Hugging Face's logo

phospho-app
/
lego_so-100-o6n9vcub5e

Safetensors
gr00t_n1
phosphobot
gr00t
replicate
Model card Files Community
LegrandFrederic commited on
Commit
38a2fec
·
verified ·
1 Parent(s): cbc445c

Upload trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. trainer_state.json +280 -0
trainer_state.json ADDED
@@ -0,0 +1,280 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 340,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.14705882352941177,
13
+ "grad_norm": 2.458341360092163,
14
+ "learning_rate": 0.00011764705882352942,
15
+ "loss": 0.8805,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.29411764705882354,
20
+ "grad_norm": 1.3460900783538818,
21
+ "learning_rate": 0.00019995743267092514,
22
+ "loss": 0.4012,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.4411764705882353,
27
+ "grad_norm": 1.291209101676941,
28
+ "learning_rate": 0.0001992016878768271,
29
+ "loss": 0.3084,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.5882352941176471,
34
+ "grad_norm": 1.0544739961624146,
35
+ "learning_rate": 0.00019750822700209488,
36
+ "loss": 0.2579,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.7352941176470589,
41
+ "grad_norm": 1.0863096714019775,
42
+ "learning_rate": 0.00019489305769264812,
43
+ "loss": 0.241,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.8823529411764706,
48
+ "grad_norm": 0.8423298001289368,
49
+ "learning_rate": 0.00019138090015605118,
50
+ "loss": 0.2391,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 1.0294117647058822,
55
+ "grad_norm": 0.7478500008583069,
56
+ "learning_rate": 0.0001870049534907294,
57
+ "loss": 0.1854,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 1.1764705882352942,
62
+ "grad_norm": 0.7334464192390442,
63
+ "learning_rate": 0.00018180658186743332,
64
+ "loss": 0.1821,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 1.3235294117647058,
69
+ "grad_norm": 1.0398321151733398,
70
+ "learning_rate": 0.00017583492352935814,
71
+ "loss": 0.164,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 1.4705882352941178,
76
+ "grad_norm": 0.9809992909431458,
77
+ "learning_rate": 0.00016914642630689388,
78
+ "loss": 0.1647,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 1.6176470588235294,
83
+ "grad_norm": 0.5706636905670166,
84
+ "learning_rate": 0.00016180431403760837,
85
+ "loss": 0.1683,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 1.7647058823529411,
90
+ "grad_norm": 0.7732464671134949,
91
+ "learning_rate": 0.00015387798893519455,
92
+ "loss": 0.1546,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 1.9117647058823528,
97
+ "grad_norm": 0.7296786308288574,
98
+ "learning_rate": 0.00014544237555656216,
99
+ "loss": 0.1286,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 2.0588235294117645,
104
+ "grad_norm": 0.6389240622520447,
105
+ "learning_rate": 0.00013657721256830506,
106
+ "loss": 0.1227,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 2.2058823529411766,
111
+ "grad_norm": 0.46665242314338684,
112
+ "learning_rate": 0.0001273662990072083,
113
+ "loss": 0.1368,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 2.3529411764705883,
118
+ "grad_norm": 0.6480994820594788,
119
+ "learning_rate": 0.00011789670215960975,
120
+ "loss": 0.1192,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 2.5,
125
+ "grad_norm": 0.4292305111885071,
126
+ "learning_rate": 0.00010825793454723325,
127
+ "loss": 0.1051,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 2.6470588235294117,
132
+ "grad_norm": 0.6904204487800598,
133
+ "learning_rate": 9.854110779913537e-05,
134
+ "loss": 0.1065,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 2.7941176470588234,
139
+ "grad_norm": 0.6822876334190369,
140
+ "learning_rate": 8.883807140789478e-05,
141
+ "loss": 0.1107,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 2.9411764705882355,
146
+ "grad_norm": 0.5520216822624207,
147
+ "learning_rate": 7.924054451105614e-05,
148
+ "loss": 0.1155,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 3.088235294117647,
153
+ "grad_norm": 0.4506421685218811,
154
+ "learning_rate": 6.983924890477138e-05,
155
+ "loss": 0.0978,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 3.235294117647059,
160
+ "grad_norm": 0.538611650466919,
161
+ "learning_rate": 6.072305148493195e-05,
162
+ "loss": 0.0987,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 3.3823529411764706,
167
+ "grad_norm": 0.3745705485343933,
168
+ "learning_rate": 5.197812422197286e-05,
169
+ "loss": 0.0956,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 3.5294117647058822,
174
+ "grad_norm": 0.458775132894516,
175
+ "learning_rate": 4.368712960978864e-05,
176
+ "loss": 0.0928,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 3.6764705882352944,
181
+ "grad_norm": 0.31457090377807617,
182
+ "learning_rate": 3.59284392884057e-05,
183
+ "loss": 0.0906,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 3.8235294117647056,
188
+ "grad_norm": 0.48355451226234436,
189
+ "learning_rate": 2.8775393226475224e-05,
190
+ "loss": 0.0907,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 3.9705882352941178,
195
+ "grad_norm": 0.32496538758277893,
196
+ "learning_rate": 2.229560646625448e-05,
197
+ "loss": 0.0813,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 4.117647058823529,
202
+ "grad_norm": 0.38124969601631165,
203
+ "learning_rate": 1.6550329984155112e-05,
204
+ "loss": 0.0902,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 4.264705882352941,
209
+ "grad_norm": 0.3412385880947113,
210
+ "learning_rate": 1.1593871708401526e-05,
211
+ "loss": 0.0727,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 4.411764705882353,
216
+ "grad_norm": 0.36698442697525024,
217
+ "learning_rate": 7.473083166700945e-06,
218
+ "loss": 0.0796,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 4.5588235294117645,
223
+ "grad_norm": 0.43249696493148804,
224
+ "learning_rate": 4.226916616450916e-06,
225
+ "loss": 0.0807,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 4.705882352941177,
230
+ "grad_norm": 0.40810427069664,
231
+ "learning_rate": 1.8860568437648052e-06,
232
+ "loss": 0.0825,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 4.852941176470588,
237
+ "grad_norm": 0.3101021945476532,
238
+ "learning_rate": 4.726311117803084e-07,
239
+ "loss": 0.082,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 5.0,
244
+ "grad_norm": 0.40530508756637573,
245
+ "learning_rate": 0.0,
246
+ "loss": 0.0693,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 5.0,
251
+ "step": 340,
252
+ "total_flos": 1.1211231724308e+16,
253
+ "train_loss": 0.161671401998576,
254
+ "train_runtime": 161.3443,
255
+ "train_samples_per_second": 33.717,
256
+ "train_steps_per_second": 2.107
257
+ }
258
+ ],
259
+ "logging_steps": 10,
260
+ "max_steps": 340,
261
+ "num_input_tokens_seen": 0,
262
+ "num_train_epochs": 5,
263
+ "save_steps": 500,
264
+ "stateful_callbacks": {
265
+ "TrainerControl": {
266
+ "args": {
267
+ "should_epoch_stop": false,
268
+ "should_evaluate": false,
269
+ "should_log": false,
270
+ "should_save": true,
271
+ "should_training_stop": true
272
+ },
273
+ "attributes": {}
274
+ }
275
+ },
276
+ "total_flos": 1.1211231724308e+16,
277
+ "train_batch_size": 16,
278
+ "trial_name": null,
279
+ "trial_params": null
280
+ }