chuanmew commited on
Commit
2806c88
·
verified ·
1 Parent(s): 1651216

test-3-checkpoint-3000

Browse files
test-3-checkpoint-3000/config.json ADDED
@@ -0,0 +1,138 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "batch_size": 64,
3
+ "buffer_size": 64,
4
+ "from_pretrained": "oxe-g2-checkpoint-300000",
5
+ "frozen_keys": [
6
+ "*hf_model*"
7
+ ],
8
+ "model": {
9
+ "heads": {
10
+ "action": {
11
+ "args": [],
12
+ "kwargs": {
13
+ "action_dim": 7,
14
+ "action_horizon": 4,
15
+ "discrete_indices": [
16
+ 0,
17
+ 1,
18
+ 2,
19
+ 3,
20
+ 4,
21
+ 5
22
+ ],
23
+ "readout_key": "readout_action",
24
+ "token_embedding_size": 768
25
+ },
26
+ "module": "model.octo.components.action_heads",
27
+ "name": "MixedActionHead"
28
+ }
29
+ },
30
+ "max_horizon": 10,
31
+ "observation_tokenizers": {
32
+ "primary": {
33
+ "args": [],
34
+ "kwargs": {
35
+ "encoder": {
36
+ "args": [],
37
+ "kwargs": {
38
+ "in_features": 6
39
+ },
40
+ "module": "octo.model.components.vit_encoders",
41
+ "name": "SmallStem16"
42
+ },
43
+ "obs_stack_keys": [
44
+ "image_primary"
45
+ ],
46
+ "task_stack_keys": [
47
+ "image_primary"
48
+ ]
49
+ },
50
+ "module": "octo.model.components.tokenizers",
51
+ "name": "ImageTokenizer"
52
+ }
53
+ },
54
+ "readouts": {
55
+ "action": 1
56
+ },
57
+ "repeat_task_tokens": true,
58
+ "task_tokenizers": {
59
+ "language": {
60
+ "args": [],
61
+ "kwargs": {
62
+ "encoder": "t5-base",
63
+ "finetune_encoder": false
64
+ },
65
+ "module": "octo.model.components.tokenizers",
66
+ "name": "LanguageTokenizer"
67
+ }
68
+ },
69
+ "token_embedding_size": 768,
70
+ "transformer_kwargs": {
71
+ "add_position_embedding": false,
72
+ "attention_dropout_rate": 0.0,
73
+ "dropout_rate": 0.0,
74
+ "mlp_dim": 3072,
75
+ "num_attention_heads": 12,
76
+ "num_layers": 12
77
+ },
78
+ "use_correct_attention": true
79
+ },
80
+ "normalize_method": "sign",
81
+ "obs_token_nums": {
82
+ "primary": 256
83
+ },
84
+ "sampler_num_samples": 2560000,
85
+ "seed": 2,
86
+ "subsample_length": 99999,
87
+ "text_processor": {
88
+ "args": [],
89
+ "kwargs": {
90
+ "encode_with_model": false,
91
+ "tokenizer_kwargs": {
92
+ "max_length": 16,
93
+ "padding": "max_length",
94
+ "return_tensors": "np",
95
+ "truncation": true
96
+ },
97
+ "tokenizer_name": "t5-base"
98
+ },
99
+ "module": "octo.components.text_processing",
100
+ "name": "HFTokenizer"
101
+ },
102
+ "training_arguments": {
103
+ "bf16": true,
104
+ "dataloader_pin_memory": true,
105
+ "ddp_find_unused_parameters": true,
106
+ "eval_steps": 5000,
107
+ "gradient_accumulation_steps": 4,
108
+ "learning_rate": 3e-05,
109
+ "logging_nan_inf_filter": false,
110
+ "logging_steps": 100,
111
+ "lr_scheduler_kwargs": {
112
+ "decay_type": "cosine",
113
+ "min_lr_ratio": 0.05,
114
+ "num_decay_steps": 298000
115
+ },
116
+ "lr_scheduler_type": "constant",
117
+ "max_grad_norm": 1.0,
118
+ "max_steps": 300000,
119
+ "optim": "adamw_torch_fused",
120
+ "per_device_eval_batch_size": 1,
121
+ "per_device_train_batch_size": 1,
122
+ "report_to": "wandb",
123
+ "save_safetensors": true,
124
+ "save_steps": 500,
125
+ "torch_compile": true,
126
+ "warmup_steps": 2000,
127
+ "weight_decay": 0.1
128
+ },
129
+ "training_keys": [
130
+ "*action*",
131
+ "*task_projections*",
132
+ "*obs_projections*",
133
+ "*readout_embeddings*",
134
+ "*task_pos_embeddings*",
135
+ "*obs_pos_embeddings*",
136
+ "*observation_tokenizers*"
137
+ ]
138
+ }
test-3-checkpoint-3000/dataset_statistics.json ADDED
@@ -0,0 +1,253 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "episode_index": {
4
+ "min": [
5
+ 0
6
+ ],
7
+ "max": [
8
+ 128
9
+ ],
10
+ "mean": [
11
+ 63.14946338383838
12
+ ],
13
+ "std": [
14
+ 35.1467891774593
15
+ ],
16
+ "count": [
17
+ 12672
18
+ ]
19
+ },
20
+ "frame_index": {
21
+ "min": [
22
+ 0
23
+ ],
24
+ "max": [
25
+ 225
26
+ ],
27
+ "mean": [
28
+ 55.168955176767675
29
+ ],
30
+ "std": [
31
+ 39.5185866669507
32
+ ],
33
+ "count": [
34
+ 12672
35
+ ]
36
+ },
37
+ "index": {
38
+ "min": [
39
+ 0
40
+ ],
41
+ "max": [
42
+ 12671
43
+ ],
44
+ "mean": [
45
+ 6335.5
46
+ ],
47
+ "std": [
48
+ 3658.0912941951938
49
+ ],
50
+ "count": [
51
+ 12672
52
+ ]
53
+ },
54
+ "task_index": {
55
+ "min": [
56
+ 0
57
+ ],
58
+ "max": [
59
+ 3
60
+ ],
61
+ "mean": [
62
+ 1.6840277777777777
63
+ ],
64
+ "std": [
65
+ 1.1113384592218372
66
+ ],
67
+ "count": [
68
+ 12672
69
+ ]
70
+ },
71
+ "action": {
72
+ "min": [
73
+ -0.009999999776482582,
74
+ -0.009999999776482582,
75
+ -0.009999999776482582,
76
+ -0.06283185631036758,
77
+ -0.06283185631036758,
78
+ -0.06283185631036758,
79
+ 0.0
80
+ ],
81
+ "max": [
82
+ 0.009999999776482582,
83
+ 0.009999999776482582,
84
+ 0.009999999776482582,
85
+ 0.06283185631036758,
86
+ 0.06283185631036758,
87
+ 0.06283185631036758,
88
+ 1.0
89
+ ],
90
+ "mean": [
91
+ -0.0010779668760702325,
92
+ -0.000870422678087375,
93
+ -0.0009524932320082003,
94
+ -0.00011404143052376722,
95
+ 0.001646163140721359,
96
+ 0.0006842485724881945,
97
+ 0.14094065714126566
98
+ ],
99
+ "std": [
100
+ 0.0050928476793778805,
101
+ 0.0052109778002382215,
102
+ 0.0062727072406226275,
103
+ 0.01305372613557191,
104
+ 0.014969692486291531,
105
+ 0.021519857205295197,
106
+ 0.3479603303557627
107
+ ],
108
+ "count": [
109
+ 12672
110
+ ],
111
+ "mask": [
112
+ true,
113
+ true,
114
+ true,
115
+ true,
116
+ true,
117
+ true,
118
+ false
119
+ ]
120
+ },
121
+ "timestamp": {
122
+ "min": [
123
+ 0.0
124
+ ],
125
+ "max": [
126
+ 22.5
127
+ ],
128
+ "mean": [
129
+ 5.516895517676768
130
+ ],
131
+ "std": [
132
+ 3.9518586666950704
133
+ ],
134
+ "count": [
135
+ 12672
136
+ ]
137
+ },
138
+ "observation.state": {
139
+ "min": [
140
+ -0.6913691163063049,
141
+ -0.25204867124557495,
142
+ -0.22021731734275818,
143
+ -3.140528440475464,
144
+ -1.213579535484314,
145
+ -3.1340115070343018,
146
+ 0.0
147
+ ],
148
+ "max": [
149
+ -0.26134854555130005,
150
+ 0.40225377678871155,
151
+ 0.4610653519630432,
152
+ 3.1412761211395264,
153
+ 0.644866406917572,
154
+ 3.1401240825653076,
155
+ 1.0
156
+ ],
157
+ "mean": [
158
+ -0.4765559839921994,
159
+ 0.03277433536791847,
160
+ 0.01813845893630427,
161
+ 1.4840563985447381,
162
+ -0.1872646863000659,
163
+ -1.201557804914303,
164
+ 0.13328598546378098
165
+ ],
166
+ "std": [
167
+ 0.09873974979292631,
168
+ 0.12291375325367411,
169
+ 0.13182701724212956,
170
+ 2.530463134923631,
171
+ 0.39532953579234853,
172
+ 1.3639962652103377,
173
+ 0.33988356830665484
174
+ ],
175
+ "count": [
176
+ 12672
177
+ ]
178
+ },
179
+ "observation.images.main_camera": {
180
+ "min": [
181
+ [
182
+ [
183
+ 0.0
184
+ ]
185
+ ],
186
+ [
187
+ [
188
+ 0.0
189
+ ]
190
+ ],
191
+ [
192
+ [
193
+ 0.0
194
+ ]
195
+ ]
196
+ ],
197
+ "max": [
198
+ [
199
+ [
200
+ 1.0
201
+ ]
202
+ ],
203
+ [
204
+ [
205
+ 1.0
206
+ ]
207
+ ],
208
+ [
209
+ [
210
+ 1.0
211
+ ]
212
+ ]
213
+ ],
214
+ "mean": [
215
+ [
216
+ [
217
+ 0.56009308397514
218
+ ]
219
+ ],
220
+ [
221
+ [
222
+ 0.5088963212208076
223
+ ]
224
+ ],
225
+ [
226
+ [
227
+ 0.47626117961949455
228
+ ]
229
+ ]
230
+ ],
231
+ "std": [
232
+ [
233
+ [
234
+ 0.27688289864943944
235
+ ]
236
+ ],
237
+ [
238
+ [
239
+ 0.26883972589038224
240
+ ]
241
+ ],
242
+ [
243
+ [
244
+ 0.29031452356480364
245
+ ]
246
+ ]
247
+ ],
248
+ "count": [
249
+ 11006
250
+ ]
251
+ }
252
+ }
253
+ ]
test-3-checkpoint-3000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b920260b8f8bd3317a0fd7de9e2d0d1d77ef15bec0e3cf20718e23e4eb41fd4
3
+ size 397587984
test-3-checkpoint-3000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb933f394f541f151f2d13f8609ec2617251dce84990ea38f5b86c6276c09382
3
+ size 19363642
test-3-checkpoint-3000/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c135e65e0df41da6500caafd2754e60a1b8955d809ce5df77fe60dd1f2ee19e7
3
+ size 15984
test-3-checkpoint-3000/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71bf33c2c4be9bb1119bcae98ddd597f2a06cdbb2e9a7e9539f12de5ee25ed9a
3
+ size 15984
test-3-checkpoint-3000/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35bb6b6666625e001f6024a833f8ee02c77af73f2fee852fa7bd142ff51a7bb3
3
+ size 15984
test-3-checkpoint-3000/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c96e868d0152935a5df4b2ac9468a12d0a7954274b8bd6d9378addaad224676d
3
+ size 15984
test-3-checkpoint-3000/rng_state_4.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc6a033bae2cd81d50eb6263e37afc05fbf9db00eadcba44de5e6fc8017603ed
3
+ size 15984
test-3-checkpoint-3000/rng_state_5.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35edbeb1b236c7d43d6776c2a3c5bf56e275e20204cedd5a215179ed82ae5199
3
+ size 15984
test-3-checkpoint-3000/rng_state_6.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:259c38f3a88cf8baa49a49045eda90937576f1bfb97856182e4d859b0a1868a8
3
+ size 15984
test-3-checkpoint-3000/rng_state_7.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d85ac1d270b0fe4af758efd5e401a2ced3b2c7f549b578d78cd54c16e6b8beb
3
+ size 15984
test-3-checkpoint-3000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86056ae5174226c268b9270745ad733d853b8f8c426ce01e6e2dd7143837aa9b
3
+ size 1064
test-3-checkpoint-3000/trainer_state.json ADDED
@@ -0,0 +1,243 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.4,
5
+ "eval_steps": 5000,
6
+ "global_step": 3000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.08,
13
+ "grad_norm": 2.015625,
14
+ "learning_rate": 3e-05,
15
+ "loss": 4.5735,
16
+ "step": 100
17
+ },
18
+ {
19
+ "epoch": 0.16,
20
+ "grad_norm": 3.875,
21
+ "learning_rate": 3e-05,
22
+ "loss": 2.7494,
23
+ "step": 200
24
+ },
25
+ {
26
+ "epoch": 0.24,
27
+ "grad_norm": 3.578125,
28
+ "learning_rate": 3e-05,
29
+ "loss": 2.1482,
30
+ "step": 300
31
+ },
32
+ {
33
+ "epoch": 0.32,
34
+ "grad_norm": 8.9375,
35
+ "learning_rate": 3e-05,
36
+ "loss": 1.8173,
37
+ "step": 400
38
+ },
39
+ {
40
+ "epoch": 0.4,
41
+ "grad_norm": 6.71875,
42
+ "learning_rate": 3e-05,
43
+ "loss": 1.6718,
44
+ "step": 500
45
+ },
46
+ {
47
+ "epoch": 0.48,
48
+ "grad_norm": 2.15625,
49
+ "learning_rate": 3e-05,
50
+ "loss": 1.5987,
51
+ "step": 600
52
+ },
53
+ {
54
+ "epoch": 0.56,
55
+ "grad_norm": 3.03125,
56
+ "learning_rate": 3e-05,
57
+ "loss": 1.5527,
58
+ "step": 700
59
+ },
60
+ {
61
+ "epoch": 0.64,
62
+ "grad_norm": 5.03125,
63
+ "learning_rate": 3e-05,
64
+ "loss": 1.522,
65
+ "step": 800
66
+ },
67
+ {
68
+ "epoch": 0.72,
69
+ "grad_norm": 3.71875,
70
+ "learning_rate": 3e-05,
71
+ "loss": 1.4953,
72
+ "step": 900
73
+ },
74
+ {
75
+ "epoch": 0.8,
76
+ "grad_norm": 2.171875,
77
+ "learning_rate": 3e-05,
78
+ "loss": 1.4772,
79
+ "step": 1000
80
+ },
81
+ {
82
+ "epoch": 0.88,
83
+ "grad_norm": 2.421875,
84
+ "learning_rate": 3e-05,
85
+ "loss": 1.4622,
86
+ "step": 1100
87
+ },
88
+ {
89
+ "epoch": 0.96,
90
+ "grad_norm": 3.21875,
91
+ "learning_rate": 3e-05,
92
+ "loss": 1.4474,
93
+ "step": 1200
94
+ },
95
+ {
96
+ "epoch": 1.04,
97
+ "grad_norm": 2.34375,
98
+ "learning_rate": 3e-05,
99
+ "loss": 1.4344,
100
+ "step": 1300
101
+ },
102
+ {
103
+ "epoch": 1.12,
104
+ "grad_norm": 2.75,
105
+ "learning_rate": 3e-05,
106
+ "loss": 1.4236,
107
+ "step": 1400
108
+ },
109
+ {
110
+ "epoch": 1.2,
111
+ "grad_norm": 3.359375,
112
+ "learning_rate": 3e-05,
113
+ "loss": 1.4133,
114
+ "step": 1500
115
+ },
116
+ {
117
+ "epoch": 1.28,
118
+ "grad_norm": 3.140625,
119
+ "learning_rate": 3e-05,
120
+ "loss": 1.4087,
121
+ "step": 1600
122
+ },
123
+ {
124
+ "epoch": 1.3599999999999999,
125
+ "grad_norm": 2.15625,
126
+ "learning_rate": 3e-05,
127
+ "loss": 1.3957,
128
+ "step": 1700
129
+ },
130
+ {
131
+ "epoch": 1.44,
132
+ "grad_norm": 4.25,
133
+ "learning_rate": 3e-05,
134
+ "loss": 1.3863,
135
+ "step": 1800
136
+ },
137
+ {
138
+ "epoch": 1.52,
139
+ "grad_norm": 2.5625,
140
+ "learning_rate": 3e-05,
141
+ "loss": 1.3845,
142
+ "step": 1900
143
+ },
144
+ {
145
+ "epoch": 1.6,
146
+ "grad_norm": 3.78125,
147
+ "learning_rate": 3e-05,
148
+ "loss": 1.3799,
149
+ "step": 2000
150
+ },
151
+ {
152
+ "epoch": 1.6800000000000002,
153
+ "grad_norm": 3.921875,
154
+ "learning_rate": 3e-05,
155
+ "loss": 1.3774,
156
+ "step": 2100
157
+ },
158
+ {
159
+ "epoch": 1.76,
160
+ "grad_norm": 3.328125,
161
+ "learning_rate": 3e-05,
162
+ "loss": 1.3743,
163
+ "step": 2200
164
+ },
165
+ {
166
+ "epoch": 1.8399999999999999,
167
+ "grad_norm": 4.03125,
168
+ "learning_rate": 3e-05,
169
+ "loss": 1.37,
170
+ "step": 2300
171
+ },
172
+ {
173
+ "epoch": 1.92,
174
+ "grad_norm": 3.84375,
175
+ "learning_rate": 3e-05,
176
+ "loss": 1.3643,
177
+ "step": 2400
178
+ },
179
+ {
180
+ "epoch": 2.0,
181
+ "grad_norm": 3.375,
182
+ "learning_rate": 3e-05,
183
+ "loss": 1.3668,
184
+ "step": 2500
185
+ },
186
+ {
187
+ "epoch": 2.08,
188
+ "grad_norm": 4.0625,
189
+ "learning_rate": 3e-05,
190
+ "loss": 1.3536,
191
+ "step": 2600
192
+ },
193
+ {
194
+ "epoch": 2.16,
195
+ "grad_norm": 2.859375,
196
+ "learning_rate": 3e-05,
197
+ "loss": 1.3499,
198
+ "step": 2700
199
+ },
200
+ {
201
+ "epoch": 2.24,
202
+ "grad_norm": 3.15625,
203
+ "learning_rate": 3e-05,
204
+ "loss": 1.3494,
205
+ "step": 2800
206
+ },
207
+ {
208
+ "epoch": 2.32,
209
+ "grad_norm": 3.421875,
210
+ "learning_rate": 3e-05,
211
+ "loss": 1.3465,
212
+ "step": 2900
213
+ },
214
+ {
215
+ "epoch": 2.4,
216
+ "grad_norm": 4.28125,
217
+ "learning_rate": 3e-05,
218
+ "loss": 1.3432,
219
+ "step": 3000
220
+ }
221
+ ],
222
+ "logging_steps": 100,
223
+ "max_steps": 300000,
224
+ "num_input_tokens_seen": 0,
225
+ "num_train_epochs": 240,
226
+ "save_steps": 500,
227
+ "stateful_callbacks": {
228
+ "TrainerControl": {
229
+ "args": {
230
+ "should_epoch_stop": false,
231
+ "should_evaluate": false,
232
+ "should_log": false,
233
+ "should_save": true,
234
+ "should_training_stop": false
235
+ },
236
+ "attributes": {}
237
+ }
238
+ },
239
+ "total_flos": 0.0,
240
+ "train_batch_size": 1,
241
+ "trial_name": null,
242
+ "trial_params": null
243
+ }