eqhylxx commited on
Commit
a4fda50
1 Parent(s): 6ed4d7e

gsm8k teacher fwd distill

Browse files
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "JackFram/llama-160m",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 0,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 768,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 3072,
12
+ "max_position_embeddings": 2048,
13
+ "model_type": "llama",
14
+ "num_attention_heads": 12,
15
+ "num_hidden_layers": 12,
16
+ "num_key_value_heads": 12,
17
+ "pad_token_id": 1,
18
+ "pretraining_tp": 1,
19
+ "rms_norm_eps": 1e-06,
20
+ "rope_scaling": null,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.31.0",
24
+ "use_cache": true,
25
+ "vocab_size": 32000
26
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 1,
6
+ "transformers_version": "4.31.0"
7
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17c03b9f632128b3918b9d26971a5fbddb2ecf1629275cef5a896b7a7898aaa7
3
+ size 649710457
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<unk>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "clean_up_tokenization_spaces": false,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "legacy": true,
22
+ "model_max_length": 2048,
23
+ "pad_token": null,
24
+ "padding_side": "right",
25
+ "sp_model_kwargs": {},
26
+ "tokenizer_class": "LlamaTokenizer",
27
+ "unk_token": {
28
+ "__type": "AddedToken",
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ }
35
+ }
trainer_state.json ADDED
@@ -0,0 +1,721 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.9850267379679143,
5
+ "global_step": 116,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.02,
12
+ "learning_rate": 5e-06,
13
+ "loss": 2.127,
14
+ "step": 1
15
+ },
16
+ {
17
+ "epoch": 0.03,
18
+ "learning_rate": 1e-05,
19
+ "loss": 2.0803,
20
+ "step": 2
21
+ },
22
+ {
23
+ "epoch": 0.05,
24
+ "learning_rate": 1.5000000000000002e-05,
25
+ "loss": 2.0116,
26
+ "step": 3
27
+ },
28
+ {
29
+ "epoch": 0.07,
30
+ "learning_rate": 2e-05,
31
+ "loss": 1.9464,
32
+ "step": 4
33
+ },
34
+ {
35
+ "epoch": 0.09,
36
+ "learning_rate": 1.9996066263830533e-05,
37
+ "loss": 1.8489,
38
+ "step": 5
39
+ },
40
+ {
41
+ "epoch": 0.1,
42
+ "learning_rate": 1.998426815017817e-05,
43
+ "loss": 1.6761,
44
+ "step": 6
45
+ },
46
+ {
47
+ "epoch": 0.12,
48
+ "learning_rate": 1.9964614941176194e-05,
49
+ "loss": 1.6074,
50
+ "step": 7
51
+ },
52
+ {
53
+ "epoch": 0.14,
54
+ "learning_rate": 1.9937122098932428e-05,
55
+ "loss": 1.538,
56
+ "step": 8
57
+ },
58
+ {
59
+ "epoch": 0.15,
60
+ "learning_rate": 1.9901811253364458e-05,
61
+ "loss": 1.5003,
62
+ "step": 9
63
+ },
64
+ {
65
+ "epoch": 0.17,
66
+ "learning_rate": 1.985871018518236e-05,
67
+ "loss": 1.4459,
68
+ "step": 10
69
+ },
70
+ {
71
+ "epoch": 0.19,
72
+ "learning_rate": 1.9807852804032306e-05,
73
+ "loss": 1.3862,
74
+ "step": 11
75
+ },
76
+ {
77
+ "epoch": 0.21,
78
+ "learning_rate": 1.9749279121818235e-05,
79
+ "loss": 1.2781,
80
+ "step": 12
81
+ },
82
+ {
83
+ "epoch": 0.22,
84
+ "learning_rate": 1.9683035221222617e-05,
85
+ "loss": 1.2523,
86
+ "step": 13
87
+ },
88
+ {
89
+ "epoch": 0.24,
90
+ "learning_rate": 1.9609173219450998e-05,
91
+ "loss": 1.2374,
92
+ "step": 14
93
+ },
94
+ {
95
+ "epoch": 0.26,
96
+ "learning_rate": 1.9527751227228964e-05,
97
+ "loss": 1.2061,
98
+ "step": 15
99
+ },
100
+ {
101
+ "epoch": 0.27,
102
+ "learning_rate": 1.9438833303083677e-05,
103
+ "loss": 1.1725,
104
+ "step": 16
105
+ },
106
+ {
107
+ "epoch": 0.29,
108
+ "learning_rate": 1.9342489402945997e-05,
109
+ "loss": 1.165,
110
+ "step": 17
111
+ },
112
+ {
113
+ "epoch": 0.31,
114
+ "learning_rate": 1.9238795325112867e-05,
115
+ "loss": 1.1516,
116
+ "step": 18
117
+ },
118
+ {
119
+ "epoch": 0.33,
120
+ "learning_rate": 1.912783265061319e-05,
121
+ "loss": 1.1238,
122
+ "step": 19
123
+ },
124
+ {
125
+ "epoch": 0.34,
126
+ "learning_rate": 1.900968867902419e-05,
127
+ "loss": 1.0967,
128
+ "step": 20
129
+ },
130
+ {
131
+ "epoch": 0.36,
132
+ "learning_rate": 1.8884456359788725e-05,
133
+ "loss": 1.1067,
134
+ "step": 21
135
+ },
136
+ {
137
+ "epoch": 0.38,
138
+ "learning_rate": 1.8752234219087538e-05,
139
+ "loss": 1.0945,
140
+ "step": 22
141
+ },
142
+ {
143
+ "epoch": 0.39,
144
+ "learning_rate": 1.8613126282324092e-05,
145
+ "loss": 1.0476,
146
+ "step": 23
147
+ },
148
+ {
149
+ "epoch": 0.41,
150
+ "learning_rate": 1.8467241992282842e-05,
151
+ "loss": 1.0808,
152
+ "step": 24
153
+ },
154
+ {
155
+ "epoch": 0.43,
156
+ "learning_rate": 1.8314696123025456e-05,
157
+ "loss": 1.0276,
158
+ "step": 25
159
+ },
160
+ {
161
+ "epoch": 0.44,
162
+ "learning_rate": 1.8155608689592604e-05,
163
+ "loss": 1.0342,
164
+ "step": 26
165
+ },
166
+ {
167
+ "epoch": 0.46,
168
+ "learning_rate": 1.7990104853582494e-05,
169
+ "loss": 1.0136,
170
+ "step": 27
171
+ },
172
+ {
173
+ "epoch": 0.48,
174
+ "learning_rate": 1.78183148246803e-05,
175
+ "loss": 1.0192,
176
+ "step": 28
177
+ },
178
+ {
179
+ "epoch": 0.5,
180
+ "learning_rate": 1.7640373758216075e-05,
181
+ "loss": 1.0024,
182
+ "step": 29
183
+ },
184
+ {
185
+ "epoch": 0.51,
186
+ "learning_rate": 1.7456421648831658e-05,
187
+ "loss": 0.984,
188
+ "step": 30
189
+ },
190
+ {
191
+ "epoch": 0.53,
192
+ "learning_rate": 1.7266603220340273e-05,
193
+ "loss": 0.9774,
194
+ "step": 31
195
+ },
196
+ {
197
+ "epoch": 0.55,
198
+ "learning_rate": 1.7071067811865477e-05,
199
+ "loss": 0.9401,
200
+ "step": 32
201
+ },
202
+ {
203
+ "epoch": 0.56,
204
+ "learning_rate": 1.686996926034902e-05,
205
+ "loss": 0.9797,
206
+ "step": 33
207
+ },
208
+ {
209
+ "epoch": 0.58,
210
+ "learning_rate": 1.6663465779520042e-05,
211
+ "loss": 0.9534,
212
+ "step": 34
213
+ },
214
+ {
215
+ "epoch": 0.6,
216
+ "learning_rate": 1.645171983542088e-05,
217
+ "loss": 0.9148,
218
+ "step": 35
219
+ },
220
+ {
221
+ "epoch": 0.62,
222
+ "learning_rate": 1.6234898018587336e-05,
223
+ "loss": 0.9408,
224
+ "step": 36
225
+ },
226
+ {
227
+ "epoch": 0.63,
228
+ "learning_rate": 1.601317091298406e-05,
229
+ "loss": 0.9417,
230
+ "step": 37
231
+ },
232
+ {
233
+ "epoch": 0.65,
234
+ "learning_rate": 1.578671296179806e-05,
235
+ "loss": 0.9484,
236
+ "step": 38
237
+ },
238
+ {
239
+ "epoch": 0.67,
240
+ "learning_rate": 1.5555702330196024e-05,
241
+ "loss": 0.9714,
242
+ "step": 39
243
+ },
244
+ {
245
+ "epoch": 0.68,
246
+ "learning_rate": 1.5320320765153367e-05,
247
+ "loss": 0.9233,
248
+ "step": 40
249
+ },
250
+ {
251
+ "epoch": 0.7,
252
+ "learning_rate": 1.5080753452465296e-05,
253
+ "loss": 0.9293,
254
+ "step": 41
255
+ },
256
+ {
257
+ "epoch": 0.72,
258
+ "learning_rate": 1.4837188871052399e-05,
259
+ "loss": 0.9469,
260
+ "step": 42
261
+ },
262
+ {
263
+ "epoch": 0.74,
264
+ "learning_rate": 1.4589818644675378e-05,
265
+ "loss": 0.9224,
266
+ "step": 43
267
+ },
268
+ {
269
+ "epoch": 0.75,
270
+ "learning_rate": 1.4338837391175582e-05,
271
+ "loss": 0.8792,
272
+ "step": 44
273
+ },
274
+ {
275
+ "epoch": 0.77,
276
+ "learning_rate": 1.4084442569359964e-05,
277
+ "loss": 0.9298,
278
+ "step": 45
279
+ },
280
+ {
281
+ "epoch": 0.79,
282
+ "learning_rate": 1.3826834323650899e-05,
283
+ "loss": 0.8869,
284
+ "step": 46
285
+ },
286
+ {
287
+ "epoch": 0.8,
288
+ "learning_rate": 1.3566215326623131e-05,
289
+ "loss": 0.9078,
290
+ "step": 47
291
+ },
292
+ {
293
+ "epoch": 0.82,
294
+ "learning_rate": 1.3302790619551673e-05,
295
+ "loss": 0.8703,
296
+ "step": 48
297
+ },
298
+ {
299
+ "epoch": 0.84,
300
+ "learning_rate": 1.3036767451096148e-05,
301
+ "loss": 0.8648,
302
+ "step": 49
303
+ },
304
+ {
305
+ "epoch": 0.86,
306
+ "learning_rate": 1.2768355114248493e-05,
307
+ "loss": 0.9123,
308
+ "step": 50
309
+ },
310
+ {
311
+ "epoch": 0.87,
312
+ "learning_rate": 1.249776478167227e-05,
313
+ "loss": 0.8753,
314
+ "step": 51
315
+ },
316
+ {
317
+ "epoch": 0.89,
318
+ "learning_rate": 1.2225209339563144e-05,
319
+ "loss": 0.8996,
320
+ "step": 52
321
+ },
322
+ {
323
+ "epoch": 0.91,
324
+ "learning_rate": 1.1950903220161286e-05,
325
+ "loss": 0.891,
326
+ "step": 53
327
+ },
328
+ {
329
+ "epoch": 0.92,
330
+ "learning_rate": 1.1675062233047365e-05,
331
+ "loss": 0.8497,
332
+ "step": 54
333
+ },
334
+ {
335
+ "epoch": 0.94,
336
+ "learning_rate": 1.1397903395354996e-05,
337
+ "loss": 0.9031,
338
+ "step": 55
339
+ },
340
+ {
341
+ "epoch": 0.96,
342
+ "learning_rate": 1.1119644761033079e-05,
343
+ "loss": 0.8373,
344
+ "step": 56
345
+ },
346
+ {
347
+ "epoch": 0.98,
348
+ "learning_rate": 1.0840505249292477e-05,
349
+ "loss": 0.8297,
350
+ "step": 57
351
+ },
352
+ {
353
+ "epoch": 0.99,
354
+ "learning_rate": 1.0560704472371919e-05,
355
+ "loss": 0.8923,
356
+ "step": 58
357
+ },
358
+ {
359
+ "epoch": 1.01,
360
+ "learning_rate": 1.028046256275869e-05,
361
+ "loss": 0.8534,
362
+ "step": 59
363
+ },
364
+ {
365
+ "epoch": 1.03,
366
+ "learning_rate": 1e-05,
367
+ "loss": 0.8152,
368
+ "step": 60
369
+ },
370
+ {
371
+ "epoch": 1.04,
372
+ "learning_rate": 9.719537437241311e-06,
373
+ "loss": 0.8488,
374
+ "step": 61
375
+ },
376
+ {
377
+ "epoch": 1.06,
378
+ "learning_rate": 9.439295527628083e-06,
379
+ "loss": 0.8453,
380
+ "step": 62
381
+ },
382
+ {
383
+ "epoch": 1.08,
384
+ "learning_rate": 9.159494750707527e-06,
385
+ "loss": 0.8441,
386
+ "step": 63
387
+ },
388
+ {
389
+ "epoch": 1.1,
390
+ "learning_rate": 8.880355238966923e-06,
391
+ "loss": 0.8281,
392
+ "step": 64
393
+ },
394
+ {
395
+ "epoch": 1.11,
396
+ "learning_rate": 8.602096604645009e-06,
397
+ "loss": 0.8209,
398
+ "step": 65
399
+ },
400
+ {
401
+ "epoch": 1.13,
402
+ "learning_rate": 8.324937766952638e-06,
403
+ "loss": 0.7932,
404
+ "step": 66
405
+ },
406
+ {
407
+ "epoch": 1.15,
408
+ "learning_rate": 8.04909677983872e-06,
409
+ "loss": 0.806,
410
+ "step": 67
411
+ },
412
+ {
413
+ "epoch": 1.16,
414
+ "learning_rate": 7.774790660436857e-06,
415
+ "loss": 0.8218,
416
+ "step": 68
417
+ },
418
+ {
419
+ "epoch": 1.18,
420
+ "learning_rate": 7.50223521832773e-06,
421
+ "loss": 0.7919,
422
+ "step": 69
423
+ },
424
+ {
425
+ "epoch": 1.2,
426
+ "learning_rate": 7.2316448857515076e-06,
427
+ "loss": 0.7795,
428
+ "step": 70
429
+ },
430
+ {
431
+ "epoch": 1.21,
432
+ "learning_rate": 6.963232548903853e-06,
433
+ "loss": 0.7774,
434
+ "step": 71
435
+ },
436
+ {
437
+ "epoch": 1.23,
438
+ "learning_rate": 6.697209380448333e-06,
439
+ "loss": 0.7844,
440
+ "step": 72
441
+ },
442
+ {
443
+ "epoch": 1.25,
444
+ "learning_rate": 6.43378467337687e-06,
445
+ "loss": 0.8,
446
+ "step": 73
447
+ },
448
+ {
449
+ "epoch": 1.27,
450
+ "learning_rate": 6.173165676349103e-06,
451
+ "loss": 0.7743,
452
+ "step": 74
453
+ },
454
+ {
455
+ "epoch": 1.28,
456
+ "learning_rate": 5.91555743064004e-06,
457
+ "loss": 0.7808,
458
+ "step": 75
459
+ },
460
+ {
461
+ "epoch": 1.3,
462
+ "learning_rate": 5.66116260882442e-06,
463
+ "loss": 0.7804,
464
+ "step": 76
465
+ },
466
+ {
467
+ "epoch": 1.32,
468
+ "learning_rate": 5.410181355324622e-06,
469
+ "loss": 0.8098,
470
+ "step": 77
471
+ },
472
+ {
473
+ "epoch": 1.33,
474
+ "learning_rate": 5.1628111289476025e-06,
475
+ "loss": 0.769,
476
+ "step": 78
477
+ },
478
+ {
479
+ "epoch": 1.35,
480
+ "learning_rate": 4.919246547534709e-06,
481
+ "loss": 0.7901,
482
+ "step": 79
483
+ },
484
+ {
485
+ "epoch": 1.37,
486
+ "learning_rate": 4.679679234846636e-06,
487
+ "loss": 0.8071,
488
+ "step": 80
489
+ },
490
+ {
491
+ "epoch": 1.39,
492
+ "learning_rate": 4.444297669803981e-06,
493
+ "loss": 0.7557,
494
+ "step": 81
495
+ },
496
+ {
497
+ "epoch": 1.4,
498
+ "learning_rate": 4.213287038201943e-06,
499
+ "loss": 0.8192,
500
+ "step": 82
501
+ },
502
+ {
503
+ "epoch": 1.42,
504
+ "learning_rate": 3.986829087015941e-06,
505
+ "loss": 0.7987,
506
+ "step": 83
507
+ },
508
+ {
509
+ "epoch": 1.44,
510
+ "learning_rate": 3.7651019814126656e-06,
511
+ "loss": 0.7918,
512
+ "step": 84
513
+ },
514
+ {
515
+ "epoch": 1.45,
516
+ "learning_rate": 3.5482801645791266e-06,
517
+ "loss": 0.8145,
518
+ "step": 85
519
+ },
520
+ {
521
+ "epoch": 1.47,
522
+ "learning_rate": 3.3365342204799613e-06,
523
+ "loss": 0.7737,
524
+ "step": 86
525
+ },
526
+ {
527
+ "epoch": 1.49,
528
+ "learning_rate": 3.1300307396509833e-06,
529
+ "loss": 0.8118,
530
+ "step": 87
531
+ },
532
+ {
533
+ "epoch": 1.51,
534
+ "learning_rate": 2.9289321881345257e-06,
535
+ "loss": 0.7845,
536
+ "step": 88
537
+ },
538
+ {
539
+ "epoch": 1.52,
540
+ "learning_rate": 2.7333967796597317e-06,
541
+ "loss": 0.7557,
542
+ "step": 89
543
+ },
544
+ {
545
+ "epoch": 1.54,
546
+ "learning_rate": 2.5435783511683444e-06,
547
+ "loss": 0.7898,
548
+ "step": 90
549
+ },
550
+ {
551
+ "epoch": 1.56,
552
+ "learning_rate": 2.3596262417839256e-06,
553
+ "loss": 0.7754,
554
+ "step": 91
555
+ },
556
+ {
557
+ "epoch": 1.57,
558
+ "learning_rate": 2.1816851753197023e-06,
559
+ "loss": 0.7875,
560
+ "step": 92
561
+ },
562
+ {
563
+ "epoch": 1.59,
564
+ "learning_rate": 2.009895146417512e-06,
565
+ "loss": 0.7739,
566
+ "step": 93
567
+ },
568
+ {
569
+ "epoch": 1.61,
570
+ "learning_rate": 1.8443913104073984e-06,
571
+ "loss": 0.7745,
572
+ "step": 94
573
+ },
574
+ {
575
+ "epoch": 1.63,
576
+ "learning_rate": 1.6853038769745466e-06,
577
+ "loss": 0.7868,
578
+ "step": 95
579
+ },
580
+ {
581
+ "epoch": 1.64,
582
+ "learning_rate": 1.5327580077171589e-06,
583
+ "loss": 0.7942,
584
+ "step": 96
585
+ },
586
+ {
587
+ "epoch": 1.66,
588
+ "learning_rate": 1.3868737176759105e-06,
589
+ "loss": 0.8101,
590
+ "step": 97
591
+ },
592
+ {
593
+ "epoch": 1.68,
594
+ "learning_rate": 1.2477657809124632e-06,
595
+ "loss": 0.7955,
596
+ "step": 98
597
+ },
598
+ {
599
+ "epoch": 1.69,
600
+ "learning_rate": 1.1155436402112785e-06,
601
+ "loss": 0.7964,
602
+ "step": 99
603
+ },
604
+ {
605
+ "epoch": 1.71,
606
+ "learning_rate": 9.903113209758098e-07,
607
+ "loss": 0.8203,
608
+ "step": 100
609
+ },
610
+ {
611
+ "epoch": 1.73,
612
+ "learning_rate": 8.721673493868111e-07,
613
+ "loss": 0.8105,
614
+ "step": 101
615
+ },
616
+ {
617
+ "epoch": 1.75,
618
+ "learning_rate": 7.612046748871327e-07,
619
+ "loss": 0.775,
620
+ "step": 102
621
+ },
622
+ {
623
+ "epoch": 1.76,
624
+ "learning_rate": 6.57510597054003e-07,
625
+ "loss": 0.77,
626
+ "step": 103
627
+ },
628
+ {
629
+ "epoch": 1.78,
630
+ "learning_rate": 5.611666969163243e-07,
631
+ "loss": 0.7998,
632
+ "step": 104
633
+ },
634
+ {
635
+ "epoch": 1.8,
636
+ "learning_rate": 4.7224877277103673e-07,
637
+ "loss": 0.7854,
638
+ "step": 105
639
+ },
640
+ {
641
+ "epoch": 1.81,
642
+ "learning_rate": 3.908267805490051e-07,
643
+ "loss": 0.8004,
644
+ "step": 106
645
+ },
646
+ {
647
+ "epoch": 1.83,
648
+ "learning_rate": 3.1696477877738664e-07,
649
+ "loss": 0.7801,
650
+ "step": 107
651
+ },
652
+ {
653
+ "epoch": 1.85,
654
+ "learning_rate": 2.507208781817638e-07,
655
+ "loss": 0.7748,
656
+ "step": 108
657
+ },
658
+ {
659
+ "epoch": 1.87,
660
+ "learning_rate": 1.921471959676957e-07,
661
+ "loss": 0.8109,
662
+ "step": 109
663
+ },
664
+ {
665
+ "epoch": 1.88,
666
+ "learning_rate": 1.4128981481764115e-07,
667
+ "loss": 0.8023,
668
+ "step": 110
669
+ },
670
+ {
671
+ "epoch": 1.9,
672
+ "learning_rate": 9.818874663554356e-08,
673
+ "loss": 0.7938,
674
+ "step": 111
675
+ },
676
+ {
677
+ "epoch": 1.92,
678
+ "learning_rate": 6.287790106757396e-08,
679
+ "loss": 0.8001,
680
+ "step": 112
681
+ },
682
+ {
683
+ "epoch": 1.93,
684
+ "learning_rate": 3.538505882380916e-08,
685
+ "loss": 0.775,
686
+ "step": 113
687
+ },
688
+ {
689
+ "epoch": 1.95,
690
+ "learning_rate": 1.5731849821833955e-08,
691
+ "loss": 0.7893,
692
+ "step": 114
693
+ },
694
+ {
695
+ "epoch": 1.97,
696
+ "learning_rate": 3.933736169471347e-09,
697
+ "loss": 0.7897,
698
+ "step": 115
699
+ },
700
+ {
701
+ "epoch": 1.99,
702
+ "learning_rate": 0.0,
703
+ "loss": 0.7657,
704
+ "step": 116
705
+ },
706
+ {
707
+ "epoch": 1.99,
708
+ "step": 116,
709
+ "total_flos": 2.5137614882340864e+16,
710
+ "train_loss": 0.9649588188220715,
711
+ "train_runtime": 7099.8763,
712
+ "train_samples_per_second": 2.105,
713
+ "train_steps_per_second": 0.016
714
+ }
715
+ ],
716
+ "max_steps": 116,
717
+ "num_train_epochs": 2,
718
+ "total_flos": 2.5137614882340864e+16,
719
+ "trial_name": null,
720
+ "trial_params": null
721
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf488916bc3b87fd4e5e04dd2f130d8f70604593235d68f5fa2172f93292b393
3
+ size 4219