Xianjun commited on
Commit
8b2a546
1 Parent(s): cb8b52b

Upload 9 files

Browse files
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[PAD]": 32000
3
+ }
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/mnt/dsss_data/xianjun/project_data/material_llama2_7b",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "end_token_id": 2,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 11008,
13
+ "max_position_embeddings": 2048,
14
+ "model_type": "llama",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 32,
17
+ "num_key_value_heads": 32,
18
+ "pad_token_id": 2,
19
+ "pretraining_tp": 1,
20
+ "rms_norm_eps": 1e-05,
21
+ "rope_scaling": null,
22
+ "tie_word_embeddings": false,
23
+ "torch_dtype": "bfloat16",
24
+ "transformers_version": "4.28.1",
25
+ "use_cache": true,
26
+ "vocab_size": 32001
27
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 2,
6
+ "transformers_version": "4.28.1"
7
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69c4eba119e9f4d600232226a71bb3527816840f948610348172a0d726b2162c
3
+ size 13476958625
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": "[PAD]",
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 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "model_max_length": 1024,
22
+ "pad_token": null,
23
+ "padding_side": "right",
24
+ "sp_model_kwargs": {},
25
+ "tokenizer_class": "LlamaTokenizer",
26
+ "unk_token": {
27
+ "__type": "AddedToken",
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ }
34
+ }
trainer_state.json ADDED
@@ -0,0 +1,805 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 4.976076555023924,
5
+ "global_step": 130,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.04,
12
+ "learning_rate": 0.0,
13
+ "loss": 25.0234,
14
+ "step": 1
15
+ },
16
+ {
17
+ "epoch": 0.08,
18
+ "learning_rate": 5e-06,
19
+ "loss": 20.7754,
20
+ "step": 2
21
+ },
22
+ {
23
+ "epoch": 0.11,
24
+ "learning_rate": 7.924812503605782e-06,
25
+ "loss": 20.7559,
26
+ "step": 3
27
+ },
28
+ {
29
+ "epoch": 0.15,
30
+ "learning_rate": 1e-05,
31
+ "loss": 13.4424,
32
+ "step": 4
33
+ },
34
+ {
35
+ "epoch": 0.19,
36
+ "learning_rate": 1e-05,
37
+ "loss": 8.2891,
38
+ "step": 5
39
+ },
40
+ {
41
+ "epoch": 0.23,
42
+ "learning_rate": 9.920634920634922e-06,
43
+ "loss": 6.2437,
44
+ "step": 6
45
+ },
46
+ {
47
+ "epoch": 0.27,
48
+ "learning_rate": 9.841269841269842e-06,
49
+ "loss": 2.3472,
50
+ "step": 7
51
+ },
52
+ {
53
+ "epoch": 0.31,
54
+ "learning_rate": 9.761904761904762e-06,
55
+ "loss": 1.9103,
56
+ "step": 8
57
+ },
58
+ {
59
+ "epoch": 0.34,
60
+ "learning_rate": 9.682539682539683e-06,
61
+ "loss": 1.5619,
62
+ "step": 9
63
+ },
64
+ {
65
+ "epoch": 0.38,
66
+ "learning_rate": 9.603174603174605e-06,
67
+ "loss": 1.3292,
68
+ "step": 10
69
+ },
70
+ {
71
+ "epoch": 0.42,
72
+ "learning_rate": 9.523809523809525e-06,
73
+ "loss": 1.3256,
74
+ "step": 11
75
+ },
76
+ {
77
+ "epoch": 0.46,
78
+ "learning_rate": 9.444444444444445e-06,
79
+ "loss": 0.902,
80
+ "step": 12
81
+ },
82
+ {
83
+ "epoch": 0.5,
84
+ "learning_rate": 9.365079365079366e-06,
85
+ "loss": 1.163,
86
+ "step": 13
87
+ },
88
+ {
89
+ "epoch": 0.54,
90
+ "learning_rate": 9.285714285714288e-06,
91
+ "loss": 1.0538,
92
+ "step": 14
93
+ },
94
+ {
95
+ "epoch": 0.57,
96
+ "learning_rate": 9.206349206349207e-06,
97
+ "loss": 0.944,
98
+ "step": 15
99
+ },
100
+ {
101
+ "epoch": 0.61,
102
+ "learning_rate": 9.126984126984127e-06,
103
+ "loss": 0.8447,
104
+ "step": 16
105
+ },
106
+ {
107
+ "epoch": 0.65,
108
+ "learning_rate": 9.047619047619049e-06,
109
+ "loss": 1.1726,
110
+ "step": 17
111
+ },
112
+ {
113
+ "epoch": 0.69,
114
+ "learning_rate": 8.968253968253968e-06,
115
+ "loss": 1.138,
116
+ "step": 18
117
+ },
118
+ {
119
+ "epoch": 0.73,
120
+ "learning_rate": 8.888888888888888e-06,
121
+ "loss": 1.1524,
122
+ "step": 19
123
+ },
124
+ {
125
+ "epoch": 0.77,
126
+ "learning_rate": 8.80952380952381e-06,
127
+ "loss": 1.026,
128
+ "step": 20
129
+ },
130
+ {
131
+ "epoch": 0.8,
132
+ "learning_rate": 8.730158730158731e-06,
133
+ "loss": 1.0569,
134
+ "step": 21
135
+ },
136
+ {
137
+ "epoch": 0.84,
138
+ "learning_rate": 8.650793650793651e-06,
139
+ "loss": 0.9084,
140
+ "step": 22
141
+ },
142
+ {
143
+ "epoch": 0.88,
144
+ "learning_rate": 8.571428571428571e-06,
145
+ "loss": 0.8767,
146
+ "step": 23
147
+ },
148
+ {
149
+ "epoch": 0.92,
150
+ "learning_rate": 8.492063492063492e-06,
151
+ "loss": 1.101,
152
+ "step": 24
153
+ },
154
+ {
155
+ "epoch": 0.96,
156
+ "learning_rate": 8.412698412698414e-06,
157
+ "loss": 1.0402,
158
+ "step": 25
159
+ },
160
+ {
161
+ "epoch": 1.0,
162
+ "learning_rate": 8.333333333333334e-06,
163
+ "loss": 0.8947,
164
+ "step": 26
165
+ },
166
+ {
167
+ "epoch": 1.03,
168
+ "learning_rate": 8.253968253968254e-06,
169
+ "loss": 0.8985,
170
+ "step": 27
171
+ },
172
+ {
173
+ "epoch": 1.07,
174
+ "learning_rate": 8.174603174603175e-06,
175
+ "loss": 0.8772,
176
+ "step": 28
177
+ },
178
+ {
179
+ "epoch": 1.11,
180
+ "learning_rate": 8.095238095238097e-06,
181
+ "loss": 0.9256,
182
+ "step": 29
183
+ },
184
+ {
185
+ "epoch": 1.15,
186
+ "learning_rate": 8.015873015873016e-06,
187
+ "loss": 0.9597,
188
+ "step": 30
189
+ },
190
+ {
191
+ "epoch": 1.19,
192
+ "learning_rate": 7.936507936507936e-06,
193
+ "loss": 0.9373,
194
+ "step": 31
195
+ },
196
+ {
197
+ "epoch": 1.22,
198
+ "learning_rate": 7.857142857142858e-06,
199
+ "loss": 0.8894,
200
+ "step": 32
201
+ },
202
+ {
203
+ "epoch": 1.26,
204
+ "learning_rate": 7.77777777777778e-06,
205
+ "loss": 0.8194,
206
+ "step": 33
207
+ },
208
+ {
209
+ "epoch": 1.3,
210
+ "learning_rate": 7.698412698412699e-06,
211
+ "loss": 0.9131,
212
+ "step": 34
213
+ },
214
+ {
215
+ "epoch": 1.34,
216
+ "learning_rate": 7.61904761904762e-06,
217
+ "loss": 0.9411,
218
+ "step": 35
219
+ },
220
+ {
221
+ "epoch": 1.38,
222
+ "learning_rate": 7.53968253968254e-06,
223
+ "loss": 0.8598,
224
+ "step": 36
225
+ },
226
+ {
227
+ "epoch": 1.42,
228
+ "learning_rate": 7.460317460317461e-06,
229
+ "loss": 0.959,
230
+ "step": 37
231
+ },
232
+ {
233
+ "epoch": 1.45,
234
+ "learning_rate": 7.380952380952382e-06,
235
+ "loss": 0.8196,
236
+ "step": 38
237
+ },
238
+ {
239
+ "epoch": 1.49,
240
+ "learning_rate": 7.301587301587301e-06,
241
+ "loss": 1.0758,
242
+ "step": 39
243
+ },
244
+ {
245
+ "epoch": 1.53,
246
+ "learning_rate": 7.222222222222223e-06,
247
+ "loss": 0.822,
248
+ "step": 40
249
+ },
250
+ {
251
+ "epoch": 1.57,
252
+ "learning_rate": 7.1428571428571436e-06,
253
+ "loss": 0.889,
254
+ "step": 41
255
+ },
256
+ {
257
+ "epoch": 1.61,
258
+ "learning_rate": 7.063492063492064e-06,
259
+ "loss": 0.8716,
260
+ "step": 42
261
+ },
262
+ {
263
+ "epoch": 1.65,
264
+ "learning_rate": 6.984126984126984e-06,
265
+ "loss": 0.8108,
266
+ "step": 43
267
+ },
268
+ {
269
+ "epoch": 1.68,
270
+ "learning_rate": 6.9047619047619055e-06,
271
+ "loss": 0.7736,
272
+ "step": 44
273
+ },
274
+ {
275
+ "epoch": 1.72,
276
+ "learning_rate": 6.825396825396826e-06,
277
+ "loss": 0.7957,
278
+ "step": 45
279
+ },
280
+ {
281
+ "epoch": 1.76,
282
+ "learning_rate": 6.746031746031747e-06,
283
+ "loss": 0.6562,
284
+ "step": 46
285
+ },
286
+ {
287
+ "epoch": 1.8,
288
+ "learning_rate": 6.666666666666667e-06,
289
+ "loss": 0.9037,
290
+ "step": 47
291
+ },
292
+ {
293
+ "epoch": 1.84,
294
+ "learning_rate": 6.587301587301588e-06,
295
+ "loss": 0.7161,
296
+ "step": 48
297
+ },
298
+ {
299
+ "epoch": 1.88,
300
+ "learning_rate": 6.507936507936509e-06,
301
+ "loss": 0.8124,
302
+ "step": 49
303
+ },
304
+ {
305
+ "epoch": 1.91,
306
+ "learning_rate": 6.4285714285714295e-06,
307
+ "loss": 0.8216,
308
+ "step": 50
309
+ },
310
+ {
311
+ "epoch": 1.95,
312
+ "learning_rate": 6.349206349206349e-06,
313
+ "loss": 0.8413,
314
+ "step": 51
315
+ },
316
+ {
317
+ "epoch": 1.99,
318
+ "learning_rate": 6.26984126984127e-06,
319
+ "loss": 0.8208,
320
+ "step": 52
321
+ },
322
+ {
323
+ "epoch": 2.03,
324
+ "learning_rate": 6.1904761904761914e-06,
325
+ "loss": 0.673,
326
+ "step": 53
327
+ },
328
+ {
329
+ "epoch": 2.07,
330
+ "learning_rate": 6.111111111111112e-06,
331
+ "loss": 0.7171,
332
+ "step": 54
333
+ },
334
+ {
335
+ "epoch": 2.11,
336
+ "learning_rate": 6.031746031746032e-06,
337
+ "loss": 0.6513,
338
+ "step": 55
339
+ },
340
+ {
341
+ "epoch": 2.14,
342
+ "learning_rate": 5.9523809523809525e-06,
343
+ "loss": 0.6463,
344
+ "step": 56
345
+ },
346
+ {
347
+ "epoch": 2.18,
348
+ "learning_rate": 5.873015873015874e-06,
349
+ "loss": 0.6753,
350
+ "step": 57
351
+ },
352
+ {
353
+ "epoch": 2.22,
354
+ "learning_rate": 5.793650793650795e-06,
355
+ "loss": 0.8448,
356
+ "step": 58
357
+ },
358
+ {
359
+ "epoch": 2.26,
360
+ "learning_rate": 5.7142857142857145e-06,
361
+ "loss": 0.7941,
362
+ "step": 59
363
+ },
364
+ {
365
+ "epoch": 2.3,
366
+ "learning_rate": 5.634920634920635e-06,
367
+ "loss": 0.7198,
368
+ "step": 60
369
+ },
370
+ {
371
+ "epoch": 2.33,
372
+ "learning_rate": 5.555555555555557e-06,
373
+ "loss": 0.6262,
374
+ "step": 61
375
+ },
376
+ {
377
+ "epoch": 2.37,
378
+ "learning_rate": 5.476190476190477e-06,
379
+ "loss": 0.7605,
380
+ "step": 62
381
+ },
382
+ {
383
+ "epoch": 2.41,
384
+ "learning_rate": 5.396825396825397e-06,
385
+ "loss": 0.6028,
386
+ "step": 63
387
+ },
388
+ {
389
+ "epoch": 2.45,
390
+ "learning_rate": 5.317460317460318e-06,
391
+ "loss": 0.4278,
392
+ "step": 64
393
+ },
394
+ {
395
+ "epoch": 2.49,
396
+ "learning_rate": 5.2380952380952384e-06,
397
+ "loss": 0.6504,
398
+ "step": 65
399
+ },
400
+ {
401
+ "epoch": 2.53,
402
+ "learning_rate": 5.15873015873016e-06,
403
+ "loss": 0.7392,
404
+ "step": 66
405
+ },
406
+ {
407
+ "epoch": 2.56,
408
+ "learning_rate": 5.07936507936508e-06,
409
+ "loss": 0.5725,
410
+ "step": 67
411
+ },
412
+ {
413
+ "epoch": 2.6,
414
+ "learning_rate": 5e-06,
415
+ "loss": 0.6088,
416
+ "step": 68
417
+ },
418
+ {
419
+ "epoch": 2.64,
420
+ "learning_rate": 4.920634920634921e-06,
421
+ "loss": 0.6365,
422
+ "step": 69
423
+ },
424
+ {
425
+ "epoch": 2.68,
426
+ "learning_rate": 4.841269841269842e-06,
427
+ "loss": 0.6722,
428
+ "step": 70
429
+ },
430
+ {
431
+ "epoch": 2.72,
432
+ "learning_rate": 4.761904761904762e-06,
433
+ "loss": 0.8014,
434
+ "step": 71
435
+ },
436
+ {
437
+ "epoch": 2.76,
438
+ "learning_rate": 4.682539682539683e-06,
439
+ "loss": 0.6103,
440
+ "step": 72
441
+ },
442
+ {
443
+ "epoch": 2.79,
444
+ "learning_rate": 4.603174603174604e-06,
445
+ "loss": 0.8294,
446
+ "step": 73
447
+ },
448
+ {
449
+ "epoch": 2.83,
450
+ "learning_rate": 4.523809523809524e-06,
451
+ "loss": 0.6915,
452
+ "step": 74
453
+ },
454
+ {
455
+ "epoch": 2.87,
456
+ "learning_rate": 4.444444444444444e-06,
457
+ "loss": 0.6409,
458
+ "step": 75
459
+ },
460
+ {
461
+ "epoch": 2.91,
462
+ "learning_rate": 4.365079365079366e-06,
463
+ "loss": 0.8038,
464
+ "step": 76
465
+ },
466
+ {
467
+ "epoch": 2.95,
468
+ "learning_rate": 4.2857142857142855e-06,
469
+ "loss": 0.7051,
470
+ "step": 77
471
+ },
472
+ {
473
+ "epoch": 2.99,
474
+ "learning_rate": 4.206349206349207e-06,
475
+ "loss": 0.6997,
476
+ "step": 78
477
+ },
478
+ {
479
+ "epoch": 3.02,
480
+ "learning_rate": 4.126984126984127e-06,
481
+ "loss": 0.3337,
482
+ "step": 79
483
+ },
484
+ {
485
+ "epoch": 3.06,
486
+ "learning_rate": 4.047619047619048e-06,
487
+ "loss": 0.6256,
488
+ "step": 80
489
+ },
490
+ {
491
+ "epoch": 3.1,
492
+ "learning_rate": 3.968253968253968e-06,
493
+ "loss": 0.4855,
494
+ "step": 81
495
+ },
496
+ {
497
+ "epoch": 3.14,
498
+ "learning_rate": 3.88888888888889e-06,
499
+ "loss": 0.6082,
500
+ "step": 82
501
+ },
502
+ {
503
+ "epoch": 3.18,
504
+ "learning_rate": 3.80952380952381e-06,
505
+ "loss": 0.6208,
506
+ "step": 83
507
+ },
508
+ {
509
+ "epoch": 3.22,
510
+ "learning_rate": 3.7301587301587305e-06,
511
+ "loss": 0.4755,
512
+ "step": 84
513
+ },
514
+ {
515
+ "epoch": 3.25,
516
+ "learning_rate": 3.6507936507936507e-06,
517
+ "loss": 0.4758,
518
+ "step": 85
519
+ },
520
+ {
521
+ "epoch": 3.29,
522
+ "learning_rate": 3.5714285714285718e-06,
523
+ "loss": 0.4895,
524
+ "step": 86
525
+ },
526
+ {
527
+ "epoch": 3.33,
528
+ "learning_rate": 3.492063492063492e-06,
529
+ "loss": 0.5123,
530
+ "step": 87
531
+ },
532
+ {
533
+ "epoch": 3.37,
534
+ "learning_rate": 3.412698412698413e-06,
535
+ "loss": 0.5344,
536
+ "step": 88
537
+ },
538
+ {
539
+ "epoch": 3.41,
540
+ "learning_rate": 3.3333333333333333e-06,
541
+ "loss": 0.5446,
542
+ "step": 89
543
+ },
544
+ {
545
+ "epoch": 3.44,
546
+ "learning_rate": 3.2539682539682544e-06,
547
+ "loss": 0.5323,
548
+ "step": 90
549
+ },
550
+ {
551
+ "epoch": 3.48,
552
+ "learning_rate": 3.1746031746031746e-06,
553
+ "loss": 0.5662,
554
+ "step": 91
555
+ },
556
+ {
557
+ "epoch": 3.52,
558
+ "learning_rate": 3.0952380952380957e-06,
559
+ "loss": 0.5845,
560
+ "step": 92
561
+ },
562
+ {
563
+ "epoch": 3.56,
564
+ "learning_rate": 3.015873015873016e-06,
565
+ "loss": 0.5142,
566
+ "step": 93
567
+ },
568
+ {
569
+ "epoch": 3.6,
570
+ "learning_rate": 2.936507936507937e-06,
571
+ "loss": 0.5691,
572
+ "step": 94
573
+ },
574
+ {
575
+ "epoch": 3.64,
576
+ "learning_rate": 2.8571428571428573e-06,
577
+ "loss": 0.5474,
578
+ "step": 95
579
+ },
580
+ {
581
+ "epoch": 3.67,
582
+ "learning_rate": 2.7777777777777783e-06,
583
+ "loss": 0.7691,
584
+ "step": 96
585
+ },
586
+ {
587
+ "epoch": 3.71,
588
+ "learning_rate": 2.6984126984126986e-06,
589
+ "loss": 0.5452,
590
+ "step": 97
591
+ },
592
+ {
593
+ "epoch": 3.75,
594
+ "learning_rate": 2.6190476190476192e-06,
595
+ "loss": 0.5924,
596
+ "step": 98
597
+ },
598
+ {
599
+ "epoch": 3.79,
600
+ "learning_rate": 2.53968253968254e-06,
601
+ "loss": 0.5127,
602
+ "step": 99
603
+ },
604
+ {
605
+ "epoch": 3.83,
606
+ "learning_rate": 2.4603174603174605e-06,
607
+ "loss": 0.4649,
608
+ "step": 100
609
+ },
610
+ {
611
+ "epoch": 3.87,
612
+ "learning_rate": 2.380952380952381e-06,
613
+ "loss": 0.524,
614
+ "step": 101
615
+ },
616
+ {
617
+ "epoch": 3.9,
618
+ "learning_rate": 2.301587301587302e-06,
619
+ "loss": 0.6315,
620
+ "step": 102
621
+ },
622
+ {
623
+ "epoch": 3.94,
624
+ "learning_rate": 2.222222222222222e-06,
625
+ "loss": 0.6544,
626
+ "step": 103
627
+ },
628
+ {
629
+ "epoch": 3.98,
630
+ "learning_rate": 2.1428571428571427e-06,
631
+ "loss": 0.6733,
632
+ "step": 104
633
+ },
634
+ {
635
+ "epoch": 4.02,
636
+ "learning_rate": 2.0634920634920634e-06,
637
+ "loss": 0.6155,
638
+ "step": 105
639
+ },
640
+ {
641
+ "epoch": 4.06,
642
+ "learning_rate": 1.984126984126984e-06,
643
+ "loss": 0.504,
644
+ "step": 106
645
+ },
646
+ {
647
+ "epoch": 4.1,
648
+ "learning_rate": 1.904761904761905e-06,
649
+ "loss": 0.4849,
650
+ "step": 107
651
+ },
652
+ {
653
+ "epoch": 4.13,
654
+ "learning_rate": 1.8253968253968254e-06,
655
+ "loss": 0.465,
656
+ "step": 108
657
+ },
658
+ {
659
+ "epoch": 4.17,
660
+ "learning_rate": 1.746031746031746e-06,
661
+ "loss": 0.4481,
662
+ "step": 109
663
+ },
664
+ {
665
+ "epoch": 4.21,
666
+ "learning_rate": 1.6666666666666667e-06,
667
+ "loss": 0.6087,
668
+ "step": 110
669
+ },
670
+ {
671
+ "epoch": 4.25,
672
+ "learning_rate": 1.5873015873015873e-06,
673
+ "loss": 0.4352,
674
+ "step": 111
675
+ },
676
+ {
677
+ "epoch": 4.29,
678
+ "learning_rate": 1.507936507936508e-06,
679
+ "loss": 0.4346,
680
+ "step": 112
681
+ },
682
+ {
683
+ "epoch": 4.33,
684
+ "learning_rate": 1.4285714285714286e-06,
685
+ "loss": 0.57,
686
+ "step": 113
687
+ },
688
+ {
689
+ "epoch": 4.36,
690
+ "learning_rate": 1.3492063492063493e-06,
691
+ "loss": 0.4804,
692
+ "step": 114
693
+ },
694
+ {
695
+ "epoch": 4.4,
696
+ "learning_rate": 1.26984126984127e-06,
697
+ "loss": 0.5602,
698
+ "step": 115
699
+ },
700
+ {
701
+ "epoch": 4.44,
702
+ "learning_rate": 1.1904761904761906e-06,
703
+ "loss": 0.5102,
704
+ "step": 116
705
+ },
706
+ {
707
+ "epoch": 4.48,
708
+ "learning_rate": 1.111111111111111e-06,
709
+ "loss": 0.3693,
710
+ "step": 117
711
+ },
712
+ {
713
+ "epoch": 4.52,
714
+ "learning_rate": 1.0317460317460317e-06,
715
+ "loss": 0.5274,
716
+ "step": 118
717
+ },
718
+ {
719
+ "epoch": 4.56,
720
+ "learning_rate": 9.523809523809525e-07,
721
+ "loss": 0.4763,
722
+ "step": 119
723
+ },
724
+ {
725
+ "epoch": 4.59,
726
+ "learning_rate": 8.73015873015873e-07,
727
+ "loss": 0.5746,
728
+ "step": 120
729
+ },
730
+ {
731
+ "epoch": 4.63,
732
+ "learning_rate": 7.936507936507937e-07,
733
+ "loss": 0.4454,
734
+ "step": 121
735
+ },
736
+ {
737
+ "epoch": 4.67,
738
+ "learning_rate": 7.142857142857143e-07,
739
+ "loss": 0.3733,
740
+ "step": 122
741
+ },
742
+ {
743
+ "epoch": 4.71,
744
+ "learning_rate": 6.34920634920635e-07,
745
+ "loss": 0.5295,
746
+ "step": 123
747
+ },
748
+ {
749
+ "epoch": 4.75,
750
+ "learning_rate": 5.555555555555555e-07,
751
+ "loss": 0.4557,
752
+ "step": 124
753
+ },
754
+ {
755
+ "epoch": 4.78,
756
+ "learning_rate": 4.7619047619047623e-07,
757
+ "loss": 0.3931,
758
+ "step": 125
759
+ },
760
+ {
761
+ "epoch": 4.82,
762
+ "learning_rate": 3.9682539682539683e-07,
763
+ "loss": 0.4848,
764
+ "step": 126
765
+ },
766
+ {
767
+ "epoch": 4.86,
768
+ "learning_rate": 3.174603174603175e-07,
769
+ "loss": 0.5132,
770
+ "step": 127
771
+ },
772
+ {
773
+ "epoch": 4.9,
774
+ "learning_rate": 2.3809523809523811e-07,
775
+ "loss": 0.3818,
776
+ "step": 128
777
+ },
778
+ {
779
+ "epoch": 4.94,
780
+ "learning_rate": 1.5873015873015874e-07,
781
+ "loss": 0.5238,
782
+ "step": 129
783
+ },
784
+ {
785
+ "epoch": 4.98,
786
+ "learning_rate": 7.936507936507937e-08,
787
+ "loss": 0.5189,
788
+ "step": 130
789
+ },
790
+ {
791
+ "epoch": 4.98,
792
+ "step": 130,
793
+ "total_flos": 13498620395520.0,
794
+ "train_loss": 1.4273854613304138,
795
+ "train_runtime": 4877.3379,
796
+ "train_samples_per_second": 3.428,
797
+ "train_steps_per_second": 0.027
798
+ }
799
+ ],
800
+ "max_steps": 130,
801
+ "num_train_epochs": 5,
802
+ "total_flos": 13498620395520.0,
803
+ "trial_name": null,
804
+ "trial_params": null
805
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb7728218f093cdb1ff1032293384ae7edefcad15950f4b72b6c75fc8a3012b5
3
+ size 4923