pavan01729 commited on
Commit
aaa908e
·
verified ·
1 Parent(s): f3f40aa

Add trainer_state.json

Browse files
Files changed (1) hide show
  1. trainer_state.json +339 -0
trainer_state.json ADDED
@@ -0,0 +1,339 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 5.0,
6
+ "eval_steps": 100,
7
+ "global_step": 200,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.12578616352201258,
14
+ "grad_norm": 1.6983928680419922,
15
+ "learning_rate": 1e-05,
16
+ "loss": 1.9207,
17
+ "step": 5
18
+ },
19
+ {
20
+ "epoch": 0.25157232704402516,
21
+ "grad_norm": 2.0057549476623535,
22
+ "learning_rate": 2.25e-05,
23
+ "loss": 1.8211,
24
+ "step": 10
25
+ },
26
+ {
27
+ "epoch": 0.37735849056603776,
28
+ "grad_norm": 2.055621385574341,
29
+ "learning_rate": 3.5e-05,
30
+ "loss": 1.517,
31
+ "step": 15
32
+ },
33
+ {
34
+ "epoch": 0.5031446540880503,
35
+ "grad_norm": 1.7859697341918945,
36
+ "learning_rate": 4.75e-05,
37
+ "loss": 0.9972,
38
+ "step": 20
39
+ },
40
+ {
41
+ "epoch": 0.6289308176100629,
42
+ "grad_norm": 2.006009817123413,
43
+ "learning_rate": 4.993910125649561e-05,
44
+ "loss": 0.6685,
45
+ "step": 25
46
+ },
47
+ {
48
+ "epoch": 0.7547169811320755,
49
+ "grad_norm": 1.7193933725357056,
50
+ "learning_rate": 4.9692208514878444e-05,
51
+ "loss": 0.521,
52
+ "step": 30
53
+ },
54
+ {
55
+ "epoch": 0.8805031446540881,
56
+ "grad_norm": 1.2538529634475708,
57
+ "learning_rate": 4.925739315689991e-05,
58
+ "loss": 0.4388,
59
+ "step": 35
60
+ },
61
+ {
62
+ "epoch": 1.0,
63
+ "grad_norm": 1.2421389818191528,
64
+ "learning_rate": 4.8637964389982926e-05,
65
+ "loss": 0.4147,
66
+ "step": 40
67
+ },
68
+ {
69
+ "epoch": 1.1257861635220126,
70
+ "grad_norm": 1.097655177116394,
71
+ "learning_rate": 4.783863644106502e-05,
72
+ "loss": 0.3337,
73
+ "step": 45
74
+ },
75
+ {
76
+ "epoch": 1.251572327044025,
77
+ "grad_norm": 1.446738839149475,
78
+ "learning_rate": 4.6865492678484895e-05,
79
+ "loss": 0.3674,
80
+ "step": 50
81
+ },
82
+ {
83
+ "epoch": 1.3773584905660377,
84
+ "grad_norm": 1.0339725017547607,
85
+ "learning_rate": 4.572593931387604e-05,
86
+ "loss": 0.3454,
87
+ "step": 55
88
+ },
89
+ {
90
+ "epoch": 1.5031446540880502,
91
+ "grad_norm": 1.1563431024551392,
92
+ "learning_rate": 4.442864903642428e-05,
93
+ "loss": 0.3299,
94
+ "step": 60
95
+ },
96
+ {
97
+ "epoch": 1.6289308176100628,
98
+ "grad_norm": 1.6715773344039917,
99
+ "learning_rate": 4.2983495008466276e-05,
100
+ "loss": 0.3243,
101
+ "step": 65
102
+ },
103
+ {
104
+ "epoch": 1.7547169811320755,
105
+ "grad_norm": 4.052298545837402,
106
+ "learning_rate": 4.140147572476268e-05,
107
+ "loss": 0.3037,
108
+ "step": 70
109
+ },
110
+ {
111
+ "epoch": 1.880503144654088,
112
+ "grad_norm": 1.0090709924697876,
113
+ "learning_rate": 3.969463130731183e-05,
114
+ "loss": 0.2797,
115
+ "step": 75
116
+ },
117
+ {
118
+ "epoch": 2.0,
119
+ "grad_norm": 1.0944145917892456,
120
+ "learning_rate": 3.787595187275136e-05,
121
+ "loss": 0.2966,
122
+ "step": 80
123
+ },
124
+ {
125
+ "epoch": 2.1257861635220126,
126
+ "grad_norm": 0.9973664879798889,
127
+ "learning_rate": 3.5959278669726935e-05,
128
+ "loss": 0.2336,
129
+ "step": 85
130
+ },
131
+ {
132
+ "epoch": 2.251572327044025,
133
+ "grad_norm": 0.9893947839736938,
134
+ "learning_rate": 3.39591987386325e-05,
135
+ "loss": 0.2068,
136
+ "step": 90
137
+ },
138
+ {
139
+ "epoch": 2.3773584905660377,
140
+ "grad_norm": 1.6538398265838623,
141
+ "learning_rate": 3.1890933895424976e-05,
142
+ "loss": 0.2066,
143
+ "step": 95
144
+ },
145
+ {
146
+ "epoch": 2.50314465408805,
147
+ "grad_norm": 1.2943580150604248,
148
+ "learning_rate": 2.9770224884413623e-05,
149
+ "loss": 0.2127,
150
+ "step": 100
151
+ },
152
+ {
153
+ "epoch": 2.50314465408805,
154
+ "eval_loss": 0.25331389904022217,
155
+ "eval_runtime": 2.6526,
156
+ "eval_samples_per_second": 13.572,
157
+ "eval_steps_per_second": 6.786,
158
+ "step": 100
159
+ },
160
+ {
161
+ "epoch": 2.6289308176100628,
162
+ "grad_norm": 1.2970905303955078,
163
+ "learning_rate": 2.761321158169134e-05,
164
+ "loss": 0.2128,
165
+ "step": 105
166
+ },
167
+ {
168
+ "epoch": 2.7547169811320753,
169
+ "grad_norm": 1.2746000289916992,
170
+ "learning_rate": 2.5436310160932092e-05,
171
+ "loss": 0.2079,
172
+ "step": 110
173
+ },
174
+ {
175
+ "epoch": 2.880503144654088,
176
+ "grad_norm": 1.2576719522476196,
177
+ "learning_rate": 2.3256088156396868e-05,
178
+ "loss": 0.222,
179
+ "step": 115
180
+ },
181
+ {
182
+ "epoch": 3.0,
183
+ "grad_norm": 1.5171639919281006,
184
+ "learning_rate": 2.1089138373994223e-05,
185
+ "loss": 0.2071,
186
+ "step": 120
187
+ },
188
+ {
189
+ "epoch": 3.1257861635220126,
190
+ "grad_norm": 0.8614316582679749,
191
+ "learning_rate": 1.895195261000831e-05,
192
+ "loss": 0.1476,
193
+ "step": 125
194
+ },
195
+ {
196
+ "epoch": 3.251572327044025,
197
+ "grad_norm": 1.1631187200546265,
198
+ "learning_rate": 1.686079613857109e-05,
199
+ "loss": 0.1453,
200
+ "step": 130
201
+ },
202
+ {
203
+ "epoch": 3.3773584905660377,
204
+ "grad_norm": 1.5442155599594116,
205
+ "learning_rate": 1.4831583923104999e-05,
206
+ "loss": 0.1565,
207
+ "step": 135
208
+ },
209
+ {
210
+ "epoch": 3.50314465408805,
211
+ "grad_norm": 1.555525541305542,
212
+ "learning_rate": 1.2879759493841575e-05,
213
+ "loss": 0.1452,
214
+ "step": 140
215
+ },
216
+ {
217
+ "epoch": 3.6289308176100628,
218
+ "grad_norm": 2.1617038249969482,
219
+ "learning_rate": 1.1020177413231334e-05,
220
+ "loss": 0.1494,
221
+ "step": 145
222
+ },
223
+ {
224
+ "epoch": 3.7547169811320753,
225
+ "grad_norm": 1.2040760517120361,
226
+ "learning_rate": 9.266990223754069e-06,
227
+ "loss": 0.1674,
228
+ "step": 150
229
+ },
230
+ {
231
+ "epoch": 3.880503144654088,
232
+ "grad_norm": 1.2778819799423218,
233
+ "learning_rate": 7.633540738525066e-06,
234
+ "loss": 0.1466,
235
+ "step": 155
236
+ },
237
+ {
238
+ "epoch": 4.0,
239
+ "grad_norm": 1.4193259477615356,
240
+ "learning_rate": 6.1322604944307e-06,
241
+ "loss": 0.1431,
242
+ "step": 160
243
+ },
244
+ {
245
+ "epoch": 4.1257861635220126,
246
+ "grad_norm": 0.9114992618560791,
247
+ "learning_rate": 4.7745751406263165e-06,
248
+ "loss": 0.1318,
249
+ "step": 165
250
+ },
251
+ {
252
+ "epoch": 4.251572327044025,
253
+ "grad_norm": 0.9443201422691345,
254
+ "learning_rate": 3.5708174824471947e-06,
255
+ "loss": 0.1157,
256
+ "step": 170
257
+ },
258
+ {
259
+ "epoch": 4.377358490566038,
260
+ "grad_norm": 0.9356920719146729,
261
+ "learning_rate": 2.5301488425208296e-06,
262
+ "loss": 0.1248,
263
+ "step": 175
264
+ },
265
+ {
266
+ "epoch": 4.50314465408805,
267
+ "grad_norm": 0.7772902846336365,
268
+ "learning_rate": 1.6604893375699594e-06,
269
+ "loss": 0.1201,
270
+ "step": 180
271
+ },
272
+ {
273
+ "epoch": 4.628930817610063,
274
+ "grad_norm": 1.1060445308685303,
275
+ "learning_rate": 9.684576015420278e-07,
276
+ "loss": 0.1147,
277
+ "step": 185
278
+ },
279
+ {
280
+ "epoch": 4.754716981132075,
281
+ "grad_norm": 0.6479562520980835,
282
+ "learning_rate": 4.5932041380840065e-07,
283
+ "loss": 0.1335,
284
+ "step": 190
285
+ },
286
+ {
287
+ "epoch": 4.880503144654088,
288
+ "grad_norm": 0.9411827325820923,
289
+ "learning_rate": 1.3695261579316777e-07,
290
+ "loss": 0.1151,
291
+ "step": 195
292
+ },
293
+ {
294
+ "epoch": 5.0,
295
+ "grad_norm": 1.4004632234573364,
296
+ "learning_rate": 3.807621090218261e-09,
297
+ "loss": 0.1242,
298
+ "step": 200
299
+ },
300
+ {
301
+ "epoch": 5.0,
302
+ "eval_loss": 0.22299104928970337,
303
+ "eval_runtime": 2.1223,
304
+ "eval_samples_per_second": 16.962,
305
+ "eval_steps_per_second": 8.481,
306
+ "step": 200
307
+ },
308
+ {
309
+ "epoch": 5.0,
310
+ "step": 200,
311
+ "total_flos": 8601980193079296.0,
312
+ "train_loss": 0.369250630736351,
313
+ "train_runtime": 349.7562,
314
+ "train_samples_per_second": 4.546,
315
+ "train_steps_per_second": 0.572
316
+ }
317
+ ],
318
+ "logging_steps": 5,
319
+ "max_steps": 200,
320
+ "num_input_tokens_seen": 0,
321
+ "num_train_epochs": 5,
322
+ "save_steps": 100,
323
+ "stateful_callbacks": {
324
+ "TrainerControl": {
325
+ "args": {
326
+ "should_epoch_stop": false,
327
+ "should_evaluate": false,
328
+ "should_log": false,
329
+ "should_save": true,
330
+ "should_training_stop": true
331
+ },
332
+ "attributes": {}
333
+ }
334
+ },
335
+ "total_flos": 8601980193079296.0,
336
+ "train_batch_size": 2,
337
+ "trial_name": null,
338
+ "trial_params": null
339
+ }