huytranduck commited on
Commit
d7480bc
·
verified ·
1 Parent(s): 74c54c6

Upload full checkpoint with tokenizer and model configs

Browse files
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<mask>": 64000
3
+ }
bpe.codes ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9718df1289fbd794c724511fab709027cff01755aa78e21e23b6949390f26719
3
  size 540026460
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:708ef2d8e5647b5422eec6f660ce929f3ef1cd7e30e51b8c1442c49a6aabc502
3
  size 540026460
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f84d13706e61db8a6f3510450c6e8f329d1873f263cc153f39083038ff2bc4e1
3
+ size 1080172794
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36ebc2cc6d2188705d5a00922f3effe7a402af89d1ab0c86ec76eef4614fbdcb
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb6933115d20752996ae544564ed5af748c321cf1155739d9dfb75dfd8b9270e
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": "<mask>",
6
+ "pad_token": "<pad>",
7
+ "sep_token": "</s>",
8
+ "unk_token": "<unk>"
9
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "64000": {
36
+ "content": "<mask>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": false,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "extra_special_tokens": {},
49
+ "mask_token": "<mask>",
50
+ "model_max_length": 1000000000000000019884624838656,
51
+ "pad_token": "<pad>",
52
+ "sep_token": "</s>",
53
+ "tokenizer_class": "PhobertTokenizer",
54
+ "unk_token": "<unk>"
55
+ }
trainer_state.json ADDED
@@ -0,0 +1,387 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 3146,
3
+ "best_metric": 0.4961947202682495,
4
+ "best_model_checkpoint": "./results/checkpoint-3146",
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 4719,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.06357279084551812,
14
+ "grad_norm": 9.905113220214844,
15
+ "learning_rate": 1.958041958041958e-05,
16
+ "loss": 0.8792,
17
+ "step": 100
18
+ },
19
+ {
20
+ "epoch": 0.12714558169103624,
21
+ "grad_norm": 34.34392166137695,
22
+ "learning_rate": 1.9156600974782794e-05,
23
+ "loss": 0.7359,
24
+ "step": 200
25
+ },
26
+ {
27
+ "epoch": 0.19071837253655435,
28
+ "grad_norm": 10.16415023803711,
29
+ "learning_rate": 1.8732782369146007e-05,
30
+ "loss": 0.6854,
31
+ "step": 300
32
+ },
33
+ {
34
+ "epoch": 0.25429116338207247,
35
+ "grad_norm": 16.56046485900879,
36
+ "learning_rate": 1.830896376350922e-05,
37
+ "loss": 0.6087,
38
+ "step": 400
39
+ },
40
+ {
41
+ "epoch": 0.3178639542275906,
42
+ "grad_norm": 4.33865213394165,
43
+ "learning_rate": 1.7885145157872432e-05,
44
+ "loss": 0.5703,
45
+ "step": 500
46
+ },
47
+ {
48
+ "epoch": 0.3814367450731087,
49
+ "grad_norm": 3.42850661277771,
50
+ "learning_rate": 1.7461326552235645e-05,
51
+ "loss": 0.5789,
52
+ "step": 600
53
+ },
54
+ {
55
+ "epoch": 0.44500953591862685,
56
+ "grad_norm": 10.796558380126953,
57
+ "learning_rate": 1.7037507946598858e-05,
58
+ "loss": 0.5224,
59
+ "step": 700
60
+ },
61
+ {
62
+ "epoch": 0.5085823267641449,
63
+ "grad_norm": 5.681849479675293,
64
+ "learning_rate": 1.661368934096207e-05,
65
+ "loss": 0.5429,
66
+ "step": 800
67
+ },
68
+ {
69
+ "epoch": 0.5721551176096631,
70
+ "grad_norm": 10.79218864440918,
71
+ "learning_rate": 1.618987073532528e-05,
72
+ "loss": 0.5732,
73
+ "step": 900
74
+ },
75
+ {
76
+ "epoch": 0.6357279084551812,
77
+ "grad_norm": 4.346675395965576,
78
+ "learning_rate": 1.5766052129688493e-05,
79
+ "loss": 0.5606,
80
+ "step": 1000
81
+ },
82
+ {
83
+ "epoch": 0.6993006993006993,
84
+ "grad_norm": 8.24238395690918,
85
+ "learning_rate": 1.5342233524051706e-05,
86
+ "loss": 0.52,
87
+ "step": 1100
88
+ },
89
+ {
90
+ "epoch": 0.7628734901462174,
91
+ "grad_norm": 6.931696891784668,
92
+ "learning_rate": 1.491841491841492e-05,
93
+ "loss": 0.5521,
94
+ "step": 1200
95
+ },
96
+ {
97
+ "epoch": 0.8264462809917356,
98
+ "grad_norm": 6.141210079193115,
99
+ "learning_rate": 1.4494596312778133e-05,
100
+ "loss": 0.5475,
101
+ "step": 1300
102
+ },
103
+ {
104
+ "epoch": 0.8900190718372537,
105
+ "grad_norm": 12.69131088256836,
106
+ "learning_rate": 1.4070777707141346e-05,
107
+ "loss": 0.5375,
108
+ "step": 1400
109
+ },
110
+ {
111
+ "epoch": 0.9535918626827717,
112
+ "grad_norm": 3.2147998809814453,
113
+ "learning_rate": 1.3646959101504557e-05,
114
+ "loss": 0.5187,
115
+ "step": 1500
116
+ },
117
+ {
118
+ "epoch": 1.0,
119
+ "eval_loss": 0.5000280737876892,
120
+ "eval_runtime": 17.0424,
121
+ "eval_samples_per_second": 369.197,
122
+ "eval_steps_per_second": 11.559,
123
+ "step": 1573
124
+ },
125
+ {
126
+ "epoch": 1.0171646535282899,
127
+ "grad_norm": 7.1118574142456055,
128
+ "learning_rate": 1.322314049586777e-05,
129
+ "loss": 0.5293,
130
+ "step": 1600
131
+ },
132
+ {
133
+ "epoch": 1.080737444373808,
134
+ "grad_norm": 12.308618545532227,
135
+ "learning_rate": 1.2799321890230982e-05,
136
+ "loss": 0.4733,
137
+ "step": 1700
138
+ },
139
+ {
140
+ "epoch": 1.1443102352193262,
141
+ "grad_norm": 7.184673309326172,
142
+ "learning_rate": 1.2375503284594195e-05,
143
+ "loss": 0.4817,
144
+ "step": 1800
145
+ },
146
+ {
147
+ "epoch": 1.2078830260648443,
148
+ "grad_norm": 12.598664283752441,
149
+ "learning_rate": 1.1951684678957406e-05,
150
+ "loss": 0.4823,
151
+ "step": 1900
152
+ },
153
+ {
154
+ "epoch": 1.2714558169103625,
155
+ "grad_norm": 9.51124382019043,
156
+ "learning_rate": 1.152786607332062e-05,
157
+ "loss": 0.5099,
158
+ "step": 2000
159
+ },
160
+ {
161
+ "epoch": 1.3350286077558806,
162
+ "grad_norm": 11.298410415649414,
163
+ "learning_rate": 1.1104047467683832e-05,
164
+ "loss": 0.4713,
165
+ "step": 2100
166
+ },
167
+ {
168
+ "epoch": 1.3986013986013985,
169
+ "grad_norm": 5.375974655151367,
170
+ "learning_rate": 1.0680228862047045e-05,
171
+ "loss": 0.4731,
172
+ "step": 2200
173
+ },
174
+ {
175
+ "epoch": 1.4621741894469167,
176
+ "grad_norm": 6.566510200500488,
177
+ "learning_rate": 1.0256410256410256e-05,
178
+ "loss": 0.4834,
179
+ "step": 2300
180
+ },
181
+ {
182
+ "epoch": 1.5257469802924348,
183
+ "grad_norm": 24.000308990478516,
184
+ "learning_rate": 9.83259165077347e-06,
185
+ "loss": 0.4692,
186
+ "step": 2400
187
+ },
188
+ {
189
+ "epoch": 1.589319771137953,
190
+ "grad_norm": 6.890144348144531,
191
+ "learning_rate": 9.408773045136681e-06,
192
+ "loss": 0.4692,
193
+ "step": 2500
194
+ },
195
+ {
196
+ "epoch": 1.6528925619834711,
197
+ "grad_norm": 4.995481491088867,
198
+ "learning_rate": 8.984954439499894e-06,
199
+ "loss": 0.4613,
200
+ "step": 2600
201
+ },
202
+ {
203
+ "epoch": 1.716465352828989,
204
+ "grad_norm": 5.291828155517578,
205
+ "learning_rate": 8.561135833863107e-06,
206
+ "loss": 0.5056,
207
+ "step": 2700
208
+ },
209
+ {
210
+ "epoch": 1.7800381436745072,
211
+ "grad_norm": 9.579062461853027,
212
+ "learning_rate": 8.13731722822632e-06,
213
+ "loss": 0.48,
214
+ "step": 2800
215
+ },
216
+ {
217
+ "epoch": 1.8436109345200253,
218
+ "grad_norm": 6.972827434539795,
219
+ "learning_rate": 7.713498622589533e-06,
220
+ "loss": 0.4831,
221
+ "step": 2900
222
+ },
223
+ {
224
+ "epoch": 1.9071837253655435,
225
+ "grad_norm": 6.582764148712158,
226
+ "learning_rate": 7.2896800169527446e-06,
227
+ "loss": 0.4987,
228
+ "step": 3000
229
+ },
230
+ {
231
+ "epoch": 1.9707565162110616,
232
+ "grad_norm": 4.8419413566589355,
233
+ "learning_rate": 6.865861411315957e-06,
234
+ "loss": 0.4875,
235
+ "step": 3100
236
+ },
237
+ {
238
+ "epoch": 2.0,
239
+ "eval_loss": 0.4961947202682495,
240
+ "eval_runtime": 17.0937,
241
+ "eval_samples_per_second": 368.089,
242
+ "eval_steps_per_second": 11.525,
243
+ "step": 3146
244
+ },
245
+ {
246
+ "epoch": 2.0343293070565798,
247
+ "grad_norm": 4.859919548034668,
248
+ "learning_rate": 6.442042805679169e-06,
249
+ "loss": 0.4774,
250
+ "step": 3200
251
+ },
252
+ {
253
+ "epoch": 2.097902097902098,
254
+ "grad_norm": 10.904428482055664,
255
+ "learning_rate": 6.018224200042382e-06,
256
+ "loss": 0.4427,
257
+ "step": 3300
258
+ },
259
+ {
260
+ "epoch": 2.161474888747616,
261
+ "grad_norm": 9.313108444213867,
262
+ "learning_rate": 5.594405594405595e-06,
263
+ "loss": 0.4337,
264
+ "step": 3400
265
+ },
266
+ {
267
+ "epoch": 2.225047679593134,
268
+ "grad_norm": 21.283798217773438,
269
+ "learning_rate": 5.170586988768808e-06,
270
+ "loss": 0.4418,
271
+ "step": 3500
272
+ },
273
+ {
274
+ "epoch": 2.2886204704386524,
275
+ "grad_norm": 6.696113586425781,
276
+ "learning_rate": 4.74676838313202e-06,
277
+ "loss": 0.4404,
278
+ "step": 3600
279
+ },
280
+ {
281
+ "epoch": 2.3521932612841705,
282
+ "grad_norm": 5.288127899169922,
283
+ "learning_rate": 4.322949777495232e-06,
284
+ "loss": 0.4443,
285
+ "step": 3700
286
+ },
287
+ {
288
+ "epoch": 2.4157660521296886,
289
+ "grad_norm": 9.664108276367188,
290
+ "learning_rate": 3.899131171858445e-06,
291
+ "loss": 0.4379,
292
+ "step": 3800
293
+ },
294
+ {
295
+ "epoch": 2.479338842975207,
296
+ "grad_norm": 9.518948554992676,
297
+ "learning_rate": 3.4753125662216576e-06,
298
+ "loss": 0.4039,
299
+ "step": 3900
300
+ },
301
+ {
302
+ "epoch": 2.542911633820725,
303
+ "grad_norm": 3.7866299152374268,
304
+ "learning_rate": 3.05149396058487e-06,
305
+ "loss": 0.4358,
306
+ "step": 4000
307
+ },
308
+ {
309
+ "epoch": 2.6064844246662426,
310
+ "grad_norm": 9.404533386230469,
311
+ "learning_rate": 2.6276753549480827e-06,
312
+ "loss": 0.4298,
313
+ "step": 4100
314
+ },
315
+ {
316
+ "epoch": 2.6700572155117612,
317
+ "grad_norm": 6.5651021003723145,
318
+ "learning_rate": 2.203856749311295e-06,
319
+ "loss": 0.436,
320
+ "step": 4200
321
+ },
322
+ {
323
+ "epoch": 2.733630006357279,
324
+ "grad_norm": 14.693212509155273,
325
+ "learning_rate": 1.7800381436745072e-06,
326
+ "loss": 0.4605,
327
+ "step": 4300
328
+ },
329
+ {
330
+ "epoch": 2.797202797202797,
331
+ "grad_norm": 8.170985221862793,
332
+ "learning_rate": 1.35621953803772e-06,
333
+ "loss": 0.4334,
334
+ "step": 4400
335
+ },
336
+ {
337
+ "epoch": 2.860775588048315,
338
+ "grad_norm": 9.423282623291016,
339
+ "learning_rate": 9.324009324009325e-07,
340
+ "loss": 0.4228,
341
+ "step": 4500
342
+ },
343
+ {
344
+ "epoch": 2.9243483788938334,
345
+ "grad_norm": 8.17439079284668,
346
+ "learning_rate": 5.08582326764145e-07,
347
+ "loss": 0.4354,
348
+ "step": 4600
349
+ },
350
+ {
351
+ "epoch": 2.9879211697393515,
352
+ "grad_norm": 4.317421913146973,
353
+ "learning_rate": 8.47637211273575e-08,
354
+ "loss": 0.3835,
355
+ "step": 4700
356
+ },
357
+ {
358
+ "epoch": 3.0,
359
+ "eval_loss": 0.5011389255523682,
360
+ "eval_runtime": 17.0986,
361
+ "eval_samples_per_second": 367.984,
362
+ "eval_steps_per_second": 11.521,
363
+ "step": 4719
364
+ }
365
+ ],
366
+ "logging_steps": 100,
367
+ "max_steps": 4719,
368
+ "num_input_tokens_seen": 0,
369
+ "num_train_epochs": 3,
370
+ "save_steps": 500,
371
+ "stateful_callbacks": {
372
+ "TrainerControl": {
373
+ "args": {
374
+ "should_epoch_stop": false,
375
+ "should_evaluate": false,
376
+ "should_log": false,
377
+ "should_save": true,
378
+ "should_training_stop": true
379
+ },
380
+ "attributes": {}
381
+ }
382
+ },
383
+ "total_flos": 3453289607031264.0,
384
+ "train_batch_size": 16,
385
+ "trial_name": null,
386
+ "trial_params": null
387
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff