Training in progress, step 72000, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 469337272
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bc5ba4b46dd67e2a49a16bd82facc11222fece8f84dc62617b2e908b04f6c169
|
| 3 |
size 469337272
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 938825803
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:be2468544f1374c838edfcc2826cfea73f333398467978c2e92f3248e38f729a
|
| 3 |
size 938825803
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a37fbaec01f56c5e37b1a1afe260103cefbac9e7d19fccf924630793e4ba7a84
|
| 3 |
size 14645
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:899e7c047ffeacb320a881df994af73296a60acae9cbaa8b910682541dc7eed6
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 0.
|
| 6 |
"eval_steps": 1000,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -5312,6 +5312,318 @@
|
|
| 5312 |
"eval_samples_per_second": 77.454,
|
| 5313 |
"eval_steps_per_second": 19.363,
|
| 5314 |
"step": 68000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5315 |
}
|
| 5316 |
],
|
| 5317 |
"logging_steps": 100,
|
|
@@ -5331,7 +5643,7 @@
|
|
| 5331 |
"attributes": {}
|
| 5332 |
}
|
| 5333 |
},
|
| 5334 |
-
"total_flos": 1.
|
| 5335 |
"train_batch_size": 22,
|
| 5336 |
"trial_name": null,
|
| 5337 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.32727272727272727,
|
| 6 |
"eval_steps": 1000,
|
| 7 |
+
"global_step": 72000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 5312 |
"eval_samples_per_second": 77.454,
|
| 5313 |
"eval_steps_per_second": 19.363,
|
| 5314 |
"step": 68000
|
| 5315 |
+
},
|
| 5316 |
+
{
|
| 5317 |
+
"epoch": 0.2918181818181818,
|
| 5318 |
+
"grad_norm": 0.18501834571361542,
|
| 5319 |
+
"learning_rate": 0.0003180402541276048,
|
| 5320 |
+
"loss": 2.650793151855469,
|
| 5321 |
+
"step": 68100
|
| 5322 |
+
},
|
| 5323 |
+
{
|
| 5324 |
+
"epoch": 0.2927272727272727,
|
| 5325 |
+
"grad_norm": 0.14561575651168823,
|
| 5326 |
+
"learning_rate": 0.00031670910433338273,
|
| 5327 |
+
"loss": 2.6040188598632814,
|
| 5328 |
+
"step": 68200
|
| 5329 |
+
},
|
| 5330 |
+
{
|
| 5331 |
+
"epoch": 0.29363636363636364,
|
| 5332 |
+
"grad_norm": 0.16025520861148834,
|
| 5333 |
+
"learning_rate": 0.00031537945367235393,
|
| 5334 |
+
"loss": 2.6409112548828126,
|
| 5335 |
+
"step": 68300
|
| 5336 |
+
},
|
| 5337 |
+
{
|
| 5338 |
+
"epoch": 0.29454545454545455,
|
| 5339 |
+
"grad_norm": 0.15475542843341827,
|
| 5340 |
+
"learning_rate": 0.00031405131301970936,
|
| 5341 |
+
"loss": 2.6054486083984374,
|
| 5342 |
+
"step": 68400
|
| 5343 |
+
},
|
| 5344 |
+
{
|
| 5345 |
+
"epoch": 0.29545454545454547,
|
| 5346 |
+
"grad_norm": 0.15857645869255066,
|
| 5347 |
+
"learning_rate": 0.0003127246932382891,
|
| 5348 |
+
"loss": 2.616719055175781,
|
| 5349 |
+
"step": 68500
|
| 5350 |
+
},
|
| 5351 |
+
{
|
| 5352 |
+
"epoch": 0.2963636363636364,
|
| 5353 |
+
"grad_norm": 0.19392845034599304,
|
| 5354 |
+
"learning_rate": 0.0003113996051784945,
|
| 5355 |
+
"loss": 2.60544921875,
|
| 5356 |
+
"step": 68600
|
| 5357 |
+
},
|
| 5358 |
+
{
|
| 5359 |
+
"epoch": 0.2972727272727273,
|
| 5360 |
+
"grad_norm": 0.19967029988765717,
|
| 5361 |
+
"learning_rate": 0.00031007605967819896,
|
| 5362 |
+
"loss": 2.6308856201171875,
|
| 5363 |
+
"step": 68700
|
| 5364 |
+
},
|
| 5365 |
+
{
|
| 5366 |
+
"epoch": 0.29818181818181816,
|
| 5367 |
+
"grad_norm": 0.19477345049381256,
|
| 5368 |
+
"learning_rate": 0.00030875406756265887,
|
| 5369 |
+
"loss": 2.6351129150390626,
|
| 5370 |
+
"step": 68800
|
| 5371 |
+
},
|
| 5372 |
+
{
|
| 5373 |
+
"epoch": 0.2990909090909091,
|
| 5374 |
+
"grad_norm": 0.15118417143821716,
|
| 5375 |
+
"learning_rate": 0.000307433639644426,
|
| 5376 |
+
"loss": 2.614127197265625,
|
| 5377 |
+
"step": 68900
|
| 5378 |
+
},
|
| 5379 |
+
{
|
| 5380 |
+
"epoch": 0.3,
|
| 5381 |
+
"grad_norm": 0.15570956468582153,
|
| 5382 |
+
"learning_rate": 0.0003061147867232582,
|
| 5383 |
+
"loss": 2.608861389160156,
|
| 5384 |
+
"step": 69000
|
| 5385 |
+
},
|
| 5386 |
+
{
|
| 5387 |
+
"epoch": 0.3,
|
| 5388 |
+
"eval_loss": 3.0342400074005127,
|
| 5389 |
+
"eval_runtime": 7.4253,
|
| 5390 |
+
"eval_samples_per_second": 77.572,
|
| 5391 |
+
"eval_steps_per_second": 19.393,
|
| 5392 |
+
"step": 69000
|
| 5393 |
+
},
|
| 5394 |
+
{
|
| 5395 |
+
"epoch": 0.3009090909090909,
|
| 5396 |
+
"grad_norm": 0.1571355015039444,
|
| 5397 |
+
"learning_rate": 0.0003047975195860318,
|
| 5398 |
+
"loss": 2.606195983886719,
|
| 5399 |
+
"step": 69100
|
| 5400 |
+
},
|
| 5401 |
+
{
|
| 5402 |
+
"epoch": 0.3018181818181818,
|
| 5403 |
+
"grad_norm": 0.15814636647701263,
|
| 5404 |
+
"learning_rate": 0.0003034818490066527,
|
| 5405 |
+
"loss": 2.5954779052734374,
|
| 5406 |
+
"step": 69200
|
| 5407 |
+
},
|
| 5408 |
+
{
|
| 5409 |
+
"epoch": 0.30272727272727273,
|
| 5410 |
+
"grad_norm": 0.14323082566261292,
|
| 5411 |
+
"learning_rate": 0.00030216778574596883,
|
| 5412 |
+
"loss": 2.6024984741210937,
|
| 5413 |
+
"step": 69300
|
| 5414 |
+
},
|
| 5415 |
+
{
|
| 5416 |
+
"epoch": 0.30363636363636365,
|
| 5417 |
+
"grad_norm": 0.17691482603549957,
|
| 5418 |
+
"learning_rate": 0.00030085534055168184,
|
| 5419 |
+
"loss": 2.602333984375,
|
| 5420 |
+
"step": 69400
|
| 5421 |
+
},
|
| 5422 |
+
{
|
| 5423 |
+
"epoch": 0.30454545454545456,
|
| 5424 |
+
"grad_norm": 0.17705939710140228,
|
| 5425 |
+
"learning_rate": 0.00029954452415825896,
|
| 5426 |
+
"loss": 2.628582763671875,
|
| 5427 |
+
"step": 69500
|
| 5428 |
+
},
|
| 5429 |
+
{
|
| 5430 |
+
"epoch": 0.3054545454545455,
|
| 5431 |
+
"grad_norm": 0.16018672287464142,
|
| 5432 |
+
"learning_rate": 0.00029823534728684587,
|
| 5433 |
+
"loss": 2.617008056640625,
|
| 5434 |
+
"step": 69600
|
| 5435 |
+
},
|
| 5436 |
+
{
|
| 5437 |
+
"epoch": 0.30636363636363634,
|
| 5438 |
+
"grad_norm": 0.16868868470191956,
|
| 5439 |
+
"learning_rate": 0.0002969278206451786,
|
| 5440 |
+
"loss": 2.597875671386719,
|
| 5441 |
+
"step": 69700
|
| 5442 |
+
},
|
| 5443 |
+
{
|
| 5444 |
+
"epoch": 0.30727272727272725,
|
| 5445 |
+
"grad_norm": 0.1678052544593811,
|
| 5446 |
+
"learning_rate": 0.0002956219549274957,
|
| 5447 |
+
"loss": 2.59896728515625,
|
| 5448 |
+
"step": 69800
|
| 5449 |
+
},
|
| 5450 |
+
{
|
| 5451 |
+
"epoch": 0.30818181818181817,
|
| 5452 |
+
"grad_norm": 0.15835554897785187,
|
| 5453 |
+
"learning_rate": 0.00029431776081445104,
|
| 5454 |
+
"loss": 2.6005072021484374,
|
| 5455 |
+
"step": 69900
|
| 5456 |
+
},
|
| 5457 |
+
{
|
| 5458 |
+
"epoch": 0.3090909090909091,
|
| 5459 |
+
"grad_norm": 0.148189514875412,
|
| 5460 |
+
"learning_rate": 0.0002930152489730271,
|
| 5461 |
+
"loss": 2.596640625,
|
| 5462 |
+
"step": 70000
|
| 5463 |
+
},
|
| 5464 |
+
{
|
| 5465 |
+
"epoch": 0.3090909090909091,
|
| 5466 |
+
"eval_loss": 3.034733772277832,
|
| 5467 |
+
"eval_runtime": 7.4478,
|
| 5468 |
+
"eval_samples_per_second": 77.338,
|
| 5469 |
+
"eval_steps_per_second": 19.335,
|
| 5470 |
+
"step": 70000
|
| 5471 |
+
},
|
| 5472 |
+
{
|
| 5473 |
+
"epoch": 0.31,
|
| 5474 |
+
"grad_norm": 0.1630752682685852,
|
| 5475 |
+
"learning_rate": 0.0002917144300564461,
|
| 5476 |
+
"loss": 2.6199655151367187,
|
| 5477 |
+
"step": 70100
|
| 5478 |
+
},
|
| 5479 |
+
{
|
| 5480 |
+
"epoch": 0.3109090909090909,
|
| 5481 |
+
"grad_norm": 0.16336363554000854,
|
| 5482 |
+
"learning_rate": 0.00029041531470408465,
|
| 5483 |
+
"loss": 2.595935974121094,
|
| 5484 |
+
"step": 70200
|
| 5485 |
+
},
|
| 5486 |
+
{
|
| 5487 |
+
"epoch": 0.3118181818181818,
|
| 5488 |
+
"grad_norm": 0.19114582240581512,
|
| 5489 |
+
"learning_rate": 0.00028911791354138574,
|
| 5490 |
+
"loss": 2.6245462036132814,
|
| 5491 |
+
"step": 70300
|
| 5492 |
+
},
|
| 5493 |
+
{
|
| 5494 |
+
"epoch": 0.31272727272727274,
|
| 5495 |
+
"grad_norm": 0.15327058732509613,
|
| 5496 |
+
"learning_rate": 0.0002878222371797716,
|
| 5497 |
+
"loss": 2.606686706542969,
|
| 5498 |
+
"step": 70400
|
| 5499 |
+
},
|
| 5500 |
+
{
|
| 5501 |
+
"epoch": 0.31363636363636366,
|
| 5502 |
+
"grad_norm": 0.16627787053585052,
|
| 5503 |
+
"learning_rate": 0.00028652829621655793,
|
| 5504 |
+
"loss": 2.6142779541015626,
|
| 5505 |
+
"step": 70500
|
| 5506 |
+
},
|
| 5507 |
+
{
|
| 5508 |
+
"epoch": 0.3145454545454546,
|
| 5509 |
+
"grad_norm": 0.17076851427555084,
|
| 5510 |
+
"learning_rate": 0.0002852361012348663,
|
| 5511 |
+
"loss": 2.6306427001953123,
|
| 5512 |
+
"step": 70600
|
| 5513 |
+
},
|
| 5514 |
+
{
|
| 5515 |
+
"epoch": 0.31545454545454543,
|
| 5516 |
+
"grad_norm": 0.15905171632766724,
|
| 5517 |
+
"learning_rate": 0.0002839456628035381,
|
| 5518 |
+
"loss": 2.646249084472656,
|
| 5519 |
+
"step": 70700
|
| 5520 |
+
},
|
| 5521 |
+
{
|
| 5522 |
+
"epoch": 0.31636363636363635,
|
| 5523 |
+
"grad_norm": 0.15757545828819275,
|
| 5524 |
+
"learning_rate": 0.000282656991477048,
|
| 5525 |
+
"loss": 2.6342782592773437,
|
| 5526 |
+
"step": 70800
|
| 5527 |
+
},
|
| 5528 |
+
{
|
| 5529 |
+
"epoch": 0.31727272727272726,
|
| 5530 |
+
"grad_norm": 0.1566353142261505,
|
| 5531 |
+
"learning_rate": 0.000281370097795417,
|
| 5532 |
+
"loss": 2.5926519775390626,
|
| 5533 |
+
"step": 70900
|
| 5534 |
+
},
|
| 5535 |
+
{
|
| 5536 |
+
"epoch": 0.3181818181818182,
|
| 5537 |
+
"grad_norm": 0.1587604433298111,
|
| 5538 |
+
"learning_rate": 0.0002800849922841273,
|
| 5539 |
+
"loss": 2.62255615234375,
|
| 5540 |
+
"step": 71000
|
| 5541 |
+
},
|
| 5542 |
+
{
|
| 5543 |
+
"epoch": 0.3181818181818182,
|
| 5544 |
+
"eval_loss": 3.0347187519073486,
|
| 5545 |
+
"eval_runtime": 7.4419,
|
| 5546 |
+
"eval_samples_per_second": 77.4,
|
| 5547 |
+
"eval_steps_per_second": 19.35,
|
| 5548 |
+
"step": 71000
|
| 5549 |
+
},
|
| 5550 |
+
{
|
| 5551 |
+
"epoch": 0.3190909090909091,
|
| 5552 |
+
"grad_norm": 0.15599116683006287,
|
| 5553 |
+
"learning_rate": 0.0002788016854540356,
|
| 5554 |
+
"loss": 2.6368426513671874,
|
| 5555 |
+
"step": 71100
|
| 5556 |
+
},
|
| 5557 |
+
{
|
| 5558 |
+
"epoch": 0.32,
|
| 5559 |
+
"grad_norm": 0.15771758556365967,
|
| 5560 |
+
"learning_rate": 0.0002775201878012872,
|
| 5561 |
+
"loss": 2.6378125,
|
| 5562 |
+
"step": 71200
|
| 5563 |
+
},
|
| 5564 |
+
{
|
| 5565 |
+
"epoch": 0.3209090909090909,
|
| 5566 |
+
"grad_norm": 0.16494904458522797,
|
| 5567 |
+
"learning_rate": 0.0002762405098072303,
|
| 5568 |
+
"loss": 2.6372637939453125,
|
| 5569 |
+
"step": 71300
|
| 5570 |
+
},
|
| 5571 |
+
{
|
| 5572 |
+
"epoch": 0.32181818181818184,
|
| 5573 |
+
"grad_norm": 0.18344129621982574,
|
| 5574 |
+
"learning_rate": 0.0002749626619383296,
|
| 5575 |
+
"loss": 2.6274960327148436,
|
| 5576 |
+
"step": 71400
|
| 5577 |
+
},
|
| 5578 |
+
{
|
| 5579 |
+
"epoch": 0.32272727272727275,
|
| 5580 |
+
"grad_norm": 0.19829513132572174,
|
| 5581 |
+
"learning_rate": 0.00027368665464608174,
|
| 5582 |
+
"loss": 2.652212829589844,
|
| 5583 |
+
"step": 71500
|
| 5584 |
+
},
|
| 5585 |
+
{
|
| 5586 |
+
"epoch": 0.3236363636363636,
|
| 5587 |
+
"grad_norm": 0.170766219496727,
|
| 5588 |
+
"learning_rate": 0.0002724124983669292,
|
| 5589 |
+
"loss": 2.6236361694335937,
|
| 5590 |
+
"step": 71600
|
| 5591 |
+
},
|
| 5592 |
+
{
|
| 5593 |
+
"epoch": 0.3245454545454545,
|
| 5594 |
+
"grad_norm": 0.15507978200912476,
|
| 5595 |
+
"learning_rate": 0.0002711402035221751,
|
| 5596 |
+
"loss": 2.612099304199219,
|
| 5597 |
+
"step": 71700
|
| 5598 |
+
},
|
| 5599 |
+
{
|
| 5600 |
+
"epoch": 0.32545454545454544,
|
| 5601 |
+
"grad_norm": 0.17562313377857208,
|
| 5602 |
+
"learning_rate": 0.00026986978051789804,
|
| 5603 |
+
"loss": 2.651109313964844,
|
| 5604 |
+
"step": 71800
|
| 5605 |
+
},
|
| 5606 |
+
{
|
| 5607 |
+
"epoch": 0.32636363636363636,
|
| 5608 |
+
"grad_norm": 0.16349823772907257,
|
| 5609 |
+
"learning_rate": 0.0002686012397448662,
|
| 5610 |
+
"loss": 2.652076416015625,
|
| 5611 |
+
"step": 71900
|
| 5612 |
+
},
|
| 5613 |
+
{
|
| 5614 |
+
"epoch": 0.32727272727272727,
|
| 5615 |
+
"grad_norm": 0.1562015861272812,
|
| 5616 |
+
"learning_rate": 0.00026733459157845385,
|
| 5617 |
+
"loss": 2.6174331665039063,
|
| 5618 |
+
"step": 72000
|
| 5619 |
+
},
|
| 5620 |
+
{
|
| 5621 |
+
"epoch": 0.32727272727272727,
|
| 5622 |
+
"eval_loss": 3.030982255935669,
|
| 5623 |
+
"eval_runtime": 7.4103,
|
| 5624 |
+
"eval_samples_per_second": 77.729,
|
| 5625 |
+
"eval_steps_per_second": 19.432,
|
| 5626 |
+
"step": 72000
|
| 5627 |
}
|
| 5628 |
],
|
| 5629 |
"logging_steps": 100,
|
|
|
|
| 5643 |
"attributes": {}
|
| 5644 |
}
|
| 5645 |
},
|
| 5646 |
+
"total_flos": 1.793849831718912e+18,
|
| 5647 |
"train_batch_size": 22,
|
| 5648 |
"trial_name": null,
|
| 5649 |
"trial_params": null
|