aDaikiKamata commited on
Commit
fe3b0da
·
verified ·
1 Parent(s): c4b3c87

checkpoint 008000

Browse files
checkpoints/008000/pretrained_model/config.json ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "type": "patch_policy",
3
+ "n_obs_steps": 2,
4
+ "input_features": {
5
+ "observation.images.image": {
6
+ "type": "VISUAL",
7
+ "shape": [
8
+ 3,
9
+ 256,
10
+ 256
11
+ ]
12
+ },
13
+ "observation.images.wrist_image": {
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
+ },
28
+ "output_features": {
29
+ "action": {
30
+ "type": "ACTION",
31
+ "shape": [
32
+ 7
33
+ ]
34
+ }
35
+ },
36
+ "device": "cuda",
37
+ "dtype": null,
38
+ "use_amp": false,
39
+ "use_peft": false,
40
+ "push_to_hub": true,
41
+ "repo_id": "aDaikiKamata/patch_policy_libero10_tipsv2_token_long",
42
+ "private": null,
43
+ "tags": null,
44
+ "license": null,
45
+ "pretrained_path": null,
46
+ "pretrained_revision": null,
47
+ "horizon": 16,
48
+ "n_action_steps": 3,
49
+ "encoder_type": "tipsv2",
50
+ "encoder_model_id": "google/tipsv2-b14",
51
+ "image_size": 224,
52
+ "language_conditioning": true,
53
+ "language_conditioning_mode": "token",
54
+ "encoder_autocast_dtype": "bfloat16",
55
+ "n_layer": 8,
56
+ "n_head": 4,
57
+ "n_embd": 256,
58
+ "p_drop_emb": 0.0,
59
+ "p_drop_attn": 0.1,
60
+ "num_train_timesteps": 100,
61
+ "beta_schedule": "squaredcos_cap_v2",
62
+ "prediction_type": "epsilon",
63
+ "clip_sample": true,
64
+ "num_inference_steps": null,
65
+ "optimizer_lr": 0.0001,
66
+ "optimizer_weight_decay": 0.0,
67
+ "scheduler_name": "cosine",
68
+ "scheduler_warmup_steps": 1000,
69
+ "use_ema": true,
70
+ "ema_power": 0.75,
71
+ "ema_max_decay": 0.9999,
72
+ "normalization_mapping": {
73
+ "VISUAL": "IDENTITY",
74
+ "STATE": "MIN_MAX",
75
+ "ACTION": "MIN_MAX"
76
+ }
77
+ }
checkpoints/008000/pretrained_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29344e0a6747c5dd86afd6ef0a1d2c67e4d67feff942da38d8ef66bdd535664d
3
+ size 911440512
checkpoints/008000/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
+ 7
13
+ ]
14
+ }
15
+ },
16
+ "norm_map": {
17
+ "VISUAL": "IDENTITY",
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
+ }
checkpoints/008000/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 sha256:362bec11490a5dcbe22158ca42260c64ed67ca7090e6f1ba887338e8794a3024
3
+ size 3836
checkpoints/008000/pretrained_model/policy_preprocessor.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "device_processor",
16
+ "config": {
17
+ "device": "cuda",
18
+ "float_dtype": null
19
+ }
20
+ },
21
+ {
22
+ "registry_name": "normalizer_processor",
23
+ "config": {
24
+ "eps": 1e-08,
25
+ "features": {
26
+ "observation.images.image": {
27
+ "type": "VISUAL",
28
+ "shape": [
29
+ 3,
30
+ 256,
31
+ 256
32
+ ]
33
+ },
34
+ "observation.images.wrist_image": {
35
+ "type": "VISUAL",
36
+ "shape": [
37
+ 3,
38
+ 256,
39
+ 256
40
+ ]
41
+ },
42
+ "observation.state": {
43
+ "type": "STATE",
44
+ "shape": [
45
+ 8
46
+ ]
47
+ },
48
+ "action": {
49
+ "type": "ACTION",
50
+ "shape": [
51
+ 7
52
+ ]
53
+ }
54
+ },
55
+ "norm_map": {
56
+ "VISUAL": "IDENTITY",
57
+ "STATE": "MIN_MAX",
58
+ "ACTION": "MIN_MAX"
59
+ }
60
+ },
61
+ "state_file": "policy_preprocessor_step_3_normalizer_processor.safetensors"
62
+ }
63
+ ]
64
+ }
checkpoints/008000/pretrained_model/policy_preprocessor_step_3_normalizer_processor.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2b203b801fffbbf547146d5d0e0d9956fc055ca810b477f023e930cc9787614
3
+ size 3844
checkpoints/008000/pretrained_model/train_config.json ADDED
@@ -0,0 +1,297 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": {
3
+ "repo_id": "lerobot/libero_10_image",
4
+ "repo_type": "dataset",
5
+ "root": null,
6
+ "episodes": null,
7
+ "exclude_episodes": null,
8
+ "image_transforms": {
9
+ "enable": false,
10
+ "max_num_transforms": 3,
11
+ "random_order": false,
12
+ "tfs": {
13
+ "brightness": {
14
+ "weight": 1.0,
15
+ "type": "ColorJitter",
16
+ "kwargs": {
17
+ "brightness": [
18
+ 0.8,
19
+ 1.2
20
+ ]
21
+ }
22
+ },
23
+ "contrast": {
24
+ "weight": 1.0,
25
+ "type": "ColorJitter",
26
+ "kwargs": {
27
+ "contrast": [
28
+ 0.8,
29
+ 1.2
30
+ ]
31
+ }
32
+ },
33
+ "saturation": {
34
+ "weight": 1.0,
35
+ "type": "ColorJitter",
36
+ "kwargs": {
37
+ "saturation": [
38
+ 0.5,
39
+ 1.5
40
+ ]
41
+ }
42
+ },
43
+ "hue": {
44
+ "weight": 1.0,
45
+ "type": "ColorJitter",
46
+ "kwargs": {
47
+ "hue": [
48
+ -0.05,
49
+ 0.05
50
+ ]
51
+ }
52
+ },
53
+ "sharpness": {
54
+ "weight": 1.0,
55
+ "type": "SharpnessJitter",
56
+ "kwargs": {
57
+ "sharpness": [
58
+ 0.5,
59
+ 1.5
60
+ ]
61
+ }
62
+ },
63
+ "affine": {
64
+ "weight": 1.0,
65
+ "type": "RandomAffine",
66
+ "kwargs": {
67
+ "degrees": [
68
+ -5.0,
69
+ 5.0
70
+ ],
71
+ "translate": [
72
+ 0.05,
73
+ 0.05
74
+ ]
75
+ }
76
+ }
77
+ }
78
+ },
79
+ "revision": null,
80
+ "use_imagenet_stats": true,
81
+ "video_backend": "torchcodec",
82
+ "return_uint8": false,
83
+ "depth_output_unit": "mm",
84
+ "streaming": false,
85
+ "streaming_episode_pool_size": 32,
86
+ "streaming_sampling_strategy": "remaining",
87
+ "streaming_prefetch_episodes": 8,
88
+ "streaming_byte_budget_gb": 8.0,
89
+ "streaming_decode_threads": 2,
90
+ "streaming_decoded_queue_size": 8,
91
+ "streaming_native_http_connections": null,
92
+ "streaming_native_http_subranges": 1,
93
+ "video_decoder_cache_size": null,
94
+ "eval_split": 0.0
95
+ },
96
+ "env": null,
97
+ "policy": {
98
+ "type": "patch_policy",
99
+ "n_obs_steps": 2,
100
+ "input_features": {
101
+ "observation.images.image": {
102
+ "type": "VISUAL",
103
+ "shape": [
104
+ 3,
105
+ 256,
106
+ 256
107
+ ]
108
+ },
109
+ "observation.images.wrist_image": {
110
+ "type": "VISUAL",
111
+ "shape": [
112
+ 3,
113
+ 256,
114
+ 256
115
+ ]
116
+ },
117
+ "observation.state": {
118
+ "type": "STATE",
119
+ "shape": [
120
+ 8
121
+ ]
122
+ }
123
+ },
124
+ "output_features": {
125
+ "action": {
126
+ "type": "ACTION",
127
+ "shape": [
128
+ 7
129
+ ]
130
+ }
131
+ },
132
+ "device": "cuda",
133
+ "dtype": null,
134
+ "use_amp": false,
135
+ "use_peft": false,
136
+ "push_to_hub": true,
137
+ "repo_id": "aDaikiKamata/patch_policy_libero10_tipsv2_token_long",
138
+ "private": null,
139
+ "tags": null,
140
+ "license": null,
141
+ "pretrained_path": null,
142
+ "pretrained_revision": null,
143
+ "horizon": 16,
144
+ "n_action_steps": 3,
145
+ "encoder_type": "tipsv2",
146
+ "encoder_model_id": "google/tipsv2-b14",
147
+ "image_size": 224,
148
+ "language_conditioning": true,
149
+ "language_conditioning_mode": "token",
150
+ "encoder_autocast_dtype": "bfloat16",
151
+ "n_layer": 8,
152
+ "n_head": 4,
153
+ "n_embd": 256,
154
+ "p_drop_emb": 0.0,
155
+ "p_drop_attn": 0.1,
156
+ "num_train_timesteps": 100,
157
+ "beta_schedule": "squaredcos_cap_v2",
158
+ "prediction_type": "epsilon",
159
+ "clip_sample": true,
160
+ "num_inference_steps": null,
161
+ "optimizer_lr": 0.0001,
162
+ "optimizer_weight_decay": 0.0,
163
+ "scheduler_name": "cosine",
164
+ "scheduler_warmup_steps": 1000,
165
+ "use_ema": true,
166
+ "ema_power": 0.75,
167
+ "ema_max_decay": 0.9999,
168
+ "normalization_mapping": {
169
+ "VISUAL": "IDENTITY",
170
+ "STATE": "MIN_MAX",
171
+ "ACTION": "MIN_MAX"
172
+ }
173
+ },
174
+ "reward_model": null,
175
+ "output_dir": "outputs/patch_policy_libero10_tipsv2_token_long",
176
+ "job_name": "patch_policy",
177
+ "resume": false,
178
+ "seed": 1000,
179
+ "cudnn_deterministic": false,
180
+ "num_workers": 8,
181
+ "batch_size": 128,
182
+ "prefetch_factor": 4,
183
+ "persistent_workers": true,
184
+ "dataloader_multiprocessing_context": "spawn",
185
+ "steps": 40000,
186
+ "env_eval_freq": 20000,
187
+ "log_freq": 500,
188
+ "eval_steps": 0,
189
+ "max_eval_samples": 0,
190
+ "tolerance_s": 0.0001,
191
+ "save_checkpoint": true,
192
+ "save_freq": 8000,
193
+ "checkpoint_format": "safetensors",
194
+ "use_policy_training_preset": true,
195
+ "optimizer": {
196
+ "type": "adamw",
197
+ "lr": 0.0001,
198
+ "weight_decay": 0.0,
199
+ "grad_clip_norm": 10.0,
200
+ "betas": [
201
+ 0.9,
202
+ 0.999
203
+ ],
204
+ "eps": 1e-08
205
+ },
206
+ "scheduler": {
207
+ "type": "diffuser",
208
+ "num_warmup_steps": 1000,
209
+ "name": "cosine"
210
+ },
211
+ "parallelism": {
212
+ "dp_replicate": 1,
213
+ "dp_shard": 1,
214
+ "context_parallel": {
215
+ "ring_degree": 1,
216
+ "ulysses_degree": 1
217
+ },
218
+ "cfg_parallel": 1
219
+ },
220
+ "accelerator": {
221
+ "mixed_precision": "no",
222
+ "gradient_accumulation": {
223
+ "steps": 1
224
+ },
225
+ "grad_scaler": {
226
+ "init_scale": 65536.0,
227
+ "growth_factor": 2.0,
228
+ "backoff_factor": 0.5,
229
+ "growth_interval": 2000
230
+ },
231
+ "fsdp": {
232
+ "reshard_after_forward": true,
233
+ "wrap_modules": null,
234
+ "min_num_params": null,
235
+ "cpu_offload": false,
236
+ "ignored_modules": null
237
+ },
238
+ "ddp": {
239
+ "find_unused_parameters": true,
240
+ "gradient_as_bucket_view": false,
241
+ "static_graph": false
242
+ },
243
+ "compile": {
244
+ "enabled": false,
245
+ "backend": "inductor",
246
+ "mode": null,
247
+ "regional": true
248
+ },
249
+ "activation_checkpointing": {
250
+ "mode": "none"
251
+ }
252
+ },
253
+ "eval": {
254
+ "n_episodes": 50,
255
+ "batch_size": 50,
256
+ "use_async_envs": true,
257
+ "recording": false,
258
+ "recording_repo_id": null,
259
+ "recording_private": false
260
+ },
261
+ "ema": {
262
+ "enable": false,
263
+ "decay": null,
264
+ "update_after_step": 0,
265
+ "inv_gamma": 1.0,
266
+ "power": 0.75,
267
+ "min_decay": 0.0,
268
+ "max_decay": 0.9999,
269
+ "use_for_eval": true
270
+ },
271
+ "wandb": {
272
+ "enable": true,
273
+ "disable_artifact": false,
274
+ "project": "vla-autolab",
275
+ "entity": null,
276
+ "notes": null,
277
+ "run_id": "pnq8s5fp",
278
+ "resume": null,
279
+ "mode": null,
280
+ "console": "wrap",
281
+ "console_multipart": false,
282
+ "console_chunk_max_seconds": 0,
283
+ "add_tags": true
284
+ },
285
+ "peft": null,
286
+ "job": {
287
+ "target": null,
288
+ "image": "huggingface/lerobot-gpu:latest",
289
+ "timeout": "2d",
290
+ "detach": false,
291
+ "tags": []
292
+ },
293
+ "save_checkpoint_to_hub": true,
294
+ "sample_weighting": null,
295
+ "rename_map": {},
296
+ "checkpoint_path": null
297
+ }
checkpoints/008000/training_state/optimizer_param_groups.json ADDED
@@ -0,0 +1,277 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "lr": 9.225950427718975e-05,
4
+ "betas": [
5
+ 0.9,
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": true,
17
+ "initial_lr": 0.0001,
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
+ ]
276
+ }
277
+ ]
checkpoints/008000/training_state/optimizer_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4279df46bc6fc42ed41400bc3aad8df545ee35b13548bb1f34022d93493698b4
3
+ size 127572720
checkpoints/008000/training_state/rng_state.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03205736b98b80194c97c5d058e5840c8f7baa0a9024a26394695dad3dfec52d
3
+ size 15708
checkpoints/008000/training_state/scheduler_state.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_lrs": [
3
+ 0.0001
4
+ ],
5
+ "last_epoch": 8000,
6
+ "_step_count": 8001,
7
+ "_is_initial": false,
8
+ "_get_lr_called_within_step": false,
9
+ "_last_lr": [
10
+ 9.225950427718975e-05
11
+ ],
12
+ "lr_lambdas": [
13
+ null
14
+ ]
15
+ }
checkpoints/008000/training_state/training_step.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "step": 8000,
3
+ "dp_world_size": 1,
4
+ "batch_size": 128,
5
+ "grad_accum_steps": 1,
6
+ "mixed_precision": "no",
7
+ "parallelism": {
8
+ "dp_replicate": 1,
9
+ "dp_shard": 1,
10
+ "ring_degree": 1,
11
+ "ulysses_degree": 1
12
+ }
13
+ }