Theoreticallyhugo
commited on
Commit
•
e009f1f
1
Parent(s):
e5418c0
Training in progress, epoch 12, checkpoint
Browse files- checkpoint-492/model.safetensors +1 -1
- checkpoint-492/optimizer.pt +1 -1
- checkpoint-492/rng_state.pth +1 -1
- checkpoint-492/trainer_state.json +313 -313
- checkpoint-492/training_args.bin +1 -1
checkpoint-492/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 592318676
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8e981afc5c5878689d86a12cba5beeb3cd2dd40a2e80920babd987c6740c66e4
|
3 |
size 592318676
|
checkpoint-492/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1014645498
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dfbc2026ea09efb4e1cc1b855fddf0d0568e9e9574396508e395ce28d81a4464
|
3 |
size 1014645498
|
checkpoint-492/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b6e53e706c63ba0c275c9b6332ceadb76c337b40858f3ddadb0ab10622a334eb
|
3 |
size 14244
|
checkpoint-492/trainer_state.json
CHANGED
@@ -11,468 +11,468 @@
|
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
"eval_B": {
|
14 |
-
"f1-score": 0.
|
15 |
-
"precision": 0.
|
16 |
-
"recall": 0.
|
17 |
-
"support":
|
18 |
},
|
19 |
"eval_I": {
|
20 |
-
"f1-score": 0.
|
21 |
-
"precision": 0.
|
22 |
-
"recall": 0.
|
23 |
-
"support":
|
24 |
},
|
25 |
"eval_O": {
|
26 |
-
"f1-score": 0.
|
27 |
-
"precision": 0.
|
28 |
-
"recall": 0.
|
29 |
-
"support":
|
30 |
},
|
31 |
-
"eval_accuracy": 0.
|
32 |
-
"eval_loss": 0.
|
33 |
"eval_macro avg": {
|
34 |
-
"f1-score": 0.
|
35 |
-
"precision": 0.
|
36 |
-
"recall": 0.
|
37 |
-
"support":
|
38 |
-
},
|
39 |
-
"eval_runtime": 1.
|
40 |
-
"eval_samples_per_second": 59.
|
41 |
-
"eval_steps_per_second":
|
42 |
"eval_weighted avg": {
|
43 |
-
"f1-score": 0.
|
44 |
-
"precision": 0.
|
45 |
-
"recall": 0.
|
46 |
-
"support":
|
47 |
},
|
48 |
"step": 41
|
49 |
},
|
50 |
{
|
51 |
"epoch": 2.0,
|
52 |
"eval_B": {
|
53 |
-
"f1-score": 0.
|
54 |
-
"precision": 0.
|
55 |
-
"recall": 0.
|
56 |
-
"support":
|
57 |
},
|
58 |
"eval_I": {
|
59 |
-
"f1-score": 0.
|
60 |
-
"precision": 0.
|
61 |
-
"recall": 0.
|
62 |
-
"support":
|
63 |
},
|
64 |
"eval_O": {
|
65 |
-
"f1-score": 0.
|
66 |
-
"precision": 0.
|
67 |
-
"recall": 0.
|
68 |
-
"support":
|
69 |
},
|
70 |
-
"eval_accuracy": 0.
|
71 |
-
"eval_loss": 0.
|
72 |
"eval_macro avg": {
|
73 |
-
"f1-score": 0.
|
74 |
-
"precision": 0.
|
75 |
-
"recall": 0.
|
76 |
-
"support":
|
77 |
-
},
|
78 |
-
"eval_runtime": 1.
|
79 |
-
"eval_samples_per_second":
|
80 |
-
"eval_steps_per_second":
|
81 |
"eval_weighted avg": {
|
82 |
-
"f1-score": 0.
|
83 |
-
"precision": 0.
|
84 |
-
"recall": 0.
|
85 |
-
"support":
|
86 |
},
|
87 |
"step": 82
|
88 |
},
|
89 |
{
|
90 |
"epoch": 3.0,
|
91 |
"eval_B": {
|
92 |
-
"f1-score": 0.
|
93 |
-
"precision": 0.
|
94 |
-
"recall": 0.
|
95 |
-
"support":
|
96 |
},
|
97 |
"eval_I": {
|
98 |
-
"f1-score": 0.
|
99 |
-
"precision": 0.
|
100 |
-
"recall": 0.
|
101 |
-
"support":
|
102 |
},
|
103 |
"eval_O": {
|
104 |
-
"f1-score": 0.
|
105 |
-
"precision": 0.
|
106 |
-
"recall": 0.
|
107 |
-
"support":
|
108 |
},
|
109 |
-
"eval_accuracy": 0.
|
110 |
-
"eval_loss": 0.
|
111 |
"eval_macro avg": {
|
112 |
-
"f1-score": 0.
|
113 |
-
"precision": 0.
|
114 |
-
"recall": 0.
|
115 |
-
"support":
|
116 |
-
},
|
117 |
-
"eval_runtime": 1.
|
118 |
-
"eval_samples_per_second":
|
119 |
-
"eval_steps_per_second":
|
120 |
"eval_weighted avg": {
|
121 |
-
"f1-score": 0.
|
122 |
-
"precision": 0.
|
123 |
-
"recall": 0.
|
124 |
-
"support":
|
125 |
},
|
126 |
"step": 123
|
127 |
},
|
128 |
{
|
129 |
"epoch": 4.0,
|
130 |
"eval_B": {
|
131 |
-
"f1-score": 0.
|
132 |
-
"precision": 0.
|
133 |
-
"recall": 0.
|
134 |
-
"support":
|
135 |
},
|
136 |
"eval_I": {
|
137 |
-
"f1-score": 0.
|
138 |
-
"precision": 0.
|
139 |
-
"recall": 0.
|
140 |
-
"support":
|
141 |
},
|
142 |
"eval_O": {
|
143 |
-
"f1-score": 0.
|
144 |
-
"precision": 0.
|
145 |
-
"recall": 0.
|
146 |
-
"support":
|
147 |
},
|
148 |
-
"eval_accuracy": 0.
|
149 |
-
"eval_loss": 0.
|
150 |
"eval_macro avg": {
|
151 |
-
"f1-score": 0.
|
152 |
-
"precision": 0.
|
153 |
-
"recall": 0.
|
154 |
-
"support":
|
155 |
-
},
|
156 |
-
"eval_runtime": 1.
|
157 |
-
"eval_samples_per_second":
|
158 |
-
"eval_steps_per_second":
|
159 |
"eval_weighted avg": {
|
160 |
-
"f1-score": 0.
|
161 |
-
"precision": 0.
|
162 |
-
"recall": 0.
|
163 |
-
"support":
|
164 |
},
|
165 |
"step": 164
|
166 |
},
|
167 |
{
|
168 |
"epoch": 5.0,
|
169 |
"eval_B": {
|
170 |
-
"f1-score": 0.
|
171 |
-
"precision": 0.
|
172 |
-
"recall": 0.
|
173 |
-
"support":
|
174 |
},
|
175 |
"eval_I": {
|
176 |
-
"f1-score": 0.
|
177 |
-
"precision": 0.
|
178 |
-
"recall": 0.
|
179 |
-
"support":
|
180 |
},
|
181 |
"eval_O": {
|
182 |
-
"f1-score": 0.
|
183 |
-
"precision": 0.
|
184 |
-
"recall": 0.
|
185 |
-
"support":
|
186 |
},
|
187 |
-
"eval_accuracy": 0.
|
188 |
-
"eval_loss": 0.
|
189 |
"eval_macro avg": {
|
190 |
-
"f1-score": 0.
|
191 |
-
"precision": 0.
|
192 |
-
"recall": 0.
|
193 |
-
"support":
|
194 |
-
},
|
195 |
-
"eval_runtime": 1.
|
196 |
-
"eval_samples_per_second": 59.
|
197 |
-
"eval_steps_per_second":
|
198 |
"eval_weighted avg": {
|
199 |
-
"f1-score": 0.
|
200 |
-
"precision": 0.
|
201 |
-
"recall": 0.
|
202 |
-
"support":
|
203 |
},
|
204 |
"step": 205
|
205 |
},
|
206 |
{
|
207 |
"epoch": 6.0,
|
208 |
"eval_B": {
|
209 |
-
"f1-score": 0.
|
210 |
-
"precision": 0.
|
211 |
-
"recall": 0.
|
212 |
-
"support":
|
213 |
},
|
214 |
"eval_I": {
|
215 |
-
"f1-score": 0.
|
216 |
-
"precision": 0.
|
217 |
-
"recall": 0.
|
218 |
-
"support":
|
219 |
},
|
220 |
"eval_O": {
|
221 |
-
"f1-score": 0.
|
222 |
-
"precision": 0.
|
223 |
-
"recall": 0.
|
224 |
-
"support":
|
225 |
},
|
226 |
-
"eval_accuracy": 0.
|
227 |
-
"eval_loss": 0.
|
228 |
"eval_macro avg": {
|
229 |
-
"f1-score": 0.
|
230 |
-
"precision": 0.
|
231 |
-
"recall": 0.
|
232 |
-
"support":
|
233 |
-
},
|
234 |
-
"eval_runtime": 1.
|
235 |
-
"eval_samples_per_second": 59.
|
236 |
-
"eval_steps_per_second":
|
237 |
"eval_weighted avg": {
|
238 |
-
"f1-score": 0.
|
239 |
-
"precision": 0.
|
240 |
-
"recall": 0.
|
241 |
-
"support":
|
242 |
},
|
243 |
"step": 246
|
244 |
},
|
245 |
{
|
246 |
"epoch": 7.0,
|
247 |
"eval_B": {
|
248 |
-
"f1-score": 0.
|
249 |
-
"precision": 0.
|
250 |
-
"recall": 0.
|
251 |
-
"support":
|
252 |
},
|
253 |
"eval_I": {
|
254 |
-
"f1-score": 0.
|
255 |
-
"precision": 0.
|
256 |
-
"recall": 0.
|
257 |
-
"support":
|
258 |
},
|
259 |
"eval_O": {
|
260 |
-
"f1-score": 0.
|
261 |
-
"precision": 0.
|
262 |
-
"recall": 0.
|
263 |
-
"support":
|
264 |
},
|
265 |
-
"eval_accuracy": 0.
|
266 |
-
"eval_loss": 0.
|
267 |
"eval_macro avg": {
|
268 |
-
"f1-score": 0.
|
269 |
-
"precision": 0.
|
270 |
-
"recall": 0.
|
271 |
-
"support":
|
272 |
-
},
|
273 |
-
"eval_runtime": 1.
|
274 |
-
"eval_samples_per_second": 59.
|
275 |
-
"eval_steps_per_second":
|
276 |
"eval_weighted avg": {
|
277 |
-
"f1-score": 0.
|
278 |
-
"precision": 0.
|
279 |
-
"recall": 0.
|
280 |
-
"support":
|
281 |
},
|
282 |
"step": 287
|
283 |
},
|
284 |
{
|
285 |
"epoch": 8.0,
|
286 |
"eval_B": {
|
287 |
-
"f1-score": 0.
|
288 |
-
"precision": 0.
|
289 |
-
"recall": 0.
|
290 |
-
"support":
|
291 |
},
|
292 |
"eval_I": {
|
293 |
-
"f1-score": 0.
|
294 |
-
"precision": 0.
|
295 |
-
"recall": 0.
|
296 |
-
"support":
|
297 |
},
|
298 |
"eval_O": {
|
299 |
-
"f1-score": 0.
|
300 |
-
"precision": 0.
|
301 |
-
"recall": 0.
|
302 |
-
"support":
|
303 |
},
|
304 |
-
"eval_accuracy": 0.
|
305 |
-
"eval_loss": 0.
|
306 |
"eval_macro avg": {
|
307 |
-
"f1-score": 0.
|
308 |
-
"precision": 0.
|
309 |
-
"recall": 0.
|
310 |
-
"support":
|
311 |
-
},
|
312 |
-
"eval_runtime": 1.
|
313 |
-
"eval_samples_per_second": 59.
|
314 |
-
"eval_steps_per_second":
|
315 |
"eval_weighted avg": {
|
316 |
-
"f1-score": 0.
|
317 |
-
"precision": 0.
|
318 |
-
"recall": 0.
|
319 |
-
"support":
|
320 |
},
|
321 |
"step": 328
|
322 |
},
|
323 |
{
|
324 |
"epoch": 9.0,
|
325 |
"eval_B": {
|
326 |
-
"f1-score": 0.
|
327 |
-
"precision": 0.
|
328 |
-
"recall": 0.
|
329 |
-
"support":
|
330 |
},
|
331 |
"eval_I": {
|
332 |
-
"f1-score": 0.
|
333 |
-
"precision": 0.
|
334 |
-
"recall": 0.
|
335 |
-
"support":
|
336 |
},
|
337 |
"eval_O": {
|
338 |
-
"f1-score": 0.
|
339 |
-
"precision": 0.
|
340 |
-
"recall": 0.
|
341 |
-
"support":
|
342 |
},
|
343 |
-
"eval_accuracy": 0.
|
344 |
-
"eval_loss": 0.
|
345 |
"eval_macro avg": {
|
346 |
-
"f1-score": 0.
|
347 |
-
"precision": 0.
|
348 |
-
"recall": 0.
|
349 |
-
"support":
|
350 |
-
},
|
351 |
-
"eval_runtime": 1.
|
352 |
-
"eval_samples_per_second": 59.
|
353 |
-
"eval_steps_per_second":
|
354 |
"eval_weighted avg": {
|
355 |
-
"f1-score": 0.
|
356 |
-
"precision": 0.
|
357 |
-
"recall": 0.
|
358 |
-
"support":
|
359 |
},
|
360 |
"step": 369
|
361 |
},
|
362 |
{
|
363 |
"epoch": 10.0,
|
364 |
"eval_B": {
|
365 |
-
"f1-score": 0.
|
366 |
-
"precision": 0.
|
367 |
-
"recall": 0.
|
368 |
-
"support":
|
369 |
},
|
370 |
"eval_I": {
|
371 |
-
"f1-score": 0.
|
372 |
-
"precision": 0.
|
373 |
-
"recall": 0.
|
374 |
-
"support":
|
375 |
},
|
376 |
"eval_O": {
|
377 |
-
"f1-score": 0.
|
378 |
-
"precision": 0.
|
379 |
-
"recall": 0.
|
380 |
-
"support":
|
381 |
},
|
382 |
-
"eval_accuracy": 0.
|
383 |
-
"eval_loss": 0.
|
384 |
"eval_macro avg": {
|
385 |
-
"f1-score": 0.
|
386 |
-
"precision": 0.
|
387 |
-
"recall": 0.
|
388 |
-
"support":
|
389 |
-
},
|
390 |
-
"eval_runtime": 1.
|
391 |
-
"eval_samples_per_second": 59.
|
392 |
-
"eval_steps_per_second":
|
393 |
"eval_weighted avg": {
|
394 |
-
"f1-score": 0.
|
395 |
-
"precision": 0.
|
396 |
-
"recall": 0.
|
397 |
-
"support":
|
398 |
},
|
399 |
"step": 410
|
400 |
},
|
401 |
{
|
402 |
"epoch": 11.0,
|
403 |
"eval_B": {
|
404 |
-
"f1-score": 0.
|
405 |
-
"precision": 0.
|
406 |
-
"recall": 0.
|
407 |
-
"support":
|
408 |
},
|
409 |
"eval_I": {
|
410 |
-
"f1-score": 0.
|
411 |
-
"precision": 0.
|
412 |
-
"recall": 0.
|
413 |
-
"support":
|
414 |
},
|
415 |
"eval_O": {
|
416 |
-
"f1-score": 0.
|
417 |
-
"precision": 0.
|
418 |
-
"recall": 0.
|
419 |
-
"support":
|
420 |
},
|
421 |
-
"eval_accuracy": 0.
|
422 |
-
"eval_loss": 0.
|
423 |
"eval_macro avg": {
|
424 |
-
"f1-score": 0.
|
425 |
-
"precision": 0.
|
426 |
-
"recall": 0.
|
427 |
-
"support":
|
428 |
-
},
|
429 |
-
"eval_runtime": 1.
|
430 |
-
"eval_samples_per_second": 59.
|
431 |
-
"eval_steps_per_second":
|
432 |
"eval_weighted avg": {
|
433 |
-
"f1-score": 0.
|
434 |
-
"precision": 0.
|
435 |
-
"recall": 0.
|
436 |
-
"support":
|
437 |
},
|
438 |
"step": 451
|
439 |
},
|
440 |
{
|
441 |
"epoch": 12.0,
|
442 |
"eval_B": {
|
443 |
-
"f1-score": 0.
|
444 |
-
"precision": 0.
|
445 |
-
"recall": 0.
|
446 |
-
"support":
|
447 |
},
|
448 |
"eval_I": {
|
449 |
-
"f1-score": 0.
|
450 |
-
"precision": 0.
|
451 |
-
"recall": 0.
|
452 |
-
"support":
|
453 |
},
|
454 |
"eval_O": {
|
455 |
-
"f1-score": 0.
|
456 |
-
"precision": 0.
|
457 |
-
"recall": 0.
|
458 |
-
"support":
|
459 |
},
|
460 |
-
"eval_accuracy": 0.
|
461 |
-
"eval_loss": 0.
|
462 |
"eval_macro avg": {
|
463 |
-
"f1-score": 0.
|
464 |
-
"precision": 0.
|
465 |
-
"recall": 0.
|
466 |
-
"support":
|
467 |
-
},
|
468 |
-
"eval_runtime": 1.
|
469 |
-
"eval_samples_per_second": 59.
|
470 |
-
"eval_steps_per_second":
|
471 |
"eval_weighted avg": {
|
472 |
-
"f1-score": 0.
|
473 |
-
"precision": 0.
|
474 |
-
"recall": 0.
|
475 |
-
"support":
|
476 |
},
|
477 |
"step": 492
|
478 |
}
|
@@ -482,7 +482,7 @@
|
|
482 |
"num_input_tokens_seen": 0,
|
483 |
"num_train_epochs": 16,
|
484 |
"save_steps": 500,
|
485 |
-
"total_flos":
|
486 |
"train_batch_size": 8,
|
487 |
"trial_name": null,
|
488 |
"trial_params": null
|
|
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
"eval_B": {
|
14 |
+
"f1-score": 0.668295065950171,
|
15 |
+
"precision": 0.7871116225546605,
|
16 |
+
"recall": 0.5806451612903226,
|
17 |
+
"support": 1178.0
|
18 |
},
|
19 |
"eval_I": {
|
20 |
+
"f1-score": 0.9265394121049587,
|
21 |
+
"precision": 0.9208257120459891,
|
22 |
+
"recall": 0.9323244616117254,
|
23 |
+
"support": 18899.0
|
24 |
},
|
25 |
"eval_O": {
|
26 |
+
"f1-score": 0.8679097538295895,
|
27 |
+
"precision": 0.8648200526675119,
|
28 |
+
"recall": 0.8710216110019646,
|
29 |
+
"support": 10180.0
|
30 |
},
|
31 |
+
"eval_accuracy": 0.8980070727434973,
|
32 |
+
"eval_loss": 0.28059592843055725,
|
33 |
"eval_macro avg": {
|
34 |
+
"f1-score": 0.820914743961573,
|
35 |
+
"precision": 0.8575857957560539,
|
36 |
+
"recall": 0.7946637446346708,
|
37 |
+
"support": 30257.0
|
38 |
+
},
|
39 |
+
"eval_runtime": 1.3597,
|
40 |
+
"eval_samples_per_second": 59.57,
|
41 |
+
"eval_steps_per_second": 8.09,
|
42 |
"eval_weighted avg": {
|
43 |
+
"f1-score": 0.896759137754772,
|
44 |
+
"precision": 0.8967766387772022,
|
45 |
+
"recall": 0.8980070727434973,
|
46 |
+
"support": 30257.0
|
47 |
},
|
48 |
"step": 41
|
49 |
},
|
50 |
{
|
51 |
"epoch": 2.0,
|
52 |
"eval_B": {
|
53 |
+
"f1-score": 0.8330464716006883,
|
54 |
+
"precision": 0.8446771378708552,
|
55 |
+
"recall": 0.8217317487266553,
|
56 |
+
"support": 1178.0
|
57 |
},
|
58 |
"eval_I": {
|
59 |
+
"f1-score": 0.9456807848767648,
|
60 |
+
"precision": 0.950406156477127,
|
61 |
+
"recall": 0.9410021694269538,
|
62 |
+
"support": 18899.0
|
63 |
},
|
64 |
"eval_O": {
|
65 |
+
"f1-score": 0.8991690558336167,
|
66 |
+
"precision": 0.8897009327819982,
|
67 |
+
"recall": 0.9088408644400786,
|
68 |
+
"support": 10180.0
|
69 |
},
|
70 |
+
"eval_accuracy": 0.9255378920580362,
|
71 |
+
"eval_loss": 0.19417612254619598,
|
72 |
"eval_macro avg": {
|
73 |
+
"f1-score": 0.89263210410369,
|
74 |
+
"precision": 0.8949280757099934,
|
75 |
+
"recall": 0.8905249275312292,
|
76 |
+
"support": 30257.0
|
77 |
+
},
|
78 |
+
"eval_runtime": 1.3644,
|
79 |
+
"eval_samples_per_second": 59.368,
|
80 |
+
"eval_steps_per_second": 8.062,
|
81 |
"eval_weighted avg": {
|
82 |
+
"f1-score": 0.925646656486691,
|
83 |
+
"precision": 0.9258654564363231,
|
84 |
+
"recall": 0.9255378920580362,
|
85 |
+
"support": 30257.0
|
86 |
},
|
87 |
"step": 82
|
88 |
},
|
89 |
{
|
90 |
"epoch": 3.0,
|
91 |
"eval_B": {
|
92 |
+
"f1-score": 0.8500201045436268,
|
93 |
+
"precision": 0.8074866310160428,
|
94 |
+
"recall": 0.8972835314091681,
|
95 |
+
"support": 1178.0
|
96 |
},
|
97 |
"eval_I": {
|
98 |
+
"f1-score": 0.9522313010685104,
|
99 |
+
"precision": 0.942701581540057,
|
100 |
+
"recall": 0.9619556590295782,
|
101 |
+
"support": 18899.0
|
102 |
},
|
103 |
"eval_O": {
|
104 |
+
"f1-score": 0.907826437534647,
|
105 |
+
"precision": 0.9321121804822519,
|
106 |
+
"recall": 0.8847740667976425,
|
107 |
+
"support": 10180.0
|
108 |
},
|
109 |
+
"eval_accuracy": 0.9334699408401361,
|
110 |
+
"eval_loss": 0.18320441246032715,
|
111 |
"eval_macro avg": {
|
112 |
+
"f1-score": 0.9033592810489282,
|
113 |
+
"precision": 0.894100131012784,
|
114 |
+
"recall": 0.9146710857454629,
|
115 |
+
"support": 30257.0
|
116 |
+
},
|
117 |
+
"eval_runtime": 1.3637,
|
118 |
+
"eval_samples_per_second": 59.395,
|
119 |
+
"eval_steps_per_second": 8.066,
|
120 |
"eval_weighted avg": {
|
121 |
+
"f1-score": 0.9333118344895024,
|
122 |
+
"precision": 0.9338744237092824,
|
123 |
+
"recall": 0.9334699408401361,
|
124 |
+
"support": 30257.0
|
125 |
},
|
126 |
"step": 123
|
127 |
},
|
128 |
{
|
129 |
"epoch": 4.0,
|
130 |
"eval_B": {
|
131 |
+
"f1-score": 0.8664440734557596,
|
132 |
+
"precision": 0.8522167487684729,
|
133 |
+
"recall": 0.8811544991511036,
|
134 |
+
"support": 1178.0
|
135 |
},
|
136 |
"eval_I": {
|
137 |
+
"f1-score": 0.9518863198966544,
|
138 |
+
"precision": 0.9485603194619588,
|
139 |
+
"recall": 0.9552357267580295,
|
140 |
+
"support": 18899.0
|
141 |
},
|
142 |
"eval_O": {
|
143 |
+
"f1-score": 0.9081091791747165,
|
144 |
+
"precision": 0.9159588288198262,
|
145 |
+
"recall": 0.9003929273084479,
|
146 |
+
"support": 10180.0
|
147 |
},
|
148 |
+
"eval_accuracy": 0.9338995934825,
|
149 |
+
"eval_loss": 0.17474766075611115,
|
150 |
"eval_macro avg": {
|
151 |
+
"f1-score": 0.9088131908423769,
|
152 |
+
"precision": 0.905578632350086,
|
153 |
+
"recall": 0.912261051072527,
|
154 |
+
"support": 30257.0
|
155 |
+
},
|
156 |
+
"eval_runtime": 1.3717,
|
157 |
+
"eval_samples_per_second": 59.053,
|
158 |
+
"eval_steps_per_second": 8.02,
|
159 |
"eval_weighted avg": {
|
160 |
+
"f1-score": 0.9338309192007261,
|
161 |
+
"precision": 0.9338405554069026,
|
162 |
+
"recall": 0.9338995934825,
|
163 |
+
"support": 30257.0
|
164 |
},
|
165 |
"step": 164
|
166 |
},
|
167 |
{
|
168 |
"epoch": 5.0,
|
169 |
"eval_B": {
|
170 |
+
"f1-score": 0.8666666666666667,
|
171 |
+
"precision": 0.8224085365853658,
|
172 |
+
"recall": 0.9159592529711376,
|
173 |
+
"support": 1178.0
|
174 |
},
|
175 |
"eval_I": {
|
176 |
+
"f1-score": 0.9542531309396725,
|
177 |
+
"precision": 0.9393582120155833,
|
178 |
+
"recall": 0.9696280226467009,
|
179 |
+
"support": 18899.0
|
180 |
},
|
181 |
"eval_O": {
|
182 |
+
"f1-score": 0.9089055411123006,
|
183 |
+
"precision": 0.9446858111688037,
|
184 |
+
"recall": 0.8757367387033399,
|
185 |
+
"support": 10180.0
|
186 |
},
|
187 |
+
"eval_accuracy": 0.9359487060845424,
|
188 |
+
"eval_loss": 0.18612883985042572,
|
189 |
"eval_macro avg": {
|
190 |
+
"f1-score": 0.9099417795728799,
|
191 |
+
"precision": 0.9021508532565843,
|
192 |
+
"recall": 0.9204413381070594,
|
193 |
+
"support": 30257.0
|
194 |
+
},
|
195 |
+
"eval_runtime": 1.3578,
|
196 |
+
"eval_samples_per_second": 59.654,
|
197 |
+
"eval_steps_per_second": 8.101,
|
198 |
"eval_weighted avg": {
|
199 |
+
"f1-score": 0.9355858698312928,
|
200 |
+
"precision": 0.9365974704259672,
|
201 |
+
"recall": 0.9359487060845424,
|
202 |
+
"support": 30257.0
|
203 |
},
|
204 |
"step": 205
|
205 |
},
|
206 |
{
|
207 |
"epoch": 6.0,
|
208 |
"eval_B": {
|
209 |
+
"f1-score": 0.8542262147815436,
|
210 |
+
"precision": 0.8229740361919748,
|
211 |
+
"recall": 0.8879456706281834,
|
212 |
+
"support": 1178.0
|
213 |
},
|
214 |
"eval_I": {
|
215 |
+
"f1-score": 0.9509714713911042,
|
216 |
+
"precision": 0.962094547029837,
|
217 |
+
"recall": 0.9401026509339119,
|
218 |
+
"support": 18899.0
|
219 |
},
|
220 |
"eval_O": {
|
221 |
+
"f1-score": 0.9120247354944683,
|
222 |
+
"precision": 0.897328643407168,
|
223 |
+
"recall": 0.9272102161100196,
|
224 |
+
"support": 10180.0
|
225 |
},
|
226 |
+
"eval_accuracy": 0.9337343424662061,
|
227 |
+
"eval_loss": 0.19629183411598206,
|
228 |
"eval_macro avg": {
|
229 |
+
"f1-score": 0.9057408072223719,
|
230 |
+
"precision": 0.8941324088763266,
|
231 |
+
"recall": 0.9184195125573716,
|
232 |
+
"support": 30257.0
|
233 |
+
},
|
234 |
+
"eval_runtime": 1.3603,
|
235 |
+
"eval_samples_per_second": 59.544,
|
236 |
+
"eval_steps_per_second": 8.086,
|
237 |
"eval_weighted avg": {
|
238 |
+
"f1-score": 0.9341012038922174,
|
239 |
+
"precision": 0.9348875912627161,
|
240 |
+
"recall": 0.9337343424662061,
|
241 |
+
"support": 30257.0
|
242 |
},
|
243 |
"step": 246
|
244 |
},
|
245 |
{
|
246 |
"epoch": 7.0,
|
247 |
"eval_B": {
|
248 |
+
"f1-score": 0.8589743589743589,
|
249 |
+
"precision": 0.8133535660091047,
|
250 |
+
"recall": 0.9100169779286927,
|
251 |
+
"support": 1178.0
|
252 |
},
|
253 |
"eval_I": {
|
254 |
+
"f1-score": 0.9495904221802143,
|
255 |
+
"precision": 0.9424149252175725,
|
256 |
+
"recall": 0.9568760251865178,
|
257 |
+
"support": 18899.0
|
258 |
},
|
259 |
"eval_O": {
|
260 |
+
"f1-score": 0.9019568489713999,
|
261 |
+
"precision": 0.9218461538461539,
|
262 |
+
"recall": 0.8829076620825147,
|
263 |
+
"support": 10180.0
|
264 |
},
|
265 |
+
"eval_accuracy": 0.9301649205142611,
|
266 |
+
"eval_loss": 0.23149603605270386,
|
267 |
"eval_macro avg": {
|
268 |
+
"f1-score": 0.9035072100419911,
|
269 |
+
"precision": 0.8925382150242771,
|
270 |
+
"recall": 0.9166002217325749,
|
271 |
+
"support": 30257.0
|
272 |
+
},
|
273 |
+
"eval_runtime": 1.3656,
|
274 |
+
"eval_samples_per_second": 59.314,
|
275 |
+
"eval_steps_per_second": 8.055,
|
276 |
"eval_weighted avg": {
|
277 |
+
"f1-score": 0.9300360877213377,
|
278 |
+
"precision": 0.9304697762038363,
|
279 |
+
"recall": 0.9301649205142611,
|
280 |
+
"support": 30257.0
|
281 |
},
|
282 |
"step": 287
|
283 |
},
|
284 |
{
|
285 |
"epoch": 8.0,
|
286 |
"eval_B": {
|
287 |
+
"f1-score": 0.87409200968523,
|
288 |
+
"precision": 0.833076923076923,
|
289 |
+
"recall": 0.9193548387096774,
|
290 |
+
"support": 1178.0
|
291 |
},
|
292 |
"eval_I": {
|
293 |
+
"f1-score": 0.952083279518508,
|
294 |
+
"precision": 0.9300999293428889,
|
295 |
+
"recall": 0.9751309593100164,
|
296 |
+
"support": 18899.0
|
297 |
},
|
298 |
"eval_O": {
|
299 |
+
"f1-score": 0.9016198312891373,
|
300 |
+
"precision": 0.9527507382697146,
|
301 |
+
"recall": 0.8556974459724951,
|
302 |
+
"support": 10180.0
|
303 |
},
|
304 |
+
"eval_accuracy": 0.9327758865717024,
|
305 |
+
"eval_loss": 0.2542731761932373,
|
306 |
"eval_macro avg": {
|
307 |
+
"f1-score": 0.9092650401642918,
|
308 |
+
"precision": 0.9053091968965088,
|
309 |
+
"recall": 0.9167277479973963,
|
310 |
+
"support": 30257.0
|
311 |
+
},
|
312 |
+
"eval_runtime": 1.3569,
|
313 |
+
"eval_samples_per_second": 59.697,
|
314 |
+
"eval_steps_per_second": 8.107,
|
315 |
"eval_weighted avg": {
|
316 |
+
"f1-score": 0.932068353424097,
|
317 |
+
"precision": 0.9339434079922521,
|
318 |
+
"recall": 0.9327758865717024,
|
319 |
+
"support": 30257.0
|
320 |
},
|
321 |
"step": 328
|
322 |
},
|
323 |
{
|
324 |
"epoch": 9.0,
|
325 |
"eval_B": {
|
326 |
+
"f1-score": 0.8768793173506705,
|
327 |
+
"precision": 0.8409976617303195,
|
328 |
+
"recall": 0.9159592529711376,
|
329 |
+
"support": 1178.0
|
330 |
},
|
331 |
"eval_I": {
|
332 |
+
"f1-score": 0.9543993519220215,
|
333 |
+
"precision": 0.9428438661710037,
|
334 |
+
"recall": 0.9662416000846605,
|
335 |
+
"support": 18899.0
|
336 |
},
|
337 |
"eval_O": {
|
338 |
+
"f1-score": 0.9107449711917517,
|
339 |
+
"precision": 0.9379554445138455,
|
340 |
+
"recall": 0.8850687622789783,
|
341 |
+
"support": 10180.0
|
342 |
},
|
343 |
+
"eval_accuracy": 0.9369732623855637,
|
344 |
+
"eval_loss": 0.23665204644203186,
|
345 |
"eval_macro avg": {
|
346 |
+
"f1-score": 0.9140078801548146,
|
347 |
+
"precision": 0.9072656574717229,
|
348 |
+
"recall": 0.9224232051115923,
|
349 |
+
"support": 30257.0
|
350 |
+
},
|
351 |
+
"eval_runtime": 1.3607,
|
352 |
+
"eval_samples_per_second": 59.526,
|
353 |
+
"eval_steps_per_second": 8.084,
|
354 |
"eval_weighted avg": {
|
355 |
+
"f1-score": 0.9366936905359226,
|
356 |
+
"precision": 0.9372339589990767,
|
357 |
+
"recall": 0.9369732623855637,
|
358 |
+
"support": 30257.0
|
359 |
},
|
360 |
"step": 369
|
361 |
},
|
362 |
{
|
363 |
"epoch": 10.0,
|
364 |
"eval_B": {
|
365 |
+
"f1-score": 0.8608903020667728,
|
366 |
+
"precision": 0.8094170403587444,
|
367 |
+
"recall": 0.9193548387096774,
|
368 |
+
"support": 1178.0
|
369 |
},
|
370 |
"eval_I": {
|
371 |
+
"f1-score": 0.9494098249103614,
|
372 |
+
"precision": 0.9393060590367686,
|
373 |
+
"recall": 0.9597333192232393,
|
374 |
+
"support": 18899.0
|
375 |
},
|
376 |
"eval_O": {
|
377 |
+
"f1-score": 0.9020162716660771,
|
378 |
+
"precision": 0.9288167343115828,
|
379 |
+
"recall": 0.8767190569744597,
|
380 |
+
"support": 10180.0
|
381 |
},
|
382 |
+
"eval_accuracy": 0.9302310209207787,
|
383 |
+
"eval_loss": 0.27300411462783813,
|
384 |
"eval_macro avg": {
|
385 |
+
"f1-score": 0.9041054662144038,
|
386 |
+
"precision": 0.8925132779023652,
|
387 |
+
"recall": 0.9186024049691256,
|
388 |
+
"support": 30257.0
|
389 |
+
},
|
390 |
+
"eval_runtime": 1.3606,
|
391 |
+
"eval_samples_per_second": 59.531,
|
392 |
+
"eval_steps_per_second": 8.084,
|
393 |
"eval_weighted avg": {
|
394 |
+
"f1-score": 0.9300178703234373,
|
395 |
+
"precision": 0.9307199272423042,
|
396 |
+
"recall": 0.9302310209207787,
|
397 |
+
"support": 30257.0
|
398 |
},
|
399 |
"step": 410
|
400 |
},
|
401 |
{
|
402 |
"epoch": 11.0,
|
403 |
"eval_B": {
|
404 |
+
"f1-score": 0.8705882352941178,
|
405 |
+
"precision": 0.8337218337218337,
|
406 |
+
"recall": 0.9108658743633277,
|
407 |
+
"support": 1178.0
|
408 |
},
|
409 |
"eval_I": {
|
410 |
+
"f1-score": 0.9516225883090098,
|
411 |
+
"precision": 0.9392393320964749,
|
412 |
+
"recall": 0.9643367373935129,
|
413 |
+
"support": 18899.0
|
414 |
},
|
415 |
"eval_O": {
|
416 |
+
"f1-score": 0.9045882710422363,
|
417 |
+
"precision": 0.9336190675308383,
|
418 |
+
"recall": 0.8773084479371316,
|
419 |
+
"support": 10180.0
|
420 |
},
|
421 |
+
"eval_accuracy": 0.932974187791255,
|
422 |
+
"eval_loss": 0.2785099744796753,
|
423 |
"eval_macro avg": {
|
424 |
+
"f1-score": 0.9089330315484546,
|
425 |
+
"precision": 0.9021934111163823,
|
426 |
+
"recall": 0.9175036865646574,
|
427 |
+
"support": 30257.0
|
428 |
+
},
|
429 |
+
"eval_runtime": 1.357,
|
430 |
+
"eval_samples_per_second": 59.689,
|
431 |
+
"eval_steps_per_second": 8.106,
|
432 |
"eval_weighted avg": {
|
433 |
+
"f1-score": 0.9326429202114688,
|
434 |
+
"precision": 0.9332402605968713,
|
435 |
+
"recall": 0.932974187791255,
|
436 |
+
"support": 30257.0
|
437 |
},
|
438 |
"step": 451
|
439 |
},
|
440 |
{
|
441 |
"epoch": 12.0,
|
442 |
"eval_B": {
|
443 |
+
"f1-score": 0.871941272430669,
|
444 |
+
"precision": 0.8390894819466248,
|
445 |
+
"recall": 0.9074702886247877,
|
446 |
+
"support": 1178.0
|
447 |
},
|
448 |
"eval_I": {
|
449 |
+
"f1-score": 0.9533659666298226,
|
450 |
+
"precision": 0.9483742604324834,
|
451 |
+
"recall": 0.9584104979099424,
|
452 |
+
"support": 18899.0
|
453 |
},
|
454 |
"eval_O": {
|
455 |
+
"f1-score": 0.9108851674641149,
|
456 |
+
"precision": 0.924524484014569,
|
457 |
+
"recall": 0.8976424361493124,
|
458 |
+
"support": 10180.0
|
459 |
},
|
460 |
+
"eval_accuracy": 0.9359817562878012,
|
461 |
+
"eval_loss": 0.2702731788158417,
|
462 |
"eval_macro avg": {
|
463 |
+
"f1-score": 0.9120641355082021,
|
464 |
+
"precision": 0.903996075464559,
|
465 |
+
"recall": 0.9211744075613475,
|
466 |
+
"support": 30257.0
|
467 |
+
},
|
468 |
+
"eval_runtime": 1.3674,
|
469 |
+
"eval_samples_per_second": 59.235,
|
470 |
+
"eval_steps_per_second": 8.044,
|
471 |
"eval_weighted avg": {
|
472 |
+
"f1-score": 0.9359031373581331,
|
473 |
+
"precision": 0.9360951781377842,
|
474 |
+
"recall": 0.9359817562878012,
|
475 |
+
"support": 30257.0
|
476 |
},
|
477 |
"step": 492
|
478 |
}
|
|
|
482 |
"num_input_tokens_seen": 0,
|
483 |
"num_train_epochs": 16,
|
484 |
"save_steps": 500,
|
485 |
+
"total_flos": 1720081324029600.0,
|
486 |
"train_batch_size": 8,
|
487 |
"trial_name": null,
|
488 |
"trial_params": null
|
checkpoint-492/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4664
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:652d293bb850de701018062dce9e70536f9289fef58a5600464855a993d48087
|
3 |
size 4664
|