Hugging Face's logo

pravsels
/
molmoact2_ring_insert

Robotics
LeRobot
Safetensors
molmoact2
vla
Model card Files
xet
 Community
pravsels commited on
Commit
f05e535
·
verified ·
1 Parent(s): e3d9ba6

Upload MolmoAct2 checkpoint step 004000

Browse files
Files changed (12) hide show
  1. checkpoints/004000/pretrained_model/config.json +141 -0
  2. checkpoints/004000/pretrained_model/model.safetensors +3 -0
  3. checkpoints/004000/pretrained_model/policy_postprocessor.json +36 -0
  4. checkpoints/004000/pretrained_model/policy_postprocessor_step_1_molmoact2_masked_unnormalizer.safetensors +3 -0
  5. checkpoints/004000/pretrained_model/policy_preprocessor.json +102 -0
  6. checkpoints/004000/pretrained_model/policy_preprocessor_step_2_molmoact2_masked_normalizer.safetensors +3 -0
  7. checkpoints/004000/pretrained_model/train_config.json +279 -0
  8. checkpoints/004000/training_state/optimizer_param_groups.json +609 -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 +15 -0
  12. checkpoints/004000/training_state/training_step.json +3 -0
checkpoints/004000/pretrained_model/config.json ADDED
@@ -0,0 +1,141 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "molmoact2",
3
+ "n_obs_steps": 1,
4
+ "input_features": {
5
+ "observation.state": {
6
+ "type": "STATE",
7
+ "shape": [
8
+ 6
9
+ ]
10
+ },
11
+ "observation.images.front": {
12
+ "type": "VISUAL",
13
+ "shape": [
14
+ 3,
15
+ 576,
16
+ 1024
17
+ ]
18
+ },
19
+ "observation.images.top": {
20
+ "type": "VISUAL",
21
+ "shape": [
22
+ 3,
23
+ 576,
24
+ 1024
25
+ ]
26
+ },
27
+ "observation.images.wrist": {
28
+ "type": "VISUAL",
29
+ "shape": [
30
+ 3,
31
+ 720,
32
+ 1280
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": false,
48
+ "repo_id": null,
49
+ "private": null,
50
+ "tags": null,
51
+ "license": null,
52
+ "pretrained_path": null,
53
+ "checkpoint_path": "allenai/MolmoAct2",
54
+ "checkpoint_revision": null,
55
+ "checkpoint_force_download": false,
56
+ "trust_remote_code": true,
57
+ "chunk_size": 30,
58
+ "n_action_steps": 30,
59
+ "action_mode": "continuous",
60
+ "inference_action_mode": null,
61
+ "discrete_action_tokenizer": "allenai/MolmoAct2-FAST-Tokenizer",
62
+ "discrete_generation_max_steps": null,
63
+ "norm_tag": null,
64
+ "setup_type": "single so100/so101 robotic arm in molmoact2",
65
+ "control_mode": "absolute joint pose",
66
+ "image_keys": [
67
+ "observation.images.top",
68
+ "observation.images.wrist",
69
+ "observation.images.front"
70
+ ],
71
+ "normalize_language": true,
72
+ "add_setup_tokens": true,
73
+ "add_control_tokens": true,
74
+ "normalize_gripper": false,
75
+ "num_state_tokens": 256,
76
+ "max_sequence_length": null,
77
+ "expected_max_action_dim": 32,
78
+ "num_flow_timesteps": 8,
79
+ "flow_matching_cutoff": 1.0,
80
+ "flow_matching_time_offset": 0.001,
81
+ "flow_matching_time_scale": 0.999,
82
+ "flow_matching_beta_alpha": 1.0,
83
+ "flow_matching_beta_beta": 1.5,
84
+ "num_inference_steps": null,
85
+ "mask_action_dim_padding": true,
86
+ "enable_inference_cuda_graph": true,
87
+ "per_episode_seed": false,
88
+ "eval_seed": null,
89
+ "rtc_config": null,
90
+ "enable_lora_vlm": false,
91
+ "lora_rank": 64,
92
+ "lora_alpha": 16,
93
+ "lora_dropout": 0.05,
94
+ "lora_bias": "none",
95
+ "enable_lora_action_expert": false,
96
+ "enable_knowledge_insulation": false,
97
+ "freeze_embedding": true,
98
+ "train_action_expert_only": true,
99
+ "gradient_checkpointing": true,
100
+ "model_dtype": "bfloat16",
101
+ "softmax_auxiliary_loss": true,
102
+ "softmax_auxiliary_loss_scale": 0.0001,
103
+ "discrete_loss_token_weighting": "root_subsegments_root_tokens",
104
+ "optimizer_lr": 1e-05,
105
+ "optimizer_vit_lr": 5e-06,
106
+ "optimizer_connector_lr": 5e-06,
107
+ "optimizer_action_expert_lr": 5e-05,
108
+ "optimizer_betas": [
109
+ 0.9,
110
+ 0.95
111
+ ],
112
+ "optimizer_eps": 1e-06,
113
+ "optimizer_weight_decay": 0.0,
114
+ "optimizer_grad_clip_norm": 1.0,
115
+ "scheduler_warmup_steps": 200,
116
+ "scheduler_decay_steps": 30000,
117
+ "scheduler_decay_lr": 1e-06,
118
+ "normalization_mapping": {
119
+ "ACTION": "MEAN_STD",
120
+ "STATE": "MEAN_STD",
121
+ "VISUAL": "IDENTITY"
122
+ },
123
+ "dataset_feature_names": {
124
+ "action": [
125
+ "shoulder_pan.pos",
126
+ "shoulder_lift.pos",
127
+ "elbow_flex.pos",
128
+ "wrist_flex.pos",
129
+ "wrist_roll.pos",
130
+ "gripper.pos"
131
+ ],
132
+ "observation.state": [
133
+ "shoulder_pan.pos",
134
+ "shoulder_lift.pos",
135
+ "elbow_flex.pos",
136
+ "wrist_flex.pos",
137
+ "wrist_roll.pos",
138
+ "gripper.pos"
139
+ ]
140
+ }
141
+ }
checkpoints/004000/pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58d439fae7deb470c1225f82aba45ea925a6ed7989d4f06ce5118df1cc0acdb5
3
+ size 10884573720
checkpoints/004000/pretrained_model/policy_postprocessor.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "policy_postprocessor",
3
+ "steps": [
4
+ {
5
+ "registry_name": "molmoact2_clamp_action",
6
+ "config": {}
7
+ },
8
+ {
9
+ "registry_name": "molmoact2_masked_unnormalizer",
10
+ "config": {
11
+ "eps": 1e-08,
12
+ "features": {
13
+ "action": {
14
+ "type": "ACTION",
15
+ "shape": [
16
+ 6
17
+ ]
18
+ }
19
+ },
20
+ "norm_map": {
21
+ "ACTION": "MEAN_STD",
22
+ "STATE": "MEAN_STD",
23
+ "VISUAL": "IDENTITY"
24
+ }
25
+ },
26
+ "state_file": "policy_postprocessor_step_1_molmoact2_masked_unnormalizer.safetensors"
27
+ },
28
+ {
29
+ "registry_name": "device_processor",
30
+ "config": {
31
+ "device": "cpu",
32
+ "float_dtype": null
33
+ }
34
+ }
35
+ ]
36
+ }
checkpoints/004000/pretrained_model/policy_postprocessor_step_1_molmoact2_masked_unnormalizer.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:865a09d0365d4c80515db401dc3d7fc2d36226d0e730fa56dc7f39fe827c49ab
3
+ size 8728
checkpoints/004000/pretrained_model/policy_preprocessor.json ADDED
@@ -0,0 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "molmoact2_masked_normalizer",
16
+ "config": {
17
+ "eps": 1e-08,
18
+ "features": {
19
+ "observation.state": {
20
+ "type": "STATE",
21
+ "shape": [
22
+ 6
23
+ ]
24
+ },
25
+ "observation.images.front": {
26
+ "type": "VISUAL",
27
+ "shape": [
28
+ 3,
29
+ 576,
30
+ 1024
31
+ ]
32
+ },
33
+ "observation.images.top": {
34
+ "type": "VISUAL",
35
+ "shape": [
36
+ 3,
37
+ 576,
38
+ 1024
39
+ ]
40
+ },
41
+ "observation.images.wrist": {
42
+ "type": "VISUAL",
43
+ "shape": [
44
+ 3,
45
+ 720,
46
+ 1280
47
+ ]
48
+ },
49
+ "action": {
50
+ "type": "ACTION",
51
+ "shape": [
52
+ 6
53
+ ]
54
+ }
55
+ },
56
+ "norm_map": {
57
+ "ACTION": "MEAN_STD",
58
+ "STATE": "MEAN_STD",
59
+ "VISUAL": "IDENTITY"
60
+ }
61
+ },
62
+ "state_file": "policy_preprocessor_step_2_molmoact2_masked_normalizer.safetensors"
63
+ },
64
+ {
65
+ "registry_name": "molmoact2_clamp_normalized",
66
+ "config": {}
67
+ },
68
+ {
69
+ "registry_name": "molmoact2_pack_inputs",
70
+ "config": {
71
+ "checkpoint_path": "allenai/MolmoAct2",
72
+ "checkpoint_revision": null,
73
+ "checkpoint_force_download": false,
74
+ "trust_remote_code": true,
75
+ "action_mode": "continuous",
76
+ "discrete_action_tokenizer": "allenai/MolmoAct2-FAST-Tokenizer",
77
+ "image_keys": [
78
+ "observation.images.top",
79
+ "observation.images.wrist",
80
+ "observation.images.front"
81
+ ],
82
+ "setup_type": "single so100/so101 robotic arm in molmoact2",
83
+ "control_mode": "absolute joint pose",
84
+ "normalize_language": true,
85
+ "add_setup_tokens": true,
86
+ "add_control_tokens": true,
87
+ "num_state_tokens": 256,
88
+ "max_sequence_length": null,
89
+ "chunk_size": 30,
90
+ "max_action_dim": 32,
91
+ "env_action_dim": 6
92
+ }
93
+ },
94
+ {
95
+ "registry_name": "device_processor",
96
+ "config": {
97
+ "device": "cuda",
98
+ "float_dtype": null
99
+ }
100
+ }
101
+ ]
102
+ }
checkpoints/004000/pretrained_model/policy_preprocessor_step_2_molmoact2_masked_normalizer.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:865a09d0365d4c80515db401dc3d7fc2d36226d0e730fa56dc7f39fe827c49ab
3
+ size 8728
checkpoints/004000/pretrained_model/train_config.json ADDED
@@ -0,0 +1,279 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "villekuosmanen/armnetbench_ring_insert",
4
+ "root": null,
5
+ "episodes": null,
6
+ "image_transforms": {
7
+ "enable": true,
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": "pyav",
80
+ "return_uint8": false,
81
+ "streaming": false
82
+ },
83
+ "env": null,
84
+ "policy": {
85
+ "type": "molmoact2",
86
+ "n_obs_steps": 1,
87
+ "input_features": {
88
+ "observation.state": {
89
+ "type": "STATE",
90
+ "shape": [
91
+ 6
92
+ ]
93
+ },
94
+ "observation.images.front": {
95
+ "type": "VISUAL",
96
+ "shape": [
97
+ 3,
98
+ 576,
99
+ 1024
100
+ ]
101
+ },
102
+ "observation.images.top": {
103
+ "type": "VISUAL",
104
+ "shape": [
105
+ 3,
106
+ 576,
107
+ 1024
108
+ ]
109
+ },
110
+ "observation.images.wrist": {
111
+ "type": "VISUAL",
112
+ "shape": [
113
+ 3,
114
+ 720,
115
+ 1280
116
+ ]
117
+ }
118
+ },
119
+ "output_features": {
120
+ "action": {
121
+ "type": "ACTION",
122
+ "shape": [
123
+ 6
124
+ ]
125
+ }
126
+ },
127
+ "device": "cuda",
128
+ "use_amp": false,
129
+ "use_peft": false,
130
+ "push_to_hub": false,
131
+ "repo_id": null,
132
+ "private": null,
133
+ "tags": null,
134
+ "license": null,
135
+ "pretrained_path": null,
136
+ "checkpoint_path": "allenai/MolmoAct2",
137
+ "checkpoint_revision": null,
138
+ "checkpoint_force_download": false,
139
+ "trust_remote_code": true,
140
+ "chunk_size": 30,
141
+ "n_action_steps": 30,
142
+ "action_mode": "continuous",
143
+ "inference_action_mode": null,
144
+ "discrete_action_tokenizer": "allenai/MolmoAct2-FAST-Tokenizer",
145
+ "discrete_generation_max_steps": null,
146
+ "norm_tag": null,
147
+ "setup_type": "single so100/so101 robotic arm in molmoact2",
148
+ "control_mode": "absolute joint pose",
149
+ "image_keys": [
150
+ "observation.images.top",
151
+ "observation.images.wrist",
152
+ "observation.images.front"
153
+ ],
154
+ "normalize_language": true,
155
+ "add_setup_tokens": true,
156
+ "add_control_tokens": true,
157
+ "normalize_gripper": false,
158
+ "num_state_tokens": 256,
159
+ "max_sequence_length": null,
160
+ "expected_max_action_dim": 32,
161
+ "num_flow_timesteps": 8,
162
+ "flow_matching_cutoff": 1.0,
163
+ "flow_matching_time_offset": 0.001,
164
+ "flow_matching_time_scale": 0.999,
165
+ "flow_matching_beta_alpha": 1.0,
166
+ "flow_matching_beta_beta": 1.5,
167
+ "num_inference_steps": null,
168
+ "mask_action_dim_padding": true,
169
+ "enable_inference_cuda_graph": true,
170
+ "per_episode_seed": false,
171
+ "eval_seed": null,
172
+ "rtc_config": null,
173
+ "enable_lora_vlm": false,
174
+ "lora_rank": 64,
175
+ "lora_alpha": 16,
176
+ "lora_dropout": 0.05,
177
+ "lora_bias": "none",
178
+ "enable_lora_action_expert": false,
179
+ "enable_knowledge_insulation": false,
180
+ "freeze_embedding": true,
181
+ "train_action_expert_only": true,
182
+ "gradient_checkpointing": true,
183
+ "model_dtype": "bfloat16",
184
+ "softmax_auxiliary_loss": true,
185
+ "softmax_auxiliary_loss_scale": 0.0001,
186
+ "discrete_loss_token_weighting": "root_subsegments_root_tokens",
187
+ "optimizer_lr": 1e-05,
188
+ "optimizer_vit_lr": 5e-06,
189
+ "optimizer_connector_lr": 5e-06,
190
+ "optimizer_action_expert_lr": 5e-05,
191
+ "optimizer_betas": [
192
+ 0.9,
193
+ 0.95
194
+ ],
195
+ "optimizer_eps": 1e-06,
196
+ "optimizer_weight_decay": 0.0,
197
+ "optimizer_grad_clip_norm": 1.0,
198
+ "scheduler_warmup_steps": 200,
199
+ "scheduler_decay_steps": 30000,
200
+ "scheduler_decay_lr": 1e-06,
201
+ "normalization_mapping": {
202
+ "ACTION": "MEAN_STD",
203
+ "STATE": "MEAN_STD",
204
+ "VISUAL": "IDENTITY"
205
+ },
206
+ "dataset_feature_names": {
207
+ "action": [
208
+ "shoulder_pan.pos",
209
+ "shoulder_lift.pos",
210
+ "elbow_flex.pos",
211
+ "wrist_flex.pos",
212
+ "wrist_roll.pos",
213
+ "gripper.pos"
214
+ ],
215
+ "observation.state": [
216
+ "shoulder_pan.pos",
217
+ "shoulder_lift.pos",
218
+ "elbow_flex.pos",
219
+ "wrist_flex.pos",
220
+ "wrist_roll.pos",
221
+ "gripper.pos"
222
+ ]
223
+ }
224
+ },
225
+ "reward_model": null,
226
+ "output_dir": "/workspace/vast_runs/molmoact2/checkpoints/molmoact2_ring_insert_base",
227
+ "job_name": "molmoact2_ring_insert_base",
228
+ "resume": false,
229
+ "seed": 1000,
230
+ "cudnn_deterministic": false,
231
+ "num_workers": 8,
232
+ "batch_size": 64,
233
+ "prefetch_factor": 4,
234
+ "persistent_workers": true,
235
+ "steps": 30000,
236
+ "eval_freq": -1,
237
+ "log_freq": 20,
238
+ "tolerance_s": 0.0001,
239
+ "save_checkpoint": true,
240
+ "save_freq": 2000,
241
+ "use_policy_training_preset": true,
242
+ "optimizer": {
243
+ "type": "adamw",
244
+ "lr": 1e-05,
245
+ "weight_decay": 0.0,
246
+ "grad_clip_norm": 1.0,
247
+ "betas": [
248
+ 0.9,
249
+ 0.95
250
+ ],
251
+ "eps": 1e-06
252
+ },
253
+ "scheduler": {
254
+ "type": "molmoact2_cosine_decay_with_warmup",
255
+ "num_warmup_steps": 200,
256
+ "num_decay_steps": 30000,
257
+ "peak_lr": 1e-05,
258
+ "decay_lr": 1e-06
259
+ },
260
+ "eval": {
261
+ "n_episodes": 50,
262
+ "batch_size": 50,
263
+ "use_async_envs": true
264
+ },
265
+ "wandb": {
266
+ "enable": true,
267
+ "disable_artifact": false,
268
+ "project": "molmoact2_ring_insert",
269
+ "entity": "pravsels",
270
+ "notes": null,
271
+ "run_id": "jo0do532",
272
+ "mode": "offline",
273
+ "add_tags": true
274
+ },
275
+ "peft": null,
276
+ "sample_weighting": null,
277
+ "rename_map": {},
278
+ "checkpoint_path": null
279
+ }
checkpoints/004000/training_state/optimizer_param_groups.json ADDED
@@ -0,0 +1,609 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "lr": 4.805477279695852e-05,
4
+ "betas": [
5
+ 0.9,
6
+ 0.95
7
+ ],
8
+ "eps": 1e-06,
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": true,
17
+ "initial_lr": 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
+ ]
608
+ }
609
+ ]
checkpoints/004000/training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ea6643b3fcd7d6d44e9319e0cb7289f014de3a52c40d01df98e5039557363be
3
+ size 2310410496
checkpoints/004000/training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c973c58cc5cb4046699b89259532ba0c9ebc335c6886132553f457b21149f0e9
3
+ size 15708
checkpoints/004000/training_state/scheduler_state.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_lrs": [
3
+ 5e-05
4
+ ],
5
+ "last_epoch": 4000,
6
+ "verbose": false,
7
+ "_step_count": 4001,
8
+ "_get_lr_called_within_step": false,
9
+ "_last_lr": [
10
+ 4.805477279695852e-05
11
+ ],
12
+ "lr_lambdas": [
13
+ null
14
+ ]
15
+ }
checkpoints/004000/training_state/training_step.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "step": 4000
3
+ }