Boffl commited on
Commit
229b243
·
verified ·
1 Parent(s): 864308e

Upload trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. trainer_state.json +329 -0
trainer_state.json ADDED
@@ -0,0 +1,329 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9993906154783668,
5
+ "eval_steps": 500,
6
+ "global_step": 410,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.02437538086532602,
13
+ "grad_norm": 0.7390244007110596,
14
+ "learning_rate": 1.0975609756097562e-05,
15
+ "loss": 3.3584,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.04875076173065204,
20
+ "grad_norm": 0.30350491404533386,
21
+ "learning_rate": 2.1951219512195124e-05,
22
+ "loss": 3.1749,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.07312614259597806,
27
+ "grad_norm": 0.3087550699710846,
28
+ "learning_rate": 3.292682926829269e-05,
29
+ "loss": 2.9963,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.09750152346130408,
34
+ "grad_norm": 0.20843257009983063,
35
+ "learning_rate": 4.51219512195122e-05,
36
+ "loss": 2.8865,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.1218769043266301,
41
+ "grad_norm": 0.2306743711233139,
42
+ "learning_rate": 4.996738892723075e-05,
43
+ "loss": 2.8482,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.14625228519195613,
48
+ "grad_norm": 0.37552645802497864,
49
+ "learning_rate": 4.976840705816688e-05,
50
+ "loss": 2.8334,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.17062766605728213,
55
+ "grad_norm": 0.207833930850029,
56
+ "learning_rate": 4.939000027687756e-05,
57
+ "loss": 2.7419,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.19500304692260817,
62
+ "grad_norm": 0.213443323969841,
63
+ "learning_rate": 4.8834909801373264e-05,
64
+ "loss": 2.6897,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.21937842778793418,
69
+ "grad_norm": 0.31744861602783203,
70
+ "learning_rate": 4.810715676468894e-05,
71
+ "loss": 2.6547,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.2437538086532602,
76
+ "grad_norm": 0.3662812113761902,
77
+ "learning_rate": 4.7212013085378824e-05,
78
+ "loss": 2.6865,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.2681291895185862,
83
+ "grad_norm": 0.2681748867034912,
84
+ "learning_rate": 4.615596327719111e-05,
85
+ "loss": 2.6123,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.29250457038391225,
90
+ "grad_norm": 0.22331994771957397,
91
+ "learning_rate": 4.507424333013069e-05,
92
+ "loss": 2.5791,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.3168799512492383,
97
+ "grad_norm": 0.3823238015174866,
98
+ "learning_rate": 4.373446685572683e-05,
99
+ "loss": 2.5722,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.34125533211456427,
104
+ "grad_norm": 1.0558502674102783,
105
+ "learning_rate": 4.225897595837744e-05,
106
+ "loss": 2.5763,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.3656307129798903,
111
+ "grad_norm": 0.2607211470603943,
112
+ "learning_rate": 4.0658459247330766e-05,
113
+ "loss": 2.5901,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.39000609384521634,
118
+ "grad_norm": 0.5509762763977051,
119
+ "learning_rate": 3.8944511031809865e-05,
120
+ "loss": 2.5185,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.4143814747105424,
125
+ "grad_norm": 0.2571032643318176,
126
+ "learning_rate": 3.712954733063284e-05,
127
+ "loss": 2.4729,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.43875685557586835,
132
+ "grad_norm": 0.25064775347709656,
133
+ "learning_rate": 3.5226715929283506e-05,
134
+ "loss": 2.5748,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.4631322364411944,
139
+ "grad_norm": 0.2534530758857727,
140
+ "learning_rate": 3.324980113598824e-05,
141
+ "loss": 2.5046,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.4875076173065204,
146
+ "grad_norm": 0.5358842015266418,
147
+ "learning_rate": 3.121312392675618e-05,
148
+ "loss": 2.5345,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.5118829981718465,
153
+ "grad_norm": 0.22321267426013947,
154
+ "learning_rate": 2.9131438202742124e-05,
155
+ "loss": 2.4931,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.5362583790371724,
160
+ "grad_norm": 0.48219671845436096,
161
+ "learning_rate": 2.7019823911454812e-05,
162
+ "loss": 2.4892,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.5606337599024985,
167
+ "grad_norm": 0.22396139800548553,
168
+ "learning_rate": 2.4893577806051537e-05,
169
+ "loss": 2.5281,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.5850091407678245,
174
+ "grad_norm": 0.28134435415267944,
175
+ "learning_rate": 2.2768102634070147e-05,
176
+ "loss": 2.4737,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.6093845216331505,
181
+ "grad_norm": 0.32630693912506104,
182
+ "learning_rate": 2.0658795558326743e-05,
183
+ "loss": 2.4923,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.6337599024984766,
188
+ "grad_norm": 0.27705642580986023,
189
+ "learning_rate": 1.8580936618269696e-05,
190
+ "loss": 2.4491,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.6581352833638026,
195
+ "grad_norm": 1.0377610921859741,
196
+ "learning_rate": 1.6549578039787436e-05,
197
+ "loss": 2.5303,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.6825106642291285,
202
+ "grad_norm": 0.212926983833313,
203
+ "learning_rate": 1.4579435195321434e-05,
204
+ "loss": 2.4304,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.7068860450944546,
209
+ "grad_norm": 1.0300441980361938,
210
+ "learning_rate": 1.2684780004180414e-05,
211
+ "loss": 2.4408,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.7312614259597806,
216
+ "grad_norm": 0.33628296852111816,
217
+ "learning_rate": 1.0879337545275165e-05,
218
+ "loss": 2.4091,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.7556368068251066,
223
+ "grad_norm": 0.2797647714614868,
224
+ "learning_rate": 9.176186631221958e-06,
225
+ "loss": 2.3872,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.7800121876904327,
230
+ "grad_norm": 0.21739082038402557,
231
+ "learning_rate": 7.587665064066085e-06,
232
+ "loss": 2.4045,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.8043875685557587,
237
+ "grad_norm": 0.508171796798706,
238
+ "learning_rate": 6.125280258962873e-06,
239
+ "loss": 2.4953,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.8287629494210847,
244
+ "grad_norm": 0.2408667802810669,
245
+ "learning_rate": 4.799625883267672e-06,
246
+ "loss": 2.3752,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.8531383302864107,
251
+ "grad_norm": 0.2731145918369293,
252
+ "learning_rate": 3.6203051149095973e-06,
253
+ "loss": 2.3658,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.8775137111517367,
258
+ "grad_norm": 0.3211069703102112,
259
+ "learning_rate": 2.595861075973613e-06,
260
+ "loss": 2.4198,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.9018890920170628,
265
+ "grad_norm": 0.2237868458032608,
266
+ "learning_rate": 1.733714945437212e-06,
267
+ "loss": 2.4113,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.9262644728823888,
272
+ "grad_norm": 0.2606222629547119,
273
+ "learning_rate": 1.0401121993794033e-06,
274
+ "loss": 2.4011,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.9506398537477148,
279
+ "grad_norm": 0.47373390197753906,
280
+ "learning_rate": 5.20077368103597e-07,
281
+ "loss": 2.4523,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.9750152346130408,
286
+ "grad_norm": 0.5579819679260254,
287
+ "learning_rate": 1.77377637918405e-07,
288
+ "loss": 2.4289,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.9993906154783668,
293
+ "grad_norm": 0.25126489996910095,
294
+ "learning_rate": 1.4495561248931145e-08,
295
+ "loss": 2.4421,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.9993906154783668,
300
+ "step": 410,
301
+ "total_flos": 5.610936315118879e+18,
302
+ "train_loss": 2.5786649890062288,
303
+ "train_runtime": 34559.7112,
304
+ "train_samples_per_second": 0.38,
305
+ "train_steps_per_second": 0.012
306
+ }
307
+ ],
308
+ "logging_steps": 10,
309
+ "max_steps": 410,
310
+ "num_input_tokens_seen": 0,
311
+ "num_train_epochs": 1,
312
+ "save_steps": 100,
313
+ "stateful_callbacks": {
314
+ "TrainerControl": {
315
+ "args": {
316
+ "should_epoch_stop": false,
317
+ "should_evaluate": false,
318
+ "should_log": false,
319
+ "should_save": true,
320
+ "should_training_stop": true
321
+ },
322
+ "attributes": {}
323
+ }
324
+ },
325
+ "total_flos": 5.610936315118879e+18,
326
+ "train_batch_size": 8,
327
+ "trial_name": null,
328
+ "trial_params": null
329
+ }