Training in progress, step 1700000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +383 -3
- pytorch_model.bin +1 -1
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 893439185
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a6263ea7e43a6acbefa798ce6055706ef15240d94f08fb8faefbf26e23ac3a25
|
| 3 |
size 893439185
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 449471589
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:abc7a8543a963e582a29e31e1e0c78fea4345a1b73b925ed6cc4d7ab61edbd1e
|
| 3 |
size 449471589
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 21643
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f7eefc1725778458a372a52de0baec705be0fcd52c035947880ee6c60789db03
|
| 3 |
size 21643
|
last-checkpoint/scaler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 559
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9f873a347744a9c52f42be277b16c7300feca4fe83dae00b3348477c6cab3f68
|
| 3 |
size 559
|
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:f676f9b0130b013ba493986d64992bf63d68d6bad5cd11e3728c43b657e50e05
|
| 3 |
size 623
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -12546,11 +12546,391 @@
|
|
| 12546 |
"eval_samples_per_second": 80.739,
|
| 12547 |
"eval_steps_per_second": 0.631,
|
| 12548 |
"step": 1650000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12549 |
}
|
| 12550 |
],
|
| 12551 |
"max_steps": 2000000,
|
| 12552 |
"num_train_epochs": 9223372036854775807,
|
| 12553 |
-
"total_flos": 1.
|
| 12554 |
"trial_name": null,
|
| 12555 |
"trial_params": null
|
| 12556 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.1,
|
| 5 |
+
"global_step": 1700000,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 12546 |
"eval_samples_per_second": 80.739,
|
| 12547 |
"eval_steps_per_second": 0.631,
|
| 12548 |
"step": 1650000
|
| 12549 |
+
},
|
| 12550 |
+
{
|
| 12551 |
+
"epoch": 0.08,
|
| 12552 |
+
"learning_rate": 2.263295082033955e-05,
|
| 12553 |
+
"loss": 0.4402,
|
| 12554 |
+
"step": 1651000
|
| 12555 |
+
},
|
| 12556 |
+
{
|
| 12557 |
+
"epoch": 0.08,
|
| 12558 |
+
"learning_rate": 2.256302851518958e-05,
|
| 12559 |
+
"loss": 0.4408,
|
| 12560 |
+
"step": 1652000
|
| 12561 |
+
},
|
| 12562 |
+
{
|
| 12563 |
+
"epoch": 0.08,
|
| 12564 |
+
"learning_rate": 2.2493281173015714e-05,
|
| 12565 |
+
"loss": 0.4392,
|
| 12566 |
+
"step": 1653000
|
| 12567 |
+
},
|
| 12568 |
+
{
|
| 12569 |
+
"epoch": 0.08,
|
| 12570 |
+
"learning_rate": 2.242370900628049e-05,
|
| 12571 |
+
"loss": 0.4401,
|
| 12572 |
+
"step": 1654000
|
| 12573 |
+
},
|
| 12574 |
+
{
|
| 12575 |
+
"epoch": 0.08,
|
| 12576 |
+
"learning_rate": 2.235438153601577e-05,
|
| 12577 |
+
"loss": 0.4399,
|
| 12578 |
+
"step": 1655000
|
| 12579 |
+
},
|
| 12580 |
+
{
|
| 12581 |
+
"epoch": 0.08,
|
| 12582 |
+
"eval_loss": 0.42048439383506775,
|
| 12583 |
+
"eval_runtime": 77.8384,
|
| 12584 |
+
"eval_samples_per_second": 82.222,
|
| 12585 |
+
"eval_steps_per_second": 0.642,
|
| 12586 |
+
"step": 1655000
|
| 12587 |
+
},
|
| 12588 |
+
{
|
| 12589 |
+
"epoch": 0.08,
|
| 12590 |
+
"learning_rate": 2.2285160179706007e-05,
|
| 12591 |
+
"loss": 0.44,
|
| 12592 |
+
"step": 1656000
|
| 12593 |
+
},
|
| 12594 |
+
{
|
| 12595 |
+
"epoch": 0.08,
|
| 12596 |
+
"learning_rate": 2.2216114632807524e-05,
|
| 12597 |
+
"loss": 0.4404,
|
| 12598 |
+
"step": 1657000
|
| 12599 |
+
},
|
| 12600 |
+
{
|
| 12601 |
+
"epoch": 0.08,
|
| 12602 |
+
"learning_rate": 2.214731388718044e-05,
|
| 12603 |
+
"loss": 0.4406,
|
| 12604 |
+
"step": 1658000
|
| 12605 |
+
},
|
| 12606 |
+
{
|
| 12607 |
+
"epoch": 0.08,
|
| 12608 |
+
"learning_rate": 2.2078620413208303e-05,
|
| 12609 |
+
"loss": 0.4402,
|
| 12610 |
+
"step": 1659000
|
| 12611 |
+
},
|
| 12612 |
+
{
|
| 12613 |
+
"epoch": 0.08,
|
| 12614 |
+
"learning_rate": 2.201010337780338e-05,
|
| 12615 |
+
"loss": 0.4405,
|
| 12616 |
+
"step": 1660000
|
| 12617 |
+
},
|
| 12618 |
+
{
|
| 12619 |
+
"epoch": 0.08,
|
| 12620 |
+
"eval_loss": 0.4228270649909973,
|
| 12621 |
+
"eval_runtime": 78.2009,
|
| 12622 |
+
"eval_samples_per_second": 81.841,
|
| 12623 |
+
"eval_steps_per_second": 0.639,
|
| 12624 |
+
"step": 1660000
|
| 12625 |
+
},
|
| 12626 |
+
{
|
| 12627 |
+
"epoch": 0.08,
|
| 12628 |
+
"learning_rate": 2.1941831241763897e-05,
|
| 12629 |
+
"loss": 0.4402,
|
| 12630 |
+
"step": 1661000
|
| 12631 |
+
},
|
| 12632 |
+
{
|
| 12633 |
+
"epoch": 0.08,
|
| 12634 |
+
"learning_rate": 2.1873667532140358e-05,
|
| 12635 |
+
"loss": 0.439,
|
| 12636 |
+
"step": 1662000
|
| 12637 |
+
},
|
| 12638 |
+
{
|
| 12639 |
+
"epoch": 0.08,
|
| 12640 |
+
"learning_rate": 2.1805748783540877e-05,
|
| 12641 |
+
"loss": 0.44,
|
| 12642 |
+
"step": 1663000
|
| 12643 |
+
},
|
| 12644 |
+
{
|
| 12645 |
+
"epoch": 0.08,
|
| 12646 |
+
"learning_rate": 2.1737939229421666e-05,
|
| 12647 |
+
"loss": 0.4407,
|
| 12648 |
+
"step": 1664000
|
| 12649 |
+
},
|
| 12650 |
+
{
|
| 12651 |
+
"epoch": 0.08,
|
| 12652 |
+
"learning_rate": 2.167037469500335e-05,
|
| 12653 |
+
"loss": 0.4404,
|
| 12654 |
+
"step": 1665000
|
| 12655 |
+
},
|
| 12656 |
+
{
|
| 12657 |
+
"epoch": 0.08,
|
| 12658 |
+
"eval_loss": 0.41908711194992065,
|
| 12659 |
+
"eval_runtime": 78.8241,
|
| 12660 |
+
"eval_samples_per_second": 81.193,
|
| 12661 |
+
"eval_steps_per_second": 0.634,
|
| 12662 |
+
"step": 1665000
|
| 12663 |
+
},
|
| 12664 |
+
{
|
| 12665 |
+
"epoch": 0.08,
|
| 12666 |
+
"learning_rate": 2.160292012180046e-05,
|
| 12667 |
+
"loss": 0.4405,
|
| 12668 |
+
"step": 1666000
|
| 12669 |
+
},
|
| 12670 |
+
{
|
| 12671 |
+
"epoch": 0.08,
|
| 12672 |
+
"learning_rate": 2.1535643436230335e-05,
|
| 12673 |
+
"loss": 0.4401,
|
| 12674 |
+
"step": 1667000
|
| 12675 |
+
},
|
| 12676 |
+
{
|
| 12677 |
+
"epoch": 0.08,
|
| 12678 |
+
"learning_rate": 2.146854484322948e-05,
|
| 12679 |
+
"loss": 0.4403,
|
| 12680 |
+
"step": 1668000
|
| 12681 |
+
},
|
| 12682 |
+
{
|
| 12683 |
+
"epoch": 0.08,
|
| 12684 |
+
"learning_rate": 2.140162454719184e-05,
|
| 12685 |
+
"loss": 0.4418,
|
| 12686 |
+
"step": 1669000
|
| 12687 |
+
},
|
| 12688 |
+
{
|
| 12689 |
+
"epoch": 0.09,
|
| 12690 |
+
"learning_rate": 2.1334882751968192e-05,
|
| 12691 |
+
"loss": 0.4397,
|
| 12692 |
+
"step": 1670000
|
| 12693 |
+
},
|
| 12694 |
+
{
|
| 12695 |
+
"epoch": 0.09,
|
| 12696 |
+
"eval_loss": 0.42122882604599,
|
| 12697 |
+
"eval_runtime": 76.417,
|
| 12698 |
+
"eval_samples_per_second": 83.751,
|
| 12699 |
+
"eval_steps_per_second": 0.654,
|
| 12700 |
+
"step": 1670000
|
| 12701 |
+
},
|
| 12702 |
+
{
|
| 12703 |
+
"epoch": 0.09,
|
| 12704 |
+
"learning_rate": 2.126838613462656e-05,
|
| 12705 |
+
"loss": 0.4387,
|
| 12706 |
+
"step": 1671000
|
| 12707 |
+
},
|
| 12708 |
+
{
|
| 12709 |
+
"epoch": 0.09,
|
| 12710 |
+
"learning_rate": 2.1202001771399895e-05,
|
| 12711 |
+
"loss": 0.4387,
|
| 12712 |
+
"step": 1672000
|
| 12713 |
+
},
|
| 12714 |
+
{
|
| 12715 |
+
"epoch": 0.09,
|
| 12716 |
+
"learning_rate": 2.1135796517072863e-05,
|
| 12717 |
+
"loss": 0.4394,
|
| 12718 |
+
"step": 1673000
|
| 12719 |
+
},
|
| 12720 |
+
{
|
| 12721 |
+
"epoch": 0.09,
|
| 12722 |
+
"learning_rate": 2.106977057331812e-05,
|
| 12723 |
+
"loss": 0.4398,
|
| 12724 |
+
"step": 1674000
|
| 12725 |
+
},
|
| 12726 |
+
{
|
| 12727 |
+
"epoch": 0.09,
|
| 12728 |
+
"learning_rate": 2.1003989897961326e-05,
|
| 12729 |
+
"loss": 0.44,
|
| 12730 |
+
"step": 1675000
|
| 12731 |
+
},
|
| 12732 |
+
{
|
| 12733 |
+
"epoch": 0.09,
|
| 12734 |
+
"eval_loss": 0.41976797580718994,
|
| 12735 |
+
"eval_runtime": 77.5035,
|
| 12736 |
+
"eval_samples_per_second": 82.577,
|
| 12737 |
+
"eval_steps_per_second": 0.645,
|
| 12738 |
+
"step": 1675000
|
| 12739 |
+
},
|
| 12740 |
+
{
|
| 12741 |
+
"epoch": 0.09,
|
| 12742 |
+
"learning_rate": 2.0938388575438328e-05,
|
| 12743 |
+
"loss": 0.4403,
|
| 12744 |
+
"step": 1676000
|
| 12745 |
+
},
|
| 12746 |
+
{
|
| 12747 |
+
"epoch": 0.09,
|
| 12748 |
+
"learning_rate": 2.0872901407947595e-05,
|
| 12749 |
+
"loss": 0.4413,
|
| 12750 |
+
"step": 1677000
|
| 12751 |
+
},
|
| 12752 |
+
{
|
| 12753 |
+
"epoch": 0.09,
|
| 12754 |
+
"learning_rate": 2.080759435185324e-05,
|
| 12755 |
+
"loss": 0.4397,
|
| 12756 |
+
"step": 1678000
|
| 12757 |
+
},
|
| 12758 |
+
{
|
| 12759 |
+
"epoch": 0.09,
|
| 12760 |
+
"learning_rate": 2.0742467606091935e-05,
|
| 12761 |
+
"loss": 0.4395,
|
| 12762 |
+
"step": 1679000
|
| 12763 |
+
},
|
| 12764 |
+
{
|
| 12765 |
+
"epoch": 0.09,
|
| 12766 |
+
"learning_rate": 2.0677586225058045e-05,
|
| 12767 |
+
"loss": 0.4407,
|
| 12768 |
+
"step": 1680000
|
| 12769 |
+
},
|
| 12770 |
+
{
|
| 12771 |
+
"epoch": 0.09,
|
| 12772 |
+
"eval_loss": 0.42079994082450867,
|
| 12773 |
+
"eval_runtime": 79.6958,
|
| 12774 |
+
"eval_samples_per_second": 80.305,
|
| 12775 |
+
"eval_steps_per_second": 0.627,
|
| 12776 |
+
"step": 1680000
|
| 12777 |
+
},
|
| 12778 |
+
{
|
| 12779 |
+
"epoch": 0.09,
|
| 12780 |
+
"learning_rate": 2.0612885189152567e-05,
|
| 12781 |
+
"loss": 0.4399,
|
| 12782 |
+
"step": 1681000
|
| 12783 |
+
},
|
| 12784 |
+
{
|
| 12785 |
+
"epoch": 0.09,
|
| 12786 |
+
"learning_rate": 2.0548300200510223e-05,
|
| 12787 |
+
"loss": 0.4382,
|
| 12788 |
+
"step": 1682000
|
| 12789 |
+
},
|
| 12790 |
+
{
|
| 12791 |
+
"epoch": 0.09,
|
| 12792 |
+
"learning_rate": 2.048389631205587e-05,
|
| 12793 |
+
"loss": 0.4393,
|
| 12794 |
+
"step": 1683000
|
| 12795 |
+
},
|
| 12796 |
+
{
|
| 12797 |
+
"epoch": 0.09,
|
| 12798 |
+
"learning_rate": 2.041967371997491e-05,
|
| 12799 |
+
"loss": 0.4392,
|
| 12800 |
+
"step": 1684000
|
| 12801 |
+
},
|
| 12802 |
+
{
|
| 12803 |
+
"epoch": 0.09,
|
| 12804 |
+
"learning_rate": 2.0355760520841843e-05,
|
| 12805 |
+
"loss": 0.4403,
|
| 12806 |
+
"step": 1685000
|
| 12807 |
+
},
|
| 12808 |
+
{
|
| 12809 |
+
"epoch": 0.09,
|
| 12810 |
+
"eval_loss": 0.41910338401794434,
|
| 12811 |
+
"eval_runtime": 79.2458,
|
| 12812 |
+
"eval_samples_per_second": 80.761,
|
| 12813 |
+
"eval_steps_per_second": 0.631,
|
| 12814 |
+
"step": 1685000
|
| 12815 |
+
},
|
| 12816 |
+
{
|
| 12817 |
+
"epoch": 0.09,
|
| 12818 |
+
"learning_rate": 2.0291900744285765e-05,
|
| 12819 |
+
"loss": 0.4397,
|
| 12820 |
+
"step": 1686000
|
| 12821 |
+
},
|
| 12822 |
+
{
|
| 12823 |
+
"epoch": 0.09,
|
| 12824 |
+
"learning_rate": 2.022822284895487e-05,
|
| 12825 |
+
"loss": 0.4401,
|
| 12826 |
+
"step": 1687000
|
| 12827 |
+
},
|
| 12828 |
+
{
|
| 12829 |
+
"epoch": 0.09,
|
| 12830 |
+
"learning_rate": 2.016472702882308e-05,
|
| 12831 |
+
"loss": 0.4395,
|
| 12832 |
+
"step": 1688000
|
| 12833 |
+
},
|
| 12834 |
+
{
|
| 12835 |
+
"epoch": 0.09,
|
| 12836 |
+
"learning_rate": 2.0101476699753774e-05,
|
| 12837 |
+
"loss": 0.4394,
|
| 12838 |
+
"step": 1689000
|
| 12839 |
+
},
|
| 12840 |
+
{
|
| 12841 |
+
"epoch": 0.1,
|
| 12842 |
+
"learning_rate": 2.003840846723428e-05,
|
| 12843 |
+
"loss": 0.4408,
|
| 12844 |
+
"step": 1690000
|
| 12845 |
+
},
|
| 12846 |
+
{
|
| 12847 |
+
"epoch": 0.1,
|
| 12848 |
+
"eval_loss": 0.41959914565086365,
|
| 12849 |
+
"eval_runtime": 79.6028,
|
| 12850 |
+
"eval_samples_per_second": 80.399,
|
| 12851 |
+
"eval_steps_per_second": 0.628,
|
| 12852 |
+
"step": 1690000
|
| 12853 |
+
},
|
| 12854 |
+
{
|
| 12855 |
+
"epoch": 0.1,
|
| 12856 |
+
"learning_rate": 1.9975459665494844e-05,
|
| 12857 |
+
"loss": 0.4406,
|
| 12858 |
+
"step": 1691000
|
| 12859 |
+
},
|
| 12860 |
+
{
|
| 12861 |
+
"epoch": 0.1,
|
| 12862 |
+
"learning_rate": 1.9912693708915007e-05,
|
| 12863 |
+
"loss": 0.4403,
|
| 12864 |
+
"step": 1692000
|
| 12865 |
+
},
|
| 12866 |
+
{
|
| 12867 |
+
"epoch": 0.1,
|
| 12868 |
+
"learning_rate": 1.9850110788690757e-05,
|
| 12869 |
+
"loss": 0.4391,
|
| 12870 |
+
"step": 1693000
|
| 12871 |
+
},
|
| 12872 |
+
{
|
| 12873 |
+
"epoch": 0.1,
|
| 12874 |
+
"learning_rate": 1.978771109546051e-05,
|
| 12875 |
+
"loss": 0.4388,
|
| 12876 |
+
"step": 1694000
|
| 12877 |
+
},
|
| 12878 |
+
{
|
| 12879 |
+
"epoch": 0.1,
|
| 12880 |
+
"learning_rate": 1.9725681193643978e-05,
|
| 12881 |
+
"loss": 0.439,
|
| 12882 |
+
"step": 1695000
|
| 12883 |
+
},
|
| 12884 |
+
{
|
| 12885 |
+
"epoch": 0.1,
|
| 12886 |
+
"eval_loss": 0.4219348132610321,
|
| 12887 |
+
"eval_runtime": 78.5115,
|
| 12888 |
+
"eval_samples_per_second": 81.517,
|
| 12889 |
+
"eval_steps_per_second": 0.637,
|
| 12890 |
+
"step": 1695000
|
| 12891 |
+
},
|
| 12892 |
+
{
|
| 12893 |
+
"epoch": 0.1,
|
| 12894 |
+
"learning_rate": 1.9663647972981225e-05,
|
| 12895 |
+
"loss": 0.4389,
|
| 12896 |
+
"step": 1696000
|
| 12897 |
+
},
|
| 12898 |
+
{
|
| 12899 |
+
"epoch": 0.1,
|
| 12900 |
+
"learning_rate": 1.9601798547310563e-05,
|
| 12901 |
+
"loss": 0.4396,
|
| 12902 |
+
"step": 1697000
|
| 12903 |
+
},
|
| 12904 |
+
{
|
| 12905 |
+
"epoch": 0.1,
|
| 12906 |
+
"learning_rate": 1.954019467851605e-05,
|
| 12907 |
+
"loss": 0.4405,
|
| 12908 |
+
"step": 1698000
|
| 12909 |
+
},
|
| 12910 |
+
{
|
| 12911 |
+
"epoch": 0.1,
|
| 12912 |
+
"learning_rate": 1.9478713223216454e-05,
|
| 12913 |
+
"loss": 0.4403,
|
| 12914 |
+
"step": 1699000
|
| 12915 |
+
},
|
| 12916 |
+
{
|
| 12917 |
+
"epoch": 0.1,
|
| 12918 |
+
"learning_rate": 1.9417416126252245e-05,
|
| 12919 |
+
"loss": 0.4394,
|
| 12920 |
+
"step": 1700000
|
| 12921 |
+
},
|
| 12922 |
+
{
|
| 12923 |
+
"epoch": 0.1,
|
| 12924 |
+
"eval_loss": 0.42123520374298096,
|
| 12925 |
+
"eval_runtime": 78.2147,
|
| 12926 |
+
"eval_samples_per_second": 81.826,
|
| 12927 |
+
"eval_steps_per_second": 0.639,
|
| 12928 |
+
"step": 1700000
|
| 12929 |
}
|
| 12930 |
],
|
| 12931 |
"max_steps": 2000000,
|
| 12932 |
"num_train_epochs": 9223372036854775807,
|
| 12933 |
+
"total_flos": 1.4896305656561664e+22,
|
| 12934 |
"trial_name": null,
|
| 12935 |
"trial_params": null
|
| 12936 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 449471589
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:abc7a8543a963e582a29e31e1e0c78fea4345a1b73b925ed6cc4d7ab61edbd1e
|
| 3 |
size 449471589
|