Hariharan05 commited on
Commit
81c4a6d
·
verified ·
1 Parent(s): e398bc7

Upload 2 files

Browse files
Files changed (2) hide show
  1. trainer_state.json +384 -0
  2. training_args.bin +3 -0
trainer_state.json ADDED
@@ -0,0 +1,384 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.1907032181168058,
6
+ "eval_steps": 500,
7
+ "global_step": 500,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.023837902264600714,
14
+ "grad_norm": 8.34217357635498,
15
+ "learning_rate": 1.6e-07,
16
+ "loss": 3.2614,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.04767580452920143,
21
+ "grad_norm": 10.162466049194336,
22
+ "learning_rate": 3.6e-07,
23
+ "loss": 3.2005,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.07151370679380215,
28
+ "grad_norm": 8.322413444519043,
29
+ "learning_rate": 5.6e-07,
30
+ "loss": 3.3002,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.09535160905840286,
35
+ "grad_norm": 6.742789268493652,
36
+ "learning_rate": 7.599999999999999e-07,
37
+ "loss": 3.1868,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.11918951132300358,
42
+ "grad_norm": 6.748029708862305,
43
+ "learning_rate": 9.6e-07,
44
+ "loss": 3.1789,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.1430274135876043,
49
+ "grad_norm": 5.005261421203613,
50
+ "learning_rate": 9.992203820909905e-07,
51
+ "loss": 3.0969,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.16686531585220502,
56
+ "grad_norm": 6.2596893310546875,
57
+ "learning_rate": 9.960573506572389e-07,
58
+ "loss": 3.021,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.1907032181168057,
63
+ "grad_norm": 5.589771747589111,
64
+ "learning_rate": 9.904775776745956e-07,
65
+ "loss": 3.1221,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.21454112038140644,
70
+ "grad_norm": 7.189596176147461,
71
+ "learning_rate": 9.825082472361556e-07,
72
+ "loss": 3.0537,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.23837902264600716,
77
+ "grad_norm": 5.899924278259277,
78
+ "learning_rate": 9.721881851187405e-07,
79
+ "loss": 3.0154,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.2622169249106079,
84
+ "grad_norm": 4.845108509063721,
85
+ "learning_rate": 9.595676696276171e-07,
86
+ "loss": 3.0747,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.2860548271752086,
91
+ "grad_norm": 5.564320087432861,
92
+ "learning_rate": 9.447081866456487e-07,
93
+ "loss": 2.9519,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.3098927294398093,
98
+ "grad_norm": 6.226819038391113,
99
+ "learning_rate": 9.276821300802533e-07,
100
+ "loss": 3.0256,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.33373063170441003,
105
+ "grad_norm": 5.26694393157959,
106
+ "learning_rate": 9.085724491675642e-07,
107
+ "loss": 2.843,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.3575685339690107,
112
+ "grad_norm": 5.471522808074951,
113
+ "learning_rate": 8.874722443520898e-07,
114
+ "loss": 2.8078,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.3814064362336114,
119
+ "grad_norm": 5.0895819664001465,
120
+ "learning_rate": 8.644843137107057e-07,
121
+ "loss": 2.8523,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.4052443384982122,
126
+ "grad_norm": 4.7197794914245605,
127
+ "learning_rate": 8.397206521307583e-07,
128
+ "loss": 2.754,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.42908224076281287,
133
+ "grad_norm": 5.758249282836914,
134
+ "learning_rate": 8.133019056822302e-07,
135
+ "loss": 2.7133,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.45292014302741357,
140
+ "grad_norm": 4.340641021728516,
141
+ "learning_rate": 7.853567838422159e-07,
142
+ "loss": 2.6577,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.4767580452920143,
147
+ "grad_norm": 4.795559406280518,
148
+ "learning_rate": 7.560214324352858e-07,
149
+ "loss": 2.7179,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.5005959475566151,
154
+ "grad_norm": 5.540432929992676,
155
+ "learning_rate": 7.254387703447153e-07,
156
+ "loss": 2.6652,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.5244338498212158,
161
+ "grad_norm": 4.245532035827637,
162
+ "learning_rate": 6.937577932260514e-07,
163
+ "loss": 2.6331,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.5482717520858165,
168
+ "grad_norm": 4.427391052246094,
169
+ "learning_rate": 6.611328476152556e-07,
170
+ "loss": 2.6846,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.5721096543504172,
175
+ "grad_norm": 5.0143842697143555,
176
+ "learning_rate": 6.277228789678953e-07,
177
+ "loss": 2.605,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.5959475566150179,
182
+ "grad_norm": 5.8499603271484375,
183
+ "learning_rate": 5.936906572928624e-07,
184
+ "loss": 2.4651,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.6197854588796186,
189
+ "grad_norm": 4.577277183532715,
190
+ "learning_rate": 5.592019841532506e-07,
191
+ "loss": 2.4897,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.6436233611442194,
196
+ "grad_norm": 4.542954444885254,
197
+ "learning_rate": 5.244248848978067e-07,
198
+ "loss": 2.4942,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.6674612634088201,
203
+ "grad_norm": 5.428004741668701,
204
+ "learning_rate": 4.895287900583216e-07,
205
+ "loss": 2.5005,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.6912991656734208,
210
+ "grad_norm": 4.4296956062316895,
211
+ "learning_rate": 4.5468370990110997e-07,
212
+ "loss": 2.3997,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.7151370679380215,
217
+ "grad_norm": 4.045319557189941,
218
+ "learning_rate": 4.200594061540826e-07,
219
+ "loss": 2.3467,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.7389749702026222,
224
+ "grad_norm": 4.404695510864258,
225
+ "learning_rate": 3.8582456494467206e-07,
226
+ "loss": 2.4801,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.7628128724672228,
231
+ "grad_norm": 5.092370510101318,
232
+ "learning_rate": 3.521459749779768e-07,
233
+ "loss": 2.4103,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.7866507747318237,
238
+ "grad_norm": 5.434021472930908,
239
+ "learning_rate": 3.191877149589539e-07,
240
+ "loss": 2.401,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.8104886769964244,
245
+ "grad_norm": 4.2743353843688965,
246
+ "learning_rate": 2.8711035421746363e-07,
247
+ "loss": 2.4399,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.834326579261025,
252
+ "grad_norm": 4.966851711273193,
253
+ "learning_rate": 2.5607017043063353e-07,
254
+ "loss": 2.3473,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.8581644815256257,
259
+ "grad_norm": 5.600205898284912,
260
+ "learning_rate": 2.262183882537249e-07,
261
+ "loss": 2.4595,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.8820023837902264,
266
+ "grad_norm": 4.966123580932617,
267
+ "learning_rate": 1.9770044256881258e-07,
268
+ "loss": 2.4161,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.9058402860548271,
273
+ "grad_norm": 4.942025184631348,
274
+ "learning_rate": 1.7065526994065972e-07,
275
+ "loss": 2.3971,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.929678188319428,
280
+ "grad_norm": 5.2323102951049805,
281
+ "learning_rate": 1.4521463173173965e-07,
282
+ "loss": 2.3786,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.9535160905840286,
287
+ "grad_norm": 5.717218399047852,
288
+ "learning_rate": 1.2150247217412185e-07,
289
+ "loss": 2.3473,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.9773539928486293,
294
+ "grad_norm": 5.0170416831970215,
295
+ "learning_rate": 9.963431452563331e-08,
296
+ "loss": 2.401,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 1.0,
301
+ "grad_norm": 7.488749980926514,
302
+ "learning_rate": 7.971669825215787e-08,
303
+ "loss": 2.3823,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 1.0238379022646007,
308
+ "grad_norm": 6.092284202575684,
309
+ "learning_rate": 6.184665997806831e-08,
310
+ "loss": 2.3511,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 1.0476758045292014,
315
+ "grad_norm": 5.5308709144592285,
316
+ "learning_rate": 4.611126073354571e-08,
317
+ "loss": 2.4092,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 1.071513706793802,
322
+ "grad_norm": 5.2230119705200195,
323
+ "learning_rate": 3.258716180199278e-08,
324
+ "loss": 2.3573,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 1.0953516090584028,
329
+ "grad_norm": 4.9154510498046875,
330
+ "learning_rate": 2.1340251233966377e-08,
331
+ "loss": 2.3055,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 1.1191895113230035,
336
+ "grad_norm": 4.627120494842529,
337
+ "learning_rate": 1.2425322847218367e-08,
338
+ "loss": 2.3723,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 1.1430274135876042,
343
+ "grad_norm": 6.616613864898682,
344
+ "learning_rate": 5.8858092767236076e-09,
345
+ "loss": 2.2949,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 1.166865315852205,
350
+ "grad_norm": 5.475731372833252,
351
+ "learning_rate": 1.7535703752478147e-09,
352
+ "loss": 2.4503,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 1.1907032181168058,
357
+ "grad_norm": 5.741678237915039,
358
+ "learning_rate": 4.873799534788059e-11,
359
+ "loss": 2.2666,
360
+ "step": 500
361
+ }
362
+ ],
363
+ "logging_steps": 10,
364
+ "max_steps": 500,
365
+ "num_input_tokens_seen": 0,
366
+ "num_train_epochs": 2,
367
+ "save_steps": 500,
368
+ "stateful_callbacks": {
369
+ "TrainerControl": {
370
+ "args": {
371
+ "should_epoch_stop": false,
372
+ "should_evaluate": false,
373
+ "should_log": false,
374
+ "should_save": true,
375
+ "should_training_stop": true
376
+ },
377
+ "attributes": {}
378
+ }
379
+ },
380
+ "total_flos": 7169104310525952.0,
381
+ "train_batch_size": 2,
382
+ "trial_name": null,
383
+ "trial_params": null
384
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:976f0b6d72522cb6a661245289321f415673af56c4a3b8b85e3f41abfa0d1c1e
3
+ size 6097