aswinkumar99 commited on
Commit
87c317b
·
verified ·
1 Parent(s): 7b48010

Add files using upload-large-folder tool

Browse files
pretrained_model/config.json ADDED
@@ -0,0 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "multi_task_dit",
3
+ "n_obs_steps": 2,
4
+ "input_features": {
5
+ "observation.state": {
6
+ "type": "STATE",
7
+ "shape": [
8
+ 6
9
+ ]
10
+ },
11
+ "observation.images.overhead": {
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": true,
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": 32,
46
+ "n_action_steps": 24,
47
+ "objective": "diffusion",
48
+ "noise_scheduler_type": "DDPM",
49
+ "num_train_timesteps": 100,
50
+ "beta_schedule": "squaredcos_cap_v2",
51
+ "beta_start": 0.0001,
52
+ "beta_end": 0.02,
53
+ "prediction_type": "epsilon",
54
+ "clip_sample": true,
55
+ "clip_sample_range": 1.0,
56
+ "num_inference_steps": null,
57
+ "sigma_min": 0.0,
58
+ "num_integration_steps": 100,
59
+ "integration_method": "euler",
60
+ "timestep_sampling_strategy": "beta",
61
+ "timestep_sampling_s": 0.999,
62
+ "timestep_sampling_alpha": 1.5,
63
+ "timestep_sampling_beta": 1.0,
64
+ "hidden_dim": 512,
65
+ "num_layers": 4,
66
+ "num_heads": 8,
67
+ "dropout": 0.1,
68
+ "use_positional_encoding": false,
69
+ "timestep_embed_dim": 256,
70
+ "use_rope": true,
71
+ "rope_base": 10000.0,
72
+ "vision_encoder_name": "openai/clip-vit-base-patch16",
73
+ "use_separate_rgb_encoder_per_camera": false,
74
+ "vision_encoder_lr_multiplier": 0.1,
75
+ "image_resize_shape": null,
76
+ "image_crop_shape": [
77
+ 224,
78
+ 224
79
+ ],
80
+ "image_crop_is_random": true,
81
+ "text_encoder_name": "openai/clip-vit-base-patch16",
82
+ "tokenizer_max_length": 77,
83
+ "tokenizer_padding": "max_length",
84
+ "tokenizer_padding_side": "right",
85
+ "tokenizer_truncation": true,
86
+ "normalization_mapping": {
87
+ "VISUAL": "MEAN_STD",
88
+ "STATE": "MIN_MAX",
89
+ "ACTION": "MIN_MAX"
90
+ },
91
+ "optimizer_lr": 2e-05,
92
+ "optimizer_betas": [
93
+ 0.95,
94
+ 0.999
95
+ ],
96
+ "optimizer_eps": 1e-08,
97
+ "optimizer_weight_decay": 0.0,
98
+ "scheduler_name": "cosine",
99
+ "scheduler_warmup_steps": 0,
100
+ "do_mask_loss_for_padding": false,
101
+ "drop_n_last_frames": 7
102
+ }
pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51055b4ed2b3d15783f7354ebba8dc6b9849d25749d360899c8ffdb05e2b87ad
3
+ size 863014648
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
+ }
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 sha256:5b3cb9ad6b7efbadf59a5b1f620e6613437a269307470ddb8d5fb87135db3b5f
3
+ size 7584
pretrained_model/policy_preprocessor.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "tokenizer_processor",
16
+ "config": {
17
+ "max_length": 77,
18
+ "task_key": "task",
19
+ "padding_side": "right",
20
+ "padding": "max_length",
21
+ "truncation": true,
22
+ "tokenizer_name": "openai/clip-vit-base-patch16"
23
+ }
24
+ },
25
+ {
26
+ "registry_name": "device_processor",
27
+ "config": {
28
+ "device": "cuda",
29
+ "float_dtype": null
30
+ }
31
+ },
32
+ {
33
+ "registry_name": "normalizer_processor",
34
+ "config": {
35
+ "eps": 1e-08,
36
+ "features": {
37
+ "observation.state": {
38
+ "type": "STATE",
39
+ "shape": [
40
+ 6
41
+ ]
42
+ },
43
+ "observation.images.overhead": {
44
+ "type": "VISUAL",
45
+ "shape": [
46
+ 3,
47
+ 480,
48
+ 640
49
+ ]
50
+ },
51
+ "observation.images.wrist": {
52
+ "type": "VISUAL",
53
+ "shape": [
54
+ 3,
55
+ 480,
56
+ 640
57
+ ]
58
+ },
59
+ "action": {
60
+ "type": "ACTION",
61
+ "shape": [
62
+ 6
63
+ ]
64
+ }
65
+ },
66
+ "norm_map": {
67
+ "VISUAL": "MEAN_STD",
68
+ "STATE": "MIN_MAX",
69
+ "ACTION": "MIN_MAX"
70
+ }
71
+ },
72
+ "state_file": "policy_preprocessor_step_4_normalizer_processor.safetensors"
73
+ }
74
+ ]
75
+ }
pretrained_model/policy_preprocessor_step_4_normalizer_processor.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b3cb9ad6b7efbadf59a5b1f620e6613437a269307470ddb8d5fb87135db3b5f
3
+ size 7584
pretrained_model/train_config.json ADDED
@@ -0,0 +1,241 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "aswinkumar99/task3-all",
4
+ "root": "/home/riftuser/datasets_combined/aswinkumar99/task3-all",
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
+ "affine": {
62
+ "weight": 1.0,
63
+ "type": "RandomAffine",
64
+ "kwargs": {
65
+ "degrees": [
66
+ -5.0,
67
+ 5.0
68
+ ],
69
+ "translate": [
70
+ 0.05,
71
+ 0.05
72
+ ]
73
+ }
74
+ }
75
+ }
76
+ },
77
+ "revision": null,
78
+ "use_imagenet_stats": true,
79
+ "video_backend": "torchcodec",
80
+ "return_uint8": false,
81
+ "streaming": false
82
+ },
83
+ "env": null,
84
+ "policy": {
85
+ "type": "multi_task_dit",
86
+ "n_obs_steps": 2,
87
+ "input_features": {
88
+ "observation.state": {
89
+ "type": "STATE",
90
+ "shape": [
91
+ 6
92
+ ]
93
+ },
94
+ "observation.images.overhead": {
95
+ "type": "VISUAL",
96
+ "shape": [
97
+ 3,
98
+ 480,
99
+ 640
100
+ ]
101
+ },
102
+ "observation.images.wrist": {
103
+ "type": "VISUAL",
104
+ "shape": [
105
+ 3,
106
+ 480,
107
+ 640
108
+ ]
109
+ }
110
+ },
111
+ "output_features": {
112
+ "action": {
113
+ "type": "ACTION",
114
+ "shape": [
115
+ 6
116
+ ]
117
+ }
118
+ },
119
+ "device": "cuda",
120
+ "use_amp": true,
121
+ "use_peft": false,
122
+ "push_to_hub": false,
123
+ "repo_id": null,
124
+ "private": null,
125
+ "tags": null,
126
+ "license": null,
127
+ "pretrained_path": null,
128
+ "horizon": 32,
129
+ "n_action_steps": 24,
130
+ "objective": "diffusion",
131
+ "noise_scheduler_type": "DDPM",
132
+ "num_train_timesteps": 100,
133
+ "beta_schedule": "squaredcos_cap_v2",
134
+ "beta_start": 0.0001,
135
+ "beta_end": 0.02,
136
+ "prediction_type": "epsilon",
137
+ "clip_sample": true,
138
+ "clip_sample_range": 1.0,
139
+ "num_inference_steps": null,
140
+ "sigma_min": 0.0,
141
+ "num_integration_steps": 100,
142
+ "integration_method": "euler",
143
+ "timestep_sampling_strategy": "beta",
144
+ "timestep_sampling_s": 0.999,
145
+ "timestep_sampling_alpha": 1.5,
146
+ "timestep_sampling_beta": 1.0,
147
+ "hidden_dim": 512,
148
+ "num_layers": 4,
149
+ "num_heads": 8,
150
+ "dropout": 0.1,
151
+ "use_positional_encoding": false,
152
+ "timestep_embed_dim": 256,
153
+ "use_rope": true,
154
+ "rope_base": 10000.0,
155
+ "vision_encoder_name": "openai/clip-vit-base-patch16",
156
+ "use_separate_rgb_encoder_per_camera": false,
157
+ "vision_encoder_lr_multiplier": 0.1,
158
+ "image_resize_shape": null,
159
+ "image_crop_shape": [
160
+ 224,
161
+ 224
162
+ ],
163
+ "image_crop_is_random": true,
164
+ "text_encoder_name": "openai/clip-vit-base-patch16",
165
+ "tokenizer_max_length": 77,
166
+ "tokenizer_padding": "max_length",
167
+ "tokenizer_padding_side": "right",
168
+ "tokenizer_truncation": true,
169
+ "normalization_mapping": {
170
+ "VISUAL": "MEAN_STD",
171
+ "STATE": "MIN_MAX",
172
+ "ACTION": "MIN_MAX"
173
+ },
174
+ "optimizer_lr": 2e-05,
175
+ "optimizer_betas": [
176
+ 0.95,
177
+ 0.999
178
+ ],
179
+ "optimizer_eps": 1e-08,
180
+ "optimizer_weight_decay": 0.0,
181
+ "scheduler_name": "cosine",
182
+ "scheduler_warmup_steps": 0,
183
+ "do_mask_loss_for_padding": false,
184
+ "drop_n_last_frames": 7
185
+ },
186
+ "output_dir": "/home/riftuser/outputs_matrix/multi_task_dit/task3-all_bs128_s30000",
187
+ "job_name": "multi_task_dit_task3-all_bs128",
188
+ "resume": false,
189
+ "seed": 1000,
190
+ "cudnn_deterministic": false,
191
+ "num_workers": 8,
192
+ "batch_size": 128,
193
+ "prefetch_factor": 4,
194
+ "persistent_workers": true,
195
+ "steps": 30000,
196
+ "eval_freq": 20000,
197
+ "log_freq": 200,
198
+ "tolerance_s": 0.0001,
199
+ "save_checkpoint": true,
200
+ "save_freq": 5000,
201
+ "use_policy_training_preset": true,
202
+ "optimizer": {
203
+ "type": "adam",
204
+ "lr": 2e-05,
205
+ "weight_decay": 0.0,
206
+ "grad_clip_norm": 10.0,
207
+ "betas": [
208
+ 0.95,
209
+ 0.999
210
+ ],
211
+ "eps": 1e-08
212
+ },
213
+ "scheduler": {
214
+ "type": "diffuser",
215
+ "num_warmup_steps": 0,
216
+ "name": "cosine"
217
+ },
218
+ "eval": {
219
+ "n_episodes": 50,
220
+ "batch_size": 46,
221
+ "use_async_envs": true
222
+ },
223
+ "wandb": {
224
+ "enable": true,
225
+ "disable_artifact": true,
226
+ "project": "so101-layout-generalization",
227
+ "entity": null,
228
+ "notes": null,
229
+ "run_id": "xbi19jrl",
230
+ "mode": "online",
231
+ "add_tags": true
232
+ },
233
+ "peft": null,
234
+ "use_rabc": false,
235
+ "rabc_progress_path": null,
236
+ "rabc_kappa": 0.01,
237
+ "rabc_epsilon": 1e-06,
238
+ "rabc_head_mode": "sparse",
239
+ "rename_map": {},
240
+ "checkpoint_path": null
241
+ }
training_state/optimizer_param_groups.json ADDED
@@ -0,0 +1,289 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "lr": 0.0,
4
+ "betas": [
5
+ 0.95,
6
+ 0.999
7
+ ],
8
+ "eps": 1e-08,
9
+ "weight_decay": 0.0,
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": 2e-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
+ ]
70
+ },
71
+ {
72
+ "lr": 0.0,
73
+ "betas": [
74
+ 0.95,
75
+ 0.999
76
+ ],
77
+ "eps": 1e-08,
78
+ "weight_decay": 0.0,
79
+ "amsgrad": false,
80
+ "maximize": false,
81
+ "foreach": null,
82
+ "capturable": false,
83
+ "differentiable": false,
84
+ "fused": null,
85
+ "decoupled_weight_decay": false,
86
+ "initial_lr": 2.0000000000000003e-06,
87
+ "params": [
88
+ 50,
89
+ 51,
90
+ 52,
91
+ 53,
92
+ 54,
93
+ 55,
94
+ 56,
95
+ 57,
96
+ 58,
97
+ 59,
98
+ 60,
99
+ 61,
100
+ 62,
101
+ 63,
102
+ 64,
103
+ 65,
104
+ 66,
105
+ 67,
106
+ 68,
107
+ 69,
108
+ 70,
109
+ 71,
110
+ 72,
111
+ 73,
112
+ 74,
113
+ 75,
114
+ 76,
115
+ 77,
116
+ 78,
117
+ 79,
118
+ 80,
119
+ 81,
120
+ 82,
121
+ 83,
122
+ 84,
123
+ 85,
124
+ 86,
125
+ 87,
126
+ 88,
127
+ 89,
128
+ 90,
129
+ 91,
130
+ 92,
131
+ 93,
132
+ 94,
133
+ 95,
134
+ 96,
135
+ 97,
136
+ 98,
137
+ 99,
138
+ 100,
139
+ 101,
140
+ 102,
141
+ 103,
142
+ 104,
143
+ 105,
144
+ 106,
145
+ 107,
146
+ 108,
147
+ 109,
148
+ 110,
149
+ 111,
150
+ 112,
151
+ 113,
152
+ 114,
153
+ 115,
154
+ 116,
155
+ 117,
156
+ 118,
157
+ 119,
158
+ 120,
159
+ 121,
160
+ 122,
161
+ 123,
162
+ 124,
163
+ 125,
164
+ 126,
165
+ 127,
166
+ 128,
167
+ 129,
168
+ 130,
169
+ 131,
170
+ 132,
171
+ 133,
172
+ 134,
173
+ 135,
174
+ 136,
175
+ 137,
176
+ 138,
177
+ 139,
178
+ 140,
179
+ 141,
180
+ 142,
181
+ 143,
182
+ 144,
183
+ 145,
184
+ 146,
185
+ 147,
186
+ 148,
187
+ 149,
188
+ 150,
189
+ 151,
190
+ 152,
191
+ 153,
192
+ 154,
193
+ 155,
194
+ 156,
195
+ 157,
196
+ 158,
197
+ 159,
198
+ 160,
199
+ 161,
200
+ 162,
201
+ 163,
202
+ 164,
203
+ 165,
204
+ 166,
205
+ 167,
206
+ 168,
207
+ 169,
208
+ 170,
209
+ 171,
210
+ 172,
211
+ 173,
212
+ 174,
213
+ 175,
214
+ 176,
215
+ 177,
216
+ 178,
217
+ 179,
218
+ 180,
219
+ 181,
220
+ 182,
221
+ 183,
222
+ 184,
223
+ 185,
224
+ 186,
225
+ 187,
226
+ 188,
227
+ 189,
228
+ 190,
229
+ 191,
230
+ 192,
231
+ 193,
232
+ 194,
233
+ 195,
234
+ 196,
235
+ 197,
236
+ 198,
237
+ 199,
238
+ 200,
239
+ 201,
240
+ 202,
241
+ 203,
242
+ 204,
243
+ 205,
244
+ 206,
245
+ 207,
246
+ 208,
247
+ 209,
248
+ 210,
249
+ 211,
250
+ 212,
251
+ 213,
252
+ 214,
253
+ 215,
254
+ 216,
255
+ 217,
256
+ 218,
257
+ 219,
258
+ 220,
259
+ 221,
260
+ 222,
261
+ 223,
262
+ 224,
263
+ 225,
264
+ 226,
265
+ 227,
266
+ 228,
267
+ 229,
268
+ 230,
269
+ 231,
270
+ 232,
271
+ 233,
272
+ 234,
273
+ 235,
274
+ 236,
275
+ 237,
276
+ 238,
277
+ 239,
278
+ 240,
279
+ 241,
280
+ 242,
281
+ 243,
282
+ 244,
283
+ 245,
284
+ 246,
285
+ 247,
286
+ 248
287
+ ]
288
+ }
289
+ ]
training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fb9e38b69c868d6e63f4f293ded95be815c9dd2bd1ddf0069acfcbdb35de4a4
3
+ size 1220614068
training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6773f99f925ec33c141f4e49d3dc522c92cd80a3aff840b30223c8ff0cbf4f84
3
+ size 15708
training_state/scheduler_state.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_lrs": [
3
+ 2e-05,
4
+ 2.0000000000000003e-06
5
+ ],
6
+ "last_epoch": 30000,
7
+ "_step_count": 30001,
8
+ "_is_initial": false,
9
+ "_get_lr_called_within_step": false,
10
+ "_last_lr": [
11
+ 0.0,
12
+ 0.0
13
+ ],
14
+ "lr_lambdas": [
15
+ null,
16
+ null
17
+ ]
18
+ }
training_state/training_step.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "step": 30000
3
+ }