Theoreticallyhugo
commited on
Commit
•
11e7834
1
Parent(s):
5d8d62a
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:ea06a7166e0cb6f67c545e8261fecfaa50b5ff2f245bee8491cbeb43c3ed0703
|
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:b453b657df9670e0c14adab9b5ef3ade6d8285ddd5c18130521bd050e85b646d
|
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 sha256:1c189466643703424c77db24cb1c70bb1b76b65752ddeeaa3d7bb424b6ea3dcb
|
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": 59.
|
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":
|
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":
|
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": 0.6054590570719602,
|
15 |
+
"precision": 0.8472222222222222,
|
16 |
+
"recall": 0.47104247104247104,
|
17 |
+
"support": 1295.0
|
18 |
},
|
19 |
"eval_I": {
|
20 |
+
"f1-score": 0.9281628372580799,
|
21 |
+
"precision": 0.8894522863277146,
|
22 |
+
"recall": 0.9703962123099925,
|
23 |
+
"support": 20065.0
|
24 |
},
|
25 |
"eval_O": {
|
26 |
+
"f1-score": 0.826809241932404,
|
27 |
+
"precision": 0.8983402489626556,
|
28 |
+
"recall": 0.7658295012380616,
|
29 |
+
"support": 8481.0
|
30 |
},
|
31 |
+
"eval_accuracy": 0.8905867765825543,
|
32 |
+
"eval_loss": 0.3152744174003601,
|
33 |
"eval_macro avg": {
|
34 |
+
"f1-score": 0.786810378754148,
|
35 |
+
"precision": 0.8783382525041974,
|
36 |
+
"recall": 0.735756061530175,
|
37 |
+
"support": 29841.0
|
38 |
+
},
|
39 |
+
"eval_runtime": 1.3493,
|
40 |
+
"eval_samples_per_second": 59.291,
|
41 |
+
"eval_steps_per_second": 7.411,
|
42 |
"eval_weighted avg": {
|
43 |
+
"f1-score": 0.8853532384745914,
|
44 |
+
"precision": 0.8901456571293072,
|
45 |
+
"recall": 0.8905867765825543,
|
46 |
+
"support": 29841.0
|
47 |
},
|
48 |
"step": 41
|
49 |
},
|
50 |
{
|
51 |
"epoch": 2.0,
|
52 |
"eval_B": {
|
53 |
+
"f1-score": 0.8510791366906474,
|
54 |
+
"precision": 0.7966329966329966,
|
55 |
+
"recall": 0.9135135135135135,
|
56 |
+
"support": 1295.0
|
57 |
},
|
58 |
"eval_I": {
|
59 |
+
"f1-score": 0.9477035236938031,
|
60 |
+
"precision": 0.9247806497510078,
|
61 |
+
"recall": 0.9717916770495888,
|
62 |
+
"support": 20065.0
|
63 |
},
|
64 |
"eval_O": {
|
65 |
+
"f1-score": 0.8622397155916709,
|
66 |
+
"precision": 0.9339843212763032,
|
67 |
+
"recall": 0.8007310458672326,
|
68 |
+
"support": 8481.0
|
69 |
},
|
70 |
+
"eval_accuracy": 0.9206460909486948,
|
71 |
+
"eval_loss": 0.22530655562877655,
|
72 |
"eval_macro avg": {
|
73 |
+
"f1-score": 0.8870074586587071,
|
74 |
+
"precision": 0.8851326558867693,
|
75 |
+
"recall": 0.895345412143445,
|
76 |
+
"support": 29841.0
|
77 |
+
},
|
78 |
+
"eval_runtime": 1.356,
|
79 |
+
"eval_samples_per_second": 58.999,
|
80 |
+
"eval_steps_per_second": 7.375,
|
81 |
"eval_weighted avg": {
|
82 |
+
"f1-score": 0.9192209950358067,
|
83 |
+
"precision": 0.9218352098333846,
|
84 |
+
"recall": 0.9206460909486948,
|
85 |
+
"support": 29841.0
|
86 |
},
|
87 |
"step": 82
|
88 |
},
|
89 |
{
|
90 |
"epoch": 3.0,
|
91 |
"eval_B": {
|
92 |
+
"f1-score": 0.8718693284936478,
|
93 |
+
"precision": 0.8226027397260274,
|
94 |
+
"recall": 0.9274131274131274,
|
95 |
+
"support": 1295.0
|
96 |
},
|
97 |
"eval_I": {
|
98 |
+
"f1-score": 0.95727385377943,
|
99 |
+
"precision": 0.9520828198175992,
|
100 |
+
"recall": 0.9625218041365562,
|
101 |
+
"support": 20065.0
|
102 |
},
|
103 |
"eval_O": {
|
104 |
+
"f1-score": 0.8947336671291549,
|
105 |
+
"precision": 0.91600790513834,
|
106 |
+
"recall": 0.8744251857092324,
|
107 |
+
"support": 8481.0
|
108 |
},
|
109 |
+
"eval_accuracy": 0.9359605911330049,
|
110 |
+
"eval_loss": 0.18091395497322083,
|
111 |
"eval_macro avg": {
|
112 |
+
"f1-score": 0.9079589498007442,
|
113 |
+
"precision": 0.8968978215606556,
|
114 |
+
"recall": 0.9214533724196388,
|
115 |
+
"support": 29841.0
|
116 |
+
},
|
117 |
+
"eval_runtime": 1.3616,
|
118 |
+
"eval_samples_per_second": 58.756,
|
119 |
+
"eval_steps_per_second": 7.344,
|
120 |
"eval_weighted avg": {
|
121 |
+
"f1-score": 0.9357932672298482,
|
122 |
+
"precision": 0.9362110978540797,
|
123 |
+
"recall": 0.9359605911330049,
|
124 |
+
"support": 29841.0
|
125 |
},
|
126 |
"step": 123
|
127 |
},
|
128 |
{
|
129 |
"epoch": 4.0,
|
130 |
"eval_B": {
|
131 |
+
"f1-score": 0.8863383931877082,
|
132 |
+
"precision": 0.8513513513513513,
|
133 |
+
"recall": 0.9243243243243243,
|
134 |
+
"support": 1295.0
|
135 |
},
|
136 |
"eval_I": {
|
137 |
+
"f1-score": 0.9597514129823103,
|
138 |
+
"precision": 0.942660770931462,
|
139 |
+
"recall": 0.9774732120608024,
|
140 |
+
"support": 20065.0
|
141 |
},
|
142 |
"eval_O": {
|
143 |
+
"f1-score": 0.8954686530105526,
|
144 |
+
"precision": 0.9454712282081531,
|
145 |
+
"recall": 0.8504893290885509,
|
146 |
+
"support": 8481.0
|
147 |
},
|
148 |
+
"eval_accuracy": 0.9390771086759827,
|
149 |
+
"eval_loss": 0.19618020951747894,
|
150 |
"eval_macro avg": {
|
151 |
+
"f1-score": 0.913852819726857,
|
152 |
+
"precision": 0.9131611168303221,
|
153 |
+
"recall": 0.9174289551578925,
|
154 |
+
"support": 29841.0
|
155 |
+
},
|
156 |
+
"eval_runtime": 1.355,
|
157 |
+
"eval_samples_per_second": 59.041,
|
158 |
+
"eval_steps_per_second": 7.38,
|
159 |
"eval_weighted avg": {
|
160 |
+
"f1-score": 0.9382959675228925,
|
161 |
+
"precision": 0.9394969959174669,
|
162 |
+
"recall": 0.9390771086759827,
|
163 |
+
"support": 29841.0
|
164 |
},
|
165 |
"step": 164
|
166 |
},
|
167 |
{
|
168 |
"epoch": 5.0,
|
169 |
"eval_B": {
|
170 |
+
"f1-score": 0.8794862108046846,
|
171 |
+
"precision": 0.8609467455621301,
|
172 |
+
"recall": 0.8988416988416988,
|
173 |
+
"support": 1295.0
|
174 |
},
|
175 |
"eval_I": {
|
176 |
+
"f1-score": 0.955187788105494,
|
177 |
+
"precision": 0.9656717938270347,
|
178 |
+
"recall": 0.9449289808123599,
|
179 |
+
"support": 20065.0
|
180 |
},
|
181 |
"eval_O": {
|
182 |
+
"f1-score": 0.8953622519612366,
|
183 |
+
"precision": 0.8764539808018069,
|
184 |
+
"recall": 0.9151043509020163,
|
185 |
+
"support": 8481.0
|
186 |
},
|
187 |
+
"eval_accuracy": 0.9344525987734995,
|
188 |
+
"eval_loss": 0.1936398446559906,
|
189 |
"eval_macro avg": {
|
190 |
+
"f1-score": 0.9100120836238051,
|
191 |
+
"precision": 0.9010241733969906,
|
192 |
+
"recall": 0.9196250101853582,
|
193 |
+
"support": 29841.0
|
194 |
+
},
|
195 |
+
"eval_runtime": 1.3533,
|
196 |
+
"eval_samples_per_second": 59.115,
|
197 |
+
"eval_steps_per_second": 7.389,
|
198 |
"eval_weighted avg": {
|
199 |
+
"f1-score": 0.9348997979361299,
|
200 |
+
"precision": 0.9357708116290517,
|
201 |
+
"recall": 0.9344525987734995,
|
202 |
+
"support": 29841.0
|
203 |
},
|
204 |
"step": 205
|
205 |
},
|
206 |
{
|
207 |
"epoch": 6.0,
|
208 |
"eval_B": {
|
209 |
+
"f1-score": 0.8813928182807399,
|
210 |
+
"precision": 0.8310533515731874,
|
211 |
+
"recall": 0.9382239382239382,
|
212 |
+
"support": 1295.0
|
213 |
},
|
214 |
"eval_I": {
|
215 |
+
"f1-score": 0.9576389581878055,
|
216 |
+
"precision": 0.958739197762126,
|
217 |
+
"recall": 0.9565412409668577,
|
218 |
+
"support": 20065.0
|
219 |
},
|
220 |
"eval_O": {
|
221 |
+
"f1-score": 0.8994715278190131,
|
222 |
+
"precision": 0.9059808612440191,
|
223 |
+
"recall": 0.8930550642612899,
|
224 |
+
"support": 8481.0
|
225 |
},
|
226 |
+
"eval_accuracy": 0.9377031600817667,
|
227 |
+
"eval_loss": 0.19472843408584595,
|
228 |
"eval_macro avg": {
|
229 |
+
"f1-score": 0.9128344347625195,
|
230 |
+
"precision": 0.8985911368597775,
|
231 |
+
"recall": 0.9292734144840287,
|
232 |
+
"support": 29841.0
|
233 |
+
},
|
234 |
+
"eval_runtime": 1.351,
|
235 |
+
"eval_samples_per_second": 59.216,
|
236 |
+
"eval_steps_per_second": 7.402,
|
237 |
"eval_weighted avg": {
|
238 |
+
"f1-score": 0.9377985799116962,
|
239 |
+
"precision": 0.9382038060921168,
|
240 |
+
"recall": 0.9377031600817667,
|
241 |
+
"support": 29841.0
|
242 |
},
|
243 |
"step": 246
|
244 |
},
|
245 |
{
|
246 |
"epoch": 7.0,
|
247 |
"eval_B": {
|
248 |
+
"f1-score": 0.8952959028831563,
|
249 |
+
"precision": 0.8799403430275914,
|
250 |
+
"recall": 0.9111969111969112,
|
251 |
+
"support": 1295.0
|
252 |
},
|
253 |
"eval_I": {
|
254 |
+
"f1-score": 0.9592318906147891,
|
255 |
+
"precision": 0.9675979919882359,
|
256 |
+
"recall": 0.9510092200348866,
|
257 |
+
"support": 20065.0
|
258 |
},
|
259 |
"eval_O": {
|
260 |
+
"f1-score": 0.9041714947856316,
|
261 |
+
"precision": 0.8888256065611118,
|
262 |
+
"recall": 0.9200565970993987,
|
263 |
+
"support": 8481.0
|
264 |
},
|
265 |
+
"eval_accuracy": 0.940484568211521,
|
266 |
+
"eval_loss": 0.20142190158367157,
|
267 |
"eval_macro avg": {
|
268 |
+
"f1-score": 0.919566429427859,
|
269 |
+
"precision": 0.9121213138589797,
|
270 |
+
"recall": 0.9274209094437321,
|
271 |
+
"support": 29841.0
|
272 |
+
},
|
273 |
+
"eval_runtime": 1.3501,
|
274 |
+
"eval_samples_per_second": 59.256,
|
275 |
+
"eval_steps_per_second": 7.407,
|
276 |
"eval_weighted avg": {
|
277 |
+
"f1-score": 0.9408087707079646,
|
278 |
+
"precision": 0.9414063343289258,
|
279 |
+
"recall": 0.940484568211521,
|
280 |
+
"support": 29841.0
|
281 |
},
|
282 |
"step": 287
|
283 |
},
|
284 |
{
|
285 |
"epoch": 8.0,
|
286 |
"eval_B": {
|
287 |
+
"f1-score": 0.8921130952380952,
|
288 |
+
"precision": 0.8607322325915291,
|
289 |
+
"recall": 0.9258687258687258,
|
290 |
+
"support": 1295.0
|
291 |
},
|
292 |
"eval_I": {
|
293 |
+
"f1-score": 0.9613341204250295,
|
294 |
+
"precision": 0.9490554125588849,
|
295 |
+
"recall": 0.9739347121853975,
|
296 |
+
"support": 20065.0
|
297 |
},
|
298 |
"eval_O": {
|
299 |
+
"f1-score": 0.9013343126453666,
|
300 |
+
"precision": 0.9371261295659921,
|
301 |
+
"recall": 0.8681759226506308,
|
302 |
+
"support": 8481.0
|
303 |
},
|
304 |
+
"eval_accuracy": 0.9417914949230924,
|
305 |
+
"eval_loss": 0.21689558029174805,
|
306 |
"eval_macro avg": {
|
307 |
+
"f1-score": 0.9182605094361639,
|
308 |
+
"precision": 0.9156379249054686,
|
309 |
+
"recall": 0.9226597869015847,
|
310 |
+
"support": 29841.0
|
311 |
+
},
|
312 |
+
"eval_runtime": 1.3576,
|
313 |
+
"eval_samples_per_second": 58.928,
|
314 |
+
"eval_steps_per_second": 7.366,
|
315 |
"eval_weighted avg": {
|
316 |
+
"f1-score": 0.9412778355352336,
|
317 |
+
"precision": 0.9418321034499257,
|
318 |
+
"recall": 0.9417914949230924,
|
319 |
+
"support": 29841.0
|
320 |
},
|
321 |
"step": 328
|
322 |
},
|
323 |
{
|
324 |
"epoch": 9.0,
|
325 |
"eval_B": {
|
326 |
+
"f1-score": 0.8985947588302315,
|
327 |
+
"precision": 0.8841554559043349,
|
328 |
+
"recall": 0.9135135135135135,
|
329 |
+
"support": 1295.0
|
330 |
},
|
331 |
"eval_I": {
|
332 |
+
"f1-score": 0.9622013609496847,
|
333 |
+
"precision": 0.958962427602594,
|
334 |
+
"recall": 0.9654622476949912,
|
335 |
+
"support": 20065.0
|
336 |
},
|
337 |
"eval_O": {
|
338 |
+
"f1-score": 0.9079425609247452,
|
339 |
+
"precision": 0.9177306673090821,
|
340 |
+
"recall": 0.8983610423299139,
|
341 |
+
"support": 8481.0
|
342 |
},
|
343 |
+
"eval_accuracy": 0.9441372608156563,
|
344 |
+
"eval_loss": 0.23563022911548615,
|
345 |
"eval_macro avg": {
|
346 |
+
"f1-score": 0.9229128935682205,
|
347 |
+
"precision": 0.9202828502720036,
|
348 |
+
"recall": 0.9257789345128061,
|
349 |
+
"support": 29841.0
|
350 |
+
},
|
351 |
+
"eval_runtime": 1.3543,
|
352 |
+
"eval_samples_per_second": 59.071,
|
353 |
+
"eval_steps_per_second": 7.384,
|
354 |
"eval_weighted avg": {
|
355 |
+
"f1-score": 0.944020353853535,
|
356 |
+
"precision": 0.9439977284504704,
|
357 |
+
"recall": 0.9441372608156563,
|
358 |
+
"support": 29841.0
|
359 |
},
|
360 |
"step": 369
|
361 |
},
|
362 |
{
|
363 |
"epoch": 10.0,
|
364 |
"eval_B": {
|
365 |
+
"f1-score": 0.883806713389893,
|
366 |
+
"precision": 0.846045197740113,
|
367 |
+
"recall": 0.9250965250965251,
|
368 |
+
"support": 1295.0
|
369 |
},
|
370 |
"eval_I": {
|
371 |
+
"f1-score": 0.9612357047378584,
|
372 |
+
"precision": 0.9549009000147544,
|
373 |
+
"recall": 0.9676551208572141,
|
374 |
+
"support": 20065.0
|
375 |
},
|
376 |
"eval_O": {
|
377 |
+
"f1-score": 0.904241839135944,
|
378 |
+
"precision": 0.9259762728620861,
|
379 |
+
"recall": 0.8835043037377668,
|
380 |
+
"support": 8481.0
|
381 |
},
|
382 |
+
"eval_accuracy": 0.9418920277470594,
|
383 |
+
"eval_loss": 0.2491447478532791,
|
384 |
"eval_macro avg": {
|
385 |
+
"f1-score": 0.9164280857545651,
|
386 |
+
"precision": 0.9089741235389845,
|
387 |
+
"recall": 0.9254186498971686,
|
388 |
+
"support": 29841.0
|
389 |
+
},
|
390 |
+
"eval_runtime": 1.3513,
|
391 |
+
"eval_samples_per_second": 59.204,
|
392 |
+
"eval_steps_per_second": 7.401,
|
393 |
"eval_weighted avg": {
|
394 |
+
"f1-score": 0.9416775291416837,
|
395 |
+
"precision": 0.941956364063297,
|
396 |
+
"recall": 0.9418920277470594,
|
397 |
+
"support": 29841.0
|
398 |
},
|
399 |
"step": 410
|
400 |
},
|
401 |
{
|
402 |
"epoch": 11.0,
|
403 |
"eval_B": {
|
404 |
+
"f1-score": 0.8962935230250841,
|
405 |
+
"precision": 0.8699127906976745,
|
406 |
+
"recall": 0.9243243243243243,
|
407 |
+
"support": 1295.0
|
408 |
},
|
409 |
"eval_I": {
|
410 |
+
"f1-score": 0.9609275419158742,
|
411 |
+
"precision": 0.9454922579711543,
|
412 |
+
"recall": 0.9768751557438325,
|
413 |
+
"support": 20065.0
|
414 |
},
|
415 |
"eval_O": {
|
416 |
+
"f1-score": 0.8992907801418439,
|
417 |
+
"precision": 0.9427204551331781,
|
418 |
+
"recall": 0.8596863577408325,
|
419 |
+
"support": 8481.0
|
420 |
},
|
421 |
+
"eval_accuracy": 0.9412888308032573,
|
422 |
+
"eval_loss": 0.2823159396648407,
|
423 |
"eval_macro avg": {
|
424 |
+
"f1-score": 0.9188372816942675,
|
425 |
+
"precision": 0.9193751679340023,
|
426 |
+
"recall": 0.9202952792696631,
|
427 |
+
"support": 29841.0
|
428 |
+
},
|
429 |
+
"eval_runtime": 1.359,
|
430 |
+
"eval_samples_per_second": 58.865,
|
431 |
+
"eval_steps_per_second": 7.358,
|
432 |
"eval_weighted avg": {
|
433 |
+
"f1-score": 0.9406050851929385,
|
434 |
+
"precision": 0.9414245970352596,
|
435 |
+
"recall": 0.9412888308032573,
|
436 |
+
"support": 29841.0
|
437 |
},
|
438 |
"step": 451
|
439 |
},
|
440 |
{
|
441 |
"epoch": 12.0,
|
442 |
"eval_B": {
|
443 |
+
"f1-score": 0.896006028636021,
|
444 |
+
"precision": 0.8749080206033848,
|
445 |
+
"recall": 0.9181467181467181,
|
446 |
+
"support": 1295.0
|
447 |
},
|
448 |
"eval_I": {
|
449 |
+
"f1-score": 0.9606028094513335,
|
450 |
+
"precision": 0.9618267212950934,
|
451 |
+
"recall": 0.9593820084724645,
|
452 |
+
"support": 20065.0
|
453 |
},
|
454 |
"eval_O": {
|
455 |
+
"f1-score": 0.9053041477373296,
|
456 |
+
"precision": 0.9059990552668871,
|
457 |
+
"recall": 0.9046103053885155,
|
458 |
+
"support": 8481.0
|
459 |
},
|
460 |
+
"eval_accuracy": 0.9420260715123487,
|
461 |
+
"eval_loss": 0.2665592133998871,
|
462 |
"eval_macro avg": {
|
463 |
+
"f1-score": 0.9206376619415613,
|
464 |
+
"precision": 0.9142445990551217,
|
465 |
+
"recall": 0.9273796773358992,
|
466 |
+
"support": 29841.0
|
467 |
+
},
|
468 |
+
"eval_runtime": 1.3553,
|
469 |
+
"eval_samples_per_second": 59.028,
|
470 |
+
"eval_steps_per_second": 7.379,
|
471 |
"eval_weighted avg": {
|
472 |
+
"f1-score": 0.9420832966618057,
|
473 |
+
"precision": 0.9421881651816595,
|
474 |
+
"recall": 0.9420260715123487,
|
475 |
+
"support": 29841.0
|
476 |
},
|
477 |
"step": 492
|
478 |
}
|
|
|
482 |
"num_input_tokens_seen": 0,
|
483 |
"num_train_epochs": 16,
|
484 |
"save_steps": 500,
|
485 |
+
"total_flos": 1725439832827200.0,
|
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:bfd4286d28d76d8e118be26c28e11f81993aa41382921ccbb13e9cdeb7b58cf4
|
3 |
size 4664
|