Commit
•
e570d6b
1
Parent(s):
b7e6ae0
End of training
Browse files- all_results.json +5 -5
- train_results.json +5 -5
- trainer_state.json +116 -22
all_results.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"train_loss": 0.
|
4 |
-
"train_runtime":
|
5 |
-
"train_samples_per_second":
|
6 |
-
"train_steps_per_second": 0.
|
7 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 20.0,
|
3 |
+
"train_loss": 0.2986434628709249,
|
4 |
+
"train_runtime": 16684.611,
|
5 |
+
"train_samples_per_second": 119.871,
|
6 |
+
"train_steps_per_second": 0.832
|
7 |
}
|
train_results.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"train_loss": 0.
|
4 |
-
"train_runtime":
|
5 |
-
"train_samples_per_second":
|
6 |
-
"train_steps_per_second": 0.
|
7 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 20.0,
|
3 |
+
"train_loss": 0.2986434628709249,
|
4 |
+
"train_runtime": 16684.611,
|
5 |
+
"train_samples_per_second": 119.871,
|
6 |
+
"train_steps_per_second": 0.832
|
7 |
}
|
trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -365,37 +365,131 @@
|
|
365 |
"step": 11000
|
366 |
},
|
367 |
{
|
368 |
-
"epoch":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
369 |
"eval_f1": 0.9134,
|
370 |
-
"eval_gen_len": 25.
|
371 |
-
"eval_loss": 1.
|
372 |
"eval_precision": 0.9133,
|
373 |
"eval_recall": 0.9138,
|
374 |
-
"eval_rouge1": 0.
|
375 |
-
"eval_rouge2": 0.
|
376 |
-
"eval_rougeL": 0.
|
377 |
-
"eval_rougeLsum": 0.
|
378 |
-
"eval_runtime":
|
379 |
-
"eval_samples_per_second": 6.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
380 |
"eval_steps_per_second": 0.398,
|
381 |
-
"step":
|
382 |
},
|
383 |
{
|
384 |
-
"epoch":
|
385 |
-
"step":
|
386 |
-
"total_flos": 2.
|
387 |
-
"train_loss": 0.
|
388 |
-
"train_runtime":
|
389 |
-
"train_samples_per_second":
|
390 |
-
"train_steps_per_second": 0.
|
391 |
}
|
392 |
],
|
393 |
"logging_steps": 500,
|
394 |
-
"max_steps":
|
395 |
"num_input_tokens_seen": 0,
|
396 |
-
"num_train_epochs":
|
397 |
"save_steps": 500,
|
398 |
-
"total_flos": 2.
|
399 |
"train_batch_size": 24,
|
400 |
"trial_name": null,
|
401 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 19.99640028797696,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 13880,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
365 |
"step": 11000
|
366 |
},
|
367 |
{
|
368 |
+
"epoch": 16.0,
|
369 |
+
"eval_f1": 0.9133,
|
370 |
+
"eval_gen_len": 26.034545454545455,
|
371 |
+
"eval_loss": 1.4474281072616577,
|
372 |
+
"eval_precision": 0.9131,
|
373 |
+
"eval_recall": 0.9139,
|
374 |
+
"eval_rouge1": 0.4942,
|
375 |
+
"eval_rouge2": 0.2456,
|
376 |
+
"eval_rougeL": 0.4133,
|
377 |
+
"eval_rougeLsum": 0.4134,
|
378 |
+
"eval_runtime": 875.1275,
|
379 |
+
"eval_samples_per_second": 6.285,
|
380 |
+
"eval_steps_per_second": 0.393,
|
381 |
+
"step": 11104
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 16.57,
|
385 |
+
"learning_rate": 3.4293948126801158e-06,
|
386 |
+
"loss": 1.4441,
|
387 |
+
"step": 11500
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 17.0,
|
391 |
"eval_f1": 0.9134,
|
392 |
+
"eval_gen_len": 25.939090909090908,
|
393 |
+
"eval_loss": 1.4446682929992676,
|
394 |
"eval_precision": 0.9133,
|
395 |
"eval_recall": 0.9138,
|
396 |
+
"eval_rouge1": 0.4945,
|
397 |
+
"eval_rouge2": 0.2457,
|
398 |
+
"eval_rougeL": 0.4139,
|
399 |
+
"eval_rougeLsum": 0.414,
|
400 |
+
"eval_runtime": 853.4658,
|
401 |
+
"eval_samples_per_second": 6.444,
|
402 |
+
"eval_steps_per_second": 0.403,
|
403 |
+
"step": 11799
|
404 |
+
},
|
405 |
+
{
|
406 |
+
"epoch": 17.29,
|
407 |
+
"learning_rate": 2.708933717579251e-06,
|
408 |
+
"loss": 1.444,
|
409 |
+
"step": 12000
|
410 |
+
},
|
411 |
+
{
|
412 |
+
"epoch": 18.0,
|
413 |
+
"eval_f1": 0.9135,
|
414 |
+
"eval_gen_len": 26.010727272727273,
|
415 |
+
"eval_loss": 1.4445807933807373,
|
416 |
+
"eval_precision": 0.9133,
|
417 |
+
"eval_recall": 0.9141,
|
418 |
+
"eval_rouge1": 0.4957,
|
419 |
+
"eval_rouge2": 0.2473,
|
420 |
+
"eval_rougeL": 0.415,
|
421 |
+
"eval_rougeLsum": 0.4151,
|
422 |
+
"eval_runtime": 869.7396,
|
423 |
+
"eval_samples_per_second": 6.324,
|
424 |
+
"eval_steps_per_second": 0.396,
|
425 |
+
"step": 12493
|
426 |
+
},
|
427 |
+
{
|
428 |
+
"epoch": 18.01,
|
429 |
+
"learning_rate": 1.988472622478386e-06,
|
430 |
+
"loss": 1.4378,
|
431 |
+
"step": 12500
|
432 |
+
},
|
433 |
+
{
|
434 |
+
"epoch": 18.73,
|
435 |
+
"learning_rate": 1.2680115273775217e-06,
|
436 |
+
"loss": 1.4375,
|
437 |
+
"step": 13000
|
438 |
+
},
|
439 |
+
{
|
440 |
+
"epoch": 19.0,
|
441 |
+
"eval_f1": 0.9136,
|
442 |
+
"eval_gen_len": 25.88690909090909,
|
443 |
+
"eval_loss": 1.4433233737945557,
|
444 |
+
"eval_precision": 0.9136,
|
445 |
+
"eval_recall": 0.914,
|
446 |
+
"eval_rouge1": 0.4961,
|
447 |
+
"eval_rouge2": 0.2473,
|
448 |
+
"eval_rougeL": 0.4153,
|
449 |
+
"eval_rougeLsum": 0.4153,
|
450 |
+
"eval_runtime": 854.4011,
|
451 |
+
"eval_samples_per_second": 6.437,
|
452 |
+
"eval_steps_per_second": 0.403,
|
453 |
+
"step": 13188
|
454 |
+
},
|
455 |
+
{
|
456 |
+
"epoch": 19.45,
|
457 |
+
"learning_rate": 5.475504322766571e-07,
|
458 |
+
"loss": 1.4361,
|
459 |
+
"step": 13500
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 20.0,
|
463 |
+
"eval_f1": 0.9137,
|
464 |
+
"eval_gen_len": 25.862909090909092,
|
465 |
+
"eval_loss": 1.4432713985443115,
|
466 |
+
"eval_precision": 0.9136,
|
467 |
+
"eval_recall": 0.914,
|
468 |
+
"eval_rouge1": 0.4961,
|
469 |
+
"eval_rouge2": 0.2476,
|
470 |
+
"eval_rougeL": 0.4155,
|
471 |
+
"eval_rougeLsum": 0.4154,
|
472 |
+
"eval_runtime": 863.7254,
|
473 |
+
"eval_samples_per_second": 6.368,
|
474 |
"eval_steps_per_second": 0.398,
|
475 |
+
"step": 13880
|
476 |
},
|
477 |
{
|
478 |
+
"epoch": 20.0,
|
479 |
+
"step": 13880,
|
480 |
+
"total_flos": 2.818047373345161e+18,
|
481 |
+
"train_loss": 0.2986434628709249,
|
482 |
+
"train_runtime": 16684.611,
|
483 |
+
"train_samples_per_second": 119.871,
|
484 |
+
"train_steps_per_second": 0.832
|
485 |
}
|
486 |
],
|
487 |
"logging_steps": 500,
|
488 |
+
"max_steps": 13880,
|
489 |
"num_input_tokens_seen": 0,
|
490 |
+
"num_train_epochs": 20,
|
491 |
"save_steps": 500,
|
492 |
+
"total_flos": 2.818047373345161e+18,
|
493 |
"train_batch_size": 24,
|
494 |
"trial_name": null,
|
495 |
"trial_params": null
|