Dilyara commited on
Commit
9dfc560
1 Parent(s): 9909983

feat: add files

Browse files
added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<|endoftext|>": 50257}
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "rudialogpt3_medium_based_on_gpt2_local",
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
+ "gradient_checkpointing": false,
12
+ "id2label": {
13
+ "0": "LABEL_0"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "label2id": {
17
+ "LABEL_0": 0
18
+ },
19
+ "layer_norm_epsilon": 1e-05,
20
+ "model_type": "gpt2",
21
+ "n_ctx": 2048,
22
+ "n_embd": 1024,
23
+ "n_head": 16,
24
+ "n_inner": null,
25
+ "n_layer": 24,
26
+ "n_positions": 2048,
27
+ "n_special": 0,
28
+ "output_past": true,
29
+ "predict_special_tokens": true,
30
+ "reorder_and_upcast_attn": false,
31
+ "resid_pdrop": 0.1,
32
+ "scale_attn_by_inverse_layer_idx": false,
33
+ "scale_attn_weights": true,
34
+ "summary_activation": null,
35
+ "summary_first_dropout": 0.1,
36
+ "summary_proj_to_labels": true,
37
+ "summary_type": "cls_index",
38
+ "summary_use_proj": true,
39
+ "torch_dtype": "float32",
40
+ "transformers_version": "4.17.0",
41
+ "use_cache": true,
42
+ "vocab_size": 50257
43
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec2a3be98cf5b0a3cf53e7f0132c9aab79b55dfa504c79390730ee3a4ff2dd1b
3
+ size 1524274265
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "additional_special_tokens": ["<mask>", "</s>", "<unk>", "<pad>"]}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "special_tokens_map_file": null, "name_or_path": "Grossmend/rudialogpt3_medium_based_on_gpt2", "errors": "replace"}
trainer_state.json ADDED
@@ -0,0 +1,774 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "global_step": 62988,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.01,
12
+ "learning_rate": 1.998412396011939e-05,
13
+ "loss": 1.6197,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.02,
18
+ "learning_rate": 1.9968247920238778e-05,
19
+ "loss": 1.5231,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.02,
24
+ "learning_rate": 1.9952371880358167e-05,
25
+ "loss": 1.508,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.03,
30
+ "learning_rate": 1.9936495840477554e-05,
31
+ "loss": 1.4933,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.04,
36
+ "learning_rate": 1.992061980059694e-05,
37
+ "loss": 1.4876,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.05,
42
+ "learning_rate": 1.990474376071633e-05,
43
+ "loss": 1.4779,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.06,
48
+ "learning_rate": 1.9888867720835716e-05,
49
+ "loss": 1.4754,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.06,
54
+ "learning_rate": 1.9872991680955105e-05,
55
+ "loss": 1.4712,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.07,
60
+ "learning_rate": 1.9857115641074492e-05,
61
+ "loss": 1.4677,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.08,
66
+ "learning_rate": 1.984123960119388e-05,
67
+ "loss": 1.4622,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 0.09,
72
+ "learning_rate": 1.9825363561313268e-05,
73
+ "loss": 1.4638,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 0.1,
78
+ "learning_rate": 1.9809487521432654e-05,
79
+ "loss": 1.4594,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 0.1,
84
+ "learning_rate": 1.9793611481552044e-05,
85
+ "loss": 1.4514,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 0.11,
90
+ "learning_rate": 1.977773544167143e-05,
91
+ "loss": 1.4568,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 0.12,
96
+ "learning_rate": 1.976185940179082e-05,
97
+ "loss": 1.4524,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 0.13,
102
+ "learning_rate": 1.9745983361910206e-05,
103
+ "loss": 1.4469,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 0.13,
108
+ "learning_rate": 1.9730107322029596e-05,
109
+ "loss": 1.4478,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 0.14,
114
+ "learning_rate": 1.9714231282148982e-05,
115
+ "loss": 1.4443,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 0.15,
120
+ "learning_rate": 1.969835524226837e-05,
121
+ "loss": 1.442,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 0.16,
126
+ "learning_rate": 1.9682479202387758e-05,
127
+ "loss": 1.4395,
128
+ "step": 10000
129
+ },
130
+ {
131
+ "epoch": 0.17,
132
+ "learning_rate": 1.9666603162507144e-05,
133
+ "loss": 1.4377,
134
+ "step": 10500
135
+ },
136
+ {
137
+ "epoch": 0.17,
138
+ "learning_rate": 1.9650727122626534e-05,
139
+ "loss": 1.4381,
140
+ "step": 11000
141
+ },
142
+ {
143
+ "epoch": 0.18,
144
+ "learning_rate": 1.963485108274592e-05,
145
+ "loss": 1.4337,
146
+ "step": 11500
147
+ },
148
+ {
149
+ "epoch": 0.19,
150
+ "learning_rate": 1.961897504286531e-05,
151
+ "loss": 1.4338,
152
+ "step": 12000
153
+ },
154
+ {
155
+ "epoch": 0.2,
156
+ "learning_rate": 1.96030990029847e-05,
157
+ "loss": 1.4347,
158
+ "step": 12500
159
+ },
160
+ {
161
+ "epoch": 0.21,
162
+ "learning_rate": 1.9587222963104086e-05,
163
+ "loss": 1.436,
164
+ "step": 13000
165
+ },
166
+ {
167
+ "epoch": 0.21,
168
+ "learning_rate": 1.9571346923223472e-05,
169
+ "loss": 1.4333,
170
+ "step": 13500
171
+ },
172
+ {
173
+ "epoch": 0.22,
174
+ "learning_rate": 1.955547088334286e-05,
175
+ "loss": 1.425,
176
+ "step": 14000
177
+ },
178
+ {
179
+ "epoch": 0.23,
180
+ "learning_rate": 1.9539594843462248e-05,
181
+ "loss": 1.4254,
182
+ "step": 14500
183
+ },
184
+ {
185
+ "epoch": 0.24,
186
+ "learning_rate": 1.9523718803581638e-05,
187
+ "loss": 1.4285,
188
+ "step": 15000
189
+ },
190
+ {
191
+ "epoch": 0.25,
192
+ "learning_rate": 1.9507842763701024e-05,
193
+ "loss": 1.4226,
194
+ "step": 15500
195
+ },
196
+ {
197
+ "epoch": 0.25,
198
+ "learning_rate": 1.9491966723820414e-05,
199
+ "loss": 1.4261,
200
+ "step": 16000
201
+ },
202
+ {
203
+ "epoch": 0.26,
204
+ "learning_rate": 1.94760906839398e-05,
205
+ "loss": 1.4233,
206
+ "step": 16500
207
+ },
208
+ {
209
+ "epoch": 0.27,
210
+ "learning_rate": 1.9460214644059186e-05,
211
+ "loss": 1.4206,
212
+ "step": 17000
213
+ },
214
+ {
215
+ "epoch": 0.28,
216
+ "learning_rate": 1.9444338604178576e-05,
217
+ "loss": 1.4224,
218
+ "step": 17500
219
+ },
220
+ {
221
+ "epoch": 0.29,
222
+ "learning_rate": 1.9428462564297962e-05,
223
+ "loss": 1.414,
224
+ "step": 18000
225
+ },
226
+ {
227
+ "epoch": 0.29,
228
+ "learning_rate": 1.9412586524417352e-05,
229
+ "loss": 1.424,
230
+ "step": 18500
231
+ },
232
+ {
233
+ "epoch": 0.3,
234
+ "learning_rate": 1.9396710484536738e-05,
235
+ "loss": 1.4181,
236
+ "step": 19000
237
+ },
238
+ {
239
+ "epoch": 0.31,
240
+ "learning_rate": 1.9380834444656128e-05,
241
+ "loss": 1.4168,
242
+ "step": 19500
243
+ },
244
+ {
245
+ "epoch": 0.32,
246
+ "learning_rate": 1.9364958404775514e-05,
247
+ "loss": 1.4171,
248
+ "step": 20000
249
+ },
250
+ {
251
+ "epoch": 0.33,
252
+ "learning_rate": 1.9349082364894904e-05,
253
+ "loss": 1.4116,
254
+ "step": 20500
255
+ },
256
+ {
257
+ "epoch": 0.33,
258
+ "learning_rate": 1.933320632501429e-05,
259
+ "loss": 1.4055,
260
+ "step": 21000
261
+ },
262
+ {
263
+ "epoch": 0.34,
264
+ "learning_rate": 1.9317330285133676e-05,
265
+ "loss": 1.4118,
266
+ "step": 21500
267
+ },
268
+ {
269
+ "epoch": 0.35,
270
+ "learning_rate": 1.9301454245253066e-05,
271
+ "loss": 1.4134,
272
+ "step": 22000
273
+ },
274
+ {
275
+ "epoch": 0.36,
276
+ "learning_rate": 1.9285578205372452e-05,
277
+ "loss": 1.4205,
278
+ "step": 22500
279
+ },
280
+ {
281
+ "epoch": 0.37,
282
+ "learning_rate": 1.9269702165491842e-05,
283
+ "loss": 1.4088,
284
+ "step": 23000
285
+ },
286
+ {
287
+ "epoch": 0.37,
288
+ "learning_rate": 1.925382612561123e-05,
289
+ "loss": 1.4104,
290
+ "step": 23500
291
+ },
292
+ {
293
+ "epoch": 0.38,
294
+ "learning_rate": 1.9237950085730618e-05,
295
+ "loss": 1.4109,
296
+ "step": 24000
297
+ },
298
+ {
299
+ "epoch": 0.39,
300
+ "learning_rate": 1.9222074045850004e-05,
301
+ "loss": 1.4073,
302
+ "step": 24500
303
+ },
304
+ {
305
+ "epoch": 0.4,
306
+ "learning_rate": 1.920619800596939e-05,
307
+ "loss": 1.4048,
308
+ "step": 25000
309
+ },
310
+ {
311
+ "epoch": 0.4,
312
+ "learning_rate": 1.919032196608878e-05,
313
+ "loss": 1.4056,
314
+ "step": 25500
315
+ },
316
+ {
317
+ "epoch": 0.41,
318
+ "learning_rate": 1.9174445926208167e-05,
319
+ "loss": 1.4045,
320
+ "step": 26000
321
+ },
322
+ {
323
+ "epoch": 0.42,
324
+ "learning_rate": 1.9158569886327556e-05,
325
+ "loss": 1.4042,
326
+ "step": 26500
327
+ },
328
+ {
329
+ "epoch": 0.43,
330
+ "learning_rate": 1.9142693846446946e-05,
331
+ "loss": 1.4001,
332
+ "step": 27000
333
+ },
334
+ {
335
+ "epoch": 0.44,
336
+ "learning_rate": 1.9126817806566332e-05,
337
+ "loss": 1.4065,
338
+ "step": 27500
339
+ },
340
+ {
341
+ "epoch": 0.44,
342
+ "learning_rate": 1.911094176668572e-05,
343
+ "loss": 1.4041,
344
+ "step": 28000
345
+ },
346
+ {
347
+ "epoch": 0.45,
348
+ "learning_rate": 1.9095065726805108e-05,
349
+ "loss": 1.3994,
350
+ "step": 28500
351
+ },
352
+ {
353
+ "epoch": 0.46,
354
+ "learning_rate": 1.9079189686924494e-05,
355
+ "loss": 1.3991,
356
+ "step": 29000
357
+ },
358
+ {
359
+ "epoch": 0.47,
360
+ "learning_rate": 1.9063313647043884e-05,
361
+ "loss": 1.3956,
362
+ "step": 29500
363
+ },
364
+ {
365
+ "epoch": 0.48,
366
+ "learning_rate": 1.904743760716327e-05,
367
+ "loss": 1.3995,
368
+ "step": 30000
369
+ },
370
+ {
371
+ "epoch": 0.48,
372
+ "learning_rate": 1.903156156728266e-05,
373
+ "loss": 1.4011,
374
+ "step": 30500
375
+ },
376
+ {
377
+ "epoch": 0.49,
378
+ "learning_rate": 1.9015685527402046e-05,
379
+ "loss": 1.3964,
380
+ "step": 31000
381
+ },
382
+ {
383
+ "epoch": 0.5,
384
+ "learning_rate": 1.8999809487521436e-05,
385
+ "loss": 1.3925,
386
+ "step": 31500
387
+ },
388
+ {
389
+ "epoch": 0.51,
390
+ "learning_rate": 1.8983933447640822e-05,
391
+ "loss": 1.3875,
392
+ "step": 32000
393
+ },
394
+ {
395
+ "epoch": 0.52,
396
+ "learning_rate": 1.896805740776021e-05,
397
+ "loss": 1.3945,
398
+ "step": 32500
399
+ },
400
+ {
401
+ "epoch": 0.52,
402
+ "learning_rate": 1.8952181367879598e-05,
403
+ "loss": 1.3919,
404
+ "step": 33000
405
+ },
406
+ {
407
+ "epoch": 0.53,
408
+ "learning_rate": 1.8936305327998985e-05,
409
+ "loss": 1.3942,
410
+ "step": 33500
411
+ },
412
+ {
413
+ "epoch": 0.54,
414
+ "learning_rate": 1.8920429288118374e-05,
415
+ "loss": 1.3906,
416
+ "step": 34000
417
+ },
418
+ {
419
+ "epoch": 0.55,
420
+ "learning_rate": 1.890455324823776e-05,
421
+ "loss": 1.3916,
422
+ "step": 34500
423
+ },
424
+ {
425
+ "epoch": 0.56,
426
+ "learning_rate": 1.888867720835715e-05,
427
+ "loss": 1.3871,
428
+ "step": 35000
429
+ },
430
+ {
431
+ "epoch": 0.56,
432
+ "learning_rate": 1.8872801168476536e-05,
433
+ "loss": 1.3824,
434
+ "step": 35500
435
+ },
436
+ {
437
+ "epoch": 0.57,
438
+ "learning_rate": 1.8856925128595923e-05,
439
+ "loss": 1.3919,
440
+ "step": 36000
441
+ },
442
+ {
443
+ "epoch": 0.58,
444
+ "learning_rate": 1.8841049088715312e-05,
445
+ "loss": 1.3885,
446
+ "step": 36500
447
+ },
448
+ {
449
+ "epoch": 0.59,
450
+ "learning_rate": 1.88251730488347e-05,
451
+ "loss": 1.3837,
452
+ "step": 37000
453
+ },
454
+ {
455
+ "epoch": 0.6,
456
+ "learning_rate": 1.880929700895409e-05,
457
+ "loss": 1.389,
458
+ "step": 37500
459
+ },
460
+ {
461
+ "epoch": 0.6,
462
+ "learning_rate": 1.8793420969073475e-05,
463
+ "loss": 1.3841,
464
+ "step": 38000
465
+ },
466
+ {
467
+ "epoch": 0.61,
468
+ "learning_rate": 1.8777544929192864e-05,
469
+ "loss": 1.3846,
470
+ "step": 38500
471
+ },
472
+ {
473
+ "epoch": 0.62,
474
+ "learning_rate": 1.876166888931225e-05,
475
+ "loss": 1.3807,
476
+ "step": 39000
477
+ },
478
+ {
479
+ "epoch": 0.63,
480
+ "learning_rate": 1.874579284943164e-05,
481
+ "loss": 1.382,
482
+ "step": 39500
483
+ },
484
+ {
485
+ "epoch": 0.64,
486
+ "learning_rate": 1.8729916809551027e-05,
487
+ "loss": 1.3831,
488
+ "step": 40000
489
+ },
490
+ {
491
+ "epoch": 0.64,
492
+ "learning_rate": 1.8714040769670413e-05,
493
+ "loss": 1.3814,
494
+ "step": 40500
495
+ },
496
+ {
497
+ "epoch": 0.65,
498
+ "learning_rate": 1.8698164729789803e-05,
499
+ "loss": 1.3858,
500
+ "step": 41000
501
+ },
502
+ {
503
+ "epoch": 0.66,
504
+ "learning_rate": 1.8682288689909192e-05,
505
+ "loss": 1.3846,
506
+ "step": 41500
507
+ },
508
+ {
509
+ "epoch": 0.67,
510
+ "learning_rate": 1.866641265002858e-05,
511
+ "loss": 1.3831,
512
+ "step": 42000
513
+ },
514
+ {
515
+ "epoch": 0.67,
516
+ "learning_rate": 1.8650536610147968e-05,
517
+ "loss": 1.3738,
518
+ "step": 42500
519
+ },
520
+ {
521
+ "epoch": 0.68,
522
+ "learning_rate": 1.8634660570267354e-05,
523
+ "loss": 1.3798,
524
+ "step": 43000
525
+ },
526
+ {
527
+ "epoch": 0.69,
528
+ "learning_rate": 1.861878453038674e-05,
529
+ "loss": 1.3755,
530
+ "step": 43500
531
+ },
532
+ {
533
+ "epoch": 0.7,
534
+ "learning_rate": 1.8602908490506127e-05,
535
+ "loss": 1.3753,
536
+ "step": 44000
537
+ },
538
+ {
539
+ "epoch": 0.71,
540
+ "learning_rate": 1.8587032450625517e-05,
541
+ "loss": 1.3745,
542
+ "step": 44500
543
+ },
544
+ {
545
+ "epoch": 0.71,
546
+ "learning_rate": 1.8571156410744906e-05,
547
+ "loss": 1.3814,
548
+ "step": 45000
549
+ },
550
+ {
551
+ "epoch": 0.72,
552
+ "learning_rate": 1.8555280370864293e-05,
553
+ "loss": 1.3759,
554
+ "step": 45500
555
+ },
556
+ {
557
+ "epoch": 0.73,
558
+ "learning_rate": 1.8539404330983682e-05,
559
+ "loss": 1.3722,
560
+ "step": 46000
561
+ },
562
+ {
563
+ "epoch": 0.74,
564
+ "learning_rate": 1.852352829110307e-05,
565
+ "loss": 1.3768,
566
+ "step": 46500
567
+ },
568
+ {
569
+ "epoch": 0.75,
570
+ "learning_rate": 1.8507652251222455e-05,
571
+ "loss": 1.3724,
572
+ "step": 47000
573
+ },
574
+ {
575
+ "epoch": 0.75,
576
+ "learning_rate": 1.8491776211341845e-05,
577
+ "loss": 1.3745,
578
+ "step": 47500
579
+ },
580
+ {
581
+ "epoch": 0.76,
582
+ "learning_rate": 1.847590017146123e-05,
583
+ "loss": 1.3727,
584
+ "step": 48000
585
+ },
586
+ {
587
+ "epoch": 0.77,
588
+ "learning_rate": 1.846002413158062e-05,
589
+ "loss": 1.3703,
590
+ "step": 48500
591
+ },
592
+ {
593
+ "epoch": 0.78,
594
+ "learning_rate": 1.8444148091700007e-05,
595
+ "loss": 1.3673,
596
+ "step": 49000
597
+ },
598
+ {
599
+ "epoch": 0.79,
600
+ "learning_rate": 1.8428272051819397e-05,
601
+ "loss": 1.3686,
602
+ "step": 49500
603
+ },
604
+ {
605
+ "epoch": 0.79,
606
+ "learning_rate": 1.8412396011938786e-05,
607
+ "loss": 1.3663,
608
+ "step": 50000
609
+ },
610
+ {
611
+ "epoch": 0.8,
612
+ "learning_rate": 1.8396519972058173e-05,
613
+ "loss": 1.3665,
614
+ "step": 50500
615
+ },
616
+ {
617
+ "epoch": 0.81,
618
+ "learning_rate": 1.838064393217756e-05,
619
+ "loss": 1.3701,
620
+ "step": 51000
621
+ },
622
+ {
623
+ "epoch": 0.82,
624
+ "learning_rate": 1.8364767892296945e-05,
625
+ "loss": 1.3678,
626
+ "step": 51500
627
+ },
628
+ {
629
+ "epoch": 0.83,
630
+ "learning_rate": 1.8348891852416335e-05,
631
+ "loss": 1.3704,
632
+ "step": 52000
633
+ },
634
+ {
635
+ "epoch": 0.83,
636
+ "learning_rate": 1.833301581253572e-05,
637
+ "loss": 1.3657,
638
+ "step": 52500
639
+ },
640
+ {
641
+ "epoch": 0.84,
642
+ "learning_rate": 1.831713977265511e-05,
643
+ "loss": 1.3683,
644
+ "step": 53000
645
+ },
646
+ {
647
+ "epoch": 0.85,
648
+ "learning_rate": 1.83012637327745e-05,
649
+ "loss": 1.3637,
650
+ "step": 53500
651
+ },
652
+ {
653
+ "epoch": 0.86,
654
+ "learning_rate": 1.8285387692893887e-05,
655
+ "loss": 1.3636,
656
+ "step": 54000
657
+ },
658
+ {
659
+ "epoch": 0.87,
660
+ "learning_rate": 1.8269511653013273e-05,
661
+ "loss": 1.3626,
662
+ "step": 54500
663
+ },
664
+ {
665
+ "epoch": 0.87,
666
+ "learning_rate": 1.825363561313266e-05,
667
+ "loss": 1.3682,
668
+ "step": 55000
669
+ },
670
+ {
671
+ "epoch": 0.88,
672
+ "learning_rate": 1.823775957325205e-05,
673
+ "loss": 1.3653,
674
+ "step": 55500
675
+ },
676
+ {
677
+ "epoch": 0.89,
678
+ "learning_rate": 1.822188353337144e-05,
679
+ "loss": 1.3654,
680
+ "step": 56000
681
+ },
682
+ {
683
+ "epoch": 0.9,
684
+ "learning_rate": 1.8206007493490825e-05,
685
+ "loss": 1.3609,
686
+ "step": 56500
687
+ },
688
+ {
689
+ "epoch": 0.9,
690
+ "learning_rate": 1.8190131453610215e-05,
691
+ "loss": 1.3616,
692
+ "step": 57000
693
+ },
694
+ {
695
+ "epoch": 0.91,
696
+ "learning_rate": 1.81742554137296e-05,
697
+ "loss": 1.362,
698
+ "step": 57500
699
+ },
700
+ {
701
+ "epoch": 0.92,
702
+ "learning_rate": 1.815837937384899e-05,
703
+ "loss": 1.364,
704
+ "step": 58000
705
+ },
706
+ {
707
+ "epoch": 0.93,
708
+ "learning_rate": 1.8142503333968377e-05,
709
+ "loss": 1.3573,
710
+ "step": 58500
711
+ },
712
+ {
713
+ "epoch": 0.94,
714
+ "learning_rate": 1.8126627294087763e-05,
715
+ "loss": 1.3543,
716
+ "step": 59000
717
+ },
718
+ {
719
+ "epoch": 0.94,
720
+ "learning_rate": 1.8110751254207153e-05,
721
+ "loss": 1.3592,
722
+ "step": 59500
723
+ },
724
+ {
725
+ "epoch": 0.95,
726
+ "learning_rate": 1.809487521432654e-05,
727
+ "loss": 1.3598,
728
+ "step": 60000
729
+ },
730
+ {
731
+ "epoch": 0.96,
732
+ "learning_rate": 1.807899917444593e-05,
733
+ "loss": 1.3561,
734
+ "step": 60500
735
+ },
736
+ {
737
+ "epoch": 0.97,
738
+ "learning_rate": 1.8063123134565315e-05,
739
+ "loss": 1.3575,
740
+ "step": 61000
741
+ },
742
+ {
743
+ "epoch": 0.98,
744
+ "learning_rate": 1.8047247094684705e-05,
745
+ "loss": 1.3614,
746
+ "step": 61500
747
+ },
748
+ {
749
+ "epoch": 0.98,
750
+ "learning_rate": 1.803137105480409e-05,
751
+ "loss": 1.3575,
752
+ "step": 62000
753
+ },
754
+ {
755
+ "epoch": 0.99,
756
+ "learning_rate": 1.8015495014923477e-05,
757
+ "loss": 1.3558,
758
+ "step": 62500
759
+ },
760
+ {
761
+ "epoch": 1.0,
762
+ "eval_loss": 1.3514442443847656,
763
+ "eval_runtime": 2650.2414,
764
+ "eval_samples_per_second": 237.786,
765
+ "eval_steps_per_second": 2.973,
766
+ "step": 62988
767
+ }
768
+ ],
769
+ "max_steps": 629880,
770
+ "num_train_epochs": 10,
771
+ "total_flos": 2.3398437545501e+18,
772
+ "trial_name": null,
773
+ "trial_params": null
774
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05d64e1a6f598956b55983c72fdf1ebb47ac44a4600df71825b6eb4284702f08
3
+ size 3119
vocab.json ADDED
The diff for this file is too large to render. See raw diff