Cameron Clarke
commited on
Commit
•
97ca996
1
Parent(s):
51ead71
remove model files
Browse files- config.json +0 -24
- optimizer.pt +0 -3
- pytorch_model.bin +0 -3
- scheduler.pt +0 -3
- special_tokens_map.json +0 -1
- tokenizer_config.json +0 -1
- trainer_state.json +0 -1610
- training_args.bin +0 -3
- vocab.txt +0 -0
config.json
DELETED
@@ -1,24 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"_name_or_path": "bert-base-cased",
|
3 |
-
"architectures": [
|
4 |
-
"BertForSequenceClassification"
|
5 |
-
],
|
6 |
-
"attention_probs_dropout_prob": 0.1,
|
7 |
-
"gradient_checkpointing": false,
|
8 |
-
"hidden_act": "gelu",
|
9 |
-
"hidden_dropout_prob": 0.1,
|
10 |
-
"hidden_size": 768,
|
11 |
-
"initializer_range": 0.02,
|
12 |
-
"intermediate_size": 3072,
|
13 |
-
"layer_norm_eps": 1e-12,
|
14 |
-
"max_position_embeddings": 512,
|
15 |
-
"model_type": "bert",
|
16 |
-
"num_attention_heads": 12,
|
17 |
-
"num_hidden_layers": 12,
|
18 |
-
"pad_token_id": 0,
|
19 |
-
"position_embedding_type": "absolute",
|
20 |
-
"transformers_version": "4.5.0",
|
21 |
-
"type_vocab_size": 2,
|
22 |
-
"use_cache": true,
|
23 |
-
"vocab_size": 28996
|
24 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
optimizer.pt
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:d10c2cca23d0f9ac02aeb742a247f9e6db080813e88b49c350e575cb3c616dd0
|
3 |
-
size 866621073
|
|
|
|
|
|
|
|
pytorch_model.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:722a999f794d0cd7ac8ff7fcac2e1b6fea547c5e856d6b31b4720b0c0123286e
|
3 |
-
size 433336585
|
|
|
|
|
|
|
|
scheduler.pt
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:48232fa4997e5070bebd224fec3935c788fb404182f240e4ae46db86885f0144
|
3 |
-
size 623
|
|
|
|
|
|
|
|
special_tokens_map.json
DELETED
@@ -1 +0,0 @@
|
|
1 |
-
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
|
|
|
tokenizer_config.json
DELETED
@@ -1 +0,0 @@
|
|
1 |
-
{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-cased"}
|
|
|
|
trainer_state.json
DELETED
@@ -1,1610 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"best_metric": 0.8993437882326771,
|
3 |
-
"best_model_checkpoint": "/scratch/ccc779/md_gender_convai_binary_model/checkpoint-131438",
|
4 |
-
"epoch": 2.0,
|
5 |
-
"global_step": 131438,
|
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": 1.2135202030247535e-05,
|
13 |
-
"loss": 0.6602,
|
14 |
-
"step": 500
|
15 |
-
},
|
16 |
-
{
|
17 |
-
"epoch": 0.02,
|
18 |
-
"learning_rate": 1.208886253357641e-05,
|
19 |
-
"loss": 0.7994,
|
20 |
-
"step": 1000
|
21 |
-
},
|
22 |
-
{
|
23 |
-
"epoch": 0.02,
|
24 |
-
"learning_rate": 1.2042523036905285e-05,
|
25 |
-
"loss": 0.7787,
|
26 |
-
"step": 1500
|
27 |
-
},
|
28 |
-
{
|
29 |
-
"epoch": 0.03,
|
30 |
-
"learning_rate": 1.199618354023416e-05,
|
31 |
-
"loss": 0.739,
|
32 |
-
"step": 2000
|
33 |
-
},
|
34 |
-
{
|
35 |
-
"epoch": 0.04,
|
36 |
-
"learning_rate": 1.1949844043563036e-05,
|
37 |
-
"loss": 0.7037,
|
38 |
-
"step": 2500
|
39 |
-
},
|
40 |
-
{
|
41 |
-
"epoch": 0.05,
|
42 |
-
"learning_rate": 1.190350454689191e-05,
|
43 |
-
"loss": 0.7881,
|
44 |
-
"step": 3000
|
45 |
-
},
|
46 |
-
{
|
47 |
-
"epoch": 0.05,
|
48 |
-
"learning_rate": 1.1857165050220785e-05,
|
49 |
-
"loss": 0.6767,
|
50 |
-
"step": 3500
|
51 |
-
},
|
52 |
-
{
|
53 |
-
"epoch": 0.06,
|
54 |
-
"learning_rate": 1.181082555354966e-05,
|
55 |
-
"loss": 0.6549,
|
56 |
-
"step": 4000
|
57 |
-
},
|
58 |
-
{
|
59 |
-
"epoch": 0.07,
|
60 |
-
"learning_rate": 1.1764486056878534e-05,
|
61 |
-
"loss": 0.7037,
|
62 |
-
"step": 4500
|
63 |
-
},
|
64 |
-
{
|
65 |
-
"epoch": 0.08,
|
66 |
-
"learning_rate": 1.171814656020741e-05,
|
67 |
-
"loss": 0.673,
|
68 |
-
"step": 5000
|
69 |
-
},
|
70 |
-
{
|
71 |
-
"epoch": 0.08,
|
72 |
-
"learning_rate": 1.1671807063536285e-05,
|
73 |
-
"loss": 0.6841,
|
74 |
-
"step": 5500
|
75 |
-
},
|
76 |
-
{
|
77 |
-
"epoch": 0.09,
|
78 |
-
"learning_rate": 1.162546756686516e-05,
|
79 |
-
"loss": 0.6733,
|
80 |
-
"step": 6000
|
81 |
-
},
|
82 |
-
{
|
83 |
-
"epoch": 0.1,
|
84 |
-
"learning_rate": 1.1579128070194034e-05,
|
85 |
-
"loss": 0.6232,
|
86 |
-
"step": 6500
|
87 |
-
},
|
88 |
-
{
|
89 |
-
"epoch": 0.11,
|
90 |
-
"learning_rate": 1.153278857352291e-05,
|
91 |
-
"loss": 0.6997,
|
92 |
-
"step": 7000
|
93 |
-
},
|
94 |
-
{
|
95 |
-
"epoch": 0.11,
|
96 |
-
"learning_rate": 1.1486449076851784e-05,
|
97 |
-
"loss": 0.699,
|
98 |
-
"step": 7500
|
99 |
-
},
|
100 |
-
{
|
101 |
-
"epoch": 0.12,
|
102 |
-
"learning_rate": 1.144010958018066e-05,
|
103 |
-
"loss": 0.7068,
|
104 |
-
"step": 8000
|
105 |
-
},
|
106 |
-
{
|
107 |
-
"epoch": 0.13,
|
108 |
-
"learning_rate": 1.1393770083509534e-05,
|
109 |
-
"loss": 0.6735,
|
110 |
-
"step": 8500
|
111 |
-
},
|
112 |
-
{
|
113 |
-
"epoch": 0.14,
|
114 |
-
"learning_rate": 1.134743058683841e-05,
|
115 |
-
"loss": 0.6557,
|
116 |
-
"step": 9000
|
117 |
-
},
|
118 |
-
{
|
119 |
-
"epoch": 0.14,
|
120 |
-
"learning_rate": 1.1301091090167285e-05,
|
121 |
-
"loss": 0.642,
|
122 |
-
"step": 9500
|
123 |
-
},
|
124 |
-
{
|
125 |
-
"epoch": 0.15,
|
126 |
-
"learning_rate": 1.1254751593496159e-05,
|
127 |
-
"loss": 0.7834,
|
128 |
-
"step": 10000
|
129 |
-
},
|
130 |
-
{
|
131 |
-
"epoch": 0.16,
|
132 |
-
"learning_rate": 1.1208412096825035e-05,
|
133 |
-
"loss": 0.6036,
|
134 |
-
"step": 10500
|
135 |
-
},
|
136 |
-
{
|
137 |
-
"epoch": 0.17,
|
138 |
-
"learning_rate": 1.116207260015391e-05,
|
139 |
-
"loss": 0.6158,
|
140 |
-
"step": 11000
|
141 |
-
},
|
142 |
-
{
|
143 |
-
"epoch": 0.17,
|
144 |
-
"learning_rate": 1.1115733103482786e-05,
|
145 |
-
"loss": 0.6603,
|
146 |
-
"step": 11500
|
147 |
-
},
|
148 |
-
{
|
149 |
-
"epoch": 0.18,
|
150 |
-
"learning_rate": 1.106939360681166e-05,
|
151 |
-
"loss": 0.6956,
|
152 |
-
"step": 12000
|
153 |
-
},
|
154 |
-
{
|
155 |
-
"epoch": 0.19,
|
156 |
-
"learning_rate": 1.1023054110140535e-05,
|
157 |
-
"loss": 0.6401,
|
158 |
-
"step": 12500
|
159 |
-
},
|
160 |
-
{
|
161 |
-
"epoch": 0.2,
|
162 |
-
"learning_rate": 1.0976714613469409e-05,
|
163 |
-
"loss": 0.6084,
|
164 |
-
"step": 13000
|
165 |
-
},
|
166 |
-
{
|
167 |
-
"epoch": 0.21,
|
168 |
-
"learning_rate": 1.0930375116798284e-05,
|
169 |
-
"loss": 0.6862,
|
170 |
-
"step": 13500
|
171 |
-
},
|
172 |
-
{
|
173 |
-
"epoch": 0.21,
|
174 |
-
"learning_rate": 1.088403562012716e-05,
|
175 |
-
"loss": 0.6216,
|
176 |
-
"step": 14000
|
177 |
-
},
|
178 |
-
{
|
179 |
-
"epoch": 0.22,
|
180 |
-
"learning_rate": 1.0837696123456035e-05,
|
181 |
-
"loss": 0.6424,
|
182 |
-
"step": 14500
|
183 |
-
},
|
184 |
-
{
|
185 |
-
"epoch": 0.23,
|
186 |
-
"learning_rate": 1.079135662678491e-05,
|
187 |
-
"loss": 0.6291,
|
188 |
-
"step": 15000
|
189 |
-
},
|
190 |
-
{
|
191 |
-
"epoch": 0.24,
|
192 |
-
"learning_rate": 1.0745017130113784e-05,
|
193 |
-
"loss": 0.6556,
|
194 |
-
"step": 15500
|
195 |
-
},
|
196 |
-
{
|
197 |
-
"epoch": 0.24,
|
198 |
-
"learning_rate": 1.069867763344266e-05,
|
199 |
-
"loss": 0.5622,
|
200 |
-
"step": 16000
|
201 |
-
},
|
202 |
-
{
|
203 |
-
"epoch": 0.25,
|
204 |
-
"learning_rate": 1.0652338136771533e-05,
|
205 |
-
"loss": 0.548,
|
206 |
-
"step": 16500
|
207 |
-
},
|
208 |
-
{
|
209 |
-
"epoch": 0.26,
|
210 |
-
"learning_rate": 1.0605998640100409e-05,
|
211 |
-
"loss": 0.6619,
|
212 |
-
"step": 17000
|
213 |
-
},
|
214 |
-
{
|
215 |
-
"epoch": 0.27,
|
216 |
-
"learning_rate": 1.0559659143429284e-05,
|
217 |
-
"loss": 0.6335,
|
218 |
-
"step": 17500
|
219 |
-
},
|
220 |
-
{
|
221 |
-
"epoch": 0.27,
|
222 |
-
"learning_rate": 1.051331964675816e-05,
|
223 |
-
"loss": 0.6125,
|
224 |
-
"step": 18000
|
225 |
-
},
|
226 |
-
{
|
227 |
-
"epoch": 0.28,
|
228 |
-
"learning_rate": 1.0466980150087035e-05,
|
229 |
-
"loss": 0.6169,
|
230 |
-
"step": 18500
|
231 |
-
},
|
232 |
-
{
|
233 |
-
"epoch": 0.29,
|
234 |
-
"learning_rate": 1.0420640653415909e-05,
|
235 |
-
"loss": 0.6318,
|
236 |
-
"step": 19000
|
237 |
-
},
|
238 |
-
{
|
239 |
-
"epoch": 0.3,
|
240 |
-
"learning_rate": 1.0374301156744785e-05,
|
241 |
-
"loss": 0.5748,
|
242 |
-
"step": 19500
|
243 |
-
},
|
244 |
-
{
|
245 |
-
"epoch": 0.3,
|
246 |
-
"learning_rate": 1.0327961660073658e-05,
|
247 |
-
"loss": 0.5709,
|
248 |
-
"step": 20000
|
249 |
-
},
|
250 |
-
{
|
251 |
-
"epoch": 0.31,
|
252 |
-
"learning_rate": 1.0281622163402535e-05,
|
253 |
-
"loss": 0.6047,
|
254 |
-
"step": 20500
|
255 |
-
},
|
256 |
-
{
|
257 |
-
"epoch": 0.32,
|
258 |
-
"learning_rate": 1.023528266673141e-05,
|
259 |
-
"loss": 0.5993,
|
260 |
-
"step": 21000
|
261 |
-
},
|
262 |
-
{
|
263 |
-
"epoch": 0.33,
|
264 |
-
"learning_rate": 1.0188943170060285e-05,
|
265 |
-
"loss": 0.6734,
|
266 |
-
"step": 21500
|
267 |
-
},
|
268 |
-
{
|
269 |
-
"epoch": 0.33,
|
270 |
-
"learning_rate": 1.0142603673389158e-05,
|
271 |
-
"loss": 0.6137,
|
272 |
-
"step": 22000
|
273 |
-
},
|
274 |
-
{
|
275 |
-
"epoch": 0.34,
|
276 |
-
"learning_rate": 1.0096264176718034e-05,
|
277 |
-
"loss": 0.5737,
|
278 |
-
"step": 22500
|
279 |
-
},
|
280 |
-
{
|
281 |
-
"epoch": 0.35,
|
282 |
-
"learning_rate": 1.004992468004691e-05,
|
283 |
-
"loss": 0.5608,
|
284 |
-
"step": 23000
|
285 |
-
},
|
286 |
-
{
|
287 |
-
"epoch": 0.36,
|
288 |
-
"learning_rate": 1.0003585183375783e-05,
|
289 |
-
"loss": 0.6101,
|
290 |
-
"step": 23500
|
291 |
-
},
|
292 |
-
{
|
293 |
-
"epoch": 0.37,
|
294 |
-
"learning_rate": 9.95724568670466e-06,
|
295 |
-
"loss": 0.6001,
|
296 |
-
"step": 24000
|
297 |
-
},
|
298 |
-
{
|
299 |
-
"epoch": 0.37,
|
300 |
-
"learning_rate": 9.910906190033534e-06,
|
301 |
-
"loss": 0.5991,
|
302 |
-
"step": 24500
|
303 |
-
},
|
304 |
-
{
|
305 |
-
"epoch": 0.38,
|
306 |
-
"learning_rate": 9.86456669336241e-06,
|
307 |
-
"loss": 0.6062,
|
308 |
-
"step": 25000
|
309 |
-
},
|
310 |
-
{
|
311 |
-
"epoch": 0.39,
|
312 |
-
"learning_rate": 9.818227196691283e-06,
|
313 |
-
"loss": 0.6098,
|
314 |
-
"step": 25500
|
315 |
-
},
|
316 |
-
{
|
317 |
-
"epoch": 0.4,
|
318 |
-
"learning_rate": 9.771887700020159e-06,
|
319 |
-
"loss": 0.6106,
|
320 |
-
"step": 26000
|
321 |
-
},
|
322 |
-
{
|
323 |
-
"epoch": 0.4,
|
324 |
-
"learning_rate": 9.725548203349034e-06,
|
325 |
-
"loss": 0.61,
|
326 |
-
"step": 26500
|
327 |
-
},
|
328 |
-
{
|
329 |
-
"epoch": 0.41,
|
330 |
-
"learning_rate": 9.67920870667791e-06,
|
331 |
-
"loss": 0.6177,
|
332 |
-
"step": 27000
|
333 |
-
},
|
334 |
-
{
|
335 |
-
"epoch": 0.42,
|
336 |
-
"learning_rate": 9.632869210006785e-06,
|
337 |
-
"loss": 0.5629,
|
338 |
-
"step": 27500
|
339 |
-
},
|
340 |
-
{
|
341 |
-
"epoch": 0.43,
|
342 |
-
"learning_rate": 9.586529713335659e-06,
|
343 |
-
"loss": 0.6405,
|
344 |
-
"step": 28000
|
345 |
-
},
|
346 |
-
{
|
347 |
-
"epoch": 0.43,
|
348 |
-
"learning_rate": 9.540190216664534e-06,
|
349 |
-
"loss": 0.6154,
|
350 |
-
"step": 28500
|
351 |
-
},
|
352 |
-
{
|
353 |
-
"epoch": 0.44,
|
354 |
-
"learning_rate": 9.493850719993408e-06,
|
355 |
-
"loss": 0.6146,
|
356 |
-
"step": 29000
|
357 |
-
},
|
358 |
-
{
|
359 |
-
"epoch": 0.45,
|
360 |
-
"learning_rate": 9.447511223322284e-06,
|
361 |
-
"loss": 0.633,
|
362 |
-
"step": 29500
|
363 |
-
},
|
364 |
-
{
|
365 |
-
"epoch": 0.46,
|
366 |
-
"learning_rate": 9.401171726651159e-06,
|
367 |
-
"loss": 0.6552,
|
368 |
-
"step": 30000
|
369 |
-
},
|
370 |
-
{
|
371 |
-
"epoch": 0.46,
|
372 |
-
"learning_rate": 9.354832229980035e-06,
|
373 |
-
"loss": 0.5682,
|
374 |
-
"step": 30500
|
375 |
-
},
|
376 |
-
{
|
377 |
-
"epoch": 0.47,
|
378 |
-
"learning_rate": 9.308492733308908e-06,
|
379 |
-
"loss": 0.5061,
|
380 |
-
"step": 31000
|
381 |
-
},
|
382 |
-
{
|
383 |
-
"epoch": 0.48,
|
384 |
-
"learning_rate": 9.262153236637784e-06,
|
385 |
-
"loss": 0.6001,
|
386 |
-
"step": 31500
|
387 |
-
},
|
388 |
-
{
|
389 |
-
"epoch": 0.49,
|
390 |
-
"learning_rate": 9.21581373996666e-06,
|
391 |
-
"loss": 0.5967,
|
392 |
-
"step": 32000
|
393 |
-
},
|
394 |
-
{
|
395 |
-
"epoch": 0.49,
|
396 |
-
"learning_rate": 9.169474243295533e-06,
|
397 |
-
"loss": 0.6021,
|
398 |
-
"step": 32500
|
399 |
-
},
|
400 |
-
{
|
401 |
-
"epoch": 0.5,
|
402 |
-
"learning_rate": 9.12313474662441e-06,
|
403 |
-
"loss": 0.4967,
|
404 |
-
"step": 33000
|
405 |
-
},
|
406 |
-
{
|
407 |
-
"epoch": 0.51,
|
408 |
-
"learning_rate": 9.076795249953284e-06,
|
409 |
-
"loss": 0.6182,
|
410 |
-
"step": 33500
|
411 |
-
},
|
412 |
-
{
|
413 |
-
"epoch": 0.52,
|
414 |
-
"learning_rate": 9.03045575328216e-06,
|
415 |
-
"loss": 0.5827,
|
416 |
-
"step": 34000
|
417 |
-
},
|
418 |
-
{
|
419 |
-
"epoch": 0.52,
|
420 |
-
"learning_rate": 8.984116256611033e-06,
|
421 |
-
"loss": 0.5692,
|
422 |
-
"step": 34500
|
423 |
-
},
|
424 |
-
{
|
425 |
-
"epoch": 0.53,
|
426 |
-
"learning_rate": 8.937776759939909e-06,
|
427 |
-
"loss": 0.5936,
|
428 |
-
"step": 35000
|
429 |
-
},
|
430 |
-
{
|
431 |
-
"epoch": 0.54,
|
432 |
-
"learning_rate": 8.891437263268784e-06,
|
433 |
-
"loss": 0.6002,
|
434 |
-
"step": 35500
|
435 |
-
},
|
436 |
-
{
|
437 |
-
"epoch": 0.55,
|
438 |
-
"learning_rate": 8.845097766597658e-06,
|
439 |
-
"loss": 0.5215,
|
440 |
-
"step": 36000
|
441 |
-
},
|
442 |
-
{
|
443 |
-
"epoch": 0.56,
|
444 |
-
"learning_rate": 8.798758269926535e-06,
|
445 |
-
"loss": 0.605,
|
446 |
-
"step": 36500
|
447 |
-
},
|
448 |
-
{
|
449 |
-
"epoch": 0.56,
|
450 |
-
"learning_rate": 8.752418773255409e-06,
|
451 |
-
"loss": 0.6066,
|
452 |
-
"step": 37000
|
453 |
-
},
|
454 |
-
{
|
455 |
-
"epoch": 0.57,
|
456 |
-
"learning_rate": 8.706079276584284e-06,
|
457 |
-
"loss": 0.5443,
|
458 |
-
"step": 37500
|
459 |
-
},
|
460 |
-
{
|
461 |
-
"epoch": 0.58,
|
462 |
-
"learning_rate": 8.659739779913158e-06,
|
463 |
-
"loss": 0.6155,
|
464 |
-
"step": 38000
|
465 |
-
},
|
466 |
-
{
|
467 |
-
"epoch": 0.59,
|
468 |
-
"learning_rate": 8.613400283242034e-06,
|
469 |
-
"loss": 0.5728,
|
470 |
-
"step": 38500
|
471 |
-
},
|
472 |
-
{
|
473 |
-
"epoch": 0.59,
|
474 |
-
"learning_rate": 8.567060786570907e-06,
|
475 |
-
"loss": 0.5995,
|
476 |
-
"step": 39000
|
477 |
-
},
|
478 |
-
{
|
479 |
-
"epoch": 0.6,
|
480 |
-
"learning_rate": 8.520721289899785e-06,
|
481 |
-
"loss": 0.6017,
|
482 |
-
"step": 39500
|
483 |
-
},
|
484 |
-
{
|
485 |
-
"epoch": 0.61,
|
486 |
-
"learning_rate": 8.474381793228658e-06,
|
487 |
-
"loss": 0.5758,
|
488 |
-
"step": 40000
|
489 |
-
},
|
490 |
-
{
|
491 |
-
"epoch": 0.62,
|
492 |
-
"learning_rate": 8.428042296557534e-06,
|
493 |
-
"loss": 0.6072,
|
494 |
-
"step": 40500
|
495 |
-
},
|
496 |
-
{
|
497 |
-
"epoch": 0.62,
|
498 |
-
"learning_rate": 8.38170279988641e-06,
|
499 |
-
"loss": 0.5563,
|
500 |
-
"step": 41000
|
501 |
-
},
|
502 |
-
{
|
503 |
-
"epoch": 0.63,
|
504 |
-
"learning_rate": 8.335363303215283e-06,
|
505 |
-
"loss": 0.6322,
|
506 |
-
"step": 41500
|
507 |
-
},
|
508 |
-
{
|
509 |
-
"epoch": 0.64,
|
510 |
-
"learning_rate": 8.289023806544158e-06,
|
511 |
-
"loss": 0.5698,
|
512 |
-
"step": 42000
|
513 |
-
},
|
514 |
-
{
|
515 |
-
"epoch": 0.65,
|
516 |
-
"learning_rate": 8.242684309873034e-06,
|
517 |
-
"loss": 0.6107,
|
518 |
-
"step": 42500
|
519 |
-
},
|
520 |
-
{
|
521 |
-
"epoch": 0.65,
|
522 |
-
"learning_rate": 8.19634481320191e-06,
|
523 |
-
"loss": 0.5788,
|
524 |
-
"step": 43000
|
525 |
-
},
|
526 |
-
{
|
527 |
-
"epoch": 0.66,
|
528 |
-
"learning_rate": 8.150005316530783e-06,
|
529 |
-
"loss": 0.5403,
|
530 |
-
"step": 43500
|
531 |
-
},
|
532 |
-
{
|
533 |
-
"epoch": 0.67,
|
534 |
-
"learning_rate": 8.103665819859659e-06,
|
535 |
-
"loss": 0.5333,
|
536 |
-
"step": 44000
|
537 |
-
},
|
538 |
-
{
|
539 |
-
"epoch": 0.68,
|
540 |
-
"learning_rate": 8.057326323188534e-06,
|
541 |
-
"loss": 0.5569,
|
542 |
-
"step": 44500
|
543 |
-
},
|
544 |
-
{
|
545 |
-
"epoch": 0.68,
|
546 |
-
"learning_rate": 8.010986826517408e-06,
|
547 |
-
"loss": 0.5639,
|
548 |
-
"step": 45000
|
549 |
-
},
|
550 |
-
{
|
551 |
-
"epoch": 0.69,
|
552 |
-
"learning_rate": 7.964647329846283e-06,
|
553 |
-
"loss": 0.5301,
|
554 |
-
"step": 45500
|
555 |
-
},
|
556 |
-
{
|
557 |
-
"epoch": 0.7,
|
558 |
-
"learning_rate": 7.918307833175159e-06,
|
559 |
-
"loss": 0.5699,
|
560 |
-
"step": 46000
|
561 |
-
},
|
562 |
-
{
|
563 |
-
"epoch": 0.71,
|
564 |
-
"learning_rate": 7.871968336504034e-06,
|
565 |
-
"loss": 0.5564,
|
566 |
-
"step": 46500
|
567 |
-
},
|
568 |
-
{
|
569 |
-
"epoch": 0.72,
|
570 |
-
"learning_rate": 7.825628839832908e-06,
|
571 |
-
"loss": 0.6376,
|
572 |
-
"step": 47000
|
573 |
-
},
|
574 |
-
{
|
575 |
-
"epoch": 0.72,
|
576 |
-
"learning_rate": 7.779289343161783e-06,
|
577 |
-
"loss": 0.6091,
|
578 |
-
"step": 47500
|
579 |
-
},
|
580 |
-
{
|
581 |
-
"epoch": 0.73,
|
582 |
-
"learning_rate": 7.732949846490657e-06,
|
583 |
-
"loss": 0.5098,
|
584 |
-
"step": 48000
|
585 |
-
},
|
586 |
-
{
|
587 |
-
"epoch": 0.74,
|
588 |
-
"learning_rate": 7.686610349819533e-06,
|
589 |
-
"loss": 0.5479,
|
590 |
-
"step": 48500
|
591 |
-
},
|
592 |
-
{
|
593 |
-
"epoch": 0.75,
|
594 |
-
"learning_rate": 7.640270853148408e-06,
|
595 |
-
"loss": 0.5418,
|
596 |
-
"step": 49000
|
597 |
-
},
|
598 |
-
{
|
599 |
-
"epoch": 0.75,
|
600 |
-
"learning_rate": 7.593931356477284e-06,
|
601 |
-
"loss": 0.5351,
|
602 |
-
"step": 49500
|
603 |
-
},
|
604 |
-
{
|
605 |
-
"epoch": 0.76,
|
606 |
-
"learning_rate": 7.547591859806158e-06,
|
607 |
-
"loss": 0.5245,
|
608 |
-
"step": 50000
|
609 |
-
},
|
610 |
-
{
|
611 |
-
"epoch": 0.77,
|
612 |
-
"learning_rate": 7.501252363135033e-06,
|
613 |
-
"loss": 0.5558,
|
614 |
-
"step": 50500
|
615 |
-
},
|
616 |
-
{
|
617 |
-
"epoch": 0.78,
|
618 |
-
"learning_rate": 7.4549128664639075e-06,
|
619 |
-
"loss": 0.5626,
|
620 |
-
"step": 51000
|
621 |
-
},
|
622 |
-
{
|
623 |
-
"epoch": 0.78,
|
624 |
-
"learning_rate": 7.408573369792783e-06,
|
625 |
-
"loss": 0.4787,
|
626 |
-
"step": 51500
|
627 |
-
},
|
628 |
-
{
|
629 |
-
"epoch": 0.79,
|
630 |
-
"learning_rate": 7.3622338731216584e-06,
|
631 |
-
"loss": 0.5866,
|
632 |
-
"step": 52000
|
633 |
-
},
|
634 |
-
{
|
635 |
-
"epoch": 0.8,
|
636 |
-
"learning_rate": 7.315894376450534e-06,
|
637 |
-
"loss": 0.4853,
|
638 |
-
"step": 52500
|
639 |
-
},
|
640 |
-
{
|
641 |
-
"epoch": 0.81,
|
642 |
-
"learning_rate": 7.2695548797794085e-06,
|
643 |
-
"loss": 0.572,
|
644 |
-
"step": 53000
|
645 |
-
},
|
646 |
-
{
|
647 |
-
"epoch": 0.81,
|
648 |
-
"learning_rate": 7.223215383108283e-06,
|
649 |
-
"loss": 0.5298,
|
650 |
-
"step": 53500
|
651 |
-
},
|
652 |
-
{
|
653 |
-
"epoch": 0.82,
|
654 |
-
"learning_rate": 7.176875886437158e-06,
|
655 |
-
"loss": 0.6197,
|
656 |
-
"step": 54000
|
657 |
-
},
|
658 |
-
{
|
659 |
-
"epoch": 0.83,
|
660 |
-
"learning_rate": 7.130536389766032e-06,
|
661 |
-
"loss": 0.5327,
|
662 |
-
"step": 54500
|
663 |
-
},
|
664 |
-
{
|
665 |
-
"epoch": 0.84,
|
666 |
-
"learning_rate": 7.084196893094909e-06,
|
667 |
-
"loss": 0.5813,
|
668 |
-
"step": 55000
|
669 |
-
},
|
670 |
-
{
|
671 |
-
"epoch": 0.84,
|
672 |
-
"learning_rate": 7.037857396423783e-06,
|
673 |
-
"loss": 0.5529,
|
674 |
-
"step": 55500
|
675 |
-
},
|
676 |
-
{
|
677 |
-
"epoch": 0.85,
|
678 |
-
"learning_rate": 6.991517899752658e-06,
|
679 |
-
"loss": 0.5726,
|
680 |
-
"step": 56000
|
681 |
-
},
|
682 |
-
{
|
683 |
-
"epoch": 0.86,
|
684 |
-
"learning_rate": 6.945178403081533e-06,
|
685 |
-
"loss": 0.4898,
|
686 |
-
"step": 56500
|
687 |
-
},
|
688 |
-
{
|
689 |
-
"epoch": 0.87,
|
690 |
-
"learning_rate": 6.898838906410408e-06,
|
691 |
-
"loss": 0.5598,
|
692 |
-
"step": 57000
|
693 |
-
},
|
694 |
-
{
|
695 |
-
"epoch": 0.87,
|
696 |
-
"learning_rate": 6.852499409739283e-06,
|
697 |
-
"loss": 0.5537,
|
698 |
-
"step": 57500
|
699 |
-
},
|
700 |
-
{
|
701 |
-
"epoch": 0.88,
|
702 |
-
"learning_rate": 6.806159913068157e-06,
|
703 |
-
"loss": 0.6059,
|
704 |
-
"step": 58000
|
705 |
-
},
|
706 |
-
{
|
707 |
-
"epoch": 0.89,
|
708 |
-
"learning_rate": 6.7598204163970336e-06,
|
709 |
-
"loss": 0.4777,
|
710 |
-
"step": 58500
|
711 |
-
},
|
712 |
-
{
|
713 |
-
"epoch": 0.9,
|
714 |
-
"learning_rate": 6.713480919725908e-06,
|
715 |
-
"loss": 0.5659,
|
716 |
-
"step": 59000
|
717 |
-
},
|
718 |
-
{
|
719 |
-
"epoch": 0.91,
|
720 |
-
"learning_rate": 6.667141423054783e-06,
|
721 |
-
"loss": 0.5679,
|
722 |
-
"step": 59500
|
723 |
-
},
|
724 |
-
{
|
725 |
-
"epoch": 0.91,
|
726 |
-
"learning_rate": 6.6208019263836574e-06,
|
727 |
-
"loss": 0.5418,
|
728 |
-
"step": 60000
|
729 |
-
},
|
730 |
-
{
|
731 |
-
"epoch": 0.92,
|
732 |
-
"learning_rate": 6.574462429712533e-06,
|
733 |
-
"loss": 0.5393,
|
734 |
-
"step": 60500
|
735 |
-
},
|
736 |
-
{
|
737 |
-
"epoch": 0.93,
|
738 |
-
"learning_rate": 6.5281229330414075e-06,
|
739 |
-
"loss": 0.5489,
|
740 |
-
"step": 61000
|
741 |
-
},
|
742 |
-
{
|
743 |
-
"epoch": 0.94,
|
744 |
-
"learning_rate": 6.481783436370284e-06,
|
745 |
-
"loss": 0.4798,
|
746 |
-
"step": 61500
|
747 |
-
},
|
748 |
-
{
|
749 |
-
"epoch": 0.94,
|
750 |
-
"learning_rate": 6.4354439396991584e-06,
|
751 |
-
"loss": 0.5113,
|
752 |
-
"step": 62000
|
753 |
-
},
|
754 |
-
{
|
755 |
-
"epoch": 0.95,
|
756 |
-
"learning_rate": 6.389104443028033e-06,
|
757 |
-
"loss": 0.6167,
|
758 |
-
"step": 62500
|
759 |
-
},
|
760 |
-
{
|
761 |
-
"epoch": 0.96,
|
762 |
-
"learning_rate": 6.342764946356908e-06,
|
763 |
-
"loss": 0.4932,
|
764 |
-
"step": 63000
|
765 |
-
},
|
766 |
-
{
|
767 |
-
"epoch": 0.97,
|
768 |
-
"learning_rate": 6.296425449685782e-06,
|
769 |
-
"loss": 0.5314,
|
770 |
-
"step": 63500
|
771 |
-
},
|
772 |
-
{
|
773 |
-
"epoch": 0.97,
|
774 |
-
"learning_rate": 6.250085953014657e-06,
|
775 |
-
"loss": 0.5689,
|
776 |
-
"step": 64000
|
777 |
-
},
|
778 |
-
{
|
779 |
-
"epoch": 0.98,
|
780 |
-
"learning_rate": 6.203746456343533e-06,
|
781 |
-
"loss": 0.5066,
|
782 |
-
"step": 64500
|
783 |
-
},
|
784 |
-
{
|
785 |
-
"epoch": 0.99,
|
786 |
-
"learning_rate": 6.157406959672408e-06,
|
787 |
-
"loss": 0.5767,
|
788 |
-
"step": 65000
|
789 |
-
},
|
790 |
-
{
|
791 |
-
"epoch": 1.0,
|
792 |
-
"learning_rate": 6.111067463001283e-06,
|
793 |
-
"loss": 0.5411,
|
794 |
-
"step": 65500
|
795 |
-
},
|
796 |
-
{
|
797 |
-
"epoch": 1.0,
|
798 |
-
"eval_accuracy": 0.8742468914241764,
|
799 |
-
"eval_f1": 0.8908908908908909,
|
800 |
-
"eval_loss": 0.5635416507720947,
|
801 |
-
"eval_precision": 0.8884205856255546,
|
802 |
-
"eval_recall": 0.893374972116886,
|
803 |
-
"eval_runtime": 30.4301,
|
804 |
-
"eval_samples_per_second": 256.358,
|
805 |
-
"step": 65719
|
806 |
-
},
|
807 |
-
{
|
808 |
-
"epoch": 1.0,
|
809 |
-
"learning_rate": 6.064727966330158e-06,
|
810 |
-
"loss": 0.49,
|
811 |
-
"step": 66000
|
812 |
-
},
|
813 |
-
{
|
814 |
-
"epoch": 1.01,
|
815 |
-
"learning_rate": 6.0183884696590325e-06,
|
816 |
-
"loss": 0.3784,
|
817 |
-
"step": 66500
|
818 |
-
},
|
819 |
-
{
|
820 |
-
"epoch": 1.02,
|
821 |
-
"learning_rate": 5.972048972987908e-06,
|
822 |
-
"loss": 0.3905,
|
823 |
-
"step": 67000
|
824 |
-
},
|
825 |
-
{
|
826 |
-
"epoch": 1.03,
|
827 |
-
"learning_rate": 5.925709476316783e-06,
|
828 |
-
"loss": 0.4364,
|
829 |
-
"step": 67500
|
830 |
-
},
|
831 |
-
{
|
832 |
-
"epoch": 1.03,
|
833 |
-
"learning_rate": 5.879369979645657e-06,
|
834 |
-
"loss": 0.4364,
|
835 |
-
"step": 68000
|
836 |
-
},
|
837 |
-
{
|
838 |
-
"epoch": 1.04,
|
839 |
-
"learning_rate": 5.833030482974533e-06,
|
840 |
-
"loss": 0.3572,
|
841 |
-
"step": 68500
|
842 |
-
},
|
843 |
-
{
|
844 |
-
"epoch": 1.05,
|
845 |
-
"learning_rate": 5.786690986303407e-06,
|
846 |
-
"loss": 0.3814,
|
847 |
-
"step": 69000
|
848 |
-
},
|
849 |
-
{
|
850 |
-
"epoch": 1.06,
|
851 |
-
"learning_rate": 5.740351489632283e-06,
|
852 |
-
"loss": 0.3181,
|
853 |
-
"step": 69500
|
854 |
-
},
|
855 |
-
{
|
856 |
-
"epoch": 1.07,
|
857 |
-
"learning_rate": 5.694011992961158e-06,
|
858 |
-
"loss": 0.4026,
|
859 |
-
"step": 70000
|
860 |
-
},
|
861 |
-
{
|
862 |
-
"epoch": 1.07,
|
863 |
-
"learning_rate": 5.647672496290033e-06,
|
864 |
-
"loss": 0.3932,
|
865 |
-
"step": 70500
|
866 |
-
},
|
867 |
-
{
|
868 |
-
"epoch": 1.08,
|
869 |
-
"learning_rate": 5.6013329996189075e-06,
|
870 |
-
"loss": 0.4452,
|
871 |
-
"step": 71000
|
872 |
-
},
|
873 |
-
{
|
874 |
-
"epoch": 1.09,
|
875 |
-
"learning_rate": 5.554993502947783e-06,
|
876 |
-
"loss": 0.4005,
|
877 |
-
"step": 71500
|
878 |
-
},
|
879 |
-
{
|
880 |
-
"epoch": 1.1,
|
881 |
-
"learning_rate": 5.508654006276658e-06,
|
882 |
-
"loss": 0.4221,
|
883 |
-
"step": 72000
|
884 |
-
},
|
885 |
-
{
|
886 |
-
"epoch": 1.1,
|
887 |
-
"learning_rate": 5.462314509605532e-06,
|
888 |
-
"loss": 0.3841,
|
889 |
-
"step": 72500
|
890 |
-
},
|
891 |
-
{
|
892 |
-
"epoch": 1.11,
|
893 |
-
"learning_rate": 5.415975012934407e-06,
|
894 |
-
"loss": 0.3099,
|
895 |
-
"step": 73000
|
896 |
-
},
|
897 |
-
{
|
898 |
-
"epoch": 1.12,
|
899 |
-
"learning_rate": 5.369635516263282e-06,
|
900 |
-
"loss": 0.3968,
|
901 |
-
"step": 73500
|
902 |
-
},
|
903 |
-
{
|
904 |
-
"epoch": 1.13,
|
905 |
-
"learning_rate": 5.323296019592158e-06,
|
906 |
-
"loss": 0.3942,
|
907 |
-
"step": 74000
|
908 |
-
},
|
909 |
-
{
|
910 |
-
"epoch": 1.13,
|
911 |
-
"learning_rate": 5.276956522921032e-06,
|
912 |
-
"loss": 0.4086,
|
913 |
-
"step": 74500
|
914 |
-
},
|
915 |
-
{
|
916 |
-
"epoch": 1.14,
|
917 |
-
"learning_rate": 5.230617026249908e-06,
|
918 |
-
"loss": 0.3567,
|
919 |
-
"step": 75000
|
920 |
-
},
|
921 |
-
{
|
922 |
-
"epoch": 1.15,
|
923 |
-
"learning_rate": 5.1842775295787825e-06,
|
924 |
-
"loss": 0.4006,
|
925 |
-
"step": 75500
|
926 |
-
},
|
927 |
-
{
|
928 |
-
"epoch": 1.16,
|
929 |
-
"learning_rate": 5.137938032907657e-06,
|
930 |
-
"loss": 0.3688,
|
931 |
-
"step": 76000
|
932 |
-
},
|
933 |
-
{
|
934 |
-
"epoch": 1.16,
|
935 |
-
"learning_rate": 5.0915985362365325e-06,
|
936 |
-
"loss": 0.4031,
|
937 |
-
"step": 76500
|
938 |
-
},
|
939 |
-
{
|
940 |
-
"epoch": 1.17,
|
941 |
-
"learning_rate": 5.045259039565407e-06,
|
942 |
-
"loss": 0.3325,
|
943 |
-
"step": 77000
|
944 |
-
},
|
945 |
-
{
|
946 |
-
"epoch": 1.18,
|
947 |
-
"learning_rate": 4.998919542894282e-06,
|
948 |
-
"loss": 0.3927,
|
949 |
-
"step": 77500
|
950 |
-
},
|
951 |
-
{
|
952 |
-
"epoch": 1.19,
|
953 |
-
"learning_rate": 4.952580046223157e-06,
|
954 |
-
"loss": 0.3841,
|
955 |
-
"step": 78000
|
956 |
-
},
|
957 |
-
{
|
958 |
-
"epoch": 1.19,
|
959 |
-
"learning_rate": 4.906240549552033e-06,
|
960 |
-
"loss": 0.3571,
|
961 |
-
"step": 78500
|
962 |
-
},
|
963 |
-
{
|
964 |
-
"epoch": 1.2,
|
965 |
-
"learning_rate": 4.859901052880907e-06,
|
966 |
-
"loss": 0.3655,
|
967 |
-
"step": 79000
|
968 |
-
},
|
969 |
-
{
|
970 |
-
"epoch": 1.21,
|
971 |
-
"learning_rate": 4.813561556209783e-06,
|
972 |
-
"loss": 0.4454,
|
973 |
-
"step": 79500
|
974 |
-
},
|
975 |
-
{
|
976 |
-
"epoch": 1.22,
|
977 |
-
"learning_rate": 4.767222059538657e-06,
|
978 |
-
"loss": 0.4193,
|
979 |
-
"step": 80000
|
980 |
-
},
|
981 |
-
{
|
982 |
-
"epoch": 1.22,
|
983 |
-
"learning_rate": 4.720882562867532e-06,
|
984 |
-
"loss": 0.4013,
|
985 |
-
"step": 80500
|
986 |
-
},
|
987 |
-
{
|
988 |
-
"epoch": 1.23,
|
989 |
-
"learning_rate": 4.6745430661964075e-06,
|
990 |
-
"loss": 0.3883,
|
991 |
-
"step": 81000
|
992 |
-
},
|
993 |
-
{
|
994 |
-
"epoch": 1.24,
|
995 |
-
"learning_rate": 4.628203569525282e-06,
|
996 |
-
"loss": 0.3564,
|
997 |
-
"step": 81500
|
998 |
-
},
|
999 |
-
{
|
1000 |
-
"epoch": 1.25,
|
1001 |
-
"learning_rate": 4.581864072854157e-06,
|
1002 |
-
"loss": 0.4217,
|
1003 |
-
"step": 82000
|
1004 |
-
},
|
1005 |
-
{
|
1006 |
-
"epoch": 1.26,
|
1007 |
-
"learning_rate": 4.535524576183032e-06,
|
1008 |
-
"loss": 0.4001,
|
1009 |
-
"step": 82500
|
1010 |
-
},
|
1011 |
-
{
|
1012 |
-
"epoch": 1.26,
|
1013 |
-
"learning_rate": 4.489185079511908e-06,
|
1014 |
-
"loss": 0.409,
|
1015 |
-
"step": 83000
|
1016 |
-
},
|
1017 |
-
{
|
1018 |
-
"epoch": 1.27,
|
1019 |
-
"learning_rate": 4.442845582840782e-06,
|
1020 |
-
"loss": 0.3639,
|
1021 |
-
"step": 83500
|
1022 |
-
},
|
1023 |
-
{
|
1024 |
-
"epoch": 1.28,
|
1025 |
-
"learning_rate": 4.396506086169657e-06,
|
1026 |
-
"loss": 0.4244,
|
1027 |
-
"step": 84000
|
1028 |
-
},
|
1029 |
-
{
|
1030 |
-
"epoch": 1.29,
|
1031 |
-
"learning_rate": 4.350166589498532e-06,
|
1032 |
-
"loss": 0.3756,
|
1033 |
-
"step": 84500
|
1034 |
-
},
|
1035 |
-
{
|
1036 |
-
"epoch": 1.29,
|
1037 |
-
"learning_rate": 4.303827092827407e-06,
|
1038 |
-
"loss": 0.4072,
|
1039 |
-
"step": 85000
|
1040 |
-
},
|
1041 |
-
{
|
1042 |
-
"epoch": 1.3,
|
1043 |
-
"learning_rate": 4.257487596156282e-06,
|
1044 |
-
"loss": 0.3886,
|
1045 |
-
"step": 85500
|
1046 |
-
},
|
1047 |
-
{
|
1048 |
-
"epoch": 1.31,
|
1049 |
-
"learning_rate": 4.211148099485157e-06,
|
1050 |
-
"loss": 0.4289,
|
1051 |
-
"step": 86000
|
1052 |
-
},
|
1053 |
-
{
|
1054 |
-
"epoch": 1.32,
|
1055 |
-
"learning_rate": 4.164808602814032e-06,
|
1056 |
-
"loss": 0.3935,
|
1057 |
-
"step": 86500
|
1058 |
-
},
|
1059 |
-
{
|
1060 |
-
"epoch": 1.32,
|
1061 |
-
"learning_rate": 4.118469106142907e-06,
|
1062 |
-
"loss": 0.4124,
|
1063 |
-
"step": 87000
|
1064 |
-
},
|
1065 |
-
{
|
1066 |
-
"epoch": 1.33,
|
1067 |
-
"learning_rate": 4.072129609471782e-06,
|
1068 |
-
"loss": 0.3975,
|
1069 |
-
"step": 87500
|
1070 |
-
},
|
1071 |
-
{
|
1072 |
-
"epoch": 1.34,
|
1073 |
-
"learning_rate": 4.025790112800657e-06,
|
1074 |
-
"loss": 0.3353,
|
1075 |
-
"step": 88000
|
1076 |
-
},
|
1077 |
-
{
|
1078 |
-
"epoch": 1.35,
|
1079 |
-
"learning_rate": 3.979450616129532e-06,
|
1080 |
-
"loss": 0.4332,
|
1081 |
-
"step": 88500
|
1082 |
-
},
|
1083 |
-
{
|
1084 |
-
"epoch": 1.35,
|
1085 |
-
"learning_rate": 3.933111119458407e-06,
|
1086 |
-
"loss": 0.3528,
|
1087 |
-
"step": 89000
|
1088 |
-
},
|
1089 |
-
{
|
1090 |
-
"epoch": 1.36,
|
1091 |
-
"learning_rate": 3.886771622787282e-06,
|
1092 |
-
"loss": 0.2923,
|
1093 |
-
"step": 89500
|
1094 |
-
},
|
1095 |
-
{
|
1096 |
-
"epoch": 1.37,
|
1097 |
-
"learning_rate": 3.8404321261161566e-06,
|
1098 |
-
"loss": 0.4617,
|
1099 |
-
"step": 90000
|
1100 |
-
},
|
1101 |
-
{
|
1102 |
-
"epoch": 1.38,
|
1103 |
-
"learning_rate": 3.794092629445032e-06,
|
1104 |
-
"loss": 0.3681,
|
1105 |
-
"step": 90500
|
1106 |
-
},
|
1107 |
-
{
|
1108 |
-
"epoch": 1.38,
|
1109 |
-
"learning_rate": 3.747753132773907e-06,
|
1110 |
-
"loss": 0.387,
|
1111 |
-
"step": 91000
|
1112 |
-
},
|
1113 |
-
{
|
1114 |
-
"epoch": 1.39,
|
1115 |
-
"learning_rate": 3.7014136361027817e-06,
|
1116 |
-
"loss": 0.3805,
|
1117 |
-
"step": 91500
|
1118 |
-
},
|
1119 |
-
{
|
1120 |
-
"epoch": 1.4,
|
1121 |
-
"learning_rate": 3.655074139431657e-06,
|
1122 |
-
"loss": 0.3903,
|
1123 |
-
"step": 92000
|
1124 |
-
},
|
1125 |
-
{
|
1126 |
-
"epoch": 1.41,
|
1127 |
-
"learning_rate": 3.6087346427605318e-06,
|
1128 |
-
"loss": 0.3267,
|
1129 |
-
"step": 92500
|
1130 |
-
},
|
1131 |
-
{
|
1132 |
-
"epoch": 1.42,
|
1133 |
-
"learning_rate": 3.562395146089407e-06,
|
1134 |
-
"loss": 0.3575,
|
1135 |
-
"step": 93000
|
1136 |
-
},
|
1137 |
-
{
|
1138 |
-
"epoch": 1.42,
|
1139 |
-
"learning_rate": 3.5160556494182823e-06,
|
1140 |
-
"loss": 0.3535,
|
1141 |
-
"step": 93500
|
1142 |
-
},
|
1143 |
-
{
|
1144 |
-
"epoch": 1.43,
|
1145 |
-
"learning_rate": 3.469716152747157e-06,
|
1146 |
-
"loss": 0.4105,
|
1147 |
-
"step": 94000
|
1148 |
-
},
|
1149 |
-
{
|
1150 |
-
"epoch": 1.44,
|
1151 |
-
"learning_rate": 3.4233766560760315e-06,
|
1152 |
-
"loss": 0.4479,
|
1153 |
-
"step": 94500
|
1154 |
-
},
|
1155 |
-
{
|
1156 |
-
"epoch": 1.45,
|
1157 |
-
"learning_rate": 3.3770371594049066e-06,
|
1158 |
-
"loss": 0.4064,
|
1159 |
-
"step": 95000
|
1160 |
-
},
|
1161 |
-
{
|
1162 |
-
"epoch": 1.45,
|
1163 |
-
"learning_rate": 3.330697662733782e-06,
|
1164 |
-
"loss": 0.4434,
|
1165 |
-
"step": 95500
|
1166 |
-
},
|
1167 |
-
{
|
1168 |
-
"epoch": 1.46,
|
1169 |
-
"learning_rate": 3.2843581660626566e-06,
|
1170 |
-
"loss": 0.395,
|
1171 |
-
"step": 96000
|
1172 |
-
},
|
1173 |
-
{
|
1174 |
-
"epoch": 1.47,
|
1175 |
-
"learning_rate": 3.2380186693915313e-06,
|
1176 |
-
"loss": 0.4032,
|
1177 |
-
"step": 96500
|
1178 |
-
},
|
1179 |
-
{
|
1180 |
-
"epoch": 1.48,
|
1181 |
-
"learning_rate": 3.1916791727204067e-06,
|
1182 |
-
"loss": 0.3686,
|
1183 |
-
"step": 97000
|
1184 |
-
},
|
1185 |
-
{
|
1186 |
-
"epoch": 1.48,
|
1187 |
-
"learning_rate": 3.1453396760492818e-06,
|
1188 |
-
"loss": 0.3647,
|
1189 |
-
"step": 97500
|
1190 |
-
},
|
1191 |
-
{
|
1192 |
-
"epoch": 1.49,
|
1193 |
-
"learning_rate": 3.0990001793781564e-06,
|
1194 |
-
"loss": 0.4247,
|
1195 |
-
"step": 98000
|
1196 |
-
},
|
1197 |
-
{
|
1198 |
-
"epoch": 1.5,
|
1199 |
-
"learning_rate": 3.052660682707032e-06,
|
1200 |
-
"loss": 0.3991,
|
1201 |
-
"step": 98500
|
1202 |
-
},
|
1203 |
-
{
|
1204 |
-
"epoch": 1.51,
|
1205 |
-
"learning_rate": 3.0063211860359065e-06,
|
1206 |
-
"loss": 0.3971,
|
1207 |
-
"step": 99000
|
1208 |
-
},
|
1209 |
-
{
|
1210 |
-
"epoch": 1.51,
|
1211 |
-
"learning_rate": 2.9599816893647815e-06,
|
1212 |
-
"loss": 0.3602,
|
1213 |
-
"step": 99500
|
1214 |
-
},
|
1215 |
-
{
|
1216 |
-
"epoch": 1.52,
|
1217 |
-
"learning_rate": 2.9136421926936566e-06,
|
1218 |
-
"loss": 0.4215,
|
1219 |
-
"step": 100000
|
1220 |
-
},
|
1221 |
-
{
|
1222 |
-
"epoch": 1.53,
|
1223 |
-
"learning_rate": 2.8673026960225316e-06,
|
1224 |
-
"loss": 0.3961,
|
1225 |
-
"step": 100500
|
1226 |
-
},
|
1227 |
-
{
|
1228 |
-
"epoch": 1.54,
|
1229 |
-
"learning_rate": 2.8209631993514066e-06,
|
1230 |
-
"loss": 0.3718,
|
1231 |
-
"step": 101000
|
1232 |
-
},
|
1233 |
-
{
|
1234 |
-
"epoch": 1.54,
|
1235 |
-
"learning_rate": 2.7746237026802813e-06,
|
1236 |
-
"loss": 0.3655,
|
1237 |
-
"step": 101500
|
1238 |
-
},
|
1239 |
-
{
|
1240 |
-
"epoch": 1.55,
|
1241 |
-
"learning_rate": 2.7282842060091567e-06,
|
1242 |
-
"loss": 0.3872,
|
1243 |
-
"step": 102000
|
1244 |
-
},
|
1245 |
-
{
|
1246 |
-
"epoch": 1.56,
|
1247 |
-
"learning_rate": 2.6819447093380318e-06,
|
1248 |
-
"loss": 0.3425,
|
1249 |
-
"step": 102500
|
1250 |
-
},
|
1251 |
-
{
|
1252 |
-
"epoch": 1.57,
|
1253 |
-
"learning_rate": 2.6356052126669064e-06,
|
1254 |
-
"loss": 0.3535,
|
1255 |
-
"step": 103000
|
1256 |
-
},
|
1257 |
-
{
|
1258 |
-
"epoch": 1.57,
|
1259 |
-
"learning_rate": 2.5892657159957814e-06,
|
1260 |
-
"loss": 0.3695,
|
1261 |
-
"step": 103500
|
1262 |
-
},
|
1263 |
-
{
|
1264 |
-
"epoch": 1.58,
|
1265 |
-
"learning_rate": 2.5429262193246565e-06,
|
1266 |
-
"loss": 0.4084,
|
1267 |
-
"step": 104000
|
1268 |
-
},
|
1269 |
-
{
|
1270 |
-
"epoch": 1.59,
|
1271 |
-
"learning_rate": 2.4965867226535315e-06,
|
1272 |
-
"loss": 0.3987,
|
1273 |
-
"step": 104500
|
1274 |
-
},
|
1275 |
-
{
|
1276 |
-
"epoch": 1.6,
|
1277 |
-
"learning_rate": 2.4502472259824066e-06,
|
1278 |
-
"loss": 0.4317,
|
1279 |
-
"step": 105000
|
1280 |
-
},
|
1281 |
-
{
|
1282 |
-
"epoch": 1.61,
|
1283 |
-
"learning_rate": 2.403907729311281e-06,
|
1284 |
-
"loss": 0.3273,
|
1285 |
-
"step": 105500
|
1286 |
-
},
|
1287 |
-
{
|
1288 |
-
"epoch": 1.61,
|
1289 |
-
"learning_rate": 2.3575682326401562e-06,
|
1290 |
-
"loss": 0.428,
|
1291 |
-
"step": 106000
|
1292 |
-
},
|
1293 |
-
{
|
1294 |
-
"epoch": 1.62,
|
1295 |
-
"learning_rate": 2.3112287359690317e-06,
|
1296 |
-
"loss": 0.4092,
|
1297 |
-
"step": 106500
|
1298 |
-
},
|
1299 |
-
{
|
1300 |
-
"epoch": 1.63,
|
1301 |
-
"learning_rate": 2.2648892392979063e-06,
|
1302 |
-
"loss": 0.4357,
|
1303 |
-
"step": 107000
|
1304 |
-
},
|
1305 |
-
{
|
1306 |
-
"epoch": 1.64,
|
1307 |
-
"learning_rate": 2.2185497426267813e-06,
|
1308 |
-
"loss": 0.4054,
|
1309 |
-
"step": 107500
|
1310 |
-
},
|
1311 |
-
{
|
1312 |
-
"epoch": 1.64,
|
1313 |
-
"learning_rate": 2.1722102459556564e-06,
|
1314 |
-
"loss": 0.3343,
|
1315 |
-
"step": 108000
|
1316 |
-
},
|
1317 |
-
{
|
1318 |
-
"epoch": 1.65,
|
1319 |
-
"learning_rate": 2.1258707492845314e-06,
|
1320 |
-
"loss": 0.3598,
|
1321 |
-
"step": 108500
|
1322 |
-
},
|
1323 |
-
{
|
1324 |
-
"epoch": 1.66,
|
1325 |
-
"learning_rate": 2.0795312526134065e-06,
|
1326 |
-
"loss": 0.3702,
|
1327 |
-
"step": 109000
|
1328 |
-
},
|
1329 |
-
{
|
1330 |
-
"epoch": 1.67,
|
1331 |
-
"learning_rate": 2.033191755942281e-06,
|
1332 |
-
"loss": 0.3351,
|
1333 |
-
"step": 109500
|
1334 |
-
},
|
1335 |
-
{
|
1336 |
-
"epoch": 1.67,
|
1337 |
-
"learning_rate": 1.986852259271156e-06,
|
1338 |
-
"loss": 0.4569,
|
1339 |
-
"step": 110000
|
1340 |
-
},
|
1341 |
-
{
|
1342 |
-
"epoch": 1.68,
|
1343 |
-
"learning_rate": 1.940512762600031e-06,
|
1344 |
-
"loss": 0.3851,
|
1345 |
-
"step": 110500
|
1346 |
-
},
|
1347 |
-
{
|
1348 |
-
"epoch": 1.69,
|
1349 |
-
"learning_rate": 1.894173265928906e-06,
|
1350 |
-
"loss": 0.444,
|
1351 |
-
"step": 111000
|
1352 |
-
},
|
1353 |
-
{
|
1354 |
-
"epoch": 1.7,
|
1355 |
-
"learning_rate": 1.8478337692577813e-06,
|
1356 |
-
"loss": 0.3208,
|
1357 |
-
"step": 111500
|
1358 |
-
},
|
1359 |
-
{
|
1360 |
-
"epoch": 1.7,
|
1361 |
-
"learning_rate": 1.8014942725866563e-06,
|
1362 |
-
"loss": 0.4196,
|
1363 |
-
"step": 112000
|
1364 |
-
},
|
1365 |
-
{
|
1366 |
-
"epoch": 1.71,
|
1367 |
-
"learning_rate": 1.7551547759155311e-06,
|
1368 |
-
"loss": 0.3886,
|
1369 |
-
"step": 112500
|
1370 |
-
},
|
1371 |
-
{
|
1372 |
-
"epoch": 1.72,
|
1373 |
-
"learning_rate": 1.7088152792444062e-06,
|
1374 |
-
"loss": 0.3924,
|
1375 |
-
"step": 113000
|
1376 |
-
},
|
1377 |
-
{
|
1378 |
-
"epoch": 1.73,
|
1379 |
-
"learning_rate": 1.6624757825732812e-06,
|
1380 |
-
"loss": 0.4011,
|
1381 |
-
"step": 113500
|
1382 |
-
},
|
1383 |
-
{
|
1384 |
-
"epoch": 1.73,
|
1385 |
-
"learning_rate": 1.616136285902156e-06,
|
1386 |
-
"loss": 0.3969,
|
1387 |
-
"step": 114000
|
1388 |
-
},
|
1389 |
-
{
|
1390 |
-
"epoch": 1.74,
|
1391 |
-
"learning_rate": 1.569796789231031e-06,
|
1392 |
-
"loss": 0.3593,
|
1393 |
-
"step": 114500
|
1394 |
-
},
|
1395 |
-
{
|
1396 |
-
"epoch": 1.75,
|
1397 |
-
"learning_rate": 1.523457292559906e-06,
|
1398 |
-
"loss": 0.3142,
|
1399 |
-
"step": 115000
|
1400 |
-
},
|
1401 |
-
{
|
1402 |
-
"epoch": 1.76,
|
1403 |
-
"learning_rate": 1.477117795888781e-06,
|
1404 |
-
"loss": 0.4051,
|
1405 |
-
"step": 115500
|
1406 |
-
},
|
1407 |
-
{
|
1408 |
-
"epoch": 1.77,
|
1409 |
-
"learning_rate": 1.430778299217656e-06,
|
1410 |
-
"loss": 0.4112,
|
1411 |
-
"step": 116000
|
1412 |
-
},
|
1413 |
-
{
|
1414 |
-
"epoch": 1.77,
|
1415 |
-
"learning_rate": 1.384438802546531e-06,
|
1416 |
-
"loss": 0.3921,
|
1417 |
-
"step": 116500
|
1418 |
-
},
|
1419 |
-
{
|
1420 |
-
"epoch": 1.78,
|
1421 |
-
"learning_rate": 1.338099305875406e-06,
|
1422 |
-
"loss": 0.3689,
|
1423 |
-
"step": 117000
|
1424 |
-
},
|
1425 |
-
{
|
1426 |
-
"epoch": 1.79,
|
1427 |
-
"learning_rate": 1.291759809204281e-06,
|
1428 |
-
"loss": 0.3388,
|
1429 |
-
"step": 117500
|
1430 |
-
},
|
1431 |
-
{
|
1432 |
-
"epoch": 1.8,
|
1433 |
-
"learning_rate": 1.245420312533156e-06,
|
1434 |
-
"loss": 0.3644,
|
1435 |
-
"step": 118000
|
1436 |
-
},
|
1437 |
-
{
|
1438 |
-
"epoch": 1.8,
|
1439 |
-
"learning_rate": 1.199080815862031e-06,
|
1440 |
-
"loss": 0.358,
|
1441 |
-
"step": 118500
|
1442 |
-
},
|
1443 |
-
{
|
1444 |
-
"epoch": 1.81,
|
1445 |
-
"learning_rate": 1.1527413191909058e-06,
|
1446 |
-
"loss": 0.3112,
|
1447 |
-
"step": 119000
|
1448 |
-
},
|
1449 |
-
{
|
1450 |
-
"epoch": 1.82,
|
1451 |
-
"learning_rate": 1.1064018225197809e-06,
|
1452 |
-
"loss": 0.4384,
|
1453 |
-
"step": 119500
|
1454 |
-
},
|
1455 |
-
{
|
1456 |
-
"epoch": 1.83,
|
1457 |
-
"learning_rate": 1.060062325848656e-06,
|
1458 |
-
"loss": 0.3604,
|
1459 |
-
"step": 120000
|
1460 |
-
},
|
1461 |
-
{
|
1462 |
-
"epoch": 1.83,
|
1463 |
-
"learning_rate": 1.013722829177531e-06,
|
1464 |
-
"loss": 0.38,
|
1465 |
-
"step": 120500
|
1466 |
-
},
|
1467 |
-
{
|
1468 |
-
"epoch": 1.84,
|
1469 |
-
"learning_rate": 9.673833325064058e-07,
|
1470 |
-
"loss": 0.4989,
|
1471 |
-
"step": 121000
|
1472 |
-
},
|
1473 |
-
{
|
1474 |
-
"epoch": 1.85,
|
1475 |
-
"learning_rate": 9.210438358352809e-07,
|
1476 |
-
"loss": 0.3802,
|
1477 |
-
"step": 121500
|
1478 |
-
},
|
1479 |
-
{
|
1480 |
-
"epoch": 1.86,
|
1481 |
-
"learning_rate": 8.747043391641559e-07,
|
1482 |
-
"loss": 0.4567,
|
1483 |
-
"step": 122000
|
1484 |
-
},
|
1485 |
-
{
|
1486 |
-
"epoch": 1.86,
|
1487 |
-
"learning_rate": 8.283648424930308e-07,
|
1488 |
-
"loss": 0.3422,
|
1489 |
-
"step": 122500
|
1490 |
-
},
|
1491 |
-
{
|
1492 |
-
"epoch": 1.87,
|
1493 |
-
"learning_rate": 7.820253458219057e-07,
|
1494 |
-
"loss": 0.3748,
|
1495 |
-
"step": 123000
|
1496 |
-
},
|
1497 |
-
{
|
1498 |
-
"epoch": 1.88,
|
1499 |
-
"learning_rate": 7.356858491507808e-07,
|
1500 |
-
"loss": 0.3569,
|
1501 |
-
"step": 123500
|
1502 |
-
},
|
1503 |
-
{
|
1504 |
-
"epoch": 1.89,
|
1505 |
-
"learning_rate": 6.893463524796558e-07,
|
1506 |
-
"loss": 0.408,
|
1507 |
-
"step": 124000
|
1508 |
-
},
|
1509 |
-
{
|
1510 |
-
"epoch": 1.89,
|
1511 |
-
"learning_rate": 6.430068558085308e-07,
|
1512 |
-
"loss": 0.3582,
|
1513 |
-
"step": 124500
|
1514 |
-
},
|
1515 |
-
{
|
1516 |
-
"epoch": 1.9,
|
1517 |
-
"learning_rate": 5.966673591374057e-07,
|
1518 |
-
"loss": 0.4178,
|
1519 |
-
"step": 125000
|
1520 |
-
},
|
1521 |
-
{
|
1522 |
-
"epoch": 1.91,
|
1523 |
-
"learning_rate": 5.503278624662806e-07,
|
1524 |
-
"loss": 0.3536,
|
1525 |
-
"step": 125500
|
1526 |
-
},
|
1527 |
-
{
|
1528 |
-
"epoch": 1.92,
|
1529 |
-
"learning_rate": 5.039883657951557e-07,
|
1530 |
-
"loss": 0.3133,
|
1531 |
-
"step": 126000
|
1532 |
-
},
|
1533 |
-
{
|
1534 |
-
"epoch": 1.92,
|
1535 |
-
"learning_rate": 4.576488691240306e-07,
|
1536 |
-
"loss": 0.3779,
|
1537 |
-
"step": 126500
|
1538 |
-
},
|
1539 |
-
{
|
1540 |
-
"epoch": 1.93,
|
1541 |
-
"learning_rate": 4.1130937245290565e-07,
|
1542 |
-
"loss": 0.3002,
|
1543 |
-
"step": 127000
|
1544 |
-
},
|
1545 |
-
{
|
1546 |
-
"epoch": 1.94,
|
1547 |
-
"learning_rate": 3.6496987578178064e-07,
|
1548 |
-
"loss": 0.3598,
|
1549 |
-
"step": 127500
|
1550 |
-
},
|
1551 |
-
{
|
1552 |
-
"epoch": 1.95,
|
1553 |
-
"learning_rate": 3.1863037911065563e-07,
|
1554 |
-
"loss": 0.337,
|
1555 |
-
"step": 128000
|
1556 |
-
},
|
1557 |
-
{
|
1558 |
-
"epoch": 1.96,
|
1559 |
-
"learning_rate": 2.7229088243953057e-07,
|
1560 |
-
"loss": 0.3405,
|
1561 |
-
"step": 128500
|
1562 |
-
},
|
1563 |
-
{
|
1564 |
-
"epoch": 1.96,
|
1565 |
-
"learning_rate": 2.2595138576840556e-07,
|
1566 |
-
"loss": 0.4015,
|
1567 |
-
"step": 129000
|
1568 |
-
},
|
1569 |
-
{
|
1570 |
-
"epoch": 1.97,
|
1571 |
-
"learning_rate": 1.7961188909728057e-07,
|
1572 |
-
"loss": 0.3514,
|
1573 |
-
"step": 129500
|
1574 |
-
},
|
1575 |
-
{
|
1576 |
-
"epoch": 1.98,
|
1577 |
-
"learning_rate": 1.3327239242615553e-07,
|
1578 |
-
"loss": 0.373,
|
1579 |
-
"step": 130000
|
1580 |
-
},
|
1581 |
-
{
|
1582 |
-
"epoch": 1.99,
|
1583 |
-
"learning_rate": 8.693289575503054e-08,
|
1584 |
-
"loss": 0.3304,
|
1585 |
-
"step": 130500
|
1586 |
-
},
|
1587 |
-
{
|
1588 |
-
"epoch": 1.99,
|
1589 |
-
"learning_rate": 4.059339908390551e-08,
|
1590 |
-
"loss": 0.4458,
|
1591 |
-
"step": 131000
|
1592 |
-
},
|
1593 |
-
{
|
1594 |
-
"epoch": 2.0,
|
1595 |
-
"eval_accuracy": 0.8839892321497244,
|
1596 |
-
"eval_f1": 0.8993437882326771,
|
1597 |
-
"eval_loss": 0.6289095282554626,
|
1598 |
-
"eval_precision": 0.8968500443655724,
|
1599 |
-
"eval_recall": 0.9018514387686817,
|
1600 |
-
"eval_runtime": 29.934,
|
1601 |
-
"eval_samples_per_second": 260.607,
|
1602 |
-
"step": 131438
|
1603 |
-
}
|
1604 |
-
],
|
1605 |
-
"max_steps": 131438,
|
1606 |
-
"num_train_epochs": 2,
|
1607 |
-
"total_flos": 5237869449421320.0,
|
1608 |
-
"trial_name": null,
|
1609 |
-
"trial_params": null
|
1610 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
training_args.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:718deb060e0d8ff3b3a7cb4a6fc09fa87ab4c1a3ee3338560747a72b5155f319
|
3 |
-
size 2351
|
|
|
|
|
|
|
|
vocab.txt
DELETED
The diff for this file is too large to render.
See raw diff
|
|