Training in progress, step 6500, 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 2384234968
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4f7f960c526aaddf3dc6988e73942fac836299ec8e275266c1eba5701ae94d95
|
| 3 |
size 2384234968
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4768663315
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d1ba615b7681549fb237aead953796280a2ad4be16081ccbd5f79689ec8c3f9c
|
| 3 |
size 4768663315
|
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:edf1be9c157afb4ca46e7843711b38a681d679ee3bcd0c31f21d197c72d6bbf2
|
| 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": 1.
|
| 6 |
"eval_steps": 100,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -5408,6 +5408,456 @@
|
|
| 5408 |
"mean_token_accuracy": 0.7743395321071148,
|
| 5409 |
"num_tokens": 49145856.0,
|
| 5410 |
"step": 6000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5411 |
}
|
| 5412 |
],
|
| 5413 |
"logging_steps": 10,
|
|
@@ -5427,7 +5877,7 @@
|
|
| 5427 |
"attributes": {}
|
| 5428 |
}
|
| 5429 |
},
|
| 5430 |
-
"total_flos": 1.
|
| 5431 |
"train_batch_size": 2,
|
| 5432 |
"trial_name": null,
|
| 5433 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.9574580227392515,
|
| 6 |
"eval_steps": 100,
|
| 7 |
+
"global_step": 6500,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 5408 |
"mean_token_accuracy": 0.7743395321071148,
|
| 5409 |
"num_tokens": 49145856.0,
|
| 5410 |
"step": 6000
|
| 5411 |
+
},
|
| 5412 |
+
{
|
| 5413 |
+
"epoch": 1.8098787741886906,
|
| 5414 |
+
"grad_norm": 1.119452714920044,
|
| 5415 |
+
"learning_rate": 4.409993308052644e-06,
|
| 5416 |
+
"loss": 0.1267,
|
| 5417 |
+
"mean_token_accuracy": 0.7942514635622502,
|
| 5418 |
+
"num_tokens": 49227776.0,
|
| 5419 |
+
"step": 6010
|
| 5420 |
+
},
|
| 5421 |
+
{
|
| 5422 |
+
"epoch": 1.8128905955876817,
|
| 5423 |
+
"grad_norm": 1.5210676193237305,
|
| 5424 |
+
"learning_rate": 4.398840062458175e-06,
|
| 5425 |
+
"loss": 0.1288,
|
| 5426 |
+
"mean_token_accuracy": 0.7662426587194204,
|
| 5427 |
+
"num_tokens": 49309696.0,
|
| 5428 |
+
"step": 6020
|
| 5429 |
+
},
|
| 5430 |
+
{
|
| 5431 |
+
"epoch": 1.8159024169866727,
|
| 5432 |
+
"grad_norm": 1.1394039392471313,
|
| 5433 |
+
"learning_rate": 4.387686816863708e-06,
|
| 5434 |
+
"loss": 0.1204,
|
| 5435 |
+
"mean_token_accuracy": 0.7840264186263084,
|
| 5436 |
+
"num_tokens": 49391616.0,
|
| 5437 |
+
"step": 6030
|
| 5438 |
+
},
|
| 5439 |
+
{
|
| 5440 |
+
"epoch": 1.8189142383856636,
|
| 5441 |
+
"grad_norm": 1.3435912132263184,
|
| 5442 |
+
"learning_rate": 4.37653357126924e-06,
|
| 5443 |
+
"loss": 0.1307,
|
| 5444 |
+
"mean_token_accuracy": 0.7883317038416863,
|
| 5445 |
+
"num_tokens": 49473536.0,
|
| 5446 |
+
"step": 6040
|
| 5447 |
+
},
|
| 5448 |
+
{
|
| 5449 |
+
"epoch": 1.8219260597846547,
|
| 5450 |
+
"grad_norm": 1.6107054948806763,
|
| 5451 |
+
"learning_rate": 4.365380325674772e-06,
|
| 5452 |
+
"loss": 0.1364,
|
| 5453 |
+
"mean_token_accuracy": 0.7881237775087356,
|
| 5454 |
+
"num_tokens": 49555456.0,
|
| 5455 |
+
"step": 6050
|
| 5456 |
+
},
|
| 5457 |
+
{
|
| 5458 |
+
"epoch": 1.8249378811836459,
|
| 5459 |
+
"grad_norm": 1.3873751163482666,
|
| 5460 |
+
"learning_rate": 4.3542270800803035e-06,
|
| 5461 |
+
"loss": 0.1151,
|
| 5462 |
+
"mean_token_accuracy": 0.7963184919208288,
|
| 5463 |
+
"num_tokens": 49637376.0,
|
| 5464 |
+
"step": 6060
|
| 5465 |
+
},
|
| 5466 |
+
{
|
| 5467 |
+
"epoch": 1.8279497025826368,
|
| 5468 |
+
"grad_norm": 1.1877696514129639,
|
| 5469 |
+
"learning_rate": 4.343073834485836e-06,
|
| 5470 |
+
"loss": 0.116,
|
| 5471 |
+
"mean_token_accuracy": 0.7753791596740485,
|
| 5472 |
+
"num_tokens": 49719296.0,
|
| 5473 |
+
"step": 6070
|
| 5474 |
+
},
|
| 5475 |
+
{
|
| 5476 |
+
"epoch": 1.830961523981628,
|
| 5477 |
+
"grad_norm": 1.254225492477417,
|
| 5478 |
+
"learning_rate": 4.331920588891368e-06,
|
| 5479 |
+
"loss": 0.1247,
|
| 5480 |
+
"mean_token_accuracy": 0.7898238748311996,
|
| 5481 |
+
"num_tokens": 49801216.0,
|
| 5482 |
+
"step": 6080
|
| 5483 |
+
},
|
| 5484 |
+
{
|
| 5485 |
+
"epoch": 1.833973345380619,
|
| 5486 |
+
"grad_norm": 0.9596796631813049,
|
| 5487 |
+
"learning_rate": 4.3207673432969e-06,
|
| 5488 |
+
"loss": 0.1179,
|
| 5489 |
+
"mean_token_accuracy": 0.7971868872642517,
|
| 5490 |
+
"num_tokens": 49883136.0,
|
| 5491 |
+
"step": 6090
|
| 5492 |
+
},
|
| 5493 |
+
{
|
| 5494 |
+
"epoch": 1.83698516677961,
|
| 5495 |
+
"grad_norm": 1.2079626321792603,
|
| 5496 |
+
"learning_rate": 4.309614097702432e-06,
|
| 5497 |
+
"loss": 0.1226,
|
| 5498 |
+
"mean_token_accuracy": 0.7858732901513577,
|
| 5499 |
+
"num_tokens": 49965056.0,
|
| 5500 |
+
"step": 6100
|
| 5501 |
+
},
|
| 5502 |
+
{
|
| 5503 |
+
"epoch": 1.839996988178601,
|
| 5504 |
+
"grad_norm": 0.9496937990188599,
|
| 5505 |
+
"learning_rate": 4.298460852107964e-06,
|
| 5506 |
+
"loss": 0.1228,
|
| 5507 |
+
"mean_token_accuracy": 0.7744006861001254,
|
| 5508 |
+
"num_tokens": 50046976.0,
|
| 5509 |
+
"step": 6110
|
| 5510 |
+
},
|
| 5511 |
+
{
|
| 5512 |
+
"epoch": 1.843008809577592,
|
| 5513 |
+
"grad_norm": 1.2540092468261719,
|
| 5514 |
+
"learning_rate": 4.287307606513495e-06,
|
| 5515 |
+
"loss": 0.146,
|
| 5516 |
+
"mean_token_accuracy": 0.7829867884516716,
|
| 5517 |
+
"num_tokens": 50128896.0,
|
| 5518 |
+
"step": 6120
|
| 5519 |
+
},
|
| 5520 |
+
{
|
| 5521 |
+
"epoch": 1.8460206309765832,
|
| 5522 |
+
"grad_norm": 1.411310076713562,
|
| 5523 |
+
"learning_rate": 4.276154360919028e-06,
|
| 5524 |
+
"loss": 0.1577,
|
| 5525 |
+
"mean_token_accuracy": 0.7729085143655539,
|
| 5526 |
+
"num_tokens": 50210816.0,
|
| 5527 |
+
"step": 6130
|
| 5528 |
+
},
|
| 5529 |
+
{
|
| 5530 |
+
"epoch": 1.8490324523755741,
|
| 5531 |
+
"grad_norm": 1.2968723773956299,
|
| 5532 |
+
"learning_rate": 4.26500111532456e-06,
|
| 5533 |
+
"loss": 0.1357,
|
| 5534 |
+
"mean_token_accuracy": 0.7781433466821909,
|
| 5535 |
+
"num_tokens": 50292736.0,
|
| 5536 |
+
"step": 6140
|
| 5537 |
+
},
|
| 5538 |
+
{
|
| 5539 |
+
"epoch": 1.852044273774565,
|
| 5540 |
+
"grad_norm": 1.5124306678771973,
|
| 5541 |
+
"learning_rate": 4.253847869730091e-06,
|
| 5542 |
+
"loss": 0.127,
|
| 5543 |
+
"mean_token_accuracy": 0.7770914871245622,
|
| 5544 |
+
"num_tokens": 50374656.0,
|
| 5545 |
+
"step": 6150
|
| 5546 |
+
},
|
| 5547 |
+
{
|
| 5548 |
+
"epoch": 1.8550560951735562,
|
| 5549 |
+
"grad_norm": 1.213470220565796,
|
| 5550 |
+
"learning_rate": 4.2426946241356236e-06,
|
| 5551 |
+
"loss": 0.1265,
|
| 5552 |
+
"mean_token_accuracy": 0.7825953986495733,
|
| 5553 |
+
"num_tokens": 50456576.0,
|
| 5554 |
+
"step": 6160
|
| 5555 |
+
},
|
| 5556 |
+
{
|
| 5557 |
+
"epoch": 1.8580679165725473,
|
| 5558 |
+
"grad_norm": 1.0956401824951172,
|
| 5559 |
+
"learning_rate": 4.231541378541156e-06,
|
| 5560 |
+
"loss": 0.1175,
|
| 5561 |
+
"mean_token_accuracy": 0.7812500018626451,
|
| 5562 |
+
"num_tokens": 50538496.0,
|
| 5563 |
+
"step": 6170
|
| 5564 |
+
},
|
| 5565 |
+
{
|
| 5566 |
+
"epoch": 1.8610797379715383,
|
| 5567 |
+
"grad_norm": 1.4625799655914307,
|
| 5568 |
+
"learning_rate": 4.220388132946688e-06,
|
| 5569 |
+
"loss": 0.1221,
|
| 5570 |
+
"mean_token_accuracy": 0.7790484338998794,
|
| 5571 |
+
"num_tokens": 50620416.0,
|
| 5572 |
+
"step": 6180
|
| 5573 |
+
},
|
| 5574 |
+
{
|
| 5575 |
+
"epoch": 1.8640915593705292,
|
| 5576 |
+
"grad_norm": 1.459068775177002,
|
| 5577 |
+
"learning_rate": 4.2092348873522195e-06,
|
| 5578 |
+
"loss": 0.1256,
|
| 5579 |
+
"mean_token_accuracy": 0.7763820964843035,
|
| 5580 |
+
"num_tokens": 50702336.0,
|
| 5581 |
+
"step": 6190
|
| 5582 |
+
},
|
| 5583 |
+
{
|
| 5584 |
+
"epoch": 1.8671033807695203,
|
| 5585 |
+
"grad_norm": 1.2089377641677856,
|
| 5586 |
+
"learning_rate": 4.198081641757752e-06,
|
| 5587 |
+
"loss": 0.1144,
|
| 5588 |
+
"mean_token_accuracy": 0.7932118389755487,
|
| 5589 |
+
"num_tokens": 50784256.0,
|
| 5590 |
+
"step": 6200
|
| 5591 |
+
},
|
| 5592 |
+
{
|
| 5593 |
+
"epoch": 1.8701152021685115,
|
| 5594 |
+
"grad_norm": 1.3430728912353516,
|
| 5595 |
+
"learning_rate": 4.186928396163284e-06,
|
| 5596 |
+
"loss": 0.1357,
|
| 5597 |
+
"mean_token_accuracy": 0.7570083189755679,
|
| 5598 |
+
"num_tokens": 50866176.0,
|
| 5599 |
+
"step": 6210
|
| 5600 |
+
},
|
| 5601 |
+
{
|
| 5602 |
+
"epoch": 1.8731270235675024,
|
| 5603 |
+
"grad_norm": 1.1253952980041504,
|
| 5604 |
+
"learning_rate": 4.175775150568816e-06,
|
| 5605 |
+
"loss": 0.1388,
|
| 5606 |
+
"mean_token_accuracy": 0.770560173690319,
|
| 5607 |
+
"num_tokens": 50948096.0,
|
| 5608 |
+
"step": 6220
|
| 5609 |
+
},
|
| 5610 |
+
{
|
| 5611 |
+
"epoch": 1.8761388449664935,
|
| 5612 |
+
"grad_norm": 1.4846373796463013,
|
| 5613 |
+
"learning_rate": 4.164621904974348e-06,
|
| 5614 |
+
"loss": 0.1169,
|
| 5615 |
+
"mean_token_accuracy": 0.790007334202528,
|
| 5616 |
+
"num_tokens": 51030016.0,
|
| 5617 |
+
"step": 6230
|
| 5618 |
+
},
|
| 5619 |
+
{
|
| 5620 |
+
"epoch": 1.8791506663654847,
|
| 5621 |
+
"grad_norm": 1.1216601133346558,
|
| 5622 |
+
"learning_rate": 4.15346865937988e-06,
|
| 5623 |
+
"loss": 0.1067,
|
| 5624 |
+
"mean_token_accuracy": 0.7991316046565771,
|
| 5625 |
+
"num_tokens": 51111936.0,
|
| 5626 |
+
"step": 6240
|
| 5627 |
+
},
|
| 5628 |
+
{
|
| 5629 |
+
"epoch": 1.8821624877644756,
|
| 5630 |
+
"grad_norm": 1.0364607572555542,
|
| 5631 |
+
"learning_rate": 4.142315413785412e-06,
|
| 5632 |
+
"loss": 0.1319,
|
| 5633 |
+
"mean_token_accuracy": 0.7956824835389853,
|
| 5634 |
+
"num_tokens": 51193856.0,
|
| 5635 |
+
"step": 6250
|
| 5636 |
+
},
|
| 5637 |
+
{
|
| 5638 |
+
"epoch": 1.8851743091634665,
|
| 5639 |
+
"grad_norm": 1.2253397703170776,
|
| 5640 |
+
"learning_rate": 4.1311621681909444e-06,
|
| 5641 |
+
"loss": 0.106,
|
| 5642 |
+
"mean_token_accuracy": 0.7979452051222324,
|
| 5643 |
+
"num_tokens": 51275776.0,
|
| 5644 |
+
"step": 6260
|
| 5645 |
+
},
|
| 5646 |
+
{
|
| 5647 |
+
"epoch": 1.8881861305624577,
|
| 5648 |
+
"grad_norm": 1.4938507080078125,
|
| 5649 |
+
"learning_rate": 4.120008922596476e-06,
|
| 5650 |
+
"loss": 0.1251,
|
| 5651 |
+
"mean_token_accuracy": 0.7749999970197677,
|
| 5652 |
+
"num_tokens": 51357696.0,
|
| 5653 |
+
"step": 6270
|
| 5654 |
+
},
|
| 5655 |
+
{
|
| 5656 |
+
"epoch": 1.8911979519614488,
|
| 5657 |
+
"grad_norm": 0.9345296025276184,
|
| 5658 |
+
"learning_rate": 4.108855677002008e-06,
|
| 5659 |
+
"loss": 0.1378,
|
| 5660 |
+
"mean_token_accuracy": 0.7624633058905601,
|
| 5661 |
+
"num_tokens": 51439616.0,
|
| 5662 |
+
"step": 6280
|
| 5663 |
+
},
|
| 5664 |
+
{
|
| 5665 |
+
"epoch": 1.8942097733604397,
|
| 5666 |
+
"grad_norm": 1.692668080329895,
|
| 5667 |
+
"learning_rate": 4.0977024314075395e-06,
|
| 5668 |
+
"loss": 0.1278,
|
| 5669 |
+
"mean_token_accuracy": 0.7732876695692539,
|
| 5670 |
+
"num_tokens": 51521536.0,
|
| 5671 |
+
"step": 6290
|
| 5672 |
+
},
|
| 5673 |
+
{
|
| 5674 |
+
"epoch": 1.8972215947594306,
|
| 5675 |
+
"grad_norm": 1.1990948915481567,
|
| 5676 |
+
"learning_rate": 4.086549185813072e-06,
|
| 5677 |
+
"loss": 0.1033,
|
| 5678 |
+
"mean_token_accuracy": 0.7984222084283829,
|
| 5679 |
+
"num_tokens": 51603456.0,
|
| 5680 |
+
"step": 6300
|
| 5681 |
+
},
|
| 5682 |
+
{
|
| 5683 |
+
"epoch": 1.9002334161584218,
|
| 5684 |
+
"grad_norm": 1.023429274559021,
|
| 5685 |
+
"learning_rate": 4.075395940218604e-06,
|
| 5686 |
+
"loss": 0.141,
|
| 5687 |
+
"mean_token_accuracy": 0.7674779828637839,
|
| 5688 |
+
"num_tokens": 51685376.0,
|
| 5689 |
+
"step": 6310
|
| 5690 |
+
},
|
| 5691 |
+
{
|
| 5692 |
+
"epoch": 1.903245237557413,
|
| 5693 |
+
"grad_norm": 1.4536356925964355,
|
| 5694 |
+
"learning_rate": 4.064242694624136e-06,
|
| 5695 |
+
"loss": 0.1262,
|
| 5696 |
+
"mean_token_accuracy": 0.7853106647729874,
|
| 5697 |
+
"num_tokens": 51767296.0,
|
| 5698 |
+
"step": 6320
|
| 5699 |
+
},
|
| 5700 |
+
{
|
| 5701 |
+
"epoch": 1.9062570589564038,
|
| 5702 |
+
"grad_norm": 1.2798579931259155,
|
| 5703 |
+
"learning_rate": 4.053089449029668e-06,
|
| 5704 |
+
"loss": 0.136,
|
| 5705 |
+
"mean_token_accuracy": 0.7931629169732333,
|
| 5706 |
+
"num_tokens": 51849216.0,
|
| 5707 |
+
"step": 6330
|
| 5708 |
+
},
|
| 5709 |
+
{
|
| 5710 |
+
"epoch": 1.9092688803553948,
|
| 5711 |
+
"grad_norm": 1.8882237672805786,
|
| 5712 |
+
"learning_rate": 4.0419362034352e-06,
|
| 5713 |
+
"loss": 0.1245,
|
| 5714 |
+
"mean_token_accuracy": 0.7892612550407648,
|
| 5715 |
+
"num_tokens": 51931136.0,
|
| 5716 |
+
"step": 6340
|
| 5717 |
+
},
|
| 5718 |
+
{
|
| 5719 |
+
"epoch": 1.912280701754386,
|
| 5720 |
+
"grad_norm": 0.9331277012825012,
|
| 5721 |
+
"learning_rate": 4.030782957840732e-06,
|
| 5722 |
+
"loss": 0.1328,
|
| 5723 |
+
"mean_token_accuracy": 0.7794153604656457,
|
| 5724 |
+
"num_tokens": 52013056.0,
|
| 5725 |
+
"step": 6350
|
| 5726 |
+
},
|
| 5727 |
+
{
|
| 5728 |
+
"epoch": 1.915292523153377,
|
| 5729 |
+
"grad_norm": 1.0210968255996704,
|
| 5730 |
+
"learning_rate": 4.0196297122462645e-06,
|
| 5731 |
+
"loss": 0.1339,
|
| 5732 |
+
"mean_token_accuracy": 0.7672945164144039,
|
| 5733 |
+
"num_tokens": 52094976.0,
|
| 5734 |
+
"step": 6360
|
| 5735 |
+
},
|
| 5736 |
+
{
|
| 5737 |
+
"epoch": 1.918304344552368,
|
| 5738 |
+
"grad_norm": 0.8210415244102478,
|
| 5739 |
+
"learning_rate": 4.008476466651796e-06,
|
| 5740 |
+
"loss": 0.1383,
|
| 5741 |
+
"mean_token_accuracy": 0.7825097866356373,
|
| 5742 |
+
"num_tokens": 52176896.0,
|
| 5743 |
+
"step": 6370
|
| 5744 |
+
},
|
| 5745 |
+
{
|
| 5746 |
+
"epoch": 1.9213161659513591,
|
| 5747 |
+
"grad_norm": 1.4494845867156982,
|
| 5748 |
+
"learning_rate": 3.997323221057328e-06,
|
| 5749 |
+
"loss": 0.1251,
|
| 5750 |
+
"mean_token_accuracy": 0.7858732867985964,
|
| 5751 |
+
"num_tokens": 52258816.0,
|
| 5752 |
+
"step": 6380
|
| 5753 |
+
},
|
| 5754 |
+
{
|
| 5755 |
+
"epoch": 1.9243279873503503,
|
| 5756 |
+
"grad_norm": 1.3196386098861694,
|
| 5757 |
+
"learning_rate": 3.98616997546286e-06,
|
| 5758 |
+
"loss": 0.1248,
|
| 5759 |
+
"mean_token_accuracy": 0.7867539167404175,
|
| 5760 |
+
"num_tokens": 52340736.0,
|
| 5761 |
+
"step": 6390
|
| 5762 |
+
},
|
| 5763 |
+
{
|
| 5764 |
+
"epoch": 1.9273398087493412,
|
| 5765 |
+
"grad_norm": 1.0273571014404297,
|
| 5766 |
+
"learning_rate": 3.975016729868393e-06,
|
| 5767 |
+
"loss": 0.1305,
|
| 5768 |
+
"mean_token_accuracy": 0.7854329772293568,
|
| 5769 |
+
"num_tokens": 52422656.0,
|
| 5770 |
+
"step": 6400
|
| 5771 |
+
},
|
| 5772 |
+
{
|
| 5773 |
+
"epoch": 1.930351630148332,
|
| 5774 |
+
"grad_norm": 0.8488328456878662,
|
| 5775 |
+
"learning_rate": 3.963863484273924e-06,
|
| 5776 |
+
"loss": 0.1263,
|
| 5777 |
+
"mean_token_accuracy": 0.7624266136437654,
|
| 5778 |
+
"num_tokens": 52504576.0,
|
| 5779 |
+
"step": 6410
|
| 5780 |
+
},
|
| 5781 |
+
{
|
| 5782 |
+
"epoch": 1.9333634515473233,
|
| 5783 |
+
"grad_norm": 1.2516889572143555,
|
| 5784 |
+
"learning_rate": 3.9527102386794555e-06,
|
| 5785 |
+
"loss": 0.1152,
|
| 5786 |
+
"mean_token_accuracy": 0.7868517614901066,
|
| 5787 |
+
"num_tokens": 52586496.0,
|
| 5788 |
+
"step": 6420
|
| 5789 |
+
},
|
| 5790 |
+
{
|
| 5791 |
+
"epoch": 1.9363752729463144,
|
| 5792 |
+
"grad_norm": 0.8944329619407654,
|
| 5793 |
+
"learning_rate": 3.941556993084988e-06,
|
| 5794 |
+
"loss": 0.1433,
|
| 5795 |
+
"mean_token_accuracy": 0.7754770018160343,
|
| 5796 |
+
"num_tokens": 52668416.0,
|
| 5797 |
+
"step": 6430
|
| 5798 |
+
},
|
| 5799 |
+
{
|
| 5800 |
+
"epoch": 1.9393870943453053,
|
| 5801 |
+
"grad_norm": 1.3723251819610596,
|
| 5802 |
+
"learning_rate": 3.93040374749052e-06,
|
| 5803 |
+
"loss": 0.1303,
|
| 5804 |
+
"mean_token_accuracy": 0.7749755352735519,
|
| 5805 |
+
"num_tokens": 52750336.0,
|
| 5806 |
+
"step": 6440
|
| 5807 |
+
},
|
| 5808 |
+
{
|
| 5809 |
+
"epoch": 1.9423989157442962,
|
| 5810 |
+
"grad_norm": 1.1744338274002075,
|
| 5811 |
+
"learning_rate": 3.919250501896052e-06,
|
| 5812 |
+
"loss": 0.1262,
|
| 5813 |
+
"mean_token_accuracy": 0.7595768127590418,
|
| 5814 |
+
"num_tokens": 52832256.0,
|
| 5815 |
+
"step": 6450
|
| 5816 |
+
},
|
| 5817 |
+
{
|
| 5818 |
+
"epoch": 1.9454107371432874,
|
| 5819 |
+
"grad_norm": 1.4083287715911865,
|
| 5820 |
+
"learning_rate": 3.908097256301584e-06,
|
| 5821 |
+
"loss": 0.1206,
|
| 5822 |
+
"mean_token_accuracy": 0.7865826826542616,
|
| 5823 |
+
"num_tokens": 52914176.0,
|
| 5824 |
+
"step": 6460
|
| 5825 |
+
},
|
| 5826 |
+
{
|
| 5827 |
+
"epoch": 1.9484225585422785,
|
| 5828 |
+
"grad_norm": 1.0532681941986084,
|
| 5829 |
+
"learning_rate": 3.896944010707116e-06,
|
| 5830 |
+
"loss": 0.1319,
|
| 5831 |
+
"mean_token_accuracy": 0.7665606673806906,
|
| 5832 |
+
"num_tokens": 52996096.0,
|
| 5833 |
+
"step": 6470
|
| 5834 |
+
},
|
| 5835 |
+
{
|
| 5836 |
+
"epoch": 1.9514343799412694,
|
| 5837 |
+
"grad_norm": 1.3897960186004639,
|
| 5838 |
+
"learning_rate": 3.885790765112648e-06,
|
| 5839 |
+
"loss": 0.1262,
|
| 5840 |
+
"mean_token_accuracy": 0.7697407025843859,
|
| 5841 |
+
"num_tokens": 53078016.0,
|
| 5842 |
+
"step": 6480
|
| 5843 |
+
},
|
| 5844 |
+
{
|
| 5845 |
+
"epoch": 1.9544462013402604,
|
| 5846 |
+
"grad_norm": 1.6499828100204468,
|
| 5847 |
+
"learning_rate": 3.8746375195181804e-06,
|
| 5848 |
+
"loss": 0.1129,
|
| 5849 |
+
"mean_token_accuracy": 0.8042808264493942,
|
| 5850 |
+
"num_tokens": 53159936.0,
|
| 5851 |
+
"step": 6490
|
| 5852 |
+
},
|
| 5853 |
+
{
|
| 5854 |
+
"epoch": 1.9574580227392515,
|
| 5855 |
+
"grad_norm": 1.6160123348236084,
|
| 5856 |
+
"learning_rate": 3.863484273923712e-06,
|
| 5857 |
+
"loss": 0.1315,
|
| 5858 |
+
"mean_token_accuracy": 0.7979574371129274,
|
| 5859 |
+
"num_tokens": 53241856.0,
|
| 5860 |
+
"step": 6500
|
| 5861 |
}
|
| 5862 |
],
|
| 5863 |
"logging_steps": 10,
|
|
|
|
| 5877 |
"attributes": {}
|
| 5878 |
}
|
| 5879 |
},
|
| 5880 |
+
"total_flos": 1.4070782919023002e+17,
|
| 5881 |
"train_batch_size": 2,
|
| 5882 |
"trial_name": null,
|
| 5883 |
"trial_params": null
|