Hugging Face's logo

AriRyo
/
blockpick_gray_xvla_96

Robotics
LeRobot
Safetensors
xvla
Model card Files
xet
 Community
AriRyo commited on
Commit
ebdcbfd
·
verified ·
1 Parent(s): 59722f2

upload blockpick_gray_xvla_96 step 004000

Browse files
Files changed (12) hide show
  1. checkpoints/004000/pretrained_model/config.json +222 -0
  2. checkpoints/004000/pretrained_model/model.safetensors +3 -0
  3. checkpoints/004000/pretrained_model/policy_postprocessor.json +32 -0
  4. checkpoints/004000/pretrained_model/policy_postprocessor_step_0_unnormalizer_processor.safetensors +3 -0
  5. checkpoints/004000/pretrained_model/policy_preprocessor.json +105 -0
  6. checkpoints/004000/pretrained_model/policy_preprocessor_step_7_normalizer_processor.safetensors +3 -0
  7. checkpoints/004000/pretrained_model/train_config.json +462 -0
  8. checkpoints/004000/training_state/optimizer_param_groups.json +963 -0
  9. checkpoints/004000/training_state/optimizer_state.safetensors +3 -0
  10. checkpoints/004000/training_state/rng_state.safetensors +3 -0
  11. checkpoints/004000/training_state/scheduler_state.json +21 -0
  12. checkpoints/004000/training_state/training_step.json +3 -0
checkpoints/004000/pretrained_model/config.json ADDED
@@ -0,0 +1,222 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "xvla",
3
+ "n_obs_steps": 1,
4
+ "input_features": {
5
+ "observation.images.image": {
6
+ "type": "VISUAL",
7
+ "shape": [
8
+ 3,
9
+ 256,
10
+ 256
11
+ ]
12
+ },
13
+ "observation.images.image2": {
14
+ "type": "VISUAL",
15
+ "shape": [
16
+ 3,
17
+ 256,
18
+ 256
19
+ ]
20
+ },
21
+ "observation.state": {
22
+ "type": "STATE",
23
+ "shape": [
24
+ 8
25
+ ]
26
+ },
27
+ "observation.images.image3": {
28
+ "type": "VISUAL",
29
+ "shape": [
30
+ 3,
31
+ 224,
32
+ 224
33
+ ]
34
+ }
35
+ },
36
+ "output_features": {
37
+ "action": {
38
+ "type": "ACTION",
39
+ "shape": [
40
+ 6
41
+ ]
42
+ }
43
+ },
44
+ "device": "cuda",
45
+ "use_amp": false,
46
+ "use_peft": false,
47
+ "push_to_hub": true,
48
+ "repo_id": "AriRyo/blockpick_gray_xvla_96",
49
+ "private": null,
50
+ "tags": null,
51
+ "license": null,
52
+ "pretrained_path": "lerobot/xvla-base",
53
+ "chunk_size": 30,
54
+ "n_action_steps": 30,
55
+ "dtype": "bfloat16",
56
+ "normalization_mapping": {
57
+ "STATE": "IDENTITY",
58
+ "ACTION": "MEAN_STD",
59
+ "VISUAL": "IDENTITY"
60
+ },
61
+ "florence_config": {
62
+ "model_type": "florence2",
63
+ "bos_token_id": 0,
64
+ "eos_token_id": 2,
65
+ "ignore_index": -100,
66
+ "pad_token_id": 1,
67
+ "projection_dim": 1024,
68
+ "text_config": {
69
+ "vocab_size": 51289,
70
+ "activation_dropout": 0.1,
71
+ "activation_function": "gelu",
72
+ "add_bias_logits": false,
73
+ "add_final_layer_norm": false,
74
+ "attention_dropout": 0.1,
75
+ "bos_token_id": 0,
76
+ "classif_dropout": 0.1,
77
+ "classifier_dropout": 0.0,
78
+ "d_model": 1024,
79
+ "decoder_attention_heads": 16,
80
+ "decoder_ffn_dim": 4096,
81
+ "decoder_layerdrop": 0.0,
82
+ "decoder_layers": 12,
83
+ "decoder_start_token_id": 2,
84
+ "dropout": 0.1,
85
+ "early_stopping": true,
86
+ "encoder_attention_heads": 16,
87
+ "encoder_ffn_dim": 4096,
88
+ "encoder_layerdrop": 0.0,
89
+ "encoder_layers": 12,
90
+ "eos_token_id": 2,
91
+ "forced_eos_token_id": 2,
92
+ "forced_bos_token_id": 0,
93
+ "gradient_checkpointing": false,
94
+ "init_std": 0.02,
95
+ "is_encoder_decoder": true,
96
+ "label2id": {
97
+ "LABEL_0": 0,
98
+ "LABEL_1": 1,
99
+ "LABEL_2": 2
100
+ },
101
+ "max_position_embeddings": 4096,
102
+ "no_repeat_ngram_size": 3,
103
+ "normalize_before": false,
104
+ "num_hidden_layers": 12,
105
+ "pad_token_id": 1,
106
+ "scale_embedding": false,
107
+ "num_beams": 3
108
+ },
109
+ "vision_config": {
110
+ "model_type": "davit",
111
+ "drop_path_rate": 0.1,
112
+ "patch_size": [
113
+ 7,
114
+ 3,
115
+ 3,
116
+ 3
117
+ ],
118
+ "patch_stride": [
119
+ 4,
120
+ 2,
121
+ 2,
122
+ 2
123
+ ],
124
+ "patch_padding": [
125
+ 3,
126
+ 1,
127
+ 1,
128
+ 1
129
+ ],
130
+ "patch_prenorm": [
131
+ false,
132
+ true,
133
+ true,
134
+ true
135
+ ],
136
+ "enable_checkpoint": false,
137
+ "dim_embed": [
138
+ 256,
139
+ 512,
140
+ 1024,
141
+ 2048
142
+ ],
143
+ "num_heads": [
144
+ 8,
145
+ 16,
146
+ 32,
147
+ 64
148
+ ],
149
+ "num_groups": [
150
+ 8,
151
+ 16,
152
+ 32,
153
+ 64
154
+ ],
155
+ "depths": [
156
+ 1,
157
+ 1,
158
+ 9,
159
+ 1
160
+ ],
161
+ "window_size": 12,
162
+ "projection_dim": 1024,
163
+ "visual_temporal_embedding": {
164
+ "type": "COSINE",
165
+ "max_temporal_embeddings": 100
166
+ },
167
+ "image_pos_embed": {
168
+ "type": "learned_abs_2d",
169
+ "max_pos_embeddings": 50
170
+ },
171
+ "image_feature_source": [
172
+ "spatial_avg_pool",
173
+ "temporal_avg_pool"
174
+ ]
175
+ },
176
+ "vocab_size": 51289,
177
+ "torch_dtype": "float32",
178
+ "is_encoder_decoder": true
179
+ },
180
+ "tokenizer_name": "facebook/bart-large",
181
+ "tokenizer_max_length": 1024,
182
+ "tokenizer_padding_side": "right",
183
+ "pad_language_to": "max_length",
184
+ "hidden_size": 1024,
185
+ "depth": 24,
186
+ "num_heads": 16,
187
+ "mlp_ratio": 4.0,
188
+ "num_domains": 30,
189
+ "len_soft_prompts": 32,
190
+ "dim_time": 32,
191
+ "max_len_seq": 512,
192
+ "use_hetero_proj": false,
193
+ "action_mode": "auto",
194
+ "num_denoising_steps": 10,
195
+ "use_proprio": true,
196
+ "max_state_dim": 20,
197
+ "max_action_dim": 20,
198
+ "domain_feature_key": null,
199
+ "resize_imgs_with_padding": [
200
+ 224,
201
+ 224
202
+ ],
203
+ "num_image_views": 3,
204
+ "empty_cameras": 0,
205
+ "freeze_vision_encoder": false,
206
+ "freeze_language_encoder": false,
207
+ "train_policy_transformer": true,
208
+ "train_soft_prompts": true,
209
+ "optimizer_lr": 0.0001,
210
+ "optimizer_betas": [
211
+ 0.9,
212
+ 0.95
213
+ ],
214
+ "optimizer_eps": 1e-08,
215
+ "optimizer_weight_decay": 0.0001,
216
+ "optimizer_grad_clip_norm": 10.0,
217
+ "optimizer_soft_prompt_lr_scale": 1.0,
218
+ "optimizer_soft_prompt_warmup_lr_scale": null,
219
+ "scheduler_warmup_steps": 1000,
220
+ "scheduler_decay_steps": 30000,
221
+ "scheduler_decay_lr": 2.5e-06
222
+ }
checkpoints/004000/pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66e4a8020cb4a68a3e5b6212184eb3076c3c1d48db4b7d9dd6c26514e6246e05
3
+ size 1759596986
checkpoints/004000/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
+ "STATE": "IDENTITY",
18
+ "ACTION": "MEAN_STD",
19
+ "VISUAL": "IDENTITY"
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/004000/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/004000/pretrained_model/policy_preprocessor.json ADDED
@@ -0,0 +1,105 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "policy_preprocessor",
3
+ "steps": [
4
+ {
5
+ "registry_name": "rename_observations_processor",
6
+ "config": {
7
+ "rename_map": {
8
+ "observation.images.above": "observation.images.image",
9
+ "observation.images.side": "observation.images.image2"
10
+ }
11
+ }
12
+ },
13
+ {
14
+ "registry_name": "to_batch_processor",
15
+ "config": {}
16
+ },
17
+ {
18
+ "registry_name": "tokenizer_processor",
19
+ "config": {
20
+ "max_length": 50,
21
+ "task_key": "task",
22
+ "padding_side": "right",
23
+ "padding": "max_length",
24
+ "truncation": true,
25
+ "tokenizer_name": "facebook/bart-large"
26
+ }
27
+ },
28
+ {
29
+ "registry_name": "xvla_add_domain_id",
30
+ "config": {
31
+ "domain_id": 0
32
+ }
33
+ },
34
+ {
35
+ "registry_name": "xvla_image_to_float",
36
+ "config": {
37
+ "image_keys": null,
38
+ "validate_range": true
39
+ }
40
+ },
41
+ {
42
+ "registry_name": "xvla_imagenet_normalize",
43
+ "config": {
44
+ "image_keys": null
45
+ }
46
+ },
47
+ {
48
+ "registry_name": "device_processor",
49
+ "config": {
50
+ "device": "cuda",
51
+ "float_dtype": null
52
+ }
53
+ },
54
+ {
55
+ "registry_name": "normalizer_processor",
56
+ "config": {
57
+ "eps": 1e-08,
58
+ "features": {
59
+ "observation.images.image": {
60
+ "type": "VISUAL",
61
+ "shape": [
62
+ 3,
63
+ 256,
64
+ 256
65
+ ]
66
+ },
67
+ "observation.images.image2": {
68
+ "type": "VISUAL",
69
+ "shape": [
70
+ 3,
71
+ 256,
72
+ 256
73
+ ]
74
+ },
75
+ "observation.state": {
76
+ "type": "STATE",
77
+ "shape": [
78
+ 8
79
+ ]
80
+ },
81
+ "observation.images.image3": {
82
+ "type": "VISUAL",
83
+ "shape": [
84
+ 3,
85
+ 224,
86
+ 224
87
+ ]
88
+ },
89
+ "action": {
90
+ "type": "ACTION",
91
+ "shape": [
92
+ 6
93
+ ]
94
+ }
95
+ },
96
+ "norm_map": {
97
+ "STATE": "IDENTITY",
98
+ "ACTION": "MEAN_STD",
99
+ "VISUAL": "IDENTITY"
100
+ }
101
+ },
102
+ "state_file": "policy_preprocessor_step_7_normalizer_processor.safetensors"
103
+ }
104
+ ]
105
+ }
checkpoints/004000/pretrained_model/policy_preprocessor_step_7_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/004000/pretrained_model/train_config.json ADDED
@@ -0,0 +1,462 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ 48,
55
+ 49,
56
+ 50,
57
+ 51,
58
+ 52,
59
+ 53,
60
+ 54,
61
+ 55,
62
+ 56,
63
+ 57,
64
+ 58,
65
+ 59,
66
+ 60,
67
+ 61,
68
+ 62,
69
+ 63,
70
+ 64,
71
+ 65,
72
+ 66,
73
+ 67,
74
+ 68,
75
+ 69,
76
+ 70,
77
+ 71,
78
+ 72,
79
+ 73,
80
+ 74,
81
+ 75,
82
+ 76,
83
+ 77,
84
+ 78,
85
+ 79,
86
+ 80,
87
+ 81,
88
+ 82,
89
+ 83,
90
+ 84,
91
+ 85,
92
+ 86,
93
+ 87,
94
+ 88,
95
+ 89,
96
+ 90,
97
+ 91,
98
+ 92,
99
+ 93,
100
+ 94,
101
+ 95
102
+ ],
103
+ "image_transforms": {
104
+ "enable": false,
105
+ "max_num_transforms": 3,
106
+ "random_order": false,
107
+ "tfs": {
108
+ "brightness": {
109
+ "weight": 1.0,
110
+ "type": "ColorJitter",
111
+ "kwargs": {
112
+ "brightness": [
113
+ 0.8,
114
+ 1.2
115
+ ]
116
+ }
117
+ },
118
+ "contrast": {
119
+ "weight": 1.0,
120
+ "type": "ColorJitter",
121
+ "kwargs": {
122
+ "contrast": [
123
+ 0.8,
124
+ 1.2
125
+ ]
126
+ }
127
+ },
128
+ "saturation": {
129
+ "weight": 1.0,
130
+ "type": "ColorJitter",
131
+ "kwargs": {
132
+ "saturation": [
133
+ 0.5,
134
+ 1.5
135
+ ]
136
+ }
137
+ },
138
+ "hue": {
139
+ "weight": 1.0,
140
+ "type": "ColorJitter",
141
+ "kwargs": {
142
+ "hue": [
143
+ -0.05,
144
+ 0.05
145
+ ]
146
+ }
147
+ },
148
+ "sharpness": {
149
+ "weight": 1.0,
150
+ "type": "SharpnessJitter",
151
+ "kwargs": {
152
+ "sharpness": [
153
+ 0.5,
154
+ 1.5
155
+ ]
156
+ }
157
+ },
158
+ "affine": {
159
+ "weight": 1.0,
160
+ "type": "RandomAffine",
161
+ "kwargs": {
162
+ "degrees": [
163
+ -5.0,
164
+ 5.0
165
+ ],
166
+ "translate": [
167
+ 0.05,
168
+ 0.05
169
+ ]
170
+ }
171
+ }
172
+ }
173
+ },
174
+ "revision": null,
175
+ "use_imagenet_stats": true,
176
+ "video_backend": "torchcodec",
177
+ "streaming": false
178
+ },
179
+ "env": null,
180
+ "policy": {
181
+ "type": "xvla",
182
+ "n_obs_steps": 1,
183
+ "input_features": {
184
+ "observation.images.image": {
185
+ "type": "VISUAL",
186
+ "shape": [
187
+ 3,
188
+ 256,
189
+ 256
190
+ ]
191
+ },
192
+ "observation.images.image2": {
193
+ "type": "VISUAL",
194
+ "shape": [
195
+ 3,
196
+ 256,
197
+ 256
198
+ ]
199
+ },
200
+ "observation.state": {
201
+ "type": "STATE",
202
+ "shape": [
203
+ 8
204
+ ]
205
+ },
206
+ "observation.images.image3": {
207
+ "type": "VISUAL",
208
+ "shape": [
209
+ 3,
210
+ 224,
211
+ 224
212
+ ]
213
+ }
214
+ },
215
+ "output_features": {
216
+ "action": {
217
+ "type": "ACTION",
218
+ "shape": [
219
+ 6
220
+ ]
221
+ }
222
+ },
223
+ "device": "cuda",
224
+ "use_amp": false,
225
+ "use_peft": false,
226
+ "push_to_hub": true,
227
+ "repo_id": "AriRyo/blockpick_gray_xvla_96",
228
+ "private": null,
229
+ "tags": null,
230
+ "license": null,
231
+ "pretrained_path": "lerobot/xvla-base",
232
+ "chunk_size": 30,
233
+ "n_action_steps": 30,
234
+ "dtype": "bfloat16",
235
+ "normalization_mapping": {
236
+ "STATE": "IDENTITY",
237
+ "ACTION": "MEAN_STD",
238
+ "VISUAL": "IDENTITY"
239
+ },
240
+ "florence_config": {
241
+ "model_type": "florence2",
242
+ "bos_token_id": 0,
243
+ "eos_token_id": 2,
244
+ "ignore_index": -100,
245
+ "pad_token_id": 1,
246
+ "projection_dim": 1024,
247
+ "text_config": {
248
+ "vocab_size": 51289,
249
+ "activation_dropout": 0.1,
250
+ "activation_function": "gelu",
251
+ "add_bias_logits": false,
252
+ "add_final_layer_norm": false,
253
+ "attention_dropout": 0.1,
254
+ "bos_token_id": 0,
255
+ "classif_dropout": 0.1,
256
+ "classifier_dropout": 0.0,
257
+ "d_model": 1024,
258
+ "decoder_attention_heads": 16,
259
+ "decoder_ffn_dim": 4096,
260
+ "decoder_layerdrop": 0.0,
261
+ "decoder_layers": 12,
262
+ "decoder_start_token_id": 2,
263
+ "dropout": 0.1,
264
+ "early_stopping": true,
265
+ "encoder_attention_heads": 16,
266
+ "encoder_ffn_dim": 4096,
267
+ "encoder_layerdrop": 0.0,
268
+ "encoder_layers": 12,
269
+ "eos_token_id": 2,
270
+ "forced_eos_token_id": 2,
271
+ "forced_bos_token_id": 0,
272
+ "gradient_checkpointing": false,
273
+ "init_std": 0.02,
274
+ "is_encoder_decoder": true,
275
+ "label2id": {
276
+ "LABEL_0": 0,
277
+ "LABEL_1": 1,
278
+ "LABEL_2": 2
279
+ },
280
+ "max_position_embeddings": 4096,
281
+ "no_repeat_ngram_size": 3,
282
+ "normalize_before": false,
283
+ "num_hidden_layers": 12,
284
+ "pad_token_id": 1,
285
+ "scale_embedding": false,
286
+ "num_beams": 3
287
+ },
288
+ "vision_config": {
289
+ "model_type": "davit",
290
+ "drop_path_rate": 0.1,
291
+ "patch_size": [
292
+ 7,
293
+ 3,
294
+ 3,
295
+ 3
296
+ ],
297
+ "patch_stride": [
298
+ 4,
299
+ 2,
300
+ 2,
301
+ 2
302
+ ],
303
+ "patch_padding": [
304
+ 3,
305
+ 1,
306
+ 1,
307
+ 1
308
+ ],
309
+ "patch_prenorm": [
310
+ false,
311
+ true,
312
+ true,
313
+ true
314
+ ],
315
+ "enable_checkpoint": false,
316
+ "dim_embed": [
317
+ 256,
318
+ 512,
319
+ 1024,
320
+ 2048
321
+ ],
322
+ "num_heads": [
323
+ 8,
324
+ 16,
325
+ 32,
326
+ 64
327
+ ],
328
+ "num_groups": [
329
+ 8,
330
+ 16,
331
+ 32,
332
+ 64
333
+ ],
334
+ "depths": [
335
+ 1,
336
+ 1,
337
+ 9,
338
+ 1
339
+ ],
340
+ "window_size": 12,
341
+ "projection_dim": 1024,
342
+ "visual_temporal_embedding": {
343
+ "type": "COSINE",
344
+ "max_temporal_embeddings": 100
345
+ },
346
+ "image_pos_embed": {
347
+ "type": "learned_abs_2d",
348
+ "max_pos_embeddings": 50
349
+ },
350
+ "image_feature_source": [
351
+ "spatial_avg_pool",
352
+ "temporal_avg_pool"
353
+ ]
354
+ },
355
+ "vocab_size": 51289,
356
+ "torch_dtype": "float32",
357
+ "is_encoder_decoder": true
358
+ },
359
+ "tokenizer_name": "facebook/bart-large",
360
+ "tokenizer_max_length": 1024,
361
+ "tokenizer_padding_side": "right",
362
+ "pad_language_to": "max_length",
363
+ "hidden_size": 1024,
364
+ "depth": 24,
365
+ "num_heads": 16,
366
+ "mlp_ratio": 4.0,
367
+ "num_domains": 30,
368
+ "len_soft_prompts": 32,
369
+ "dim_time": 32,
370
+ "max_len_seq": 512,
371
+ "use_hetero_proj": false,
372
+ "action_mode": "auto",
373
+ "num_denoising_steps": 10,
374
+ "use_proprio": true,
375
+ "max_state_dim": 20,
376
+ "max_action_dim": 20,
377
+ "domain_feature_key": null,
378
+ "resize_imgs_with_padding": [
379
+ 224,
380
+ 224
381
+ ],
382
+ "num_image_views": 3,
383
+ "empty_cameras": 0,
384
+ "freeze_vision_encoder": false,
385
+ "freeze_language_encoder": false,
386
+ "train_policy_transformer": true,
387
+ "train_soft_prompts": true,
388
+ "optimizer_lr": 0.0001,
389
+ "optimizer_betas": [
390
+ 0.9,
391
+ 0.95
392
+ ],
393
+ "optimizer_eps": 1e-08,
394
+ "optimizer_weight_decay": 0.0001,
395
+ "optimizer_grad_clip_norm": 10.0,
396
+ "optimizer_soft_prompt_lr_scale": 1.0,
397
+ "optimizer_soft_prompt_warmup_lr_scale": null,
398
+ "scheduler_warmup_steps": 1000,
399
+ "scheduler_decay_steps": 30000,
400
+ "scheduler_decay_lr": 2.5e-06
401
+ },
402
+ "output_dir": "outputs/train/blockpick_gray_xvla_96",
403
+ "job_name": "blockpick_gray_xvla_96",
404
+ "resume": false,
405
+ "seed": 1000,
406
+ "cudnn_deterministic": false,
407
+ "num_workers": 4,
408
+ "batch_size": 8,
409
+ "steps": 6000,
410
+ "eval_freq": 20000,
411
+ "log_freq": 200,
412
+ "tolerance_s": 0.0001,
413
+ "save_checkpoint": true,
414
+ "save_freq": 1000,
415
+ "use_policy_training_preset": true,
416
+ "optimizer": {
417
+ "type": "xvla-adamw",
418
+ "lr": 0.0001,
419
+ "weight_decay": 0.0001,
420
+ "grad_clip_norm": 10.0,
421
+ "betas": [
422
+ 0.9,
423
+ 0.95
424
+ ],
425
+ "eps": 1e-08,
426
+ "soft_prompt_lr_scale": 1.0,
427
+ "soft_prompt_warmup_lr_scale": null
428
+ },
429
+ "scheduler": {
430
+ "type": "cosine_decay_with_warmup",
431
+ "num_warmup_steps": 1000,
432
+ "num_decay_steps": 30000,
433
+ "peak_lr": 0.0001,
434
+ "decay_lr": 2.5e-06
435
+ },
436
+ "eval": {
437
+ "n_episodes": 50,
438
+ "batch_size": 50,
439
+ "use_async_envs": false
440
+ },
441
+ "wandb": {
442
+ "enable": true,
443
+ "disable_artifact": true,
444
+ "project": "lerobot",
445
+ "entity": null,
446
+ "notes": null,
447
+ "run_id": "wh116ba6",
448
+ "mode": null,
449
+ "add_tags": true
450
+ },
451
+ "peft": null,
452
+ "use_rabc": false,
453
+ "rabc_progress_path": null,
454
+ "rabc_kappa": 0.01,
455
+ "rabc_epsilon": 1e-06,
456
+ "rabc_head_mode": "sparse",
457
+ "rename_map": {
458
+ "observation.images.above": "observation.images.image",
459
+ "observation.images.side": "observation.images.image2"
460
+ },
461
+ "checkpoint_path": null
462
+ }
checkpoints/004000/training_state/optimizer_param_groups.json ADDED
@@ -0,0 +1,963 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "lr": 2.6875000000000014e-06,
4
+ "weight_decay": 1e-05,
5
+ "name": "vlm",
6
+ "betas": [
7
+ 0.9,
8
+ 0.95
9
+ ],
10
+ "eps": 1e-08,
11
+ "amsgrad": false,
12
+ "maximize": false,
13
+ "foreach": null,
14
+ "capturable": false,
15
+ "differentiable": false,
16
+ "fused": null,
17
+ "decoupled_weight_decay": true,
18
+ "initial_lr": 1e-05,
19
+ "params": [
20
+ 0,
21
+ 1,
22
+ 2,
23
+ 3,
24
+ 4,
25
+ 5,
26
+ 6,
27
+ 7,
28
+ 8,
29
+ 9,
30
+ 10,
31
+ 11,
32
+ 12,
33
+ 13,
34
+ 14,
35
+ 15,
36
+ 16,
37
+ 17,
38
+ 18,
39
+ 19,
40
+ 20,
41
+ 21,
42
+ 22,
43
+ 23,
44
+ 24,
45
+ 25,
46
+ 26,
47
+ 27,
48
+ 28,
49
+ 29,
50
+ 30,
51
+ 31,
52
+ 32,
53
+ 33,
54
+ 34,
55
+ 35,
56
+ 36,
57
+ 37,
58
+ 38,
59
+ 39,
60
+ 40,
61
+ 41,
62
+ 42,
63
+ 43,
64
+ 44,
65
+ 45,
66
+ 46,
67
+ 47,
68
+ 48,
69
+ 49,
70
+ 50,
71
+ 51,
72
+ 52,
73
+ 53,
74
+ 54,
75
+ 55,
76
+ 56,
77
+ 57,
78
+ 58,
79
+ 59,
80
+ 60,
81
+ 61,
82
+ 62,
83
+ 63,
84
+ 64,
85
+ 65,
86
+ 66,
87
+ 67,
88
+ 68,
89
+ 69,
90
+ 70,
91
+ 71,
92
+ 72,
93
+ 73,
94
+ 74,
95
+ 75,
96
+ 76,
97
+ 77,
98
+ 78,
99
+ 79,
100
+ 80,
101
+ 81,
102
+ 82,
103
+ 83,
104
+ 84,
105
+ 85,
106
+ 86,
107
+ 87,
108
+ 88,
109
+ 89,
110
+ 90,
111
+ 91,
112
+ 92,
113
+ 93,
114
+ 94,
115
+ 95,
116
+ 96,
117
+ 97,
118
+ 98,
119
+ 99,
120
+ 100,
121
+ 101,
122
+ 102,
123
+ 103,
124
+ 104,
125
+ 105,
126
+ 106,
127
+ 107,
128
+ 108,
129
+ 109,
130
+ 110,
131
+ 111,
132
+ 112,
133
+ 113,
134
+ 114,
135
+ 115,
136
+ 116,
137
+ 117,
138
+ 118,
139
+ 119,
140
+ 120,
141
+ 121,
142
+ 122,
143
+ 123,
144
+ 124,
145
+ 125,
146
+ 126,
147
+ 127,
148
+ 128,
149
+ 129,
150
+ 130,
151
+ 131,
152
+ 132,
153
+ 133,
154
+ 134,
155
+ 135,
156
+ 136,
157
+ 137,
158
+ 138,
159
+ 139,
160
+ 140,
161
+ 141,
162
+ 142,
163
+ 143,
164
+ 144,
165
+ 145,
166
+ 146,
167
+ 147,
168
+ 148,
169
+ 149,
170
+ 150,
171
+ 151,
172
+ 152,
173
+ 153,
174
+ 154,
175
+ 155,
176
+ 156,
177
+ 157,
178
+ 158,
179
+ 159,
180
+ 160,
181
+ 161,
182
+ 162,
183
+ 163,
184
+ 164,
185
+ 165,
186
+ 166,
187
+ 167,
188
+ 168,
189
+ 169,
190
+ 170,
191
+ 171,
192
+ 172,
193
+ 173,
194
+ 174,
195
+ 175,
196
+ 176,
197
+ 177,
198
+ 178,
199
+ 179,
200
+ 180,
201
+ 181,
202
+ 182,
203
+ 183,
204
+ 184,
205
+ 185,
206
+ 186,
207
+ 187,
208
+ 188,
209
+ 189,
210
+ 190,
211
+ 191,
212
+ 192,
213
+ 193,
214
+ 194,
215
+ 195,
216
+ 196,
217
+ 197,
218
+ 198,
219
+ 199,
220
+ 200,
221
+ 201,
222
+ 202,
223
+ 203,
224
+ 204,
225
+ 205,
226
+ 206,
227
+ 207,
228
+ 208,
229
+ 209,
230
+ 210,
231
+ 211,
232
+ 212,
233
+ 213,
234
+ 214,
235
+ 215,
236
+ 216,
237
+ 217,
238
+ 218,
239
+ 219,
240
+ 220,
241
+ 221,
242
+ 222,
243
+ 223,
244
+ 224,
245
+ 225,
246
+ 226,
247
+ 227,
248
+ 228,
249
+ 229,
250
+ 230,
251
+ 231,
252
+ 232,
253
+ 233,
254
+ 234,
255
+ 235,
256
+ 236,
257
+ 237,
258
+ 238,
259
+ 239,
260
+ 240,
261
+ 241,
262
+ 242,
263
+ 243,
264
+ 244,
265
+ 245,
266
+ 246,
267
+ 247,
268
+ 248,
269
+ 249,
270
+ 250,
271
+ 251,
272
+ 252,
273
+ 253,
274
+ 254,
275
+ 255,
276
+ 256,
277
+ 257,
278
+ 258,
279
+ 259,
280
+ 260,
281
+ 261,
282
+ 262,
283
+ 263,
284
+ 264,
285
+ 265,
286
+ 266,
287
+ 267,
288
+ 268,
289
+ 269,
290
+ 270,
291
+ 271,
292
+ 272,
293
+ 273,
294
+ 274,
295
+ 275,
296
+ 276,
297
+ 277,
298
+ 278,
299
+ 279,
300
+ 280,
301
+ 281,
302
+ 282,
303
+ 283,
304
+ 284,
305
+ 285,
306
+ 286,
307
+ 287,
308
+ 288,
309
+ 289,
310
+ 290,
311
+ 291,
312
+ 292,
313
+ 293,
314
+ 294,
315
+ 295,
316
+ 296,
317
+ 297,
318
+ 298,
319
+ 299,
320
+ 300,
321
+ 301,
322
+ 302,
323
+ 303,
324
+ 304,
325
+ 305,
326
+ 306,
327
+ 307,
328
+ 308,
329
+ 309,
330
+ 310,
331
+ 311,
332
+ 312,
333
+ 313,
334
+ 314,
335
+ 315,
336
+ 316,
337
+ 317,
338
+ 318,
339
+ 319,
340
+ 320,
341
+ 321,
342
+ 322,
343
+ 323,
344
+ 324,
345
+ 325,
346
+ 326,
347
+ 327,
348
+ 328,
349
+ 329,
350
+ 330,
351
+ 331,
352
+ 332,
353
+ 333,
354
+ 334,
355
+ 335,
356
+ 336,
357
+ 337,
358
+ 338,
359
+ 339,
360
+ 340,
361
+ 341,
362
+ 342,
363
+ 343,
364
+ 344,
365
+ 345,
366
+ 346,
367
+ 347,
368
+ 348,
369
+ 349,
370
+ 350,
371
+ 351,
372
+ 352,
373
+ 353,
374
+ 354,
375
+ 355,
376
+ 356,
377
+ 357,
378
+ 358,
379
+ 359,
380
+ 360,
381
+ 361,
382
+ 362,
383
+ 363,
384
+ 364,
385
+ 365,
386
+ 366,
387
+ 367,
388
+ 368,
389
+ 369,
390
+ 370,
391
+ 371,
392
+ 372,
393
+ 373,
394
+ 374,
395
+ 375,
396
+ 376,
397
+ 377,
398
+ 378,
399
+ 379,
400
+ 380,
401
+ 381,
402
+ 382,
403
+ 383,
404
+ 384,
405
+ 385,
406
+ 386,
407
+ 387,
408
+ 388,
409
+ 389,
410
+ 390,
411
+ 391,
412
+ 392,
413
+ 393,
414
+ 394,
415
+ 395,
416
+ 396,
417
+ 397,
418
+ 398,
419
+ 399,
420
+ 400,
421
+ 401,
422
+ 402,
423
+ 403,
424
+ 404,
425
+ 405,
426
+ 406,
427
+ 407,
428
+ 408,
429
+ 409,
430
+ 410,
431
+ 411,
432
+ 412,
433
+ 413,
434
+ 414,
435
+ 415,
436
+ 416,
437
+ 417,
438
+ 418,
439
+ 419,
440
+ 420,
441
+ 421,
442
+ 422,
443
+ 423,
444
+ 424,
445
+ 425,
446
+ 426,
447
+ 427,
448
+ 428,
449
+ 429,
450
+ 430,
451
+ 431,
452
+ 432,
453
+ 433,
454
+ 434,
455
+ 435,
456
+ 436,
457
+ 437,
458
+ 438,
459
+ 439,
460
+ 440,
461
+ 441,
462
+ 442,
463
+ 443,
464
+ 444,
465
+ 445,
466
+ 446,
467
+ 447,
468
+ 448,
469
+ 449,
470
+ 450,
471
+ 451,
472
+ 452,
473
+ 453,
474
+ 454,
475
+ 455,
476
+ 456,
477
+ 457,
478
+ 458,
479
+ 459,
480
+ 460,
481
+ 461,
482
+ 462,
483
+ 463,
484
+ 464,
485
+ 465,
486
+ 466,
487
+ 467,
488
+ 468,
489
+ 469,
490
+ 470,
491
+ 471,
492
+ 472,
493
+ 473,
494
+ 474,
495
+ 475,
496
+ 476,
497
+ 477,
498
+ 478,
499
+ 479,
500
+ 480,
501
+ 481,
502
+ 482,
503
+ 483,
504
+ 484,
505
+ 485,
506
+ 486,
507
+ 487,
508
+ 488,
509
+ 489,
510
+ 490,
511
+ 491,
512
+ 492,
513
+ 493,
514
+ 494,
515
+ 495,
516
+ 496,
517
+ 497,
518
+ 498,
519
+ 499,
520
+ 500,
521
+ 501,
522
+ 502,
523
+ 503,
524
+ 504,
525
+ 505,
526
+ 506,
527
+ 507,
528
+ 508,
529
+ 509,
530
+ 510,
531
+ 511,
532
+ 512,
533
+ 513,
534
+ 514,
535
+ 515,
536
+ 516,
537
+ 517,
538
+ 518,
539
+ 519,
540
+ 520,
541
+ 521,
542
+ 522,
543
+ 523,
544
+ 524,
545
+ 525,
546
+ 526,
547
+ 527,
548
+ 528,
549
+ 529,
550
+ 530,
551
+ 531,
552
+ 532,
553
+ 533,
554
+ 534,
555
+ 535,
556
+ 536,
557
+ 537,
558
+ 538,
559
+ 539,
560
+ 540,
561
+ 541,
562
+ 542,
563
+ 543,
564
+ 544,
565
+ 545,
566
+ 546,
567
+ 547,
568
+ 548,
569
+ 549,
570
+ 550,
571
+ 551,
572
+ 552,
573
+ 553,
574
+ 554,
575
+ 555,
576
+ 556,
577
+ 557,
578
+ 558,
579
+ 559,
580
+ 560,
581
+ 561,
582
+ 562,
583
+ 563,
584
+ 564,
585
+ 565,
586
+ 566,
587
+ 567,
588
+ 568,
589
+ 569,
590
+ 570,
591
+ 571,
592
+ 572,
593
+ 573,
594
+ 574,
595
+ 575,
596
+ 576,
597
+ 577,
598
+ 578,
599
+ 579,
600
+ 580,
601
+ 581,
602
+ 582,
603
+ 583,
604
+ 584,
605
+ 585,
606
+ 586,
607
+ 587,
608
+ 588,
609
+ 589,
610
+ 590,
611
+ 591,
612
+ 592,
613
+ 593,
614
+ 594,
615
+ 595,
616
+ 596,
617
+ 597,
618
+ 598,
619
+ 599,
620
+ 600,
621
+ 601,
622
+ 602
623
+ ]
624
+ },
625
+ {
626
+ "lr": 2.6875000000000013e-05,
627
+ "weight_decay": 0.0001,
628
+ "name": "soft_prompts",
629
+ "betas": [
630
+ 0.9,
631
+ 0.95
632
+ ],
633
+ "eps": 1e-08,
634
+ "amsgrad": false,
635
+ "maximize": false,
636
+ "foreach": null,
637
+ "capturable": false,
638
+ "differentiable": false,
639
+ "fused": null,
640
+ "decoupled_weight_decay": true,
641
+ "initial_lr": 0.0001,
642
+ "params": [
643
+ 603
644
+ ]
645
+ },
646
+ {
647
+ "lr": 2.6875000000000013e-05,
648
+ "weight_decay": 0.0001,
649
+ "name": "other",
650
+ "betas": [
651
+ 0.9,
652
+ 0.95
653
+ ],
654
+ "eps": 1e-08,
655
+ "amsgrad": false,
656
+ "maximize": false,
657
+ "foreach": null,
658
+ "capturable": false,
659
+ "differentiable": false,
660
+ "fused": null,
661
+ "decoupled_weight_decay": true,
662
+ "initial_lr": 0.0001,
663
+ "params": [
664
+ 604,
665
+ 605,
666
+ 606,
667
+ 607,
668
+ 608,
669
+ 609,
670
+ 610,
671
+ 611,
672
+ 612,
673
+ 613,
674
+ 614,
675
+ 615,
676
+ 616,
677
+ 617,
678
+ 618,
679
+ 619,
680
+ 620,
681
+ 621,
682
+ 622,
683
+ 623,
684
+ 624,
685
+ 625,
686
+ 626,
687
+ 627,
688
+ 628,
689
+ 629,
690
+ 630,
691
+ 631,
692
+ 632,
693
+ 633,
694
+ 634,
695
+ 635,
696
+ 636,
697
+ 637,
698
+ 638,
699
+ 639,
700
+ 640,
701
+ 641,
702
+ 642,
703
+ 643,
704
+ 644,
705
+ 645,
706
+ 646,
707
+ 647,
708
+ 648,
709
+ 649,
710
+ 650,
711
+ 651,
712
+ 652,
713
+ 653,
714
+ 654,
715
+ 655,
716
+ 656,
717
+ 657,
718
+ 658,
719
+ 659,
720
+ 660,
721
+ 661,
722
+ 662,
723
+ 663,
724
+ 664,
725
+ 665,
726
+ 666,
727
+ 667,
728
+ 668,
729
+ 669,
730
+ 670,
731
+ 671,
732
+ 672,
733
+ 673,
734
+ 674,
735
+ 675,
736
+ 676,
737
+ 677,
738
+ 678,
739
+ 679,
740
+ 680,
741
+ 681,
742
+ 682,
743
+ 683,
744
+ 684,
745
+ 685,
746
+ 686,
747
+ 687,
748
+ 688,
749
+ 689,
750
+ 690,
751
+ 691,
752
+ 692,
753
+ 693,
754
+ 694,
755
+ 695,
756
+ 696,
757
+ 697,
758
+ 698,
759
+ 699,
760
+ 700,
761
+ 701,
762
+ 702,
763
+ 703,
764
+ 704,
765
+ 705,
766
+ 706,
767
+ 707,
768
+ 708,
769
+ 709,
770
+ 710,
771
+ 711,
772
+ 712,
773
+ 713,
774
+ 714,
775
+ 715,
776
+ 716,
777
+ 717,
778
+ 718,
779
+ 719,
780
+ 720,
781
+ 721,
782
+ 722,
783
+ 723,
784
+ 724,
785
+ 725,
786
+ 726,
787
+ 727,
788
+ 728,
789
+ 729,
790
+ 730,
791
+ 731,
792
+ 732,
793
+ 733,
794
+ 734,
795
+ 735,
796
+ 736,
797
+ 737,
798
+ 738,
799
+ 739,
800
+ 740,
801
+ 741,
802
+ 742,
803
+ 743,
804
+ 744,
805
+ 745,
806
+ 746,
807
+ 747,
808
+ 748,
809
+ 749,
810
+ 750,
811
+ 751,
812
+ 752,
813
+ 753,
814
+ 754,
815
+ 755,
816
+ 756,
817
+ 757,
818
+ 758,
819
+ 759,
820
+ 760,
821
+ 761,
822
+ 762,
823
+ 763,
824
+ 764,
825
+ 765,
826
+ 766,
827
+ 767,
828
+ 768,
829
+ 769,
830
+ 770,
831
+ 771,
832
+ 772,
833
+ 773,
834
+ 774,
835
+ 775,
836
+ 776,
837
+ 777,
838
+ 778,
839
+ 779,
840
+ 780,
841
+ 781,
842
+ 782,
843
+ 783,
844
+ 784,
845
+ 785,
846
+ 786,
847
+ 787,
848
+ 788,
849
+ 789,
850
+ 790,
851
+ 791,
852
+ 792,
853
+ 793,
854
+ 794,
855
+ 795,
856
+ 796,
857
+ 797,
858
+ 798,
859
+ 799,
860
+ 800,
861
+ 801,
862
+ 802,
863
+ 803,
864
+ 804,
865
+ 805,
866
+ 806,
867
+ 807,
868
+ 808,
869
+ 809,
870
+ 810,
871
+ 811,
872
+ 812,
873
+ 813,
874
+ 814,
875
+ 815,
876
+ 816,
877
+ 817,
878
+ 818,
879
+ 819,
880
+ 820,
881
+ 821,
882
+ 822,
883
+ 823,
884
+ 824,
885
+ 825,
886
+ 826,
887
+ 827,
888
+ 828,
889
+ 829,
890
+ 830,
891
+ 831,
892
+ 832,
893
+ 833,
894
+ 834,
895
+ 835,
896
+ 836,
897
+ 837,
898
+ 838,
899
+ 839,
900
+ 840,
901
+ 841,
902
+ 842,
903
+ 843,
904
+ 844,
905
+ 845,
906
+ 846,
907
+ 847,
908
+ 848,
909
+ 849,
910
+ 850,
911
+ 851,
912
+ 852,
913
+ 853,
914
+ 854,
915
+ 855,
916
+ 856,
917
+ 857,
918
+ 858,
919
+ 859,
920
+ 860,
921
+ 861,
922
+ 862,
923
+ 863,
924
+ 864,
925
+ 865,
926
+ 866,
927
+ 867,
928
+ 868,
929
+ 869,
930
+ 870,
931
+ 871,
932
+ 872,
933
+ 873,
934
+ 874,
935
+ 875,
936
+ 876,
937
+ 877,
938
+ 878,
939
+ 879,
940
+ 880,
941
+ 881,
942
+ 882,
943
+ 883,
944
+ 884,
945
+ 885,
946
+ 886,
947
+ 887,
948
+ 888,
949
+ 889,
950
+ 890,
951
+ 891,
952
+ 892,
953
+ 893,
954
+ 894,
955
+ 895,
956
+ 896,
957
+ 897,
958
+ 898,
959
+ 899,
960
+ 900
961
+ ]
962
+ }
963
+ ]
checkpoints/004000/training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:131bc5504ddfa78737ce2317ef7f379b9ea59c6b19e8a4440b5952b94bce56c8
3
+ size 3518165076
checkpoints/004000/training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1dd4a76f9bb9e032793f7259b85e127e335196abc091c671b499d5d845ba76c
3
+ size 15708
checkpoints/004000/training_state/scheduler_state.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_lrs": [
3
+ 1e-05,
4
+ 0.0001,
5
+ 0.0001
6
+ ],
7
+ "last_epoch": 4000,
8
+ "_step_count": 4001,
9
+ "_is_initial": false,
10
+ "_get_lr_called_within_step": false,
11
+ "_last_lr": [
12
+ 2.6875000000000014e-06,
13
+ 2.6875000000000013e-05,
14
+ 2.6875000000000013e-05
15
+ ],
16
+ "lr_lambdas": [
17
+ null,
18
+ null,
19
+ null
20
+ ]
21
+ }
checkpoints/004000/training_state/training_step.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "step": 4000
3
+ }