zlsl commited on
Commit
616fda1
1 Parent(s): 78fc8e3

Upload 13 files

Browse files
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<|endoftext|>": 50257
3
+ }
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "train_loss": 0.690881545154761,
4
+ "train_runtime": 7737.0233,
5
+ "train_samples": 5640,
6
+ "train_samples_per_second": 2.187,
7
+ "train_steps_per_second": 0.182
8
+ }
config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/zstorage/AI/text-generation-webui/models/rugpt3medium_based_on_gpt2",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "id2label": {
12
+ "0": "LABEL_0"
13
+ },
14
+ "initializer_range": 0.02,
15
+ "label2id": {
16
+ "LABEL_0": 0
17
+ },
18
+ "layer_norm_epsilon": 1e-05,
19
+ "model_type": "gpt2",
20
+ "n_ctx": 2048,
21
+ "n_embd": 1024,
22
+ "n_head": 16,
23
+ "n_inner": null,
24
+ "n_layer": 24,
25
+ "n_positions": 2048,
26
+ "n_special": 0,
27
+ "output_past": true,
28
+ "predict_special_tokens": true,
29
+ "reorder_and_upcast_attn": false,
30
+ "resid_pdrop": 0.1,
31
+ "scale_attn_by_inverse_layer_idx": false,
32
+ "scale_attn_weights": true,
33
+ "summary_activation": null,
34
+ "summary_first_dropout": 0.1,
35
+ "summary_proj_to_labels": true,
36
+ "summary_type": "cls_index",
37
+ "summary_use_proj": true,
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.30.0.dev0",
40
+ "use_cache": true,
41
+ "vocab_size": 50258
42
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.30.0.dev0"
6
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd56e98379847dd1a214fe6a85807a9bd71d26fac9176d7317a2e62400cd916d
3
+ size 1423521280
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "clean_up_tokenization_spaces": true,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "<|endoftext|>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "errors": "replace",
22
+ "model_max_length": 1000000000000000019884624838656,
23
+ "pad_token": null,
24
+ "tokenizer_class": "GPT2Tokenizer",
25
+ "unk_token": {
26
+ "__type": "AddedToken",
27
+ "content": "<|endoftext|>",
28
+ "lstrip": false,
29
+ "normalized": true,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "train_loss": 0.690881545154761,
4
+ "train_runtime": 7737.0233,
5
+ "train_samples": 5640,
6
+ "train_samples_per_second": 2.187,
7
+ "train_steps_per_second": 0.182
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,877 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "global_step": 1410,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.0,
12
+ "learning_rate": 5.000000000000001e-07,
13
+ "loss": 2.9541,
14
+ "step": 1
15
+ },
16
+ {
17
+ "epoch": 0.02,
18
+ "learning_rate": 5e-06,
19
+ "loss": 2.9089,
20
+ "step": 10
21
+ },
22
+ {
23
+ "epoch": 0.04,
24
+ "learning_rate": 1e-05,
25
+ "loss": 2.9232,
26
+ "step": 20
27
+ },
28
+ {
29
+ "epoch": 0.06,
30
+ "learning_rate": 1.5e-05,
31
+ "loss": 2.914,
32
+ "step": 30
33
+ },
34
+ {
35
+ "epoch": 0.09,
36
+ "learning_rate": 2e-05,
37
+ "loss": 2.9596,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.11,
42
+ "learning_rate": 2.5e-05,
43
+ "loss": 2.9106,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.13,
48
+ "learning_rate": 3e-05,
49
+ "loss": 2.8611,
50
+ "step": 60
51
+ },
52
+ {
53
+ "epoch": 0.15,
54
+ "learning_rate": 3.5e-05,
55
+ "loss": 2.926,
56
+ "step": 70
57
+ },
58
+ {
59
+ "epoch": 0.17,
60
+ "learning_rate": 4e-05,
61
+ "loss": 2.8827,
62
+ "step": 80
63
+ },
64
+ {
65
+ "epoch": 0.19,
66
+ "learning_rate": 4.5e-05,
67
+ "loss": 2.8972,
68
+ "step": 90
69
+ },
70
+ {
71
+ "epoch": 0.21,
72
+ "learning_rate": 5e-05,
73
+ "loss": 2.9258,
74
+ "step": 100
75
+ },
76
+ {
77
+ "epoch": 0.23,
78
+ "learning_rate": 4.9618320610687025e-05,
79
+ "loss": 2.9555,
80
+ "step": 110
81
+ },
82
+ {
83
+ "epoch": 0.26,
84
+ "learning_rate": 4.923664122137405e-05,
85
+ "loss": 2.93,
86
+ "step": 120
87
+ },
88
+ {
89
+ "epoch": 0.28,
90
+ "learning_rate": 4.885496183206107e-05,
91
+ "loss": 2.936,
92
+ "step": 130
93
+ },
94
+ {
95
+ "epoch": 0.3,
96
+ "learning_rate": 4.847328244274809e-05,
97
+ "loss": 2.8927,
98
+ "step": 140
99
+ },
100
+ {
101
+ "epoch": 0.32,
102
+ "learning_rate": 4.809160305343512e-05,
103
+ "loss": 2.8796,
104
+ "step": 150
105
+ },
106
+ {
107
+ "epoch": 0.34,
108
+ "learning_rate": 4.7709923664122144e-05,
109
+ "loss": 2.9172,
110
+ "step": 160
111
+ },
112
+ {
113
+ "epoch": 0.36,
114
+ "learning_rate": 4.7328244274809166e-05,
115
+ "loss": 2.8782,
116
+ "step": 170
117
+ },
118
+ {
119
+ "epoch": 0.38,
120
+ "learning_rate": 4.694656488549619e-05,
121
+ "loss": 2.8833,
122
+ "step": 180
123
+ },
124
+ {
125
+ "epoch": 0.4,
126
+ "learning_rate": 4.656488549618321e-05,
127
+ "loss": 2.8822,
128
+ "step": 190
129
+ },
130
+ {
131
+ "epoch": 0.43,
132
+ "learning_rate": 4.618320610687023e-05,
133
+ "loss": 2.8877,
134
+ "step": 200
135
+ },
136
+ {
137
+ "epoch": 0.45,
138
+ "learning_rate": 4.5801526717557256e-05,
139
+ "loss": 2.8287,
140
+ "step": 210
141
+ },
142
+ {
143
+ "epoch": 0.47,
144
+ "learning_rate": 4.541984732824428e-05,
145
+ "loss": 2.8852,
146
+ "step": 220
147
+ },
148
+ {
149
+ "epoch": 0.49,
150
+ "learning_rate": 4.5038167938931294e-05,
151
+ "loss": 2.8694,
152
+ "step": 230
153
+ },
154
+ {
155
+ "epoch": 0.51,
156
+ "learning_rate": 4.465648854961832e-05,
157
+ "loss": 2.8847,
158
+ "step": 240
159
+ },
160
+ {
161
+ "epoch": 0.53,
162
+ "learning_rate": 4.4274809160305345e-05,
163
+ "loss": 2.889,
164
+ "step": 250
165
+ },
166
+ {
167
+ "epoch": 0.55,
168
+ "learning_rate": 4.389312977099237e-05,
169
+ "loss": 2.8866,
170
+ "step": 260
171
+ },
172
+ {
173
+ "epoch": 0.57,
174
+ "learning_rate": 4.351145038167939e-05,
175
+ "loss": 2.8523,
176
+ "step": 270
177
+ },
178
+ {
179
+ "epoch": 0.6,
180
+ "learning_rate": 4.312977099236641e-05,
181
+ "loss": 2.8664,
182
+ "step": 280
183
+ },
184
+ {
185
+ "epoch": 0.62,
186
+ "learning_rate": 4.2748091603053435e-05,
187
+ "loss": 2.8683,
188
+ "step": 290
189
+ },
190
+ {
191
+ "epoch": 0.64,
192
+ "learning_rate": 4.236641221374046e-05,
193
+ "loss": 2.8312,
194
+ "step": 300
195
+ },
196
+ {
197
+ "epoch": 0.66,
198
+ "learning_rate": 4.198473282442748e-05,
199
+ "loss": 2.8776,
200
+ "step": 310
201
+ },
202
+ {
203
+ "epoch": 0.68,
204
+ "learning_rate": 4.160305343511451e-05,
205
+ "loss": 2.8447,
206
+ "step": 320
207
+ },
208
+ {
209
+ "epoch": 0.7,
210
+ "learning_rate": 4.122137404580153e-05,
211
+ "loss": 2.8987,
212
+ "step": 330
213
+ },
214
+ {
215
+ "epoch": 0.72,
216
+ "learning_rate": 4.0839694656488554e-05,
217
+ "loss": 2.8599,
218
+ "step": 340
219
+ },
220
+ {
221
+ "epoch": 0.74,
222
+ "learning_rate": 4.0458015267175576e-05,
223
+ "loss": 2.8863,
224
+ "step": 350
225
+ },
226
+ {
227
+ "epoch": 0.77,
228
+ "learning_rate": 4.00763358778626e-05,
229
+ "loss": 2.8449,
230
+ "step": 360
231
+ },
232
+ {
233
+ "epoch": 0.79,
234
+ "learning_rate": 3.969465648854962e-05,
235
+ "loss": 2.8262,
236
+ "step": 370
237
+ },
238
+ {
239
+ "epoch": 0.81,
240
+ "learning_rate": 3.9312977099236644e-05,
241
+ "loss": 2.9043,
242
+ "step": 380
243
+ },
244
+ {
245
+ "epoch": 0.83,
246
+ "learning_rate": 3.8931297709923666e-05,
247
+ "loss": 2.8667,
248
+ "step": 390
249
+ },
250
+ {
251
+ "epoch": 0.85,
252
+ "learning_rate": 3.854961832061069e-05,
253
+ "loss": 2.8355,
254
+ "step": 400
255
+ },
256
+ {
257
+ "epoch": 0.87,
258
+ "learning_rate": 3.816793893129771e-05,
259
+ "loss": 2.8561,
260
+ "step": 410
261
+ },
262
+ {
263
+ "epoch": 0.89,
264
+ "learning_rate": 3.778625954198473e-05,
265
+ "loss": 2.8035,
266
+ "step": 420
267
+ },
268
+ {
269
+ "epoch": 0.91,
270
+ "learning_rate": 3.7404580152671756e-05,
271
+ "loss": 2.8799,
272
+ "step": 430
273
+ },
274
+ {
275
+ "epoch": 0.94,
276
+ "learning_rate": 3.702290076335878e-05,
277
+ "loss": 2.8353,
278
+ "step": 440
279
+ },
280
+ {
281
+ "epoch": 0.96,
282
+ "learning_rate": 3.66412213740458e-05,
283
+ "loss": 2.8205,
284
+ "step": 450
285
+ },
286
+ {
287
+ "epoch": 0.98,
288
+ "learning_rate": 3.625954198473282e-05,
289
+ "loss": 2.8467,
290
+ "step": 460
291
+ },
292
+ {
293
+ "epoch": 1.0,
294
+ "learning_rate": 3.5877862595419845e-05,
295
+ "loss": 2.8587,
296
+ "step": 470
297
+ },
298
+ {
299
+ "epoch": 1.02,
300
+ "learning_rate": 3.549618320610687e-05,
301
+ "loss": 2.7819,
302
+ "step": 480
303
+ },
304
+ {
305
+ "epoch": 1.04,
306
+ "learning_rate": 3.511450381679389e-05,
307
+ "loss": 2.7764,
308
+ "step": 490
309
+ },
310
+ {
311
+ "epoch": 1.06,
312
+ "learning_rate": 3.473282442748092e-05,
313
+ "loss": 2.7744,
314
+ "step": 500
315
+ },
316
+ {
317
+ "epoch": 1.09,
318
+ "learning_rate": 3.435114503816794e-05,
319
+ "loss": 2.7788,
320
+ "step": 510
321
+ },
322
+ {
323
+ "epoch": 1.11,
324
+ "learning_rate": 3.3969465648854964e-05,
325
+ "loss": 2.7927,
326
+ "step": 520
327
+ },
328
+ {
329
+ "epoch": 1.13,
330
+ "learning_rate": 3.358778625954199e-05,
331
+ "loss": 2.7939,
332
+ "step": 530
333
+ },
334
+ {
335
+ "epoch": 1.15,
336
+ "learning_rate": 3.320610687022901e-05,
337
+ "loss": 2.7556,
338
+ "step": 540
339
+ },
340
+ {
341
+ "epoch": 1.17,
342
+ "learning_rate": 3.282442748091603e-05,
343
+ "loss": 2.7721,
344
+ "step": 550
345
+ },
346
+ {
347
+ "epoch": 1.19,
348
+ "learning_rate": 3.2442748091603054e-05,
349
+ "loss": 2.766,
350
+ "step": 560
351
+ },
352
+ {
353
+ "epoch": 1.21,
354
+ "learning_rate": 3.2061068702290076e-05,
355
+ "loss": 2.8024,
356
+ "step": 570
357
+ },
358
+ {
359
+ "epoch": 1.23,
360
+ "learning_rate": 3.16793893129771e-05,
361
+ "loss": 2.8031,
362
+ "step": 580
363
+ },
364
+ {
365
+ "epoch": 1.26,
366
+ "learning_rate": 3.129770992366413e-05,
367
+ "loss": 2.7328,
368
+ "step": 590
369
+ },
370
+ {
371
+ "epoch": 1.28,
372
+ "learning_rate": 3.091603053435115e-05,
373
+ "loss": 2.7363,
374
+ "step": 600
375
+ },
376
+ {
377
+ "epoch": 1.3,
378
+ "learning_rate": 3.053435114503817e-05,
379
+ "loss": 2.7882,
380
+ "step": 610
381
+ },
382
+ {
383
+ "epoch": 1.32,
384
+ "learning_rate": 3.0152671755725192e-05,
385
+ "loss": 2.8019,
386
+ "step": 620
387
+ },
388
+ {
389
+ "epoch": 1.34,
390
+ "learning_rate": 2.9770992366412214e-05,
391
+ "loss": 2.79,
392
+ "step": 630
393
+ },
394
+ {
395
+ "epoch": 1.36,
396
+ "learning_rate": 2.9389312977099237e-05,
397
+ "loss": 2.7596,
398
+ "step": 640
399
+ },
400
+ {
401
+ "epoch": 1.38,
402
+ "learning_rate": 2.900763358778626e-05,
403
+ "loss": 2.775,
404
+ "step": 650
405
+ },
406
+ {
407
+ "epoch": 1.4,
408
+ "learning_rate": 2.862595419847328e-05,
409
+ "loss": 2.7885,
410
+ "step": 660
411
+ },
412
+ {
413
+ "epoch": 1.43,
414
+ "learning_rate": 2.824427480916031e-05,
415
+ "loss": 2.776,
416
+ "step": 670
417
+ },
418
+ {
419
+ "epoch": 1.45,
420
+ "learning_rate": 2.7862595419847333e-05,
421
+ "loss": 2.7456,
422
+ "step": 680
423
+ },
424
+ {
425
+ "epoch": 1.47,
426
+ "learning_rate": 2.7480916030534355e-05,
427
+ "loss": 2.7306,
428
+ "step": 690
429
+ },
430
+ {
431
+ "epoch": 1.49,
432
+ "learning_rate": 2.7099236641221375e-05,
433
+ "loss": 2.7702,
434
+ "step": 700
435
+ },
436
+ {
437
+ "epoch": 1.51,
438
+ "learning_rate": 2.6717557251908397e-05,
439
+ "loss": 2.7534,
440
+ "step": 710
441
+ },
442
+ {
443
+ "epoch": 1.53,
444
+ "learning_rate": 2.633587786259542e-05,
445
+ "loss": 2.7513,
446
+ "step": 720
447
+ },
448
+ {
449
+ "epoch": 1.55,
450
+ "learning_rate": 2.5954198473282442e-05,
451
+ "loss": 2.8025,
452
+ "step": 730
453
+ },
454
+ {
455
+ "epoch": 1.57,
456
+ "learning_rate": 2.5572519083969464e-05,
457
+ "loss": 2.7708,
458
+ "step": 740
459
+ },
460
+ {
461
+ "epoch": 1.6,
462
+ "learning_rate": 2.5190839694656487e-05,
463
+ "loss": 2.7335,
464
+ "step": 750
465
+ },
466
+ {
467
+ "epoch": 1.62,
468
+ "learning_rate": 2.4809160305343512e-05,
469
+ "loss": 2.7486,
470
+ "step": 760
471
+ },
472
+ {
473
+ "epoch": 1.64,
474
+ "learning_rate": 2.4427480916030535e-05,
475
+ "loss": 2.7564,
476
+ "step": 770
477
+ },
478
+ {
479
+ "epoch": 1.66,
480
+ "learning_rate": 2.404580152671756e-05,
481
+ "loss": 2.7758,
482
+ "step": 780
483
+ },
484
+ {
485
+ "epoch": 1.68,
486
+ "learning_rate": 2.3664122137404583e-05,
487
+ "loss": 2.7942,
488
+ "step": 790
489
+ },
490
+ {
491
+ "epoch": 1.7,
492
+ "learning_rate": 2.3282442748091605e-05,
493
+ "loss": 2.7317,
494
+ "step": 800
495
+ },
496
+ {
497
+ "epoch": 1.72,
498
+ "learning_rate": 2.2900763358778628e-05,
499
+ "loss": 2.7783,
500
+ "step": 810
501
+ },
502
+ {
503
+ "epoch": 1.74,
504
+ "learning_rate": 2.2519083969465647e-05,
505
+ "loss": 2.7836,
506
+ "step": 820
507
+ },
508
+ {
509
+ "epoch": 1.77,
510
+ "learning_rate": 2.2137404580152673e-05,
511
+ "loss": 2.7881,
512
+ "step": 830
513
+ },
514
+ {
515
+ "epoch": 1.79,
516
+ "learning_rate": 2.1755725190839695e-05,
517
+ "loss": 2.7586,
518
+ "step": 840
519
+ },
520
+ {
521
+ "epoch": 1.81,
522
+ "learning_rate": 2.1374045801526718e-05,
523
+ "loss": 2.7601,
524
+ "step": 850
525
+ },
526
+ {
527
+ "epoch": 1.83,
528
+ "learning_rate": 2.099236641221374e-05,
529
+ "loss": 2.7746,
530
+ "step": 860
531
+ },
532
+ {
533
+ "epoch": 1.85,
534
+ "learning_rate": 2.0610687022900766e-05,
535
+ "loss": 2.7675,
536
+ "step": 870
537
+ },
538
+ {
539
+ "epoch": 1.87,
540
+ "learning_rate": 2.0229007633587788e-05,
541
+ "loss": 2.7414,
542
+ "step": 880
543
+ },
544
+ {
545
+ "epoch": 1.89,
546
+ "learning_rate": 1.984732824427481e-05,
547
+ "loss": 2.7352,
548
+ "step": 890
549
+ },
550
+ {
551
+ "epoch": 1.91,
552
+ "learning_rate": 1.9465648854961833e-05,
553
+ "loss": 2.7762,
554
+ "step": 900
555
+ },
556
+ {
557
+ "epoch": 1.94,
558
+ "learning_rate": 1.9083969465648855e-05,
559
+ "loss": 2.7331,
560
+ "step": 910
561
+ },
562
+ {
563
+ "epoch": 1.96,
564
+ "learning_rate": 1.8702290076335878e-05,
565
+ "loss": 2.7561,
566
+ "step": 920
567
+ },
568
+ {
569
+ "epoch": 1.98,
570
+ "learning_rate": 1.83206106870229e-05,
571
+ "loss": 2.7428,
572
+ "step": 930
573
+ },
574
+ {
575
+ "epoch": 2.0,
576
+ "learning_rate": 1.7938931297709923e-05,
577
+ "loss": 2.7049,
578
+ "step": 940
579
+ },
580
+ {
581
+ "epoch": 2.02,
582
+ "learning_rate": 1.7557251908396945e-05,
583
+ "loss": 2.7188,
584
+ "step": 950
585
+ },
586
+ {
587
+ "epoch": 2.04,
588
+ "learning_rate": 1.717557251908397e-05,
589
+ "loss": 2.699,
590
+ "step": 960
591
+ },
592
+ {
593
+ "epoch": 2.06,
594
+ "learning_rate": 1.6793893129770993e-05,
595
+ "loss": 2.6526,
596
+ "step": 970
597
+ },
598
+ {
599
+ "epoch": 2.09,
600
+ "learning_rate": 1.6412213740458016e-05,
601
+ "loss": 2.6924,
602
+ "step": 980
603
+ },
604
+ {
605
+ "epoch": 2.11,
606
+ "learning_rate": 1.6030534351145038e-05,
607
+ "loss": 2.6693,
608
+ "step": 990
609
+ },
610
+ {
611
+ "epoch": 2.13,
612
+ "learning_rate": 1.5648854961832064e-05,
613
+ "loss": 2.696,
614
+ "step": 1000
615
+ },
616
+ {
617
+ "epoch": 2.15,
618
+ "learning_rate": 1.5267175572519086e-05,
619
+ "loss": 2.687,
620
+ "step": 1010
621
+ },
622
+ {
623
+ "epoch": 2.17,
624
+ "learning_rate": 1.4885496183206107e-05,
625
+ "loss": 2.7227,
626
+ "step": 1020
627
+ },
628
+ {
629
+ "epoch": 2.19,
630
+ "learning_rate": 1.450381679389313e-05,
631
+ "loss": 2.6702,
632
+ "step": 1030
633
+ },
634
+ {
635
+ "epoch": 2.21,
636
+ "learning_rate": 1.4122137404580155e-05,
637
+ "loss": 2.6786,
638
+ "step": 1040
639
+ },
640
+ {
641
+ "epoch": 2.23,
642
+ "learning_rate": 1.3740458015267178e-05,
643
+ "loss": 2.6866,
644
+ "step": 1050
645
+ },
646
+ {
647
+ "epoch": 2.26,
648
+ "learning_rate": 1.3358778625954198e-05,
649
+ "loss": 2.7269,
650
+ "step": 1060
651
+ },
652
+ {
653
+ "epoch": 2.28,
654
+ "learning_rate": 1.2977099236641221e-05,
655
+ "loss": 2.6913,
656
+ "step": 1070
657
+ },
658
+ {
659
+ "epoch": 2.3,
660
+ "learning_rate": 1.2595419847328243e-05,
661
+ "loss": 2.7301,
662
+ "step": 1080
663
+ },
664
+ {
665
+ "epoch": 2.32,
666
+ "learning_rate": 1.2213740458015267e-05,
667
+ "loss": 2.732,
668
+ "step": 1090
669
+ },
670
+ {
671
+ "epoch": 2.34,
672
+ "learning_rate": 1.1832061068702292e-05,
673
+ "loss": 2.6862,
674
+ "step": 1100
675
+ },
676
+ {
677
+ "epoch": 2.36,
678
+ "learning_rate": 1.1450381679389314e-05,
679
+ "loss": 2.7358,
680
+ "step": 1110
681
+ },
682
+ {
683
+ "epoch": 2.38,
684
+ "learning_rate": 1.1068702290076336e-05,
685
+ "loss": 2.6862,
686
+ "step": 1120
687
+ },
688
+ {
689
+ "epoch": 2.4,
690
+ "learning_rate": 1.0687022900763359e-05,
691
+ "loss": 2.7138,
692
+ "step": 1130
693
+ },
694
+ {
695
+ "epoch": 2.43,
696
+ "learning_rate": 1.0305343511450383e-05,
697
+ "loss": 2.7312,
698
+ "step": 1140
699
+ },
700
+ {
701
+ "epoch": 2.45,
702
+ "learning_rate": 9.923664122137405e-06,
703
+ "loss": 2.7159,
704
+ "step": 1150
705
+ },
706
+ {
707
+ "epoch": 2.47,
708
+ "learning_rate": 9.541984732824428e-06,
709
+ "loss": 2.6882,
710
+ "step": 1160
711
+ },
712
+ {
713
+ "epoch": 2.49,
714
+ "learning_rate": 9.16030534351145e-06,
715
+ "loss": 2.7109,
716
+ "step": 1170
717
+ },
718
+ {
719
+ "epoch": 2.51,
720
+ "learning_rate": 8.778625954198473e-06,
721
+ "loss": 2.7363,
722
+ "step": 1180
723
+ },
724
+ {
725
+ "epoch": 2.53,
726
+ "learning_rate": 8.396946564885497e-06,
727
+ "loss": 2.7332,
728
+ "step": 1190
729
+ },
730
+ {
731
+ "epoch": 2.55,
732
+ "learning_rate": 8.015267175572519e-06,
733
+ "loss": 2.6836,
734
+ "step": 1200
735
+ },
736
+ {
737
+ "epoch": 2.57,
738
+ "learning_rate": 7.633587786259543e-06,
739
+ "loss": 2.7008,
740
+ "step": 1210
741
+ },
742
+ {
743
+ "epoch": 2.6,
744
+ "learning_rate": 7.251908396946565e-06,
745
+ "loss": 2.7129,
746
+ "step": 1220
747
+ },
748
+ {
749
+ "epoch": 2.62,
750
+ "learning_rate": 6.870229007633589e-06,
751
+ "loss": 2.7233,
752
+ "step": 1230
753
+ },
754
+ {
755
+ "epoch": 2.64,
756
+ "learning_rate": 6.4885496183206104e-06,
757
+ "loss": 2.6856,
758
+ "step": 1240
759
+ },
760
+ {
761
+ "epoch": 2.66,
762
+ "learning_rate": 6.106870229007634e-06,
763
+ "loss": 2.7376,
764
+ "step": 1250
765
+ },
766
+ {
767
+ "epoch": 2.68,
768
+ "learning_rate": 5.725190839694657e-06,
769
+ "loss": 2.7237,
770
+ "step": 1260
771
+ },
772
+ {
773
+ "epoch": 2.7,
774
+ "learning_rate": 5.343511450381679e-06,
775
+ "loss": 2.698,
776
+ "step": 1270
777
+ },
778
+ {
779
+ "epoch": 2.72,
780
+ "learning_rate": 4.961832061068703e-06,
781
+ "loss": 2.7422,
782
+ "step": 1280
783
+ },
784
+ {
785
+ "epoch": 2.74,
786
+ "learning_rate": 4.580152671755725e-06,
787
+ "loss": 2.6834,
788
+ "step": 1290
789
+ },
790
+ {
791
+ "epoch": 2.77,
792
+ "learning_rate": 4.198473282442748e-06,
793
+ "loss": 2.6675,
794
+ "step": 1300
795
+ },
796
+ {
797
+ "epoch": 2.79,
798
+ "learning_rate": 3.816793893129772e-06,
799
+ "loss": 2.6683,
800
+ "step": 1310
801
+ },
802
+ {
803
+ "epoch": 2.81,
804
+ "learning_rate": 3.4351145038167944e-06,
805
+ "loss": 2.7138,
806
+ "step": 1320
807
+ },
808
+ {
809
+ "epoch": 2.83,
810
+ "learning_rate": 3.053435114503817e-06,
811
+ "loss": 2.7272,
812
+ "step": 1330
813
+ },
814
+ {
815
+ "epoch": 2.85,
816
+ "learning_rate": 2.6717557251908397e-06,
817
+ "loss": 2.7183,
818
+ "step": 1340
819
+ },
820
+ {
821
+ "epoch": 2.87,
822
+ "learning_rate": 2.2900763358778625e-06,
823
+ "loss": 2.7036,
824
+ "step": 1350
825
+ },
826
+ {
827
+ "epoch": 2.89,
828
+ "learning_rate": 1.908396946564886e-06,
829
+ "loss": 2.6808,
830
+ "step": 1360
831
+ },
832
+ {
833
+ "epoch": 2.91,
834
+ "learning_rate": 1.5267175572519084e-06,
835
+ "loss": 2.6361,
836
+ "step": 1370
837
+ },
838
+ {
839
+ "epoch": 2.94,
840
+ "learning_rate": 1.1450381679389313e-06,
841
+ "loss": 2.7164,
842
+ "step": 1380
843
+ },
844
+ {
845
+ "epoch": 2.96,
846
+ "learning_rate": 7.633587786259542e-07,
847
+ "loss": 2.705,
848
+ "step": 1390
849
+ },
850
+ {
851
+ "epoch": 2.98,
852
+ "learning_rate": 3.816793893129771e-07,
853
+ "loss": 2.677,
854
+ "step": 1400
855
+ },
856
+ {
857
+ "epoch": 3.0,
858
+ "learning_rate": 0.0,
859
+ "loss": 2.6911,
860
+ "step": 1410
861
+ },
862
+ {
863
+ "epoch": 3.0,
864
+ "step": 1410,
865
+ "total_flos": 6.285446300565504e+16,
866
+ "train_loss": 0.690881545154761,
867
+ "train_runtime": 7737.0233,
868
+ "train_samples_per_second": 2.187,
869
+ "train_steps_per_second": 0.182
870
+ }
871
+ ],
872
+ "max_steps": 1410,
873
+ "num_train_epochs": 3,
874
+ "total_flos": 6.285446300565504e+16,
875
+ "trial_name": null,
876
+ "trial_params": null
877
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7627dabdabbcea0545cd66546a2642108f17b5be05074c671840ab6e943ef5f
3
+ size 3899
vocab.json ADDED
The diff for this file is too large to render. See raw diff