houck2040 commited on
Commit
712a1e1
1 Parent(s): 22497f2

Upload 7 files

Browse files
Files changed (7) hide show
  1. config.json +27 -0
  2. optimizer.pt +3 -0
  3. pytorch_model.bin +3 -0
  4. rng_state.pth +3 -0
  5. scheduler.pt +3 -0
  6. trainer_state.json +952 -0
  7. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilroberta-base",
3
+ "architectures": [
4
+ "RobertaForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 514,
17
+ "model_type": "roberta",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 6,
20
+ "pad_token_id": 1,
21
+ "position_embedding_type": "absolute",
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.29.2",
24
+ "type_vocab_size": 1,
25
+ "use_cache": true,
26
+ "vocab_size": 50265
27
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50910543ee48ebb87d2cd96e92e83355cd8788df074708bd36166623a9d3120a
3
+ size 657423877
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5b2b4a471d168e7c7100f95df159c749f9fbaea084c98ee7ba96f9ebc757611
3
+ size 328721273
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61b7887d51ce94043f87e80d2dc67a61dc126ca405c1f19a51accdca1f9187f5
3
+ size 14575
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:008be860f62951416b5f95ad031b54daa9ba617efacf733a6207b46197f467de
3
+ size 627
trainer_state.json ADDED
@@ -0,0 +1,952 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 9.969537524231514,
5
+ "global_step": 72000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.07,
12
+ "learning_rate": 1.9861534201052343e-05,
13
+ "loss": 2.0278,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.14,
18
+ "learning_rate": 1.972306840210468e-05,
19
+ "loss": 1.6767,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.21,
24
+ "learning_rate": 1.958460260315702e-05,
25
+ "loss": 1.5473,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.28,
30
+ "learning_rate": 1.9446136804209362e-05,
31
+ "loss": 1.4575,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.35,
36
+ "learning_rate": 1.93076710052617e-05,
37
+ "loss": 1.4112,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.42,
42
+ "learning_rate": 1.916920520631404e-05,
43
+ "loss": 1.3585,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.48,
48
+ "learning_rate": 1.903073940736638e-05,
49
+ "loss": 1.338,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.55,
54
+ "learning_rate": 1.8892273608418723e-05,
55
+ "loss": 1.2933,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.62,
60
+ "learning_rate": 1.8753807809471064e-05,
61
+ "loss": 1.2931,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.69,
66
+ "learning_rate": 1.86153420105234e-05,
67
+ "loss": 1.2415,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 0.76,
72
+ "learning_rate": 1.8476876211575742e-05,
73
+ "loss": 1.2126,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 0.83,
78
+ "learning_rate": 1.8338410412628083e-05,
79
+ "loss": 1.1998,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 0.9,
84
+ "learning_rate": 1.8199944613680424e-05,
85
+ "loss": 1.1952,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 0.97,
90
+ "learning_rate": 1.806147881473276e-05,
91
+ "loss": 1.1406,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 1.0,
96
+ "eval_loss": 1.0695199966430664,
97
+ "eval_runtime": 44.0148,
98
+ "eval_samples_per_second": 659.142,
99
+ "eval_steps_per_second": 82.404,
100
+ "step": 7222
101
+ },
102
+ {
103
+ "epoch": 1.04,
104
+ "learning_rate": 1.7923013015785103e-05,
105
+ "loss": 1.1321,
106
+ "step": 7500
107
+ },
108
+ {
109
+ "epoch": 1.11,
110
+ "learning_rate": 1.7784547216837444e-05,
111
+ "loss": 1.1054,
112
+ "step": 8000
113
+ },
114
+ {
115
+ "epoch": 1.18,
116
+ "learning_rate": 1.764608141788978e-05,
117
+ "loss": 1.1185,
118
+ "step": 8500
119
+ },
120
+ {
121
+ "epoch": 1.25,
122
+ "learning_rate": 1.7507615618942122e-05,
123
+ "loss": 1.0977,
124
+ "step": 9000
125
+ },
126
+ {
127
+ "epoch": 1.32,
128
+ "learning_rate": 1.7369149819994463e-05,
129
+ "loss": 1.1232,
130
+ "step": 9500
131
+ },
132
+ {
133
+ "epoch": 1.38,
134
+ "learning_rate": 1.72306840210468e-05,
135
+ "loss": 1.0793,
136
+ "step": 10000
137
+ },
138
+ {
139
+ "epoch": 1.45,
140
+ "learning_rate": 1.7092218222099145e-05,
141
+ "loss": 1.0588,
142
+ "step": 10500
143
+ },
144
+ {
145
+ "epoch": 1.52,
146
+ "learning_rate": 1.6953752423151483e-05,
147
+ "loss": 1.048,
148
+ "step": 11000
149
+ },
150
+ {
151
+ "epoch": 1.59,
152
+ "learning_rate": 1.6815286624203824e-05,
153
+ "loss": 1.036,
154
+ "step": 11500
155
+ },
156
+ {
157
+ "epoch": 1.66,
158
+ "learning_rate": 1.6676820825256165e-05,
159
+ "loss": 1.0414,
160
+ "step": 12000
161
+ },
162
+ {
163
+ "epoch": 1.73,
164
+ "learning_rate": 1.6538355026308502e-05,
165
+ "loss": 1.0109,
166
+ "step": 12500
167
+ },
168
+ {
169
+ "epoch": 1.8,
170
+ "learning_rate": 1.6399889227360843e-05,
171
+ "loss": 1.0186,
172
+ "step": 13000
173
+ },
174
+ {
175
+ "epoch": 1.87,
176
+ "learning_rate": 1.6261423428413184e-05,
177
+ "loss": 1.0456,
178
+ "step": 13500
179
+ },
180
+ {
181
+ "epoch": 1.94,
182
+ "learning_rate": 1.612295762946552e-05,
183
+ "loss": 0.999,
184
+ "step": 14000
185
+ },
186
+ {
187
+ "epoch": 2.0,
188
+ "eval_loss": 0.9253028035163879,
189
+ "eval_runtime": 44.5087,
190
+ "eval_samples_per_second": 651.828,
191
+ "eval_steps_per_second": 81.49,
192
+ "step": 14444
193
+ },
194
+ {
195
+ "epoch": 2.01,
196
+ "learning_rate": 1.5984491830517863e-05,
197
+ "loss": 0.9973,
198
+ "step": 14500
199
+ },
200
+ {
201
+ "epoch": 2.08,
202
+ "learning_rate": 1.5846026031570204e-05,
203
+ "loss": 1.0,
204
+ "step": 15000
205
+ },
206
+ {
207
+ "epoch": 2.15,
208
+ "learning_rate": 1.5707560232622545e-05,
209
+ "loss": 0.9893,
210
+ "step": 15500
211
+ },
212
+ {
213
+ "epoch": 2.22,
214
+ "learning_rate": 1.5569094433674882e-05,
215
+ "loss": 0.9825,
216
+ "step": 16000
217
+ },
218
+ {
219
+ "epoch": 2.28,
220
+ "learning_rate": 1.5430628634727223e-05,
221
+ "loss": 0.9775,
222
+ "step": 16500
223
+ },
224
+ {
225
+ "epoch": 2.35,
226
+ "learning_rate": 1.5292162835779564e-05,
227
+ "loss": 0.9564,
228
+ "step": 17000
229
+ },
230
+ {
231
+ "epoch": 2.42,
232
+ "learning_rate": 1.5153697036831905e-05,
233
+ "loss": 0.9555,
234
+ "step": 17500
235
+ },
236
+ {
237
+ "epoch": 2.49,
238
+ "learning_rate": 1.5015231237884244e-05,
239
+ "loss": 0.9441,
240
+ "step": 18000
241
+ },
242
+ {
243
+ "epoch": 2.56,
244
+ "learning_rate": 1.4876765438936585e-05,
245
+ "loss": 0.957,
246
+ "step": 18500
247
+ },
248
+ {
249
+ "epoch": 2.63,
250
+ "learning_rate": 1.4738299639988925e-05,
251
+ "loss": 0.9341,
252
+ "step": 19000
253
+ },
254
+ {
255
+ "epoch": 2.7,
256
+ "learning_rate": 1.4599833841041264e-05,
257
+ "loss": 0.9222,
258
+ "step": 19500
259
+ },
260
+ {
261
+ "epoch": 2.77,
262
+ "learning_rate": 1.4461368042093605e-05,
263
+ "loss": 0.9204,
264
+ "step": 20000
265
+ },
266
+ {
267
+ "epoch": 2.84,
268
+ "learning_rate": 1.4322902243145944e-05,
269
+ "loss": 0.9379,
270
+ "step": 20500
271
+ },
272
+ {
273
+ "epoch": 2.91,
274
+ "learning_rate": 1.4184436444198283e-05,
275
+ "loss": 0.9113,
276
+ "step": 21000
277
+ },
278
+ {
279
+ "epoch": 2.98,
280
+ "learning_rate": 1.4045970645250624e-05,
281
+ "loss": 0.9015,
282
+ "step": 21500
283
+ },
284
+ {
285
+ "epoch": 3.0,
286
+ "eval_loss": 0.8526855707168579,
287
+ "eval_runtime": 44.1672,
288
+ "eval_samples_per_second": 656.868,
289
+ "eval_steps_per_second": 82.12,
290
+ "step": 21666
291
+ },
292
+ {
293
+ "epoch": 3.05,
294
+ "learning_rate": 1.3907504846302964e-05,
295
+ "loss": 0.8847,
296
+ "step": 22000
297
+ },
298
+ {
299
+ "epoch": 3.12,
300
+ "learning_rate": 1.3769039047355303e-05,
301
+ "loss": 0.9032,
302
+ "step": 22500
303
+ },
304
+ {
305
+ "epoch": 3.18,
306
+ "learning_rate": 1.3630573248407644e-05,
307
+ "loss": 0.9074,
308
+ "step": 23000
309
+ },
310
+ {
311
+ "epoch": 3.25,
312
+ "learning_rate": 1.3492107449459983e-05,
313
+ "loss": 0.8774,
314
+ "step": 23500
315
+ },
316
+ {
317
+ "epoch": 3.32,
318
+ "learning_rate": 1.3353641650512326e-05,
319
+ "loss": 0.9121,
320
+ "step": 24000
321
+ },
322
+ {
323
+ "epoch": 3.39,
324
+ "learning_rate": 1.3215175851564665e-05,
325
+ "loss": 0.8713,
326
+ "step": 24500
327
+ },
328
+ {
329
+ "epoch": 3.46,
330
+ "learning_rate": 1.3076710052617006e-05,
331
+ "loss": 0.8623,
332
+ "step": 25000
333
+ },
334
+ {
335
+ "epoch": 3.53,
336
+ "learning_rate": 1.2938244253669345e-05,
337
+ "loss": 0.899,
338
+ "step": 25500
339
+ },
340
+ {
341
+ "epoch": 3.6,
342
+ "learning_rate": 1.2799778454721685e-05,
343
+ "loss": 0.8702,
344
+ "step": 26000
345
+ },
346
+ {
347
+ "epoch": 3.67,
348
+ "learning_rate": 1.2661312655774026e-05,
349
+ "loss": 0.884,
350
+ "step": 26500
351
+ },
352
+ {
353
+ "epoch": 3.74,
354
+ "learning_rate": 1.2522846856826365e-05,
355
+ "loss": 0.8518,
356
+ "step": 27000
357
+ },
358
+ {
359
+ "epoch": 3.81,
360
+ "learning_rate": 1.2384381057878704e-05,
361
+ "loss": 0.8816,
362
+ "step": 27500
363
+ },
364
+ {
365
+ "epoch": 3.88,
366
+ "learning_rate": 1.2245915258931045e-05,
367
+ "loss": 0.8495,
368
+ "step": 28000
369
+ },
370
+ {
371
+ "epoch": 3.95,
372
+ "learning_rate": 1.2107449459983384e-05,
373
+ "loss": 0.8663,
374
+ "step": 28500
375
+ },
376
+ {
377
+ "epoch": 4.0,
378
+ "eval_loss": 0.7954610586166382,
379
+ "eval_runtime": 44.1292,
380
+ "eval_samples_per_second": 657.434,
381
+ "eval_steps_per_second": 82.191,
382
+ "step": 28888
383
+ },
384
+ {
385
+ "epoch": 4.02,
386
+ "learning_rate": 1.1968983661035725e-05,
387
+ "loss": 0.852,
388
+ "step": 29000
389
+ },
390
+ {
391
+ "epoch": 4.08,
392
+ "learning_rate": 1.1830517862088065e-05,
393
+ "loss": 0.8425,
394
+ "step": 29500
395
+ },
396
+ {
397
+ "epoch": 4.15,
398
+ "learning_rate": 1.1692052063140404e-05,
399
+ "loss": 0.8379,
400
+ "step": 30000
401
+ },
402
+ {
403
+ "epoch": 4.22,
404
+ "learning_rate": 1.1553586264192745e-05,
405
+ "loss": 0.859,
406
+ "step": 30500
407
+ },
408
+ {
409
+ "epoch": 4.29,
410
+ "learning_rate": 1.1415120465245086e-05,
411
+ "loss": 0.8449,
412
+ "step": 31000
413
+ },
414
+ {
415
+ "epoch": 4.36,
416
+ "learning_rate": 1.1276654666297427e-05,
417
+ "loss": 0.8333,
418
+ "step": 31500
419
+ },
420
+ {
421
+ "epoch": 4.43,
422
+ "learning_rate": 1.1138188867349766e-05,
423
+ "loss": 0.8225,
424
+ "step": 32000
425
+ },
426
+ {
427
+ "epoch": 4.5,
428
+ "learning_rate": 1.0999723068402105e-05,
429
+ "loss": 0.8356,
430
+ "step": 32500
431
+ },
432
+ {
433
+ "epoch": 4.57,
434
+ "learning_rate": 1.0861257269454446e-05,
435
+ "loss": 0.839,
436
+ "step": 33000
437
+ },
438
+ {
439
+ "epoch": 4.64,
440
+ "learning_rate": 1.0722791470506786e-05,
441
+ "loss": 0.8511,
442
+ "step": 33500
443
+ },
444
+ {
445
+ "epoch": 4.71,
446
+ "learning_rate": 1.0584325671559127e-05,
447
+ "loss": 0.8518,
448
+ "step": 34000
449
+ },
450
+ {
451
+ "epoch": 4.78,
452
+ "learning_rate": 1.0445859872611466e-05,
453
+ "loss": 0.8101,
454
+ "step": 34500
455
+ },
456
+ {
457
+ "epoch": 4.85,
458
+ "learning_rate": 1.0307394073663805e-05,
459
+ "loss": 0.8172,
460
+ "step": 35000
461
+ },
462
+ {
463
+ "epoch": 4.92,
464
+ "learning_rate": 1.0168928274716146e-05,
465
+ "loss": 0.8387,
466
+ "step": 35500
467
+ },
468
+ {
469
+ "epoch": 4.98,
470
+ "learning_rate": 1.0030462475768485e-05,
471
+ "loss": 0.7919,
472
+ "step": 36000
473
+ },
474
+ {
475
+ "epoch": 5.0,
476
+ "eval_loss": 0.7614109516143799,
477
+ "eval_runtime": 24.141,
478
+ "eval_samples_per_second": 1201.775,
479
+ "eval_steps_per_second": 150.243,
480
+ "step": 36110
481
+ },
482
+ {
483
+ "epoch": 5.05,
484
+ "learning_rate": 9.891996676820826e-06,
485
+ "loss": 0.806,
486
+ "step": 36500
487
+ },
488
+ {
489
+ "epoch": 5.12,
490
+ "learning_rate": 9.753530877873166e-06,
491
+ "loss": 0.8068,
492
+ "step": 37000
493
+ },
494
+ {
495
+ "epoch": 5.19,
496
+ "learning_rate": 9.615065078925507e-06,
497
+ "loss": 0.8124,
498
+ "step": 37500
499
+ },
500
+ {
501
+ "epoch": 5.26,
502
+ "learning_rate": 9.476599279977846e-06,
503
+ "loss": 0.7742,
504
+ "step": 38000
505
+ },
506
+ {
507
+ "epoch": 5.33,
508
+ "learning_rate": 9.338133481030187e-06,
509
+ "loss": 0.7928,
510
+ "step": 38500
511
+ },
512
+ {
513
+ "epoch": 5.4,
514
+ "learning_rate": 9.199667682082526e-06,
515
+ "loss": 0.8034,
516
+ "step": 39000
517
+ },
518
+ {
519
+ "epoch": 5.47,
520
+ "learning_rate": 9.061201883134867e-06,
521
+ "loss": 0.802,
522
+ "step": 39500
523
+ },
524
+ {
525
+ "epoch": 5.54,
526
+ "learning_rate": 8.922736084187206e-06,
527
+ "loss": 0.7834,
528
+ "step": 40000
529
+ },
530
+ {
531
+ "epoch": 5.61,
532
+ "learning_rate": 8.784270285239547e-06,
533
+ "loss": 0.7892,
534
+ "step": 40500
535
+ },
536
+ {
537
+ "epoch": 5.68,
538
+ "learning_rate": 8.645804486291887e-06,
539
+ "loss": 0.7783,
540
+ "step": 41000
541
+ },
542
+ {
543
+ "epoch": 5.75,
544
+ "learning_rate": 8.507338687344226e-06,
545
+ "loss": 0.7757,
546
+ "step": 41500
547
+ },
548
+ {
549
+ "epoch": 5.82,
550
+ "learning_rate": 8.368872888396567e-06,
551
+ "loss": 0.7774,
552
+ "step": 42000
553
+ },
554
+ {
555
+ "epoch": 5.88,
556
+ "learning_rate": 8.230407089448906e-06,
557
+ "loss": 0.7684,
558
+ "step": 42500
559
+ },
560
+ {
561
+ "epoch": 5.95,
562
+ "learning_rate": 8.091941290501247e-06,
563
+ "loss": 0.7933,
564
+ "step": 43000
565
+ },
566
+ {
567
+ "epoch": 6.0,
568
+ "eval_loss": 0.7296460866928101,
569
+ "eval_runtime": 22.896,
570
+ "eval_samples_per_second": 1267.119,
571
+ "eval_steps_per_second": 158.412,
572
+ "step": 43332
573
+ },
574
+ {
575
+ "epoch": 6.02,
576
+ "learning_rate": 7.953475491553588e-06,
577
+ "loss": 0.7829,
578
+ "step": 43500
579
+ },
580
+ {
581
+ "epoch": 6.09,
582
+ "learning_rate": 7.815009692605927e-06,
583
+ "loss": 0.7581,
584
+ "step": 44000
585
+ },
586
+ {
587
+ "epoch": 6.16,
588
+ "learning_rate": 7.676543893658267e-06,
589
+ "loss": 0.7389,
590
+ "step": 44500
591
+ },
592
+ {
593
+ "epoch": 6.23,
594
+ "learning_rate": 7.538078094710607e-06,
595
+ "loss": 0.767,
596
+ "step": 45000
597
+ },
598
+ {
599
+ "epoch": 6.3,
600
+ "learning_rate": 7.399612295762947e-06,
601
+ "loss": 0.7517,
602
+ "step": 45500
603
+ },
604
+ {
605
+ "epoch": 6.37,
606
+ "learning_rate": 7.261146496815287e-06,
607
+ "loss": 0.7572,
608
+ "step": 46000
609
+ },
610
+ {
611
+ "epoch": 6.44,
612
+ "learning_rate": 7.122680697867628e-06,
613
+ "loss": 0.7501,
614
+ "step": 46500
615
+ },
616
+ {
617
+ "epoch": 6.51,
618
+ "learning_rate": 6.984214898919968e-06,
619
+ "loss": 0.7603,
620
+ "step": 47000
621
+ },
622
+ {
623
+ "epoch": 6.58,
624
+ "learning_rate": 6.845749099972307e-06,
625
+ "loss": 0.7432,
626
+ "step": 47500
627
+ },
628
+ {
629
+ "epoch": 6.65,
630
+ "learning_rate": 6.707283301024647e-06,
631
+ "loss": 0.7523,
632
+ "step": 48000
633
+ },
634
+ {
635
+ "epoch": 6.72,
636
+ "learning_rate": 6.5688175020769875e-06,
637
+ "loss": 0.7652,
638
+ "step": 48500
639
+ },
640
+ {
641
+ "epoch": 6.78,
642
+ "learning_rate": 6.430351703129327e-06,
643
+ "loss": 0.7707,
644
+ "step": 49000
645
+ },
646
+ {
647
+ "epoch": 6.85,
648
+ "learning_rate": 6.291885904181667e-06,
649
+ "loss": 0.7512,
650
+ "step": 49500
651
+ },
652
+ {
653
+ "epoch": 6.92,
654
+ "learning_rate": 6.153420105234008e-06,
655
+ "loss": 0.7407,
656
+ "step": 50000
657
+ },
658
+ {
659
+ "epoch": 6.99,
660
+ "learning_rate": 6.014954306286348e-06,
661
+ "loss": 0.7713,
662
+ "step": 50500
663
+ },
664
+ {
665
+ "epoch": 7.0,
666
+ "eval_loss": 0.6923113465309143,
667
+ "eval_runtime": 24.1974,
668
+ "eval_samples_per_second": 1198.969,
669
+ "eval_steps_per_second": 149.892,
670
+ "step": 50554
671
+ },
672
+ {
673
+ "epoch": 7.06,
674
+ "learning_rate": 5.876488507338688e-06,
675
+ "loss": 0.7631,
676
+ "step": 51000
677
+ },
678
+ {
679
+ "epoch": 7.13,
680
+ "learning_rate": 5.738022708391027e-06,
681
+ "loss": 0.7597,
682
+ "step": 51500
683
+ },
684
+ {
685
+ "epoch": 7.2,
686
+ "learning_rate": 5.5995569094433675e-06,
687
+ "loss": 0.7353,
688
+ "step": 52000
689
+ },
690
+ {
691
+ "epoch": 7.27,
692
+ "learning_rate": 5.461091110495708e-06,
693
+ "loss": 0.7588,
694
+ "step": 52500
695
+ },
696
+ {
697
+ "epoch": 7.34,
698
+ "learning_rate": 5.322625311548048e-06,
699
+ "loss": 0.7333,
700
+ "step": 53000
701
+ },
702
+ {
703
+ "epoch": 7.41,
704
+ "learning_rate": 5.184159512600389e-06,
705
+ "loss": 0.7562,
706
+ "step": 53500
707
+ },
708
+ {
709
+ "epoch": 7.48,
710
+ "learning_rate": 5.045693713652728e-06,
711
+ "loss": 0.7262,
712
+ "step": 54000
713
+ },
714
+ {
715
+ "epoch": 7.55,
716
+ "learning_rate": 4.907227914705068e-06,
717
+ "loss": 0.7627,
718
+ "step": 54500
719
+ },
720
+ {
721
+ "epoch": 7.62,
722
+ "learning_rate": 4.768762115757408e-06,
723
+ "loss": 0.7443,
724
+ "step": 55000
725
+ },
726
+ {
727
+ "epoch": 7.68,
728
+ "learning_rate": 4.630296316809748e-06,
729
+ "loss": 0.758,
730
+ "step": 55500
731
+ },
732
+ {
733
+ "epoch": 7.75,
734
+ "learning_rate": 4.4918305178620885e-06,
735
+ "loss": 0.7295,
736
+ "step": 56000
737
+ },
738
+ {
739
+ "epoch": 7.82,
740
+ "learning_rate": 4.353364718914429e-06,
741
+ "loss": 0.726,
742
+ "step": 56500
743
+ },
744
+ {
745
+ "epoch": 7.89,
746
+ "learning_rate": 4.214898919966769e-06,
747
+ "loss": 0.7335,
748
+ "step": 57000
749
+ },
750
+ {
751
+ "epoch": 7.96,
752
+ "learning_rate": 4.076433121019109e-06,
753
+ "loss": 0.7249,
754
+ "step": 57500
755
+ },
756
+ {
757
+ "epoch": 8.0,
758
+ "eval_loss": 0.6828723549842834,
759
+ "eval_runtime": 22.9367,
760
+ "eval_samples_per_second": 1264.871,
761
+ "eval_steps_per_second": 158.131,
762
+ "step": 57776
763
+ },
764
+ {
765
+ "epoch": 8.03,
766
+ "learning_rate": 3.937967322071449e-06,
767
+ "loss": 0.719,
768
+ "step": 58000
769
+ },
770
+ {
771
+ "epoch": 8.1,
772
+ "learning_rate": 3.7995015231237887e-06,
773
+ "loss": 0.7539,
774
+ "step": 58500
775
+ },
776
+ {
777
+ "epoch": 8.17,
778
+ "learning_rate": 3.6610357241761292e-06,
779
+ "loss": 0.7311,
780
+ "step": 59000
781
+ },
782
+ {
783
+ "epoch": 8.24,
784
+ "learning_rate": 3.522569925228469e-06,
785
+ "loss": 0.7186,
786
+ "step": 59500
787
+ },
788
+ {
789
+ "epoch": 8.31,
790
+ "learning_rate": 3.384104126280809e-06,
791
+ "loss": 0.722,
792
+ "step": 60000
793
+ },
794
+ {
795
+ "epoch": 8.38,
796
+ "learning_rate": 3.2456383273331488e-06,
797
+ "loss": 0.6963,
798
+ "step": 60500
799
+ },
800
+ {
801
+ "epoch": 8.45,
802
+ "learning_rate": 3.1071725283854893e-06,
803
+ "loss": 0.7177,
804
+ "step": 61000
805
+ },
806
+ {
807
+ "epoch": 8.52,
808
+ "learning_rate": 2.968706729437829e-06,
809
+ "loss": 0.7121,
810
+ "step": 61500
811
+ },
812
+ {
813
+ "epoch": 8.58,
814
+ "learning_rate": 2.830240930490169e-06,
815
+ "loss": 0.7165,
816
+ "step": 62000
817
+ },
818
+ {
819
+ "epoch": 8.65,
820
+ "learning_rate": 2.6917751315425097e-06,
821
+ "loss": 0.6935,
822
+ "step": 62500
823
+ },
824
+ {
825
+ "epoch": 8.72,
826
+ "learning_rate": 2.5533093325948494e-06,
827
+ "loss": 0.6841,
828
+ "step": 63000
829
+ },
830
+ {
831
+ "epoch": 8.79,
832
+ "learning_rate": 2.414843533647189e-06,
833
+ "loss": 0.7214,
834
+ "step": 63500
835
+ },
836
+ {
837
+ "epoch": 8.86,
838
+ "learning_rate": 2.2763777346995296e-06,
839
+ "loss": 0.7061,
840
+ "step": 64000
841
+ },
842
+ {
843
+ "epoch": 8.93,
844
+ "learning_rate": 2.1379119357518693e-06,
845
+ "loss": 0.7083,
846
+ "step": 64500
847
+ },
848
+ {
849
+ "epoch": 9.0,
850
+ "eval_loss": 0.6712043881416321,
851
+ "eval_runtime": 22.8269,
852
+ "eval_samples_per_second": 1270.954,
853
+ "eval_steps_per_second": 158.891,
854
+ "step": 64998
855
+ },
856
+ {
857
+ "epoch": 9.0,
858
+ "learning_rate": 1.9994461368042094e-06,
859
+ "loss": 0.709,
860
+ "step": 65000
861
+ },
862
+ {
863
+ "epoch": 9.07,
864
+ "learning_rate": 1.8609803378565498e-06,
865
+ "loss": 0.6984,
866
+ "step": 65500
867
+ },
868
+ {
869
+ "epoch": 9.14,
870
+ "learning_rate": 1.7225145389088897e-06,
871
+ "loss": 0.7085,
872
+ "step": 66000
873
+ },
874
+ {
875
+ "epoch": 9.21,
876
+ "learning_rate": 1.5840487399612298e-06,
877
+ "loss": 0.7019,
878
+ "step": 66500
879
+ },
880
+ {
881
+ "epoch": 9.28,
882
+ "learning_rate": 1.4455829410135697e-06,
883
+ "loss": 0.7084,
884
+ "step": 67000
885
+ },
886
+ {
887
+ "epoch": 9.35,
888
+ "learning_rate": 1.3071171420659098e-06,
889
+ "loss": 0.6973,
890
+ "step": 67500
891
+ },
892
+ {
893
+ "epoch": 9.42,
894
+ "learning_rate": 1.16865134311825e-06,
895
+ "loss": 0.698,
896
+ "step": 68000
897
+ },
898
+ {
899
+ "epoch": 9.48,
900
+ "learning_rate": 1.0301855441705899e-06,
901
+ "loss": 0.7298,
902
+ "step": 68500
903
+ },
904
+ {
905
+ "epoch": 9.55,
906
+ "learning_rate": 8.9171974522293e-07,
907
+ "loss": 0.7163,
908
+ "step": 69000
909
+ },
910
+ {
911
+ "epoch": 9.62,
912
+ "learning_rate": 7.532539462752701e-07,
913
+ "loss": 0.6955,
914
+ "step": 69500
915
+ },
916
+ {
917
+ "epoch": 9.69,
918
+ "learning_rate": 6.147881473276101e-07,
919
+ "loss": 0.6855,
920
+ "step": 70000
921
+ },
922
+ {
923
+ "epoch": 9.76,
924
+ "learning_rate": 4.763223483799502e-07,
925
+ "loss": 0.7026,
926
+ "step": 70500
927
+ },
928
+ {
929
+ "epoch": 9.83,
930
+ "learning_rate": 3.3785654943229026e-07,
931
+ "loss": 0.7055,
932
+ "step": 71000
933
+ },
934
+ {
935
+ "epoch": 9.9,
936
+ "learning_rate": 1.993907504846303e-07,
937
+ "loss": 0.6855,
938
+ "step": 71500
939
+ },
940
+ {
941
+ "epoch": 9.97,
942
+ "learning_rate": 6.092495153697037e-08,
943
+ "loss": 0.717,
944
+ "step": 72000
945
+ }
946
+ ],
947
+ "max_steps": 72220,
948
+ "num_train_epochs": 10,
949
+ "total_flos": 3729696905063250.0,
950
+ "trial_name": null,
951
+ "trial_params": null
952
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6df086599af6224a82673fc7232d6a83f7d65158b284f9a2eb60710f4859af0e
3
+ size 3899