Theoreticallyhugo
commited on
Commit
•
17b18ab
1
Parent(s):
f734cd4
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:cfe883009ca6eba3d193033ca6483a6c43d4f0310d57d368d86592627af508ee
|
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:c3605a0c42f33fb0a181410f66b9fcb100880a05ff6a5e8e353bdd30deec106a
|
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": 58.
|
80 |
-
"eval_steps_per_second": 7.
|
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": 58.
|
119 |
-
"eval_steps_per_second": 7.
|
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": 7.
|
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":
|
197 |
-
"eval_steps_per_second": 7.
|
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":
|
236 |
-
"eval_steps_per_second": 7.
|
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":
|
275 |
-
"eval_steps_per_second": 7.
|
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": 58.
|
314 |
-
"eval_steps_per_second": 7.
|
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":
|
353 |
-
"eval_steps_per_second": 7.
|
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":
|
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": 58.
|
431 |
-
"eval_steps_per_second": 7.
|
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":
|
470 |
-
"eval_steps_per_second": 7.
|
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": 0.6659475008989573,
|
15 |
+
"precision": 0.6905294556301268,
|
16 |
+
"recall": 0.6430555555555556,
|
17 |
+
"support": 1440.0
|
18 |
},
|
19 |
"eval_I": {
|
20 |
+
"f1-score": 0.9167863956473609,
|
21 |
+
"precision": 0.9325347388596071,
|
22 |
+
"recall": 0.9015611247510076,
|
23 |
+
"support": 21587.0
|
24 |
},
|
25 |
"eval_O": {
|
26 |
+
"f1-score": 0.8443157797996509,
|
27 |
+
"precision": 0.8138010452653025,
|
28 |
+
"recall": 0.8772080588179128,
|
29 |
+
"support": 10473.0
|
30 |
},
|
31 |
+
"eval_accuracy": 0.8828358208955224,
|
32 |
+
"eval_loss": 0.31183817982673645,
|
33 |
"eval_macro avg": {
|
34 |
+
"f1-score": 0.8090165587819897,
|
35 |
+
"precision": 0.8122884132516788,
|
36 |
+
"recall": 0.8072749130414919,
|
37 |
+
"support": 33500.0
|
38 |
+
},
|
39 |
+
"eval_runtime": 1.3725,
|
40 |
+
"eval_samples_per_second": 59.018,
|
41 |
+
"eval_steps_per_second": 8.015,
|
42 |
"eval_weighted avg": {
|
43 |
+
"f1-score": 0.8833478055515172,
|
44 |
+
"precision": 0.8850127812218876,
|
45 |
+
"recall": 0.8828358208955224,
|
46 |
+
"support": 33500.0
|
47 |
},
|
48 |
"step": 41
|
49 |
},
|
50 |
{
|
51 |
"epoch": 2.0,
|
52 |
"eval_B": {
|
53 |
+
"f1-score": 0.8377561303325496,
|
54 |
+
"precision": 0.8113207547169812,
|
55 |
+
"recall": 0.8659722222222223,
|
56 |
+
"support": 1440.0
|
57 |
},
|
58 |
"eval_I": {
|
59 |
+
"f1-score": 0.9473755107538951,
|
60 |
+
"precision": 0.9191461555216729,
|
61 |
+
"recall": 0.9773938018251725,
|
62 |
+
"support": 21587.0
|
63 |
},
|
64 |
"eval_O": {
|
65 |
+
"f1-score": 0.8803449514911966,
|
66 |
+
"precision": 0.9519316163410302,
|
67 |
+
"recall": 0.8187720805881791,
|
68 |
+
"support": 10473.0
|
69 |
},
|
70 |
+
"eval_accuracy": 0.9230149253731343,
|
71 |
+
"eval_loss": 0.22658132016658783,
|
72 |
"eval_macro avg": {
|
73 |
+
"f1-score": 0.8884921975258804,
|
74 |
+
"precision": 0.8941328421932281,
|
75 |
+
"recall": 0.8873793682118579,
|
76 |
+
"support": 33500.0
|
77 |
+
},
|
78 |
+
"eval_runtime": 1.3801,
|
79 |
+
"eval_samples_per_second": 58.69,
|
80 |
+
"eval_steps_per_second": 7.97,
|
81 |
"eval_weighted avg": {
|
82 |
+
"f1-score": 0.9217079598594182,
|
83 |
+
"precision": 0.9247608884769675,
|
84 |
+
"recall": 0.9230149253731343,
|
85 |
+
"support": 33500.0
|
86 |
},
|
87 |
"step": 82
|
88 |
},
|
89 |
{
|
90 |
"epoch": 3.0,
|
91 |
"eval_B": {
|
92 |
+
"f1-score": 0.8710106382978723,
|
93 |
+
"precision": 0.8354591836734694,
|
94 |
+
"recall": 0.9097222222222222,
|
95 |
+
"support": 1440.0
|
96 |
},
|
97 |
"eval_I": {
|
98 |
+
"f1-score": 0.9543258273315707,
|
99 |
+
"precision": 0.9392974112791063,
|
100 |
+
"recall": 0.9698429610413675,
|
101 |
+
"support": 21587.0
|
102 |
},
|
103 |
"eval_O": {
|
104 |
+
"f1-score": 0.8996818452972758,
|
105 |
+
"precision": 0.9384009125790729,
|
106 |
+
"recall": 0.8640313186288552,
|
107 |
+
"support": 10473.0
|
108 |
},
|
109 |
+
"eval_accuracy": 0.934179104477612,
|
110 |
+
"eval_loss": 0.20443089306354523,
|
111 |
"eval_macro avg": {
|
112 |
+
"f1-score": 0.908339436975573,
|
113 |
+
"precision": 0.9043858358438829,
|
114 |
+
"recall": 0.9145321672974815,
|
115 |
+
"support": 33500.0
|
116 |
+
},
|
117 |
+
"eval_runtime": 1.3812,
|
118 |
+
"eval_samples_per_second": 58.646,
|
119 |
+
"eval_steps_per_second": 7.964,
|
120 |
"eval_weighted avg": {
|
121 |
+
"f1-score": 0.9336613408822066,
|
122 |
+
"precision": 0.9345536477376863,
|
123 |
+
"recall": 0.934179104477612,
|
124 |
+
"support": 33500.0
|
125 |
},
|
126 |
"step": 123
|
127 |
},
|
128 |
{
|
129 |
"epoch": 4.0,
|
130 |
"eval_B": {
|
131 |
+
"f1-score": 0.8771342484097756,
|
132 |
+
"precision": 0.8468002585649644,
|
133 |
+
"recall": 0.9097222222222222,
|
134 |
+
"support": 1440.0
|
135 |
},
|
136 |
"eval_I": {
|
137 |
+
"f1-score": 0.959998160834981,
|
138 |
+
"precision": 0.952900369677331,
|
139 |
+
"recall": 0.9672024829758651,
|
140 |
+
"support": 21587.0
|
141 |
},
|
142 |
"eval_O": {
|
143 |
+
"f1-score": 0.9145503290275409,
|
144 |
+
"precision": 0.9341764588727345,
|
145 |
+
"recall": 0.8957318819822401,
|
146 |
+
"support": 10473.0
|
147 |
},
|
148 |
+
"eval_accuracy": 0.9423880597014925,
|
149 |
+
"eval_loss": 0.18545031547546387,
|
150 |
"eval_macro avg": {
|
151 |
+
"f1-score": 0.9172275794240993,
|
152 |
+
"precision": 0.9112923623716767,
|
153 |
+
"recall": 0.9242188623934425,
|
154 |
+
"support": 33500.0
|
155 |
+
},
|
156 |
+
"eval_runtime": 1.377,
|
157 |
+
"eval_samples_per_second": 58.824,
|
158 |
+
"eval_steps_per_second": 7.988,
|
159 |
"eval_weighted avg": {
|
160 |
+
"f1-score": 0.9422280361659775,
|
161 |
+
"precision": 0.9424860509352908,
|
162 |
+
"recall": 0.9423880597014925,
|
163 |
+
"support": 33500.0
|
164 |
},
|
165 |
"step": 164
|
166 |
},
|
167 |
{
|
168 |
"epoch": 5.0,
|
169 |
"eval_B": {
|
170 |
+
"f1-score": 0.8835341365461846,
|
171 |
+
"precision": 0.8527131782945736,
|
172 |
+
"recall": 0.9166666666666666,
|
173 |
+
"support": 1440.0
|
174 |
},
|
175 |
"eval_I": {
|
176 |
+
"f1-score": 0.9602170394181884,
|
177 |
+
"precision": 0.9453672113485365,
|
178 |
+
"recall": 0.9755408347616621,
|
179 |
+
"support": 21587.0
|
180 |
},
|
181 |
"eval_O": {
|
182 |
+
"f1-score": 0.9125018611345476,
|
183 |
+
"precision": 0.9500826787928897,
|
184 |
+
"recall": 0.877780960565263,
|
185 |
+
"support": 10473.0
|
186 |
},
|
187 |
+
"eval_accuracy": 0.9424477611940298,
|
188 |
+
"eval_loss": 0.19699566066265106,
|
189 |
"eval_macro avg": {
|
190 |
+
"f1-score": 0.9187510123663069,
|
191 |
+
"precision": 0.9160543561453333,
|
192 |
+
"recall": 0.9233294873311971,
|
193 |
+
"support": 33500.0
|
194 |
+
},
|
195 |
+
"eval_runtime": 1.3779,
|
196 |
+
"eval_samples_per_second": 58.784,
|
197 |
+
"eval_steps_per_second": 7.983,
|
198 |
"eval_weighted avg": {
|
199 |
+
"f1-score": 0.9420037724838524,
|
200 |
+
"precision": 0.9428586526305366,
|
201 |
+
"recall": 0.9424477611940298,
|
202 |
+
"support": 33500.0
|
203 |
},
|
204 |
"step": 205
|
205 |
},
|
206 |
{
|
207 |
"epoch": 6.0,
|
208 |
"eval_B": {
|
209 |
+
"f1-score": 0.882471457353929,
|
210 |
+
"precision": 0.8543563068920677,
|
211 |
+
"recall": 0.9125,
|
212 |
+
"support": 1440.0
|
213 |
},
|
214 |
"eval_I": {
|
215 |
+
"f1-score": 0.9563333022648896,
|
216 |
+
"precision": 0.9621173050775939,
|
217 |
+
"recall": 0.9506184277574466,
|
218 |
+
"support": 21587.0
|
219 |
},
|
220 |
"eval_O": {
|
221 |
+
"f1-score": 0.9094096465460059,
|
222 |
+
"precision": 0.9025674786043449,
|
223 |
+
"recall": 0.9163563448868519,
|
224 |
+
"support": 10473.0
|
225 |
},
|
226 |
+
"eval_accuracy": 0.9382686567164179,
|
227 |
+
"eval_loss": 0.22578871250152588,
|
228 |
"eval_macro avg": {
|
229 |
+
"f1-score": 0.9160714687216082,
|
230 |
+
"precision": 0.9063470301913354,
|
231 |
+
"recall": 0.9264915908814327,
|
232 |
+
"support": 33500.0
|
233 |
+
},
|
234 |
+
"eval_runtime": 1.3827,
|
235 |
+
"eval_samples_per_second": 58.582,
|
236 |
+
"eval_steps_per_second": 7.956,
|
237 |
"eval_weighted avg": {
|
238 |
+
"f1-score": 0.9384887499360641,
|
239 |
+
"precision": 0.9388683149271014,
|
240 |
+
"recall": 0.9382686567164179,
|
241 |
+
"support": 33500.0
|
242 |
},
|
243 |
"step": 246
|
244 |
},
|
245 |
{
|
246 |
"epoch": 7.0,
|
247 |
"eval_B": {
|
248 |
+
"f1-score": 0.8892651540805959,
|
249 |
+
"precision": 0.8678122934567085,
|
250 |
+
"recall": 0.9118055555555555,
|
251 |
+
"support": 1440.0
|
252 |
},
|
253 |
"eval_I": {
|
254 |
+
"f1-score": 0.9597268994787103,
|
255 |
+
"precision": 0.9557587173243901,
|
256 |
+
"recall": 0.963728169731783,
|
257 |
+
"support": 21587.0
|
258 |
},
|
259 |
"eval_O": {
|
260 |
+
"f1-score": 0.914125549702798,
|
261 |
+
"precision": 0.925440313111546,
|
262 |
+
"recall": 0.903084121073236,
|
263 |
+
"support": 10473.0
|
264 |
},
|
265 |
+
"eval_accuracy": 0.9425373134328359,
|
266 |
+
"eval_loss": 0.22205175459384918,
|
267 |
"eval_macro avg": {
|
268 |
+
"f1-score": 0.9210392010873681,
|
269 |
+
"precision": 0.9163371079642149,
|
270 |
+
"recall": 0.9262059487868582,
|
271 |
+
"support": 33500.0
|
272 |
+
},
|
273 |
+
"eval_runtime": 1.3808,
|
274 |
+
"eval_samples_per_second": 58.663,
|
275 |
+
"eval_steps_per_second": 7.967,
|
276 |
"eval_weighted avg": {
|
277 |
+
"f1-score": 0.9424418890435934,
|
278 |
+
"precision": 0.9424999860500445,
|
279 |
+
"recall": 0.9425373134328359,
|
280 |
+
"support": 33500.0
|
281 |
},
|
282 |
"step": 287
|
283 |
},
|
284 |
{
|
285 |
"epoch": 8.0,
|
286 |
"eval_B": {
|
287 |
+
"f1-score": 0.8742837883383889,
|
288 |
+
"precision": 0.8493778650949574,
|
289 |
+
"recall": 0.9006944444444445,
|
290 |
+
"support": 1440.0
|
291 |
},
|
292 |
"eval_I": {
|
293 |
+
"f1-score": 0.954344074989507,
|
294 |
+
"precision": 0.9607962815155641,
|
295 |
+
"recall": 0.9479779496919443,
|
296 |
+
"support": 21587.0
|
297 |
},
|
298 |
"eval_O": {
|
299 |
+
"f1-score": 0.9060386816096845,
|
300 |
+
"precision": 0.8975079632752483,
|
301 |
+
"recall": 0.9147331232693593,
|
302 |
+
"support": 10473.0
|
303 |
},
|
304 |
+
"eval_accuracy": 0.9355522388059702,
|
305 |
+
"eval_loss": 0.2697383165359497,
|
306 |
"eval_macro avg": {
|
307 |
+
"f1-score": 0.9115555149791934,
|
308 |
+
"precision": 0.9025607032952566,
|
309 |
+
"recall": 0.9211351724685827,
|
310 |
+
"support": 33500.0
|
311 |
+
},
|
312 |
+
"eval_runtime": 1.3839,
|
313 |
+
"eval_samples_per_second": 58.529,
|
314 |
+
"eval_steps_per_second": 7.948,
|
315 |
"eval_weighted avg": {
|
316 |
+
"f1-score": 0.9358011138657909,
|
317 |
+
"precision": 0.9362213240058178,
|
318 |
+
"recall": 0.9355522388059702,
|
319 |
+
"support": 33500.0
|
320 |
},
|
321 |
"step": 328
|
322 |
},
|
323 |
{
|
324 |
"epoch": 9.0,
|
325 |
"eval_B": {
|
326 |
+
"f1-score": 0.8867732063923836,
|
327 |
+
"precision": 0.8687541638907396,
|
328 |
+
"recall": 0.9055555555555556,
|
329 |
+
"support": 1440.0
|
330 |
},
|
331 |
"eval_I": {
|
332 |
+
"f1-score": 0.9593785402168635,
|
333 |
+
"precision": 0.9576294655220161,
|
334 |
+
"recall": 0.9611340158428684,
|
335 |
+
"support": 21587.0
|
336 |
},
|
337 |
"eval_O": {
|
338 |
+
"f1-score": 0.9133903681630298,
|
339 |
+
"precision": 0.9195780509048679,
|
340 |
+
"recall": 0.907285400553805,
|
341 |
+
"support": 10473.0
|
342 |
},
|
343 |
+
"eval_accuracy": 0.941910447761194,
|
344 |
+
"eval_loss": 0.236963152885437,
|
345 |
"eval_macro avg": {
|
346 |
+
"f1-score": 0.9198473715907589,
|
347 |
+
"precision": 0.9153205601058745,
|
348 |
+
"recall": 0.9246583239840763,
|
349 |
+
"support": 33500.0
|
350 |
+
},
|
351 |
+
"eval_runtime": 1.3821,
|
352 |
+
"eval_samples_per_second": 58.608,
|
353 |
+
"eval_steps_per_second": 7.959,
|
354 |
"eval_weighted avg": {
|
355 |
+
"f1-score": 0.9418804564369516,
|
356 |
+
"precision": 0.9419132595627793,
|
357 |
+
"recall": 0.941910447761194,
|
358 |
+
"support": 33500.0
|
359 |
},
|
360 |
"step": 369
|
361 |
},
|
362 |
{
|
363 |
"epoch": 10.0,
|
364 |
"eval_B": {
|
365 |
+
"f1-score": 0.8820989704417137,
|
366 |
+
"precision": 0.8453214513049013,
|
367 |
+
"recall": 0.9222222222222223,
|
368 |
+
"support": 1440.0
|
369 |
},
|
370 |
"eval_I": {
|
371 |
+
"f1-score": 0.9598799630655587,
|
372 |
+
"precision": 0.956655776929094,
|
373 |
+
"recall": 0.9631259554361421,
|
374 |
+
"support": 21587.0
|
375 |
},
|
376 |
"eval_O": {
|
377 |
+
"f1-score": 0.914896705210702,
|
378 |
+
"precision": 0.9273244409572381,
|
379 |
+
"recall": 0.9027976701995608,
|
380 |
+
"support": 10473.0
|
381 |
},
|
382 |
+
"eval_accuracy": 0.9425074626865672,
|
383 |
+
"eval_loss": 0.27435505390167236,
|
384 |
"eval_macro avg": {
|
385 |
+
"f1-score": 0.9189585462393248,
|
386 |
+
"precision": 0.9097672230637445,
|
387 |
+
"recall": 0.9293819492859751,
|
388 |
+
"support": 33500.0
|
389 |
+
},
|
390 |
+
"eval_runtime": 1.375,
|
391 |
+
"eval_samples_per_second": 58.909,
|
392 |
+
"eval_steps_per_second": 8.0,
|
393 |
"eval_weighted avg": {
|
394 |
+
"f1-score": 0.9424735663822079,
|
395 |
+
"precision": 0.9427002990027631,
|
396 |
+
"recall": 0.9425074626865672,
|
397 |
+
"support": 33500.0
|
398 |
},
|
399 |
"step": 410
|
400 |
},
|
401 |
{
|
402 |
"epoch": 11.0,
|
403 |
"eval_B": {
|
404 |
+
"f1-score": 0.8886590830748018,
|
405 |
+
"precision": 0.8822724161533196,
|
406 |
+
"recall": 0.8951388888888889,
|
407 |
+
"support": 1440.0
|
408 |
},
|
409 |
"eval_I": {
|
410 |
+
"f1-score": 0.9554279336882978,
|
411 |
+
"precision": 0.9591074596209505,
|
412 |
+
"recall": 0.9517765321721406,
|
413 |
+
"support": 21587.0
|
414 |
},
|
415 |
"eval_O": {
|
416 |
+
"f1-score": 0.9066856330014225,
|
417 |
+
"precision": 0.9005368748233964,
|
418 |
+
"recall": 0.91291893440275,
|
419 |
+
"support": 10473.0
|
420 |
},
|
421 |
+
"eval_accuracy": 0.9371940298507463,
|
422 |
+
"eval_loss": 0.29653802514076233,
|
423 |
"eval_macro avg": {
|
424 |
+
"f1-score": 0.916924216588174,
|
425 |
+
"precision": 0.9139722501992221,
|
426 |
+
"recall": 0.9199447851545933,
|
427 |
+
"support": 33500.0
|
428 |
+
},
|
429 |
+
"eval_runtime": 1.3782,
|
430 |
+
"eval_samples_per_second": 58.771,
|
431 |
+
"eval_steps_per_second": 7.981,
|
432 |
"eval_weighted avg": {
|
433 |
+
"f1-score": 0.9373197169725641,
|
434 |
+
"precision": 0.9374939611977214,
|
435 |
+
"recall": 0.9371940298507463,
|
436 |
+
"support": 33500.0
|
437 |
},
|
438 |
"step": 451
|
439 |
},
|
440 |
{
|
441 |
"epoch": 12.0,
|
442 |
"eval_B": {
|
443 |
+
"f1-score": 0.8851788756388416,
|
444 |
+
"precision": 0.8688963210702341,
|
445 |
+
"recall": 0.9020833333333333,
|
446 |
+
"support": 1440.0
|
447 |
},
|
448 |
"eval_I": {
|
449 |
+
"f1-score": 0.956586582154592,
|
450 |
+
"precision": 0.9624402138235019,
|
451 |
+
"recall": 0.9508037244637977,
|
452 |
+
"support": 21587.0
|
453 |
},
|
454 |
"eval_O": {
|
455 |
+
"f1-score": 0.9096066565809379,
|
456 |
+
"precision": 0.9008334113681056,
|
457 |
+
"recall": 0.9185524682516948,
|
458 |
+
"support": 10473.0
|
459 |
},
|
460 |
+
"eval_accuracy": 0.9386268656716418,
|
461 |
+
"eval_loss": 0.3317875564098358,
|
462 |
"eval_macro avg": {
|
463 |
+
"f1-score": 0.9171240381247904,
|
464 |
+
"precision": 0.9107233154206137,
|
465 |
+
"recall": 0.9238131753496086,
|
466 |
+
"support": 33500.0
|
467 |
+
},
|
468 |
+
"eval_runtime": 1.3866,
|
469 |
+
"eval_samples_per_second": 58.418,
|
470 |
+
"eval_steps_per_second": 7.933,
|
471 |
"eval_weighted avg": {
|
472 |
+
"f1-score": 0.9388299296795006,
|
473 |
+
"precision": 0.9391592810569325,
|
474 |
+
"recall": 0.9386268656716418,
|
475 |
+
"support": 33500.0
|
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 sha256:9afc9010526d77714317ce08b144ea519027c2bf7e4a39f3188a1467d7fdf528
|
3 |
size 4664
|