archit11 commited on
Commit
bb4ff55
1 Parent(s): 2b0da39

End of training

Browse files
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.25,
3
+ "eval_accuracy": 0.11733870967741936,
4
+ "eval_loss": 2.6881909370422363,
5
+ "eval_runtime": 956.0688,
6
+ "eval_samples_per_second": 5.188,
7
+ "eval_steps_per_second": 1.297
8
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:98093e8ea95d67570e6adee5f12ea599b5266087276d5c4a5e741a7a4ddff790
3
  size 344974288
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:535be6dad3a62f6829b7c666a5010a08856a39ffd3c3dc986eac3d488f15f11e
3
  size 344974288
runs/Mar17_19-54-10_6d634beb8d83/events.out.tfevents.1710718688.6d634beb8d83.25.1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:30d6e342d394993354863da95f3e8f53d6b23a86c627626677801760078857ee
3
- size 411
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d95636150b60cb0112df8ac30aed91a957292bde75537431061d151ea735135
3
+ size 734
test_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.25,
3
+ "eval_accuracy": 0.11733870967741936,
4
+ "eval_loss": 2.6881909370422363,
5
+ "eval_runtime": 956.0688,
6
+ "eval_samples_per_second": 5.188,
7
+ "eval_steps_per_second": 1.297
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,1064 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.18403036166096146,
3
+ "best_model_checkpoint": "videomae-base-finetuned-ucfcrime-full2/checkpoint-700",
4
+ "epoch": 3.25,
5
+ "eval_steps": 500,
6
+ "global_step": 700,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01,
13
+ "grad_norm": 14.482718467712402,
14
+ "learning_rate": 3.5714285714285714e-06,
15
+ "loss": 2.6878,
16
+ "step": 5
17
+ },
18
+ {
19
+ "epoch": 0.01,
20
+ "grad_norm": 21.39861297607422,
21
+ "learning_rate": 7.142857142857143e-06,
22
+ "loss": 2.6074,
23
+ "step": 10
24
+ },
25
+ {
26
+ "epoch": 0.02,
27
+ "grad_norm": 17.860671997070312,
28
+ "learning_rate": 1.0714285714285714e-05,
29
+ "loss": 2.7214,
30
+ "step": 15
31
+ },
32
+ {
33
+ "epoch": 0.03,
34
+ "grad_norm": 16.79393768310547,
35
+ "learning_rate": 1.4285714285714285e-05,
36
+ "loss": 2.5776,
37
+ "step": 20
38
+ },
39
+ {
40
+ "epoch": 0.04,
41
+ "grad_norm": 14.525908470153809,
42
+ "learning_rate": 1.785714285714286e-05,
43
+ "loss": 2.689,
44
+ "step": 25
45
+ },
46
+ {
47
+ "epoch": 0.04,
48
+ "grad_norm": 12.049698829650879,
49
+ "learning_rate": 2.1428571428571428e-05,
50
+ "loss": 2.6499,
51
+ "step": 30
52
+ },
53
+ {
54
+ "epoch": 0.05,
55
+ "grad_norm": 13.192450523376465,
56
+ "learning_rate": 2.5e-05,
57
+ "loss": 2.5365,
58
+ "step": 35
59
+ },
60
+ {
61
+ "epoch": 0.06,
62
+ "grad_norm": 10.041342735290527,
63
+ "learning_rate": 2.857142857142857e-05,
64
+ "loss": 2.4945,
65
+ "step": 40
66
+ },
67
+ {
68
+ "epoch": 0.06,
69
+ "grad_norm": 10.616167068481445,
70
+ "learning_rate": 3.2142857142857144e-05,
71
+ "loss": 2.7132,
72
+ "step": 45
73
+ },
74
+ {
75
+ "epoch": 0.07,
76
+ "grad_norm": 11.666309356689453,
77
+ "learning_rate": 3.571428571428572e-05,
78
+ "loss": 2.5329,
79
+ "step": 50
80
+ },
81
+ {
82
+ "epoch": 0.08,
83
+ "grad_norm": 8.298579216003418,
84
+ "learning_rate": 3.928571428571429e-05,
85
+ "loss": 2.4331,
86
+ "step": 55
87
+ },
88
+ {
89
+ "epoch": 0.09,
90
+ "grad_norm": 9.002656936645508,
91
+ "learning_rate": 4.2857142857142856e-05,
92
+ "loss": 2.3991,
93
+ "step": 60
94
+ },
95
+ {
96
+ "epoch": 0.09,
97
+ "grad_norm": 10.443252563476562,
98
+ "learning_rate": 4.642857142857143e-05,
99
+ "loss": 2.7184,
100
+ "step": 65
101
+ },
102
+ {
103
+ "epoch": 0.1,
104
+ "grad_norm": 8.290853500366211,
105
+ "learning_rate": 5e-05,
106
+ "loss": 2.4219,
107
+ "step": 70
108
+ },
109
+ {
110
+ "epoch": 0.11,
111
+ "grad_norm": 8.40210247039795,
112
+ "learning_rate": 4.960317460317461e-05,
113
+ "loss": 2.3317,
114
+ "step": 75
115
+ },
116
+ {
117
+ "epoch": 0.11,
118
+ "grad_norm": 9.528456687927246,
119
+ "learning_rate": 4.9206349206349204e-05,
120
+ "loss": 2.7167,
121
+ "step": 80
122
+ },
123
+ {
124
+ "epoch": 0.12,
125
+ "grad_norm": 10.601034164428711,
126
+ "learning_rate": 4.880952380952381e-05,
127
+ "loss": 2.5201,
128
+ "step": 85
129
+ },
130
+ {
131
+ "epoch": 0.13,
132
+ "grad_norm": 10.306778907775879,
133
+ "learning_rate": 4.841269841269841e-05,
134
+ "loss": 2.4928,
135
+ "step": 90
136
+ },
137
+ {
138
+ "epoch": 0.14,
139
+ "grad_norm": 10.532262802124023,
140
+ "learning_rate": 4.801587301587302e-05,
141
+ "loss": 2.4065,
142
+ "step": 95
143
+ },
144
+ {
145
+ "epoch": 0.14,
146
+ "grad_norm": 10.122940063476562,
147
+ "learning_rate": 4.761904761904762e-05,
148
+ "loss": 2.7106,
149
+ "step": 100
150
+ },
151
+ {
152
+ "epoch": 0.15,
153
+ "grad_norm": 9.78131103515625,
154
+ "learning_rate": 4.722222222222222e-05,
155
+ "loss": 2.5572,
156
+ "step": 105
157
+ },
158
+ {
159
+ "epoch": 0.16,
160
+ "grad_norm": 10.649138450622559,
161
+ "learning_rate": 4.682539682539683e-05,
162
+ "loss": 2.5781,
163
+ "step": 110
164
+ },
165
+ {
166
+ "epoch": 0.16,
167
+ "grad_norm": 7.493427753448486,
168
+ "learning_rate": 4.642857142857143e-05,
169
+ "loss": 2.6114,
170
+ "step": 115
171
+ },
172
+ {
173
+ "epoch": 0.17,
174
+ "grad_norm": 7.953385829925537,
175
+ "learning_rate": 4.603174603174603e-05,
176
+ "loss": 2.6687,
177
+ "step": 120
178
+ },
179
+ {
180
+ "epoch": 0.18,
181
+ "grad_norm": 8.582961082458496,
182
+ "learning_rate": 4.563492063492064e-05,
183
+ "loss": 2.6787,
184
+ "step": 125
185
+ },
186
+ {
187
+ "epoch": 0.19,
188
+ "grad_norm": 8.697818756103516,
189
+ "learning_rate": 4.523809523809524e-05,
190
+ "loss": 2.5829,
191
+ "step": 130
192
+ },
193
+ {
194
+ "epoch": 0.19,
195
+ "grad_norm": 9.811901092529297,
196
+ "learning_rate": 4.4841269841269846e-05,
197
+ "loss": 2.6221,
198
+ "step": 135
199
+ },
200
+ {
201
+ "epoch": 0.2,
202
+ "grad_norm": 9.103715896606445,
203
+ "learning_rate": 4.4444444444444447e-05,
204
+ "loss": 2.6806,
205
+ "step": 140
206
+ },
207
+ {
208
+ "epoch": 0.21,
209
+ "grad_norm": 8.211301803588867,
210
+ "learning_rate": 4.404761904761905e-05,
211
+ "loss": 2.6136,
212
+ "step": 145
213
+ },
214
+ {
215
+ "epoch": 0.21,
216
+ "grad_norm": 10.060530662536621,
217
+ "learning_rate": 4.3650793650793655e-05,
218
+ "loss": 2.6461,
219
+ "step": 150
220
+ },
221
+ {
222
+ "epoch": 0.22,
223
+ "grad_norm": 10.009857177734375,
224
+ "learning_rate": 4.3253968253968256e-05,
225
+ "loss": 2.571,
226
+ "step": 155
227
+ },
228
+ {
229
+ "epoch": 0.23,
230
+ "grad_norm": 11.69568157196045,
231
+ "learning_rate": 4.2857142857142856e-05,
232
+ "loss": 2.758,
233
+ "step": 160
234
+ },
235
+ {
236
+ "epoch": 0.24,
237
+ "grad_norm": 8.031876564025879,
238
+ "learning_rate": 4.2460317460317464e-05,
239
+ "loss": 2.4975,
240
+ "step": 165
241
+ },
242
+ {
243
+ "epoch": 0.24,
244
+ "grad_norm": 8.202585220336914,
245
+ "learning_rate": 4.2063492063492065e-05,
246
+ "loss": 2.719,
247
+ "step": 170
248
+ },
249
+ {
250
+ "epoch": 0.25,
251
+ "grad_norm": 8.405922889709473,
252
+ "learning_rate": 4.166666666666667e-05,
253
+ "loss": 2.6564,
254
+ "step": 175
255
+ },
256
+ {
257
+ "epoch": 0.25,
258
+ "eval_accuracy": 0.17190058044351839,
259
+ "eval_loss": 2.5464329719543457,
260
+ "eval_runtime": 2790.7409,
261
+ "eval_samples_per_second": 4.815,
262
+ "eval_steps_per_second": 1.204,
263
+ "step": 175
264
+ },
265
+ {
266
+ "epoch": 1.01,
267
+ "grad_norm": 8.090776443481445,
268
+ "learning_rate": 4.126984126984127e-05,
269
+ "loss": 2.5153,
270
+ "step": 180
271
+ },
272
+ {
273
+ "epoch": 1.01,
274
+ "grad_norm": 7.668066024780273,
275
+ "learning_rate": 4.0873015873015874e-05,
276
+ "loss": 2.6691,
277
+ "step": 185
278
+ },
279
+ {
280
+ "epoch": 1.02,
281
+ "grad_norm": 7.451665878295898,
282
+ "learning_rate": 4.047619047619048e-05,
283
+ "loss": 2.455,
284
+ "step": 190
285
+ },
286
+ {
287
+ "epoch": 1.03,
288
+ "grad_norm": 6.811094284057617,
289
+ "learning_rate": 4.007936507936508e-05,
290
+ "loss": 2.7581,
291
+ "step": 195
292
+ },
293
+ {
294
+ "epoch": 1.04,
295
+ "grad_norm": 8.437348365783691,
296
+ "learning_rate": 3.968253968253968e-05,
297
+ "loss": 2.6151,
298
+ "step": 200
299
+ },
300
+ {
301
+ "epoch": 1.04,
302
+ "grad_norm": 9.83616828918457,
303
+ "learning_rate": 3.928571428571429e-05,
304
+ "loss": 2.7035,
305
+ "step": 205
306
+ },
307
+ {
308
+ "epoch": 1.05,
309
+ "grad_norm": 7.769816875457764,
310
+ "learning_rate": 3.888888888888889e-05,
311
+ "loss": 2.6254,
312
+ "step": 210
313
+ },
314
+ {
315
+ "epoch": 1.06,
316
+ "grad_norm": 11.614434242248535,
317
+ "learning_rate": 3.84920634920635e-05,
318
+ "loss": 2.5088,
319
+ "step": 215
320
+ },
321
+ {
322
+ "epoch": 1.06,
323
+ "grad_norm": 7.872964859008789,
324
+ "learning_rate": 3.809523809523809e-05,
325
+ "loss": 2.4313,
326
+ "step": 220
327
+ },
328
+ {
329
+ "epoch": 1.07,
330
+ "grad_norm": 9.000481605529785,
331
+ "learning_rate": 3.76984126984127e-05,
332
+ "loss": 2.6319,
333
+ "step": 225
334
+ },
335
+ {
336
+ "epoch": 1.08,
337
+ "grad_norm": 7.4448394775390625,
338
+ "learning_rate": 3.730158730158731e-05,
339
+ "loss": 2.6064,
340
+ "step": 230
341
+ },
342
+ {
343
+ "epoch": 1.09,
344
+ "grad_norm": 9.439050674438477,
345
+ "learning_rate": 3.690476190476191e-05,
346
+ "loss": 2.4276,
347
+ "step": 235
348
+ },
349
+ {
350
+ "epoch": 1.09,
351
+ "grad_norm": 7.45771598815918,
352
+ "learning_rate": 3.650793650793651e-05,
353
+ "loss": 2.6828,
354
+ "step": 240
355
+ },
356
+ {
357
+ "epoch": 1.1,
358
+ "grad_norm": 9.655268669128418,
359
+ "learning_rate": 3.611111111111111e-05,
360
+ "loss": 2.4295,
361
+ "step": 245
362
+ },
363
+ {
364
+ "epoch": 1.11,
365
+ "grad_norm": 7.304623603820801,
366
+ "learning_rate": 3.571428571428572e-05,
367
+ "loss": 2.3941,
368
+ "step": 250
369
+ },
370
+ {
371
+ "epoch": 1.11,
372
+ "grad_norm": 8.936468124389648,
373
+ "learning_rate": 3.5317460317460324e-05,
374
+ "loss": 2.5164,
375
+ "step": 255
376
+ },
377
+ {
378
+ "epoch": 1.12,
379
+ "grad_norm": 6.037725448608398,
380
+ "learning_rate": 3.492063492063492e-05,
381
+ "loss": 2.3629,
382
+ "step": 260
383
+ },
384
+ {
385
+ "epoch": 1.13,
386
+ "grad_norm": 9.806131362915039,
387
+ "learning_rate": 3.4523809523809526e-05,
388
+ "loss": 2.1973,
389
+ "step": 265
390
+ },
391
+ {
392
+ "epoch": 1.14,
393
+ "grad_norm": 7.448783874511719,
394
+ "learning_rate": 3.412698412698413e-05,
395
+ "loss": 2.6785,
396
+ "step": 270
397
+ },
398
+ {
399
+ "epoch": 1.14,
400
+ "grad_norm": 7.902461528778076,
401
+ "learning_rate": 3.3730158730158734e-05,
402
+ "loss": 2.5689,
403
+ "step": 275
404
+ },
405
+ {
406
+ "epoch": 1.15,
407
+ "grad_norm": 8.133126258850098,
408
+ "learning_rate": 3.3333333333333335e-05,
409
+ "loss": 2.705,
410
+ "step": 280
411
+ },
412
+ {
413
+ "epoch": 1.16,
414
+ "grad_norm": 7.387323379516602,
415
+ "learning_rate": 3.2936507936507936e-05,
416
+ "loss": 2.4184,
417
+ "step": 285
418
+ },
419
+ {
420
+ "epoch": 1.16,
421
+ "grad_norm": 7.738976001739502,
422
+ "learning_rate": 3.253968253968254e-05,
423
+ "loss": 2.5947,
424
+ "step": 290
425
+ },
426
+ {
427
+ "epoch": 1.17,
428
+ "grad_norm": 7.019045352935791,
429
+ "learning_rate": 3.2142857142857144e-05,
430
+ "loss": 2.3066,
431
+ "step": 295
432
+ },
433
+ {
434
+ "epoch": 1.18,
435
+ "grad_norm": 7.5370588302612305,
436
+ "learning_rate": 3.1746031746031745e-05,
437
+ "loss": 2.4445,
438
+ "step": 300
439
+ },
440
+ {
441
+ "epoch": 1.19,
442
+ "grad_norm": 7.962660312652588,
443
+ "learning_rate": 3.134920634920635e-05,
444
+ "loss": 2.4807,
445
+ "step": 305
446
+ },
447
+ {
448
+ "epoch": 1.19,
449
+ "grad_norm": 8.314027786254883,
450
+ "learning_rate": 3.095238095238095e-05,
451
+ "loss": 2.5981,
452
+ "step": 310
453
+ },
454
+ {
455
+ "epoch": 1.2,
456
+ "grad_norm": 10.364777565002441,
457
+ "learning_rate": 3.055555555555556e-05,
458
+ "loss": 2.5207,
459
+ "step": 315
460
+ },
461
+ {
462
+ "epoch": 1.21,
463
+ "grad_norm": 8.472153663635254,
464
+ "learning_rate": 3.0158730158730158e-05,
465
+ "loss": 2.5291,
466
+ "step": 320
467
+ },
468
+ {
469
+ "epoch": 1.21,
470
+ "grad_norm": 8.788971900939941,
471
+ "learning_rate": 2.9761904761904762e-05,
472
+ "loss": 2.5238,
473
+ "step": 325
474
+ },
475
+ {
476
+ "epoch": 1.22,
477
+ "grad_norm": 8.0416898727417,
478
+ "learning_rate": 2.9365079365079366e-05,
479
+ "loss": 2.5041,
480
+ "step": 330
481
+ },
482
+ {
483
+ "epoch": 1.23,
484
+ "grad_norm": 8.097698211669922,
485
+ "learning_rate": 2.8968253968253974e-05,
486
+ "loss": 2.3977,
487
+ "step": 335
488
+ },
489
+ {
490
+ "epoch": 1.24,
491
+ "grad_norm": 8.505749702453613,
492
+ "learning_rate": 2.857142857142857e-05,
493
+ "loss": 2.2704,
494
+ "step": 340
495
+ },
496
+ {
497
+ "epoch": 1.24,
498
+ "grad_norm": 7.548125267028809,
499
+ "learning_rate": 2.8174603174603175e-05,
500
+ "loss": 1.993,
501
+ "step": 345
502
+ },
503
+ {
504
+ "epoch": 1.25,
505
+ "grad_norm": 8.76427936553955,
506
+ "learning_rate": 2.777777777777778e-05,
507
+ "loss": 2.3285,
508
+ "step": 350
509
+ },
510
+ {
511
+ "epoch": 1.25,
512
+ "eval_accuracy": 0.1255395148087513,
513
+ "eval_loss": 2.866504192352295,
514
+ "eval_runtime": 2724.8913,
515
+ "eval_samples_per_second": 4.932,
516
+ "eval_steps_per_second": 1.233,
517
+ "step": 350
518
+ },
519
+ {
520
+ "epoch": 2.01,
521
+ "grad_norm": 9.777434349060059,
522
+ "learning_rate": 2.7380952380952383e-05,
523
+ "loss": 2.3064,
524
+ "step": 355
525
+ },
526
+ {
527
+ "epoch": 2.01,
528
+ "grad_norm": 9.634062767028809,
529
+ "learning_rate": 2.6984126984126984e-05,
530
+ "loss": 2.6674,
531
+ "step": 360
532
+ },
533
+ {
534
+ "epoch": 2.02,
535
+ "grad_norm": 7.418952941894531,
536
+ "learning_rate": 2.6587301587301588e-05,
537
+ "loss": 2.3623,
538
+ "step": 365
539
+ },
540
+ {
541
+ "epoch": 2.03,
542
+ "grad_norm": 9.471118927001953,
543
+ "learning_rate": 2.6190476190476192e-05,
544
+ "loss": 2.5705,
545
+ "step": 370
546
+ },
547
+ {
548
+ "epoch": 2.04,
549
+ "grad_norm": 8.835360527038574,
550
+ "learning_rate": 2.5793650793650796e-05,
551
+ "loss": 2.6313,
552
+ "step": 375
553
+ },
554
+ {
555
+ "epoch": 2.04,
556
+ "grad_norm": 9.770784378051758,
557
+ "learning_rate": 2.5396825396825397e-05,
558
+ "loss": 2.3423,
559
+ "step": 380
560
+ },
561
+ {
562
+ "epoch": 2.05,
563
+ "grad_norm": 11.036508560180664,
564
+ "learning_rate": 2.5e-05,
565
+ "loss": 2.4206,
566
+ "step": 385
567
+ },
568
+ {
569
+ "epoch": 2.06,
570
+ "grad_norm": 10.88526725769043,
571
+ "learning_rate": 2.4603174603174602e-05,
572
+ "loss": 2.3682,
573
+ "step": 390
574
+ },
575
+ {
576
+ "epoch": 2.06,
577
+ "grad_norm": 9.554337501525879,
578
+ "learning_rate": 2.4206349206349206e-05,
579
+ "loss": 2.3234,
580
+ "step": 395
581
+ },
582
+ {
583
+ "epoch": 2.07,
584
+ "grad_norm": 10.911561012268066,
585
+ "learning_rate": 2.380952380952381e-05,
586
+ "loss": 2.7633,
587
+ "step": 400
588
+ },
589
+ {
590
+ "epoch": 2.08,
591
+ "grad_norm": 8.518780708312988,
592
+ "learning_rate": 2.3412698412698414e-05,
593
+ "loss": 2.209,
594
+ "step": 405
595
+ },
596
+ {
597
+ "epoch": 2.09,
598
+ "grad_norm": 10.131900787353516,
599
+ "learning_rate": 2.3015873015873015e-05,
600
+ "loss": 2.5754,
601
+ "step": 410
602
+ },
603
+ {
604
+ "epoch": 2.09,
605
+ "grad_norm": 7.803353309631348,
606
+ "learning_rate": 2.261904761904762e-05,
607
+ "loss": 2.2815,
608
+ "step": 415
609
+ },
610
+ {
611
+ "epoch": 2.1,
612
+ "grad_norm": 8.873805046081543,
613
+ "learning_rate": 2.2222222222222223e-05,
614
+ "loss": 2.4105,
615
+ "step": 420
616
+ },
617
+ {
618
+ "epoch": 2.11,
619
+ "grad_norm": 10.056378364562988,
620
+ "learning_rate": 2.1825396825396827e-05,
621
+ "loss": 2.4577,
622
+ "step": 425
623
+ },
624
+ {
625
+ "epoch": 2.11,
626
+ "grad_norm": 9.494528770446777,
627
+ "learning_rate": 2.1428571428571428e-05,
628
+ "loss": 2.5227,
629
+ "step": 430
630
+ },
631
+ {
632
+ "epoch": 2.12,
633
+ "grad_norm": 7.30636739730835,
634
+ "learning_rate": 2.1031746031746032e-05,
635
+ "loss": 2.1842,
636
+ "step": 435
637
+ },
638
+ {
639
+ "epoch": 2.13,
640
+ "grad_norm": 11.144043922424316,
641
+ "learning_rate": 2.0634920634920636e-05,
642
+ "loss": 2.3519,
643
+ "step": 440
644
+ },
645
+ {
646
+ "epoch": 2.14,
647
+ "grad_norm": 7.896585941314697,
648
+ "learning_rate": 2.023809523809524e-05,
649
+ "loss": 2.6106,
650
+ "step": 445
651
+ },
652
+ {
653
+ "epoch": 2.14,
654
+ "grad_norm": 9.881820678710938,
655
+ "learning_rate": 1.984126984126984e-05,
656
+ "loss": 2.5722,
657
+ "step": 450
658
+ },
659
+ {
660
+ "epoch": 2.15,
661
+ "grad_norm": 7.789708137512207,
662
+ "learning_rate": 1.9444444444444445e-05,
663
+ "loss": 2.385,
664
+ "step": 455
665
+ },
666
+ {
667
+ "epoch": 2.16,
668
+ "grad_norm": 15.662388801574707,
669
+ "learning_rate": 1.9047619047619046e-05,
670
+ "loss": 2.4097,
671
+ "step": 460
672
+ },
673
+ {
674
+ "epoch": 2.16,
675
+ "grad_norm": 11.497434616088867,
676
+ "learning_rate": 1.8650793650793654e-05,
677
+ "loss": 2.3551,
678
+ "step": 465
679
+ },
680
+ {
681
+ "epoch": 2.17,
682
+ "grad_norm": 8.680765151977539,
683
+ "learning_rate": 1.8253968253968254e-05,
684
+ "loss": 2.4937,
685
+ "step": 470
686
+ },
687
+ {
688
+ "epoch": 2.18,
689
+ "grad_norm": 9.611832618713379,
690
+ "learning_rate": 1.785714285714286e-05,
691
+ "loss": 2.2117,
692
+ "step": 475
693
+ },
694
+ {
695
+ "epoch": 2.19,
696
+ "grad_norm": 8.637816429138184,
697
+ "learning_rate": 1.746031746031746e-05,
698
+ "loss": 2.2063,
699
+ "step": 480
700
+ },
701
+ {
702
+ "epoch": 2.19,
703
+ "grad_norm": 8.593392372131348,
704
+ "learning_rate": 1.7063492063492063e-05,
705
+ "loss": 2.5038,
706
+ "step": 485
707
+ },
708
+ {
709
+ "epoch": 2.2,
710
+ "grad_norm": 9.811333656311035,
711
+ "learning_rate": 1.6666666666666667e-05,
712
+ "loss": 2.1935,
713
+ "step": 490
714
+ },
715
+ {
716
+ "epoch": 2.21,
717
+ "grad_norm": 9.25893497467041,
718
+ "learning_rate": 1.626984126984127e-05,
719
+ "loss": 2.7302,
720
+ "step": 495
721
+ },
722
+ {
723
+ "epoch": 2.21,
724
+ "grad_norm": 8.803714752197266,
725
+ "learning_rate": 1.5873015873015872e-05,
726
+ "loss": 2.3372,
727
+ "step": 500
728
+ },
729
+ {
730
+ "epoch": 2.22,
731
+ "grad_norm": 10.265325546264648,
732
+ "learning_rate": 1.5476190476190476e-05,
733
+ "loss": 2.3112,
734
+ "step": 505
735
+ },
736
+ {
737
+ "epoch": 2.23,
738
+ "grad_norm": 8.800261497497559,
739
+ "learning_rate": 1.5079365079365079e-05,
740
+ "loss": 2.1571,
741
+ "step": 510
742
+ },
743
+ {
744
+ "epoch": 2.24,
745
+ "grad_norm": 9.066210746765137,
746
+ "learning_rate": 1.4682539682539683e-05,
747
+ "loss": 2.4612,
748
+ "step": 515
749
+ },
750
+ {
751
+ "epoch": 2.24,
752
+ "grad_norm": 11.743760108947754,
753
+ "learning_rate": 1.4285714285714285e-05,
754
+ "loss": 2.3783,
755
+ "step": 520
756
+ },
757
+ {
758
+ "epoch": 2.25,
759
+ "grad_norm": 7.336353302001953,
760
+ "learning_rate": 1.388888888888889e-05,
761
+ "loss": 2.3545,
762
+ "step": 525
763
+ },
764
+ {
765
+ "epoch": 2.25,
766
+ "eval_accuracy": 0.13528798928411967,
767
+ "eval_loss": 2.775129556655884,
768
+ "eval_runtime": 2705.5287,
769
+ "eval_samples_per_second": 4.967,
770
+ "eval_steps_per_second": 1.242,
771
+ "step": 525
772
+ },
773
+ {
774
+ "epoch": 3.01,
775
+ "grad_norm": 11.444567680358887,
776
+ "learning_rate": 1.3492063492063492e-05,
777
+ "loss": 2.7387,
778
+ "step": 530
779
+ },
780
+ {
781
+ "epoch": 3.01,
782
+ "grad_norm": 9.247318267822266,
783
+ "learning_rate": 1.3095238095238096e-05,
784
+ "loss": 2.7047,
785
+ "step": 535
786
+ },
787
+ {
788
+ "epoch": 3.02,
789
+ "grad_norm": 9.126996040344238,
790
+ "learning_rate": 1.2698412698412699e-05,
791
+ "loss": 2.3381,
792
+ "step": 540
793
+ },
794
+ {
795
+ "epoch": 3.03,
796
+ "grad_norm": 8.4282865524292,
797
+ "learning_rate": 1.2301587301587301e-05,
798
+ "loss": 2.292,
799
+ "step": 545
800
+ },
801
+ {
802
+ "epoch": 3.04,
803
+ "grad_norm": 9.275003433227539,
804
+ "learning_rate": 1.1904761904761905e-05,
805
+ "loss": 2.3291,
806
+ "step": 550
807
+ },
808
+ {
809
+ "epoch": 3.04,
810
+ "grad_norm": 9.664990425109863,
811
+ "learning_rate": 1.1507936507936508e-05,
812
+ "loss": 2.3276,
813
+ "step": 555
814
+ },
815
+ {
816
+ "epoch": 3.05,
817
+ "grad_norm": 9.327167510986328,
818
+ "learning_rate": 1.1111111111111112e-05,
819
+ "loss": 2.1339,
820
+ "step": 560
821
+ },
822
+ {
823
+ "epoch": 3.06,
824
+ "grad_norm": 8.076509475708008,
825
+ "learning_rate": 1.0714285714285714e-05,
826
+ "loss": 2.1437,
827
+ "step": 565
828
+ },
829
+ {
830
+ "epoch": 3.06,
831
+ "grad_norm": 10.702942848205566,
832
+ "learning_rate": 1.0317460317460318e-05,
833
+ "loss": 2.4547,
834
+ "step": 570
835
+ },
836
+ {
837
+ "epoch": 3.07,
838
+ "grad_norm": 13.38920783996582,
839
+ "learning_rate": 9.92063492063492e-06,
840
+ "loss": 2.5248,
841
+ "step": 575
842
+ },
843
+ {
844
+ "epoch": 3.08,
845
+ "grad_norm": 7.934788227081299,
846
+ "learning_rate": 9.523809523809523e-06,
847
+ "loss": 2.4829,
848
+ "step": 580
849
+ },
850
+ {
851
+ "epoch": 3.09,
852
+ "grad_norm": 8.314118385314941,
853
+ "learning_rate": 9.126984126984127e-06,
854
+ "loss": 2.1392,
855
+ "step": 585
856
+ },
857
+ {
858
+ "epoch": 3.09,
859
+ "grad_norm": 11.382800102233887,
860
+ "learning_rate": 8.73015873015873e-06,
861
+ "loss": 2.2964,
862
+ "step": 590
863
+ },
864
+ {
865
+ "epoch": 3.1,
866
+ "grad_norm": 7.882699012756348,
867
+ "learning_rate": 8.333333333333334e-06,
868
+ "loss": 2.1905,
869
+ "step": 595
870
+ },
871
+ {
872
+ "epoch": 3.11,
873
+ "grad_norm": 9.530142784118652,
874
+ "learning_rate": 7.936507936507936e-06,
875
+ "loss": 2.3815,
876
+ "step": 600
877
+ },
878
+ {
879
+ "epoch": 3.11,
880
+ "grad_norm": 8.318964958190918,
881
+ "learning_rate": 7.5396825396825394e-06,
882
+ "loss": 2.4007,
883
+ "step": 605
884
+ },
885
+ {
886
+ "epoch": 3.12,
887
+ "grad_norm": 10.5969820022583,
888
+ "learning_rate": 7.142857142857143e-06,
889
+ "loss": 2.3558,
890
+ "step": 610
891
+ },
892
+ {
893
+ "epoch": 3.13,
894
+ "grad_norm": 9.391063690185547,
895
+ "learning_rate": 6.746031746031746e-06,
896
+ "loss": 2.3825,
897
+ "step": 615
898
+ },
899
+ {
900
+ "epoch": 3.14,
901
+ "grad_norm": 9.316353797912598,
902
+ "learning_rate": 6.349206349206349e-06,
903
+ "loss": 2.4972,
904
+ "step": 620
905
+ },
906
+ {
907
+ "epoch": 3.14,
908
+ "grad_norm": 9.888083457946777,
909
+ "learning_rate": 5.9523809523809525e-06,
910
+ "loss": 2.2321,
911
+ "step": 625
912
+ },
913
+ {
914
+ "epoch": 3.15,
915
+ "grad_norm": 8.392168045043945,
916
+ "learning_rate": 5.555555555555556e-06,
917
+ "loss": 2.196,
918
+ "step": 630
919
+ },
920
+ {
921
+ "epoch": 3.16,
922
+ "grad_norm": 9.588519096374512,
923
+ "learning_rate": 5.158730158730159e-06,
924
+ "loss": 2.2595,
925
+ "step": 635
926
+ },
927
+ {
928
+ "epoch": 3.16,
929
+ "grad_norm": 8.25489616394043,
930
+ "learning_rate": 4.7619047619047615e-06,
931
+ "loss": 2.0537,
932
+ "step": 640
933
+ },
934
+ {
935
+ "epoch": 3.17,
936
+ "grad_norm": 10.085835456848145,
937
+ "learning_rate": 4.365079365079365e-06,
938
+ "loss": 2.4893,
939
+ "step": 645
940
+ },
941
+ {
942
+ "epoch": 3.18,
943
+ "grad_norm": 10.919437408447266,
944
+ "learning_rate": 3.968253968253968e-06,
945
+ "loss": 2.4032,
946
+ "step": 650
947
+ },
948
+ {
949
+ "epoch": 3.19,
950
+ "grad_norm": 8.23149299621582,
951
+ "learning_rate": 3.5714285714285714e-06,
952
+ "loss": 2.1834,
953
+ "step": 655
954
+ },
955
+ {
956
+ "epoch": 3.19,
957
+ "grad_norm": 11.596048355102539,
958
+ "learning_rate": 3.1746031746031746e-06,
959
+ "loss": 2.3302,
960
+ "step": 660
961
+ },
962
+ {
963
+ "epoch": 3.2,
964
+ "grad_norm": 11.665302276611328,
965
+ "learning_rate": 2.777777777777778e-06,
966
+ "loss": 2.3287,
967
+ "step": 665
968
+ },
969
+ {
970
+ "epoch": 3.21,
971
+ "grad_norm": 9.233076095581055,
972
+ "learning_rate": 2.3809523809523808e-06,
973
+ "loss": 2.1008,
974
+ "step": 670
975
+ },
976
+ {
977
+ "epoch": 3.21,
978
+ "grad_norm": 11.429000854492188,
979
+ "learning_rate": 1.984126984126984e-06,
980
+ "loss": 2.2577,
981
+ "step": 675
982
+ },
983
+ {
984
+ "epoch": 3.22,
985
+ "grad_norm": 8.783037185668945,
986
+ "learning_rate": 1.5873015873015873e-06,
987
+ "loss": 2.0016,
988
+ "step": 680
989
+ },
990
+ {
991
+ "epoch": 3.23,
992
+ "grad_norm": 8.462553977966309,
993
+ "learning_rate": 1.1904761904761904e-06,
994
+ "loss": 2.3779,
995
+ "step": 685
996
+ },
997
+ {
998
+ "epoch": 3.24,
999
+ "grad_norm": 9.461167335510254,
1000
+ "learning_rate": 7.936507936507937e-07,
1001
+ "loss": 1.9491,
1002
+ "step": 690
1003
+ },
1004
+ {
1005
+ "epoch": 3.24,
1006
+ "grad_norm": 12.051897048950195,
1007
+ "learning_rate": 3.9682539682539683e-07,
1008
+ "loss": 2.0514,
1009
+ "step": 695
1010
+ },
1011
+ {
1012
+ "epoch": 3.25,
1013
+ "grad_norm": 11.628158569335938,
1014
+ "learning_rate": 0.0,
1015
+ "loss": 1.9726,
1016
+ "step": 700
1017
+ },
1018
+ {
1019
+ "epoch": 3.25,
1020
+ "eval_accuracy": 0.18403036166096146,
1021
+ "eval_loss": 2.5616397857666016,
1022
+ "eval_runtime": 2737.1764,
1023
+ "eval_samples_per_second": 4.909,
1024
+ "eval_steps_per_second": 1.228,
1025
+ "step": 700
1026
+ },
1027
+ {
1028
+ "epoch": 3.25,
1029
+ "step": 700,
1030
+ "total_flos": 3.4893542331777024e+18,
1031
+ "train_loss": 2.449405036653791,
1032
+ "train_runtime": 12421.7881,
1033
+ "train_samples_per_second": 0.225,
1034
+ "train_steps_per_second": 0.056
1035
+ },
1036
+ {
1037
+ "epoch": 3.25,
1038
+ "eval_accuracy": 0.11733870967741936,
1039
+ "eval_loss": 2.6881906986236572,
1040
+ "eval_runtime": 975.7268,
1041
+ "eval_samples_per_second": 5.083,
1042
+ "eval_steps_per_second": 1.271,
1043
+ "step": 700
1044
+ },
1045
+ {
1046
+ "epoch": 3.25,
1047
+ "eval_accuracy": 0.11733870967741936,
1048
+ "eval_loss": 2.6881909370422363,
1049
+ "eval_runtime": 956.0688,
1050
+ "eval_samples_per_second": 5.188,
1051
+ "eval_steps_per_second": 1.297,
1052
+ "step": 700
1053
+ }
1054
+ ],
1055
+ "logging_steps": 5,
1056
+ "max_steps": 700,
1057
+ "num_input_tokens_seen": 0,
1058
+ "num_train_epochs": 9223372036854775807,
1059
+ "save_steps": 500,
1060
+ "total_flos": 3.4893542331777024e+18,
1061
+ "train_batch_size": 4,
1062
+ "trial_name": null,
1063
+ "trial_params": null
1064
+ }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3c5acfe5781ab4d4842f3f18432afafe39ba540493f47e189e7ef2a34da69cdc
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df2acce4762af5dc9e063a4cecfa7e1eaf8aa797b3cfc1bdc47c09341075a46a
3
  size 4984