp": false,
133
+ "act_config": {
134
+ "type": "act",
135
+ "n_obs_steps": 2,
136
+ "normalization_mapping": {
137
+ "VISUAL": "MEAN_STD",
138
+ "STATE": "MEAN_STD",
139
+ "ACTION": "MEAN_STD"
140
+ },
141
+ "input_features": {
142
+ "observation.state": {
143
+ "type": "STATE",
144
+ "shape": [
145
+ 14
146
+ ]
147
+ },
148
+ "observation.images.top": {
149
+ "type": "VISUAL",
150
+ "shape": [
151
+ 3,
152
+ 480,
153
+ 640
154
+ ]
155
+ }
156
+ },
157
+ "output_features": {
158
+ "action": {
159
+ "type": "ACTION",
160
+ "shape": [
161
+ 14
162
+ ]
163
+ }
164
+ },
165
+ "device": "cuda",
166
+ "use_amp": false,
167
+ "chunk_size": 400,
168
+ "n_action_steps": 400,
169
+ "vision_backbone": "resnet18",
170
+ "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
171
+ "replace_final_stride_with_dilation": false,
172
+ "pre_norm": false,
173
+ "dim_model": 512,
174
+ "n_heads": 8,
175
+ "dim_feedforward": 3200,
176
+ "feedforward_activation": "relu",
177
+ "n_encoder_layers": 4,
178
+ "n_decoder_layers": 1,
179
+ "use_vae": true,
180
+ "latent_dim": 32,
181
+ "n_vae_encoder_layers": 4,
182
+ "temporal_ensemble_coeff": null,
183
+ "dropout": 0.1,
184
+ "kl_weight": 10.0,
185
+ "smoothness_weight": 0.0,
186
+ "smoothness_type": "velocity",
187
+ "optimizer_lr": 1e-05,
188
+ "optimizer_weight_decay": 0.0001,
189
+ "optimizer_lr_backbone": 1e-05
190
+ },
191
+ "diffusion_config": {
192
+ "type": "diffusion",
193
+ "n_obs_steps": 2,
194
+ "normalization_mapping": {
195
+ "VISUAL": "MEAN_STD",
196
+ "STATE": "MEAN_STD",
197
+ "ACTION": "MEAN_STD"
198
+ },
199
+ "input_features": {
200
+ "observation.state": {
201
+ "type": "STATE",
202
+ "shape": [
203
+ 14
204
+ ]
205
+ },
206
+ "observation.images.top": {
207
+ "type": "VISUAL",
208
+ "shape": [
209
+ 3,
210
+ 480,
211
+ 640
212
+ ]
213
+ }
214
+ },
215
+ "output_features": {
216
+ "action": {
217
+ "type": "ACTION",
218
+ "shape": [
219
+ 14
220
+ ]
221
+ }
222
+ },
223
+ "device": "cuda",
224
+ "use_amp": false,
225
+ "horizon": 16,
226
+ "n_action_steps": 1,
227
+ "drop_n_last_frames": 7,
228
+ "vision_backbone": "resnet18",
229
+ "crop_shape": null,
230
+ "crop_is_random": true,
231
+ "pretrained_backbone_weights": null,
232
+ "use_group_norm": true,
233
+ "spatial_softmax_num_keypoints": 32,
234
+ "use_separate_rgb_encoder_per_camera": false,
235
+ "down_dims": [
236
+ 128,
237
+ 256,
238
+ 512
239
+ ],
240
+ "kernel_size": 5,
241
+ "n_groups": 8,
242
+ "diffusion_step_embed_dim": 128,
243
+ "use_film_scale_modulation": true,
244
+ "noise_scheduler_type": "DDIM",
245
+ "num_train_timesteps": 100,
246
+ "beta_schedule": "squaredcos_cap_v2",
247
+ "beta_start": 0.0001,
248
+ "beta_end": 0.02,
249
+ "prediction_type": "epsilon",
250
+ "clip_sample": true,
251
+ "clip_sample_range": 1.0,
252
+ "num_inference_steps": 80,
253
+ "do_mask_loss_for_padding": false,
254
+ "optimizer_lr": 0.0001,
255
+ "optimizer_betas": [
256
+ 0.95,
257
+ 0.999
258
+ ],
259
+ "optimizer_eps": 1e-08,
260
+ "optimizer_weight_decay": 1e-06,
261
+ "scheduler_name": "cosine",
262
+ "scheduler_warmup_steps": 500
263
+ },
264
+ "act_loss_weight": 1.0,
265
+ "diffusion_loss_weight": 4.0,
266
+ "action_blend_alpha": 0.7
267
+ },
268
+ "output_dir": "/root/autodl-tmp/.autodl/output_hybrid",
269
+ "job_name": "aloha_hybrid",
270
+ "resume": true,
271
+ "seed": 1000,
272
+ "num_workers": 8,
273
+ "batch_size": 32,
274
+ "steps": 50000,
275
+ "eval_freq": 500000,
276
+ "log_freq": 400,
277
+ "save_checkpoint": true,
278
+ "save_freq": 10000,
279
+ "use_policy_training_preset": true,
280
+ "optimizer": {
281
+ "type": "adam",
282
+ "lr": 0.0001,
283
+ "weight_decay": 1e-06,
284
+ "grad_clip_norm": 10.0,
285
+ "betas": [
286
+ 0.95,
287
+ 0.999
288
+ ],
289
+ "eps": 1e-08
290
+ },
291
+ "scheduler": {
292
+ "type": "diffuser",
293
+ "num_warmup_steps": 500,
294
+ "name": "cosine"
295
+ },
296
+ "eval": {
297
+ "n_episodes": 50,
298
+ "batch_size": 50,
299
+ "use_async_envs": false
300
+ },
301
+ "wandb": {
302
+ "enable": true,
303
+ "disable_artifact": false,
304
+ "project": "hybrid_40k",
305
+ "entity": null,
306
+ "notes": null,
307
+ "run_id": "hybrid-resume-1-offline"
308
+ }
309
+ }
training_state/optimizer_param_groups.json ADDED
@@ -0,0 +1,393 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "initial_lr": 0.0001,
17
+ "params": [
18
+ 0,
19
+ 1,
20
+ 2,
21
+ 3,
22
+ 4,
23
+ 5,
24
+ 6,
25
+ 7,
26
+ 8,
27
+ 9,
28
+ 10,
29
+ 11,
30
+ 12,
31
+ 13,
32
+ 14,
33
+ 15,
34
+ 16,
35
+ 17,
36
+ 18,
37
+ 19,
38
+ 20,
39
+ 21,
40
+ 22,
41
+ 23,
42
+ 24,
43
+ 25,
44
+ 26,
45
+ 27,
46
+ 28,
47
+ 29,
48
+ 30,
49
+ 31,
50
+ 32,
51
+ 33,
52
+ 34,
53
+ 35,
54
+ 36,
55
+ 37,
56
+ 38,
57
+ 39,
58
+ 40,
59
+ 41,
60
+ 42,
61
+ 43,
62
+ 44,
63
+ 45,
64
+ 46,
65
+ 47,
66
+ 48,
67
+ 49,
68
+ 50,
69
+ 51,
70
+ 52,
71
+ 53,
72
+ 54,
73
+ 55,
74
+ 56,
75
+ 57,
76
+ 58,
77
+ 59,
78
+ 60,
79
+ 61,
80
+ 62,
81
+ 63,
82
+ 64,
83
+ 65,
84
+ 66,
85
+ 67,
86
+ 68,
87
+ 69,
88
+ 70,
89
+ 71,
90
+ 72,
91
+ 73,
92
+ 74,
93
+ 75,
94
+ 76,
95
+ 77,
96
+ 78,
97
+ 79,
98
+ 80,
99
+ 81,
100
+ 82,
101
+ 83,
102
+ 84,
103
+ 85,
104
+ 86,
105
+ 87,
106
+ 88,
107
+ 89,
108
+ 90,
109
+ 91,
110
+ 92,
111
+ 93,
112
+ 94,
113
+ 95,
114
+ 96,
115
+ 97,
116
+ 98,
117
+ 99,
118
+ 100,
119
+ 101,
120
+ 102,
121
+ 103,
122
+ 104,
123
+ 105,
124
+ 106,
125
+ 107,
126
+ 108,
127
+ 109,
128
+ 110,
129
+ 111,
130
+ 112,
131
+ 113,
132
+ 114,
133
+ 115,
134
+ 116,
135
+ 117,
136
+ 118,
137
+ 119,
138
+ 120,
139
+ 121,
140
+ 122,
141
+ 123,
142
+ 124,
143
+ 125,
144
+ 126,
145
+ 127,
146
+ 128,
147
+ 129,
148
+ 130,
149
+ 131,
150
+ 132,
151
+ 133,
152
+ 134,
153
+ 135,
154
+ 136,
155
+ 137,
156
+ 138,
157
+ 139,
158
+ 140,
159
+ 141,
160
+ 142,
161
+ 143,
162
+ 144,
163
+ 145,
164
+ 146,
165
+ 147,
166
+ 148,
167
+ 149,
168
+ 150,
169
+ 151,
170
+ 152,
171
+ 153,
172
+ 154,
173
+ 155,
174
+ 156,
175
+ 157,
176
+ 158,
177
+ 159,
178
+ 160,
179
+ 161,
180
+ 162,
181
+ 163,
182
+ 164,
183
+ 165,
184
+ 166,
185
+ 167,
186
+ 168,
187
+ 169,
188
+ 170,
189
+ 171,
190
+ 172,
191
+ 173,
192
+ 174,
193
+ 175,
194
+ 176,
195
+ 177,
196
+ 178,
197
+ 179,
198
+ 180,
199
+ 181,
200
+ 182,
201
+ 183,
202
+ 184,
203
+ 185,
204
+ 186,
205
+ 187,
206
+ 188,
207
+ 189,
208
+ 190,
209
+ 191,
210
+ 192,
211
+ 193,
212
+ 194,
213
+ 195,
214
+ 196,
215
+ 197,
216
+ 198,
217
+ 199,
218
+ 200,
219
+ 201,
220
+ 202,
221
+ 203,
222
+ 204,
223
+ 205,
224
+ 206,
225
+ 207,
226
+ 208,
227
+ 209,
228
+ 210,
229
+ 211,
230
+ 212,
231
+ 213,
232
+ 214,
233
+ 215,
234
+ 216,
235
+ 217,
236
+ 218,
237
+ 219,
238
+ 220,
239
+ 221,
240
+ 222,
241
+ 223,
242
+ 224,
243
+ 225,
244
+ 226,
245
+ 227,
246
+ 228,
247
+ 229,
248
+ 230,
249
+ 231,
250
+ 232,
251
+ 233,
252
+ 234,
253
+ 235,
254
+ 236,
255
+ 237,
256
+ 238,
257
+ 239,
258
+ 240,
259
+ 241,
260
+ 242,
261
+ 243,
262
+ 244,
263
+ 245,
264
+ 246,
265
+ 247,
266
+ 248,
267
+ 249,
268
+ 250,
269
+ 251,
270
+ 252,
271
+ 253,
272
+ 254,
273
+ 255,
274
+ 256,
275
+ 257,
276
+ 258,
277
+ 259,
278
+ 260,
279
+ 261,
280
+ 262,
281
+ 263,
282
+ 264,
283
+ 265,
284
+ 266,
285
+ 267,
286
+ 268,
287
+ 269,
288
+ 270,
289
+ 271,
290
+ 272,
291
+ 273,
292
+ 274,
293
+ 275,
294
+ 276,
295
+ 277,
296
+ 278,
297
+ 279,
298
+ 280,
299
+ 281,
300
+ 282,
301
+ 283,
302
+ 284,
303
+ 285,
304
+ 286,
305
+ 287,
306
+ 288,
307
+ 289,
308
+ 290,
309
+ 291,
310
+ 292,
311
+ 293,
312
+ 294,
313
+ 295,
314
+ 296,
315
+ 297,
316
+ 298,
317
+ 299,
318
+ 300,
319
+ 301,
320
+ 302,
321
+ 303,
322
+ 304,
323
+ 305,
324
+ 306,
325
+ 307,
326
+ 308,
327
+ 309,
328
+ 310,
329
+ 311,
330
+ 312,
331
+ 313,
332
+ 314,
333
+ 315,
334
+ 316,
335
+ 317,
336
+ 318,
337
+ 319,
338
+ 320,
339
+ 321,
340
+ 322,
341
+ 323,
342
+ 324,
343
+ 325,
344
+ 326,
345
+ 327,
346
+ 328,
347
+ 329,
348
+ 330,
349
+ 331,
350
+ 332,
351
+ 333,
352
+ 334,
353
+ 335,
354
+ 336,
355
+ 337,
356
+ 338,
357
+ 339,
358
+ 340,
359
+ 341,
360
+ 342,
361
+ 343,
362
+ 344,
363
+ 345,
364
+ 346,
365
+ 347,
366
+ 348,
367
+ 349,
368
+ 350,
369
+ 351,
370
+ 352,
371
+ 353,
372
+ 354,
373
+ 355,
374
+ 356,
375
+ 357,
376
+ 358,
377
+ 359,
378
+ 360,
379
+ 361,
380
+ 362,
381
+ 363,
382
+ 364,
383
+ 365,
384
+ 366,
385
+ 367,
386
+ 368,
387
+ 369,
388
+ 370,
389
+ 371,
390
+ 372
391
+ ]
392
+ }
393
+ ]
training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d6f3551aa2aead0447ecde84216998b6dbc3a5a6cc16c374ef04d6b1298b541
3
+ size 642741164
training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d626c32386456bc23d9dc051f23623fa38f8b9a03e53966686f49f6a885eb238
3
+ size 15708
training_state/scheduler_state.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_lrs": [
3
+ 0.0001
4
+ ],
5
+ "last_epoch": 50000,
6
+ "verbose": false,
7
+ "_step_count": 50001,
8
+ "_get_lr_called_within_step": false,
9
+ "_last_lr": [
10
+ 0.0
11
+ ],
12
+ "lr_lambdas": [
13
+ null
14
+ ]
15
+ }
training_state/training_step.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "step": 50000
3
+ }