learn3r commited on
Commit
489785a
1 Parent(s): 375e725

End of training

Browse files
Files changed (5) hide show
  1. README.md +3 -3
  2. all_results.json +13 -0
  3. eval_results.json +8 -0
  4. train_results.json +8 -0
  5. trainer_state.json +1088 -0
README.md CHANGED
@@ -4,7 +4,7 @@ base_model: google/long-t5-tglobal-xl
4
  tags:
5
  - generated_from_trainer
6
  datasets:
7
- - scrolls
8
  model-index:
9
  - name: longt5_xl_govreport_4096
10
  results: []
@@ -15,9 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # longt5_xl_govreport_4096
17
 
18
- This model is a fine-tuned version of [google/long-t5-tglobal-xl](https://huggingface.co/google/long-t5-tglobal-xl) on the scrolls dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 1.4389
21
 
22
  ## Model description
23
 
 
4
  tags:
5
  - generated_from_trainer
6
  datasets:
7
+ - tau/scrolls
8
  model-index:
9
  - name: longt5_xl_govreport_4096
10
  results: []
 
15
 
16
  # longt5_xl_govreport_4096
17
 
18
+ This model is a fine-tuned version of [google/long-t5-tglobal-xl](https://huggingface.co/google/long-t5-tglobal-xl) on the tau/scrolls gov_report dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 1.3889
21
 
22
  ## Model description
23
 
all_results.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.99,
3
+ "eval_loss": 1.3889119625091553,
4
+ "eval_runtime": 333.0151,
5
+ "eval_samples": 972,
6
+ "eval_samples_per_second": 2.919,
7
+ "eval_steps_per_second": 0.73,
8
+ "train_loss": 1.3779389661901138,
9
+ "train_runtime": 112099.6799,
10
+ "train_samples": 17457,
11
+ "train_samples_per_second": 0.779,
12
+ "train_steps_per_second": 0.003
13
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.99,
3
+ "eval_loss": 1.3889119625091553,
4
+ "eval_runtime": 333.0151,
5
+ "eval_samples": 972,
6
+ "eval_samples_per_second": 2.919,
7
+ "eval_steps_per_second": 0.73
8
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.99,
3
+ "train_loss": 1.3779389661901138,
4
+ "train_runtime": 112099.6799,
5
+ "train_samples": 17457,
6
+ "train_samples_per_second": 0.779,
7
+ "train_steps_per_second": 0.003
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,1088 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.3889119625091553,
3
+ "best_model_checkpoint": "/home/co-ou1/rds/hpc-work/models/longt5_xl_govreport_4096/checkpoint-272",
4
+ "epoch": 4.985108820160367,
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": 0.03,
13
+ "learning_rate": 0.001,
14
+ "loss": 2.6414,
15
+ "step": 2
16
+ },
17
+ {
18
+ "epoch": 0.06,
19
+ "learning_rate": 0.001,
20
+ "loss": 2.4747,
21
+ "step": 4
22
+ },
23
+ {
24
+ "epoch": 0.09,
25
+ "learning_rate": 0.001,
26
+ "loss": 1.8708,
27
+ "step": 6
28
+ },
29
+ {
30
+ "epoch": 0.12,
31
+ "learning_rate": 0.001,
32
+ "loss": 2.4373,
33
+ "step": 8
34
+ },
35
+ {
36
+ "epoch": 0.15,
37
+ "learning_rate": 0.001,
38
+ "loss": 2.2961,
39
+ "step": 10
40
+ },
41
+ {
42
+ "epoch": 0.18,
43
+ "learning_rate": 0.001,
44
+ "loss": 2.1959,
45
+ "step": 12
46
+ },
47
+ {
48
+ "epoch": 0.21,
49
+ "learning_rate": 0.001,
50
+ "loss": 1.9882,
51
+ "step": 14
52
+ },
53
+ {
54
+ "epoch": 0.23,
55
+ "learning_rate": 0.001,
56
+ "loss": 2.0164,
57
+ "step": 16
58
+ },
59
+ {
60
+ "epoch": 0.26,
61
+ "learning_rate": 0.001,
62
+ "loss": 1.8772,
63
+ "step": 18
64
+ },
65
+ {
66
+ "epoch": 0.29,
67
+ "learning_rate": 0.001,
68
+ "loss": 1.8516,
69
+ "step": 20
70
+ },
71
+ {
72
+ "epoch": 0.32,
73
+ "learning_rate": 0.001,
74
+ "loss": 1.8587,
75
+ "step": 22
76
+ },
77
+ {
78
+ "epoch": 0.35,
79
+ "learning_rate": 0.001,
80
+ "loss": 1.729,
81
+ "step": 24
82
+ },
83
+ {
84
+ "epoch": 0.38,
85
+ "learning_rate": 0.001,
86
+ "loss": 1.7265,
87
+ "step": 26
88
+ },
89
+ {
90
+ "epoch": 0.41,
91
+ "learning_rate": 0.001,
92
+ "loss": 1.7689,
93
+ "step": 28
94
+ },
95
+ {
96
+ "epoch": 0.44,
97
+ "learning_rate": 0.001,
98
+ "loss": 1.7899,
99
+ "step": 30
100
+ },
101
+ {
102
+ "epoch": 0.47,
103
+ "learning_rate": 0.001,
104
+ "loss": 1.6755,
105
+ "step": 32
106
+ },
107
+ {
108
+ "epoch": 0.5,
109
+ "learning_rate": 0.001,
110
+ "loss": 1.6701,
111
+ "step": 34
112
+ },
113
+ {
114
+ "epoch": 0.53,
115
+ "learning_rate": 0.001,
116
+ "loss": 1.6626,
117
+ "step": 36
118
+ },
119
+ {
120
+ "epoch": 0.56,
121
+ "learning_rate": 0.001,
122
+ "loss": 1.708,
123
+ "step": 38
124
+ },
125
+ {
126
+ "epoch": 0.59,
127
+ "learning_rate": 0.001,
128
+ "loss": 1.7019,
129
+ "step": 40
130
+ },
131
+ {
132
+ "epoch": 0.62,
133
+ "learning_rate": 0.001,
134
+ "loss": 1.6705,
135
+ "step": 42
136
+ },
137
+ {
138
+ "epoch": 0.65,
139
+ "learning_rate": 0.001,
140
+ "loss": 1.6039,
141
+ "step": 44
142
+ },
143
+ {
144
+ "epoch": 0.67,
145
+ "learning_rate": 0.001,
146
+ "loss": 1.6041,
147
+ "step": 46
148
+ },
149
+ {
150
+ "epoch": 0.7,
151
+ "learning_rate": 0.001,
152
+ "loss": 1.5829,
153
+ "step": 48
154
+ },
155
+ {
156
+ "epoch": 0.73,
157
+ "learning_rate": 0.001,
158
+ "loss": 1.6283,
159
+ "step": 50
160
+ },
161
+ {
162
+ "epoch": 0.76,
163
+ "learning_rate": 0.001,
164
+ "loss": 1.7403,
165
+ "step": 52
166
+ },
167
+ {
168
+ "epoch": 0.79,
169
+ "learning_rate": 0.001,
170
+ "loss": 1.6786,
171
+ "step": 54
172
+ },
173
+ {
174
+ "epoch": 0.82,
175
+ "learning_rate": 0.001,
176
+ "loss": 1.6499,
177
+ "step": 56
178
+ },
179
+ {
180
+ "epoch": 0.85,
181
+ "learning_rate": 0.001,
182
+ "loss": 1.5641,
183
+ "step": 58
184
+ },
185
+ {
186
+ "epoch": 0.88,
187
+ "learning_rate": 0.001,
188
+ "loss": 1.5824,
189
+ "step": 60
190
+ },
191
+ {
192
+ "epoch": 0.91,
193
+ "learning_rate": 0.001,
194
+ "loss": 1.6462,
195
+ "step": 62
196
+ },
197
+ {
198
+ "epoch": 0.94,
199
+ "learning_rate": 0.001,
200
+ "loss": 1.5787,
201
+ "step": 64
202
+ },
203
+ {
204
+ "epoch": 0.97,
205
+ "learning_rate": 0.001,
206
+ "loss": 1.6053,
207
+ "step": 66
208
+ },
209
+ {
210
+ "epoch": 1.0,
211
+ "learning_rate": 0.001,
212
+ "loss": 1.6043,
213
+ "step": 68
214
+ },
215
+ {
216
+ "epoch": 1.0,
217
+ "eval_loss": 1.4757200479507446,
218
+ "eval_runtime": 333.5276,
219
+ "eval_samples_per_second": 2.914,
220
+ "eval_steps_per_second": 0.729,
221
+ "step": 68
222
+ },
223
+ {
224
+ "epoch": 1.03,
225
+ "learning_rate": 0.001,
226
+ "loss": 1.549,
227
+ "step": 70
228
+ },
229
+ {
230
+ "epoch": 1.06,
231
+ "learning_rate": 0.001,
232
+ "loss": 1.4379,
233
+ "step": 72
234
+ },
235
+ {
236
+ "epoch": 1.08,
237
+ "learning_rate": 0.001,
238
+ "loss": 1.5224,
239
+ "step": 74
240
+ },
241
+ {
242
+ "epoch": 1.11,
243
+ "learning_rate": 0.001,
244
+ "loss": 1.5106,
245
+ "step": 76
246
+ },
247
+ {
248
+ "epoch": 1.14,
249
+ "learning_rate": 0.001,
250
+ "loss": 1.4786,
251
+ "step": 78
252
+ },
253
+ {
254
+ "epoch": 1.17,
255
+ "learning_rate": 0.001,
256
+ "loss": 1.5101,
257
+ "step": 80
258
+ },
259
+ {
260
+ "epoch": 1.2,
261
+ "learning_rate": 0.001,
262
+ "loss": 1.4835,
263
+ "step": 82
264
+ },
265
+ {
266
+ "epoch": 1.23,
267
+ "learning_rate": 0.001,
268
+ "loss": 1.4749,
269
+ "step": 84
270
+ },
271
+ {
272
+ "epoch": 1.26,
273
+ "learning_rate": 0.001,
274
+ "loss": 1.488,
275
+ "step": 86
276
+ },
277
+ {
278
+ "epoch": 1.29,
279
+ "learning_rate": 0.001,
280
+ "loss": 1.4604,
281
+ "step": 88
282
+ },
283
+ {
284
+ "epoch": 1.32,
285
+ "learning_rate": 0.001,
286
+ "loss": 1.5358,
287
+ "step": 90
288
+ },
289
+ {
290
+ "epoch": 1.35,
291
+ "learning_rate": 0.001,
292
+ "loss": 1.5396,
293
+ "step": 92
294
+ },
295
+ {
296
+ "epoch": 1.38,
297
+ "learning_rate": 0.001,
298
+ "loss": 1.5071,
299
+ "step": 94
300
+ },
301
+ {
302
+ "epoch": 1.41,
303
+ "learning_rate": 0.001,
304
+ "loss": 1.5219,
305
+ "step": 96
306
+ },
307
+ {
308
+ "epoch": 1.44,
309
+ "learning_rate": 0.001,
310
+ "loss": 1.4589,
311
+ "step": 98
312
+ },
313
+ {
314
+ "epoch": 1.47,
315
+ "learning_rate": 0.001,
316
+ "loss": 1.4392,
317
+ "step": 100
318
+ },
319
+ {
320
+ "epoch": 1.5,
321
+ "learning_rate": 0.001,
322
+ "loss": 1.485,
323
+ "step": 102
324
+ },
325
+ {
326
+ "epoch": 1.52,
327
+ "learning_rate": 0.001,
328
+ "loss": 1.4617,
329
+ "step": 104
330
+ },
331
+ {
332
+ "epoch": 1.55,
333
+ "learning_rate": 0.001,
334
+ "loss": 1.4659,
335
+ "step": 106
336
+ },
337
+ {
338
+ "epoch": 1.58,
339
+ "learning_rate": 0.001,
340
+ "loss": 1.4908,
341
+ "step": 108
342
+ },
343
+ {
344
+ "epoch": 1.61,
345
+ "learning_rate": 0.001,
346
+ "loss": 1.4929,
347
+ "step": 110
348
+ },
349
+ {
350
+ "epoch": 1.64,
351
+ "learning_rate": 0.001,
352
+ "loss": 1.4538,
353
+ "step": 112
354
+ },
355
+ {
356
+ "epoch": 1.67,
357
+ "learning_rate": 0.001,
358
+ "loss": 1.4815,
359
+ "step": 114
360
+ },
361
+ {
362
+ "epoch": 1.7,
363
+ "learning_rate": 0.001,
364
+ "loss": 1.4525,
365
+ "step": 116
366
+ },
367
+ {
368
+ "epoch": 1.73,
369
+ "learning_rate": 0.001,
370
+ "loss": 1.4664,
371
+ "step": 118
372
+ },
373
+ {
374
+ "epoch": 1.76,
375
+ "learning_rate": 0.001,
376
+ "loss": 1.4498,
377
+ "step": 120
378
+ },
379
+ {
380
+ "epoch": 1.79,
381
+ "learning_rate": 0.001,
382
+ "loss": 1.5247,
383
+ "step": 122
384
+ },
385
+ {
386
+ "epoch": 1.82,
387
+ "learning_rate": 0.001,
388
+ "loss": 1.5033,
389
+ "step": 124
390
+ },
391
+ {
392
+ "epoch": 1.85,
393
+ "learning_rate": 0.001,
394
+ "loss": 1.4434,
395
+ "step": 126
396
+ },
397
+ {
398
+ "epoch": 1.88,
399
+ "learning_rate": 0.001,
400
+ "loss": 1.4806,
401
+ "step": 128
402
+ },
403
+ {
404
+ "epoch": 1.91,
405
+ "learning_rate": 0.001,
406
+ "loss": 1.4551,
407
+ "step": 130
408
+ },
409
+ {
410
+ "epoch": 1.94,
411
+ "learning_rate": 0.001,
412
+ "loss": 1.4359,
413
+ "step": 132
414
+ },
415
+ {
416
+ "epoch": 1.96,
417
+ "learning_rate": 0.001,
418
+ "loss": 1.4424,
419
+ "step": 134
420
+ },
421
+ {
422
+ "epoch": 1.99,
423
+ "learning_rate": 0.001,
424
+ "loss": 1.4471,
425
+ "step": 136
426
+ },
427
+ {
428
+ "epoch": 1.99,
429
+ "eval_loss": 1.401979923248291,
430
+ "eval_runtime": 333.5413,
431
+ "eval_samples_per_second": 2.914,
432
+ "eval_steps_per_second": 0.729,
433
+ "step": 136
434
+ },
435
+ {
436
+ "epoch": 2.02,
437
+ "learning_rate": 0.001,
438
+ "loss": 1.3704,
439
+ "step": 138
440
+ },
441
+ {
442
+ "epoch": 2.05,
443
+ "learning_rate": 0.001,
444
+ "loss": 1.3246,
445
+ "step": 140
446
+ },
447
+ {
448
+ "epoch": 2.08,
449
+ "learning_rate": 0.001,
450
+ "loss": 1.3714,
451
+ "step": 142
452
+ },
453
+ {
454
+ "epoch": 2.11,
455
+ "learning_rate": 0.001,
456
+ "loss": 1.3134,
457
+ "step": 144
458
+ },
459
+ {
460
+ "epoch": 2.14,
461
+ "learning_rate": 0.001,
462
+ "loss": 1.2998,
463
+ "step": 146
464
+ },
465
+ {
466
+ "epoch": 2.17,
467
+ "learning_rate": 0.001,
468
+ "loss": 1.3643,
469
+ "step": 148
470
+ },
471
+ {
472
+ "epoch": 2.2,
473
+ "learning_rate": 0.001,
474
+ "loss": 1.306,
475
+ "step": 150
476
+ },
477
+ {
478
+ "epoch": 2.23,
479
+ "learning_rate": 0.001,
480
+ "loss": 1.3152,
481
+ "step": 152
482
+ },
483
+ {
484
+ "epoch": 2.26,
485
+ "learning_rate": 0.001,
486
+ "loss": 1.3086,
487
+ "step": 154
488
+ },
489
+ {
490
+ "epoch": 2.29,
491
+ "learning_rate": 0.001,
492
+ "loss": 1.3033,
493
+ "step": 156
494
+ },
495
+ {
496
+ "epoch": 2.32,
497
+ "learning_rate": 0.001,
498
+ "loss": 1.343,
499
+ "step": 158
500
+ },
501
+ {
502
+ "epoch": 2.35,
503
+ "learning_rate": 0.001,
504
+ "loss": 1.3399,
505
+ "step": 160
506
+ },
507
+ {
508
+ "epoch": 2.38,
509
+ "learning_rate": 0.001,
510
+ "loss": 1.3134,
511
+ "step": 162
512
+ },
513
+ {
514
+ "epoch": 2.4,
515
+ "learning_rate": 0.001,
516
+ "loss": 1.3472,
517
+ "step": 164
518
+ },
519
+ {
520
+ "epoch": 2.43,
521
+ "learning_rate": 0.001,
522
+ "loss": 1.3261,
523
+ "step": 166
524
+ },
525
+ {
526
+ "epoch": 2.46,
527
+ "learning_rate": 0.001,
528
+ "loss": 1.3162,
529
+ "step": 168
530
+ },
531
+ {
532
+ "epoch": 2.49,
533
+ "learning_rate": 0.001,
534
+ "loss": 1.3194,
535
+ "step": 170
536
+ },
537
+ {
538
+ "epoch": 2.52,
539
+ "learning_rate": 0.001,
540
+ "loss": 1.3236,
541
+ "step": 172
542
+ },
543
+ {
544
+ "epoch": 2.55,
545
+ "learning_rate": 0.001,
546
+ "loss": 1.3033,
547
+ "step": 174
548
+ },
549
+ {
550
+ "epoch": 2.58,
551
+ "learning_rate": 0.001,
552
+ "loss": 1.3212,
553
+ "step": 176
554
+ },
555
+ {
556
+ "epoch": 2.61,
557
+ "learning_rate": 0.001,
558
+ "loss": 1.3433,
559
+ "step": 178
560
+ },
561
+ {
562
+ "epoch": 2.64,
563
+ "learning_rate": 0.001,
564
+ "loss": 1.34,
565
+ "step": 180
566
+ },
567
+ {
568
+ "epoch": 2.67,
569
+ "learning_rate": 0.001,
570
+ "loss": 1.3306,
571
+ "step": 182
572
+ },
573
+ {
574
+ "epoch": 2.7,
575
+ "learning_rate": 0.001,
576
+ "loss": 1.3377,
577
+ "step": 184
578
+ },
579
+ {
580
+ "epoch": 2.73,
581
+ "learning_rate": 0.001,
582
+ "loss": 1.3048,
583
+ "step": 186
584
+ },
585
+ {
586
+ "epoch": 2.76,
587
+ "learning_rate": 0.001,
588
+ "loss": 1.3186,
589
+ "step": 188
590
+ },
591
+ {
592
+ "epoch": 2.79,
593
+ "learning_rate": 0.001,
594
+ "loss": 1.3405,
595
+ "step": 190
596
+ },
597
+ {
598
+ "epoch": 2.82,
599
+ "learning_rate": 0.001,
600
+ "loss": 1.3266,
601
+ "step": 192
602
+ },
603
+ {
604
+ "epoch": 2.84,
605
+ "learning_rate": 0.001,
606
+ "loss": 1.3182,
607
+ "step": 194
608
+ },
609
+ {
610
+ "epoch": 2.87,
611
+ "learning_rate": 0.001,
612
+ "loss": 1.3755,
613
+ "step": 196
614
+ },
615
+ {
616
+ "epoch": 2.9,
617
+ "learning_rate": 0.001,
618
+ "loss": 1.3422,
619
+ "step": 198
620
+ },
621
+ {
622
+ "epoch": 2.93,
623
+ "learning_rate": 0.001,
624
+ "loss": 1.3247,
625
+ "step": 200
626
+ },
627
+ {
628
+ "epoch": 2.96,
629
+ "learning_rate": 0.001,
630
+ "loss": 1.312,
631
+ "step": 202
632
+ },
633
+ {
634
+ "epoch": 2.99,
635
+ "learning_rate": 0.001,
636
+ "loss": 1.315,
637
+ "step": 204
638
+ },
639
+ {
640
+ "epoch": 2.99,
641
+ "eval_loss": 1.3935041427612305,
642
+ "eval_runtime": 333.777,
643
+ "eval_samples_per_second": 2.912,
644
+ "eval_steps_per_second": 0.728,
645
+ "step": 204
646
+ },
647
+ {
648
+ "epoch": 3.02,
649
+ "learning_rate": 0.001,
650
+ "loss": 1.2264,
651
+ "step": 206
652
+ },
653
+ {
654
+ "epoch": 3.05,
655
+ "learning_rate": 0.001,
656
+ "loss": 1.1606,
657
+ "step": 208
658
+ },
659
+ {
660
+ "epoch": 3.08,
661
+ "learning_rate": 0.001,
662
+ "loss": 1.1569,
663
+ "step": 210
664
+ },
665
+ {
666
+ "epoch": 3.11,
667
+ "learning_rate": 0.001,
668
+ "loss": 1.1434,
669
+ "step": 212
670
+ },
671
+ {
672
+ "epoch": 3.14,
673
+ "learning_rate": 0.001,
674
+ "loss": 1.1736,
675
+ "step": 214
676
+ },
677
+ {
678
+ "epoch": 3.17,
679
+ "learning_rate": 0.001,
680
+ "loss": 1.17,
681
+ "step": 216
682
+ },
683
+ {
684
+ "epoch": 3.2,
685
+ "learning_rate": 0.001,
686
+ "loss": 1.1802,
687
+ "step": 218
688
+ },
689
+ {
690
+ "epoch": 3.23,
691
+ "learning_rate": 0.001,
692
+ "loss": 1.1856,
693
+ "step": 220
694
+ },
695
+ {
696
+ "epoch": 3.25,
697
+ "learning_rate": 0.001,
698
+ "loss": 1.1918,
699
+ "step": 222
700
+ },
701
+ {
702
+ "epoch": 3.28,
703
+ "learning_rate": 0.001,
704
+ "loss": 1.1751,
705
+ "step": 224
706
+ },
707
+ {
708
+ "epoch": 3.31,
709
+ "learning_rate": 0.001,
710
+ "loss": 1.1896,
711
+ "step": 226
712
+ },
713
+ {
714
+ "epoch": 3.34,
715
+ "learning_rate": 0.001,
716
+ "loss": 1.1837,
717
+ "step": 228
718
+ },
719
+ {
720
+ "epoch": 3.37,
721
+ "learning_rate": 0.001,
722
+ "loss": 1.2053,
723
+ "step": 230
724
+ },
725
+ {
726
+ "epoch": 3.4,
727
+ "learning_rate": 0.001,
728
+ "loss": 1.2031,
729
+ "step": 232
730
+ },
731
+ {
732
+ "epoch": 3.43,
733
+ "learning_rate": 0.001,
734
+ "loss": 1.1886,
735
+ "step": 234
736
+ },
737
+ {
738
+ "epoch": 3.46,
739
+ "learning_rate": 0.001,
740
+ "loss": 1.1769,
741
+ "step": 236
742
+ },
743
+ {
744
+ "epoch": 3.49,
745
+ "learning_rate": 0.001,
746
+ "loss": 1.1951,
747
+ "step": 238
748
+ },
749
+ {
750
+ "epoch": 3.52,
751
+ "learning_rate": 0.001,
752
+ "loss": 1.1943,
753
+ "step": 240
754
+ },
755
+ {
756
+ "epoch": 3.55,
757
+ "learning_rate": 0.001,
758
+ "loss": 1.1816,
759
+ "step": 242
760
+ },
761
+ {
762
+ "epoch": 3.58,
763
+ "learning_rate": 0.001,
764
+ "loss": 1.1763,
765
+ "step": 244
766
+ },
767
+ {
768
+ "epoch": 3.61,
769
+ "learning_rate": 0.001,
770
+ "loss": 1.2028,
771
+ "step": 246
772
+ },
773
+ {
774
+ "epoch": 3.64,
775
+ "learning_rate": 0.001,
776
+ "loss": 1.2199,
777
+ "step": 248
778
+ },
779
+ {
780
+ "epoch": 3.67,
781
+ "learning_rate": 0.001,
782
+ "loss": 1.1948,
783
+ "step": 250
784
+ },
785
+ {
786
+ "epoch": 3.69,
787
+ "learning_rate": 0.001,
788
+ "loss": 1.1859,
789
+ "step": 252
790
+ },
791
+ {
792
+ "epoch": 3.72,
793
+ "learning_rate": 0.001,
794
+ "loss": 1.1864,
795
+ "step": 254
796
+ },
797
+ {
798
+ "epoch": 3.75,
799
+ "learning_rate": 0.001,
800
+ "loss": 1.2012,
801
+ "step": 256
802
+ },
803
+ {
804
+ "epoch": 3.78,
805
+ "learning_rate": 0.001,
806
+ "loss": 1.2177,
807
+ "step": 258
808
+ },
809
+ {
810
+ "epoch": 3.81,
811
+ "learning_rate": 0.001,
812
+ "loss": 1.2156,
813
+ "step": 260
814
+ },
815
+ {
816
+ "epoch": 3.84,
817
+ "learning_rate": 0.001,
818
+ "loss": 1.204,
819
+ "step": 262
820
+ },
821
+ {
822
+ "epoch": 3.87,
823
+ "learning_rate": 0.001,
824
+ "loss": 1.2053,
825
+ "step": 264
826
+ },
827
+ {
828
+ "epoch": 3.9,
829
+ "learning_rate": 0.001,
830
+ "loss": 1.2138,
831
+ "step": 266
832
+ },
833
+ {
834
+ "epoch": 3.93,
835
+ "learning_rate": 0.001,
836
+ "loss": 1.1992,
837
+ "step": 268
838
+ },
839
+ {
840
+ "epoch": 3.96,
841
+ "learning_rate": 0.001,
842
+ "loss": 1.1903,
843
+ "step": 270
844
+ },
845
+ {
846
+ "epoch": 3.99,
847
+ "learning_rate": 0.001,
848
+ "loss": 1.2098,
849
+ "step": 272
850
+ },
851
+ {
852
+ "epoch": 3.99,
853
+ "eval_loss": 1.3889119625091553,
854
+ "eval_runtime": 333.5624,
855
+ "eval_samples_per_second": 2.914,
856
+ "eval_steps_per_second": 0.728,
857
+ "step": 272
858
+ },
859
+ {
860
+ "epoch": 4.02,
861
+ "learning_rate": 0.001,
862
+ "loss": 1.1135,
863
+ "step": 274
864
+ },
865
+ {
866
+ "epoch": 4.05,
867
+ "learning_rate": 0.001,
868
+ "loss": 1.0318,
869
+ "step": 276
870
+ },
871
+ {
872
+ "epoch": 4.08,
873
+ "learning_rate": 0.001,
874
+ "loss": 1.068,
875
+ "step": 278
876
+ },
877
+ {
878
+ "epoch": 4.11,
879
+ "learning_rate": 0.001,
880
+ "loss": 1.0386,
881
+ "step": 280
882
+ },
883
+ {
884
+ "epoch": 4.13,
885
+ "learning_rate": 0.001,
886
+ "loss": 1.0727,
887
+ "step": 282
888
+ },
889
+ {
890
+ "epoch": 4.16,
891
+ "learning_rate": 0.001,
892
+ "loss": 1.0592,
893
+ "step": 284
894
+ },
895
+ {
896
+ "epoch": 4.19,
897
+ "learning_rate": 0.001,
898
+ "loss": 1.0348,
899
+ "step": 286
900
+ },
901
+ {
902
+ "epoch": 4.22,
903
+ "learning_rate": 0.001,
904
+ "loss": 1.045,
905
+ "step": 288
906
+ },
907
+ {
908
+ "epoch": 4.25,
909
+ "learning_rate": 0.001,
910
+ "loss": 1.0535,
911
+ "step": 290
912
+ },
913
+ {
914
+ "epoch": 4.28,
915
+ "learning_rate": 0.001,
916
+ "loss": 1.0628,
917
+ "step": 292
918
+ },
919
+ {
920
+ "epoch": 4.31,
921
+ "learning_rate": 0.001,
922
+ "loss": 1.0699,
923
+ "step": 294
924
+ },
925
+ {
926
+ "epoch": 4.34,
927
+ "learning_rate": 0.001,
928
+ "loss": 1.0482,
929
+ "step": 296
930
+ },
931
+ {
932
+ "epoch": 4.37,
933
+ "learning_rate": 0.001,
934
+ "loss": 1.0703,
935
+ "step": 298
936
+ },
937
+ {
938
+ "epoch": 4.4,
939
+ "learning_rate": 0.001,
940
+ "loss": 1.0498,
941
+ "step": 300
942
+ },
943
+ {
944
+ "epoch": 4.43,
945
+ "learning_rate": 0.001,
946
+ "loss": 1.0775,
947
+ "step": 302
948
+ },
949
+ {
950
+ "epoch": 4.46,
951
+ "learning_rate": 0.001,
952
+ "loss": 1.0609,
953
+ "step": 304
954
+ },
955
+ {
956
+ "epoch": 4.49,
957
+ "learning_rate": 0.001,
958
+ "loss": 1.0985,
959
+ "step": 306
960
+ },
961
+ {
962
+ "epoch": 4.52,
963
+ "learning_rate": 0.001,
964
+ "loss": 1.081,
965
+ "step": 308
966
+ },
967
+ {
968
+ "epoch": 4.55,
969
+ "learning_rate": 0.001,
970
+ "loss": 1.0942,
971
+ "step": 310
972
+ },
973
+ {
974
+ "epoch": 4.57,
975
+ "learning_rate": 0.001,
976
+ "loss": 1.0789,
977
+ "step": 312
978
+ },
979
+ {
980
+ "epoch": 4.6,
981
+ "learning_rate": 0.001,
982
+ "loss": 1.0897,
983
+ "step": 314
984
+ },
985
+ {
986
+ "epoch": 4.63,
987
+ "learning_rate": 0.001,
988
+ "loss": 1.0869,
989
+ "step": 316
990
+ },
991
+ {
992
+ "epoch": 4.66,
993
+ "learning_rate": 0.001,
994
+ "loss": 1.1108,
995
+ "step": 318
996
+ },
997
+ {
998
+ "epoch": 4.69,
999
+ "learning_rate": 0.001,
1000
+ "loss": 1.0687,
1001
+ "step": 320
1002
+ },
1003
+ {
1004
+ "epoch": 4.72,
1005
+ "learning_rate": 0.001,
1006
+ "loss": 1.1109,
1007
+ "step": 322
1008
+ },
1009
+ {
1010
+ "epoch": 4.75,
1011
+ "learning_rate": 0.001,
1012
+ "loss": 1.0838,
1013
+ "step": 324
1014
+ },
1015
+ {
1016
+ "epoch": 4.78,
1017
+ "learning_rate": 0.001,
1018
+ "loss": 1.0932,
1019
+ "step": 326
1020
+ },
1021
+ {
1022
+ "epoch": 4.81,
1023
+ "learning_rate": 0.001,
1024
+ "loss": 1.0923,
1025
+ "step": 328
1026
+ },
1027
+ {
1028
+ "epoch": 4.84,
1029
+ "learning_rate": 0.001,
1030
+ "loss": 1.0662,
1031
+ "step": 330
1032
+ },
1033
+ {
1034
+ "epoch": 4.87,
1035
+ "learning_rate": 0.001,
1036
+ "loss": 1.0727,
1037
+ "step": 332
1038
+ },
1039
+ {
1040
+ "epoch": 4.9,
1041
+ "learning_rate": 0.001,
1042
+ "loss": 1.0809,
1043
+ "step": 334
1044
+ },
1045
+ {
1046
+ "epoch": 4.93,
1047
+ "learning_rate": 0.001,
1048
+ "loss": 1.1087,
1049
+ "step": 336
1050
+ },
1051
+ {
1052
+ "epoch": 4.96,
1053
+ "learning_rate": 0.001,
1054
+ "loss": 1.0912,
1055
+ "step": 338
1056
+ },
1057
+ {
1058
+ "epoch": 4.99,
1059
+ "learning_rate": 0.001,
1060
+ "loss": 1.0888,
1061
+ "step": 340
1062
+ },
1063
+ {
1064
+ "epoch": 4.99,
1065
+ "eval_loss": 1.4388501644134521,
1066
+ "eval_runtime": 333.5483,
1067
+ "eval_samples_per_second": 2.914,
1068
+ "eval_steps_per_second": 0.729,
1069
+ "step": 340
1070
+ },
1071
+ {
1072
+ "epoch": 4.99,
1073
+ "step": 340,
1074
+ "total_flos": 5.95419516573578e+18,
1075
+ "train_loss": 1.3779389661901138,
1076
+ "train_runtime": 112099.6799,
1077
+ "train_samples_per_second": 0.779,
1078
+ "train_steps_per_second": 0.003
1079
+ }
1080
+ ],
1081
+ "logging_steps": 2,
1082
+ "max_steps": 340,
1083
+ "num_train_epochs": 5,
1084
+ "save_steps": 500,
1085
+ "total_flos": 5.95419516573578e+18,
1086
+ "trial_name": null,
1087
+ "trial_params": null
1088
+ }