Hugging Face's logo

phospho-app
/
small12black-rcgyenhtx4

Safetensors
gr00t_n1
phosphobot
gr00t
replicate
Model card Files Community
LegrandFrederic commited on
Commit
7145a03
·
verified ·
1 Parent(s): 4cdf84c

Upload trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. trainer_state.json +294 -0
trainer_state.json ADDED
@@ -0,0 +1,294 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 9.891891891891891,
5
+ "eval_steps": 500,
6
+ "global_step": 366,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.2702702702702703,
13
+ "grad_norm": 4.698714733123779,
14
+ "learning_rate": 0.00010526315789473685,
15
+ "loss": 0.9004,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.5405405405405406,
20
+ "grad_norm": 1.5324004888534546,
21
+ "learning_rate": 0.00019999590166142655,
22
+ "loss": 0.2857,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.8108108108108109,
27
+ "grad_norm": 1.7758814096450806,
28
+ "learning_rate": 0.00019950450737506824,
29
+ "loss": 0.1811,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 1.0810810810810811,
34
+ "grad_norm": 0.9645628929138184,
35
+ "learning_rate": 0.00019819805815653768,
36
+ "loss": 0.1416,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 1.3513513513513513,
41
+ "grad_norm": 0.9237997531890869,
42
+ "learning_rate": 0.00019608725530879375,
43
+ "loss": 0.1186,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 1.6216216216216215,
48
+ "grad_norm": 0.8899639844894409,
49
+ "learning_rate": 0.00019318938870459984,
50
+ "loss": 0.1076,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 1.8918918918918919,
55
+ "grad_norm": 0.8379050493240356,
56
+ "learning_rate": 0.0001895281951628281,
57
+ "loss": 0.1,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 2.1621621621621623,
62
+ "grad_norm": 0.49454841017723083,
63
+ "learning_rate": 0.00018513366401695276,
64
+ "loss": 0.0912,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 2.4324324324324325,
69
+ "grad_norm": 0.5223703384399414,
70
+ "learning_rate": 0.0001800417914683471,
71
+ "loss": 0.079,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 2.7027027027027026,
76
+ "grad_norm": 0.26653391122817993,
77
+ "learning_rate": 0.00017429428573651024,
78
+ "loss": 0.077,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 2.972972972972973,
83
+ "grad_norm": 0.6166922450065613,
84
+ "learning_rate": 0.0001679382254213768,
85
+ "loss": 0.0717,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 3.2432432432432434,
90
+ "grad_norm": 0.5702475309371948,
91
+ "learning_rate": 0.0001610256738761125,
92
+ "loss": 0.0612,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 3.5135135135135136,
97
+ "grad_norm": 0.4581798017024994,
98
+ "learning_rate": 0.00015361325274911779,
99
+ "loss": 0.0544,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 3.7837837837837838,
104
+ "grad_norm": 0.44726666808128357,
105
+ "learning_rate": 0.0001457616781884173,
106
+ "loss": 0.0628,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 4.054054054054054,
111
+ "grad_norm": 0.3319581151008606,
112
+ "learning_rate": 0.0001375352635074461,
113
+ "loss": 0.0648,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 4.324324324324325,
118
+ "grad_norm": 0.5032352805137634,
119
+ "learning_rate": 0.00012900139238596598,
120
+ "loss": 0.058,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 4.594594594594595,
125
+ "grad_norm": 0.36259725689888,
126
+ "learning_rate": 0.00012022996692119424,
127
+ "loss": 0.0497,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 4.864864864864865,
132
+ "grad_norm": 0.17420651018619537,
133
+ "learning_rate": 0.00011129283505023274,
134
+ "loss": 0.053,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 5.135135135135135,
139
+ "grad_norm": 0.32951629161834717,
140
+ "learning_rate": 0.00010226320203385878,
141
+ "loss": 0.0518,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 5.405405405405405,
146
+ "grad_norm": 0.27635061740875244,
147
+ "learning_rate": 9.321503082229282e-05,
148
+ "loss": 0.048,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 5.675675675675675,
153
+ "grad_norm": 0.3280782699584961,
154
+ "learning_rate": 8.422243621462969e-05,
155
+ "loss": 0.0516,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 5.945945945945946,
160
+ "grad_norm": 0.29008397459983826,
161
+ "learning_rate": 7.535907777445449e-05,
162
+ "loss": 0.0465,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 6.216216216216216,
167
+ "grad_norm": 0.24701108038425446,
168
+ "learning_rate": 6.669755647435474e-05,
169
+ "loss": 0.0436,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 6.486486486486487,
174
+ "grad_norm": 0.34741994738578796,
175
+ "learning_rate": 5.830882001149517e-05,
176
+ "loss": 0.0499,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 6.756756756756757,
181
+ "grad_norm": 0.2663642168045044,
182
+ "learning_rate": 5.0261581665395475e-05,
183
+ "loss": 0.0439,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 7.027027027027027,
188
+ "grad_norm": 0.34826692938804626,
189
+ "learning_rate": 4.2621757458127285e-05,
190
+ "loss": 0.0465,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 7.297297297297297,
195
+ "grad_norm": 0.2025139331817627,
196
+ "learning_rate": 3.5451926227225997e-05,
197
+ "loss": 0.041,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 7.5675675675675675,
202
+ "grad_norm": 0.2484084963798523,
203
+ "learning_rate": 2.8810817033934656e-05,
204
+ "loss": 0.0384,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 7.837837837837838,
209
+ "grad_norm": 0.19896186888217926,
210
+ "learning_rate": 2.275282810548811e-05,
211
+ "loss": 0.0368,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 8.108108108108109,
216
+ "grad_norm": 0.24585744738578796,
217
+ "learning_rate": 1.73275812518469e-05,
218
+ "loss": 0.0382,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 8.378378378378379,
223
+ "grad_norm": 0.2137955129146576,
224
+ "learning_rate": 1.2579515406713193e-05,
225
+ "loss": 0.0417,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 8.64864864864865,
230
+ "grad_norm": 0.29916706681251526,
231
+ "learning_rate": 8.547522622190385e-06,
232
+ "loss": 0.0349,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 8.91891891891892,
237
+ "grad_norm": 0.21314117312431335,
238
+ "learning_rate": 5.264629498702967e-06,
239
+ "loss": 0.038,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 9.18918918918919,
244
+ "grad_norm": 0.2648143470287323,
245
+ "learning_rate": 2.7577266596274576e-06,
246
+ "loss": 0.0386,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 9.45945945945946,
251
+ "grad_norm": 0.21586932241916656,
252
+ "learning_rate": 1.0473484865448525e-06,
253
+ "loss": 0.0356,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 9.72972972972973,
258
+ "grad_norm": 0.24431149661540985,
259
+ "learning_rate": 1.4750491933247512e-07,
260
+ "loss": 0.0428,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 9.891891891891891,
265
+ "step": 366,
266
+ "total_flos": 4.991850946034842e+16,
267
+ "train_loss": 0.09146885374367562,
268
+ "train_runtime": 453.0584,
269
+ "train_samples_per_second": 51.702,
270
+ "train_steps_per_second": 0.808
271
+ }
272
+ ],
273
+ "logging_steps": 10,
274
+ "max_steps": 366,
275
+ "num_input_tokens_seen": 0,
276
+ "num_train_epochs": 10,
277
+ "save_steps": 10000,
278
+ "stateful_callbacks": {
279
+ "TrainerControl": {
280
+ "args": {
281
+ "should_epoch_stop": false,
282
+ "should_evaluate": false,
283
+ "should_log": false,
284
+ "should_save": true,
285
+ "should_training_stop": true
286
+ },
287
+ "attributes": {}
288
+ }
289
+ },
290
+ "total_flos": 4.991850946034842e+16,
291
+ "train_batch_size": 64,
292
+ "trial_name": null,
293
+ "trial_params": null
294
+ }