Dr. Jorge Abreu Vicente
commited on
Commit
•
7eae63a
1
Parent(s):
50526a5
Training in progress, step 3000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +135 -3
- pytorch_model.bin +1 -1
- runs/May20_12-43-43_9288e76c4417/events.out.tfevents.1653050648.9288e76c4417.830.0 +2 -2
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 861965029
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0955c1d3b650c9c643c7f2178954f57982b9878d21c7ba1e5fef1f25104b7e68
|
3 |
size 861965029
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 431008241
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:92b2fea8cd086661eb988c0bea7b142c1c168e6b3db297f20e8b9b74ffd60ccc
|
3 |
size 431008241
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 17563
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d51440174fac5a2f22180e2bf7f977b03667d6fdb023d528355e7cdff335590f
|
3 |
size 17563
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 623
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:90caf14b68a6b815c7f5bccb73a9ee2a50f47182fd7f745e59257531952eaeb8
|
3 |
size 623
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": 0.771723286444866,
|
3 |
"best_model_checkpoint": "./tokcl_models/EMBO_bert-base-cased_NER-task/checkpoint-2000",
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -270,11 +270,143 @@
|
|
270 |
"eval_samples_per_second": 123.555,
|
271 |
"eval_steps_per_second": 0.967,
|
272 |
"step": 2000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
273 |
}
|
274 |
],
|
275 |
"max_steps": 3815,
|
276 |
"num_train_epochs": 5,
|
277 |
-
"total_flos":
|
278 |
"trial_name": null,
|
279 |
"trial_params": null
|
280 |
}
|
1 |
{
|
2 |
"best_metric": 0.771723286444866,
|
3 |
"best_model_checkpoint": "./tokcl_models/EMBO_bert-base-cased_NER-task/checkpoint-2000",
|
4 |
+
"epoch": 3.9318479685452163,
|
5 |
+
"global_step": 3000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
270 |
"eval_samples_per_second": 123.555,
|
271 |
"eval_steps_per_second": 0.967,
|
272 |
"step": 2000
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 2.69,
|
276 |
+
"learning_rate": 0.00023132372214941022,
|
277 |
+
"loss": 0.1305,
|
278 |
+
"step": 2050
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 2.75,
|
282 |
+
"learning_rate": 0.00022477064220183487,
|
283 |
+
"loss": 0.1243,
|
284 |
+
"step": 2100
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 2.82,
|
288 |
+
"learning_rate": 0.00021821756225425952,
|
289 |
+
"loss": 0.1265,
|
290 |
+
"step": 2150
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 2.88,
|
294 |
+
"learning_rate": 0.00021166448230668415,
|
295 |
+
"loss": 0.133,
|
296 |
+
"step": 2200
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 2.95,
|
300 |
+
"learning_rate": 0.00020511140235910877,
|
301 |
+
"loss": 0.1298,
|
302 |
+
"step": 2250
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 3.01,
|
306 |
+
"learning_rate": 0.00019855832241153344,
|
307 |
+
"loss": 0.123,
|
308 |
+
"step": 2300
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 3.08,
|
312 |
+
"learning_rate": 0.00019200524246395807,
|
313 |
+
"loss": 0.0871,
|
314 |
+
"step": 2350
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 3.15,
|
318 |
+
"learning_rate": 0.0001854521625163827,
|
319 |
+
"loss": 0.086,
|
320 |
+
"step": 2400
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 3.21,
|
324 |
+
"learning_rate": 0.00017889908256880736,
|
325 |
+
"loss": 0.0928,
|
326 |
+
"step": 2450
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 3.28,
|
330 |
+
"learning_rate": 0.000172346002621232,
|
331 |
+
"loss": 0.083,
|
332 |
+
"step": 2500
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 3.34,
|
336 |
+
"learning_rate": 0.0001657929226736566,
|
337 |
+
"loss": 0.0918,
|
338 |
+
"step": 2550
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 3.41,
|
342 |
+
"learning_rate": 0.00015923984272608129,
|
343 |
+
"loss": 0.0849,
|
344 |
+
"step": 2600
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 3.47,
|
348 |
+
"learning_rate": 0.0001526867627785059,
|
349 |
+
"loss": 0.0863,
|
350 |
+
"step": 2650
|
351 |
+
},
|
352 |
+
{
|
353 |
+
"epoch": 3.54,
|
354 |
+
"learning_rate": 0.00014613368283093053,
|
355 |
+
"loss": 0.0865,
|
356 |
+
"step": 2700
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 3.6,
|
360 |
+
"learning_rate": 0.00013958060288335518,
|
361 |
+
"loss": 0.0827,
|
362 |
+
"step": 2750
|
363 |
+
},
|
364 |
+
{
|
365 |
+
"epoch": 3.67,
|
366 |
+
"learning_rate": 0.00013302752293577983,
|
367 |
+
"loss": 0.083,
|
368 |
+
"step": 2800
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 3.74,
|
372 |
+
"learning_rate": 0.00012647444298820445,
|
373 |
+
"loss": 0.0849,
|
374 |
+
"step": 2850
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 3.8,
|
378 |
+
"learning_rate": 0.0001199213630406291,
|
379 |
+
"loss": 0.0813,
|
380 |
+
"step": 2900
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 3.87,
|
384 |
+
"learning_rate": 0.00011336828309305374,
|
385 |
+
"loss": 0.0873,
|
386 |
+
"step": 2950
|
387 |
+
},
|
388 |
+
{
|
389 |
+
"epoch": 3.93,
|
390 |
+
"learning_rate": 0.00010681520314547838,
|
391 |
+
"loss": 0.0808,
|
392 |
+
"step": 3000
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"epoch": 3.93,
|
396 |
+
"eval_accuracy_score": 0.909553294853392,
|
397 |
+
"eval_f1": 0.7627703980346628,
|
398 |
+
"eval_loss": 0.3164892792701721,
|
399 |
+
"eval_precision": 0.7620479900951458,
|
400 |
+
"eval_recall": 0.7634941769335782,
|
401 |
+
"eval_runtime": 111.6078,
|
402 |
+
"eval_samples_per_second": 123.656,
|
403 |
+
"eval_steps_per_second": 0.968,
|
404 |
+
"step": 3000
|
405 |
}
|
406 |
],
|
407 |
"max_steps": 3815,
|
408 |
"num_train_epochs": 5,
|
409 |
+
"total_flos": 3.419886505231602e+16,
|
410 |
"trial_name": null,
|
411 |
"trial_params": null
|
412 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 431008241
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:92b2fea8cd086661eb988c0bea7b142c1c168e6b3db297f20e8b9b74ffd60ccc
|
3 |
size 431008241
|
runs/May20_12-43-43_9288e76c4417/events.out.tfevents.1653050648.9288e76c4417.830.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e4b13de66060a370e6de71ea674d2e02faa4ec319763ec20f9ff2d1e8b45be73
|
3 |
+
size 15021
|