Training in progress, step 60000, checkpoint
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +353 -3
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 304481530
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c8ed307c1a8c6892f9c7d1763adc6de4fd66586b943a9b012b72c37652cf06a7
|
| 3 |
size 304481530
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 402029570
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e2670278693d306533b2beeaefb38a032c634518844881f8e87f94e5dbace516
|
| 3 |
size 402029570
|
last-checkpoint/rng_state_0.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14960
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:50fab9238cc598344d14526b1a8a8f1f603fce59fb4543675e2e4f0f2b585015
|
| 3 |
size 14960
|
last-checkpoint/rng_state_1.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14960
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3ef8fd71a3af2ddf15fcb7b07b1d21cb23fcbbf5abc41e4673c663e17ad40e77
|
| 3 |
size 14960
|
last-checkpoint/rng_state_2.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14960
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8afee1b5192a8fa9e386b287b40e99b4679a3232b94ada0c766e5a1cfa6284dc
|
| 3 |
size 14960
|
last-checkpoint/rng_state_3.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14960
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bfa9b9844e3c91dfe1868851e40e80991301ec5b6fd770f09f0ec1a45039509d
|
| 3 |
size 14960
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7fc543567412ce132e9cd698ae00023fd3a922f9177a4d1ded99cfb1fce9e945
|
| 3 |
size 1064
|
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": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -20658,6 +20658,356 @@
|
|
| 20658 |
"learning_rate": 0.00048555386204961854,
|
| 20659 |
"loss": 17.0075,
|
| 20660 |
"step": 59000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20661 |
}
|
| 20662 |
],
|
| 20663 |
"logging_steps": 20,
|
|
@@ -20677,7 +21027,7 @@
|
|
| 20677 |
"attributes": {}
|
| 20678 |
}
|
| 20679 |
},
|
| 20680 |
-
"total_flos": 4.
|
| 20681 |
"train_batch_size": 48,
|
| 20682 |
"trial_name": null,
|
| 20683 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.08887888178516197,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 60000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 20658 |
"learning_rate": 0.00048555386204961854,
|
| 20659 |
"loss": 17.0075,
|
| 20660 |
"step": 59000
|
| 20661 |
+
},
|
| 20662 |
+
{
|
| 20663 |
+
"epoch": 0.08742719338267099,
|
| 20664 |
+
"grad_norm": 6.84375,
|
| 20665 |
+
"learning_rate": 0.000485548923114611,
|
| 20666 |
+
"loss": 16.9763,
|
| 20667 |
+
"step": 59020
|
| 20668 |
+
},
|
| 20669 |
+
{
|
| 20670 |
+
"epoch": 0.08745681967659938,
|
| 20671 |
+
"grad_norm": 6.9375,
|
| 20672 |
+
"learning_rate": 0.0004855439841796034,
|
| 20673 |
+
"loss": 16.9323,
|
| 20674 |
+
"step": 59040
|
| 20675 |
+
},
|
| 20676 |
+
{
|
| 20677 |
+
"epoch": 0.08748644597052777,
|
| 20678 |
+
"grad_norm": 6.75,
|
| 20679 |
+
"learning_rate": 0.0004855390452445958,
|
| 20680 |
+
"loss": 16.8948,
|
| 20681 |
+
"step": 59060
|
| 20682 |
+
},
|
| 20683 |
+
{
|
| 20684 |
+
"epoch": 0.08751607226445615,
|
| 20685 |
+
"grad_norm": 6.75,
|
| 20686 |
+
"learning_rate": 0.0004855341063095883,
|
| 20687 |
+
"loss": 16.9331,
|
| 20688 |
+
"step": 59080
|
| 20689 |
+
},
|
| 20690 |
+
{
|
| 20691 |
+
"epoch": 0.08754569855838454,
|
| 20692 |
+
"grad_norm": 7.8125,
|
| 20693 |
+
"learning_rate": 0.00048552916737458067,
|
| 20694 |
+
"loss": 16.933,
|
| 20695 |
+
"step": 59100
|
| 20696 |
+
},
|
| 20697 |
+
{
|
| 20698 |
+
"epoch": 0.08757532485231292,
|
| 20699 |
+
"grad_norm": 6.1875,
|
| 20700 |
+
"learning_rate": 0.0004855242284395731,
|
| 20701 |
+
"loss": 16.9698,
|
| 20702 |
+
"step": 59120
|
| 20703 |
+
},
|
| 20704 |
+
{
|
| 20705 |
+
"epoch": 0.08760495114624131,
|
| 20706 |
+
"grad_norm": 6.8125,
|
| 20707 |
+
"learning_rate": 0.00048551928950456557,
|
| 20708 |
+
"loss": 16.9211,
|
| 20709 |
+
"step": 59140
|
| 20710 |
+
},
|
| 20711 |
+
{
|
| 20712 |
+
"epoch": 0.0876345774401697,
|
| 20713 |
+
"grad_norm": 7.40625,
|
| 20714 |
+
"learning_rate": 0.000485514350569558,
|
| 20715 |
+
"loss": 16.9048,
|
| 20716 |
+
"step": 59160
|
| 20717 |
+
},
|
| 20718 |
+
{
|
| 20719 |
+
"epoch": 0.08766420373409808,
|
| 20720 |
+
"grad_norm": 6.15625,
|
| 20721 |
+
"learning_rate": 0.0004855094116345504,
|
| 20722 |
+
"loss": 16.9459,
|
| 20723 |
+
"step": 59180
|
| 20724 |
+
},
|
| 20725 |
+
{
|
| 20726 |
+
"epoch": 0.08769383002802647,
|
| 20727 |
+
"grad_norm": 8.1875,
|
| 20728 |
+
"learning_rate": 0.00048550447269954286,
|
| 20729 |
+
"loss": 16.9266,
|
| 20730 |
+
"step": 59200
|
| 20731 |
+
},
|
| 20732 |
+
{
|
| 20733 |
+
"epoch": 0.08772345632195486,
|
| 20734 |
+
"grad_norm": 6.84375,
|
| 20735 |
+
"learning_rate": 0.0004854995337645353,
|
| 20736 |
+
"loss": 16.9213,
|
| 20737 |
+
"step": 59220
|
| 20738 |
+
},
|
| 20739 |
+
{
|
| 20740 |
+
"epoch": 0.08775308261588324,
|
| 20741 |
+
"grad_norm": 6.90625,
|
| 20742 |
+
"learning_rate": 0.00048549459482952775,
|
| 20743 |
+
"loss": 16.9731,
|
| 20744 |
+
"step": 59240
|
| 20745 |
+
},
|
| 20746 |
+
{
|
| 20747 |
+
"epoch": 0.08778270890981163,
|
| 20748 |
+
"grad_norm": 6.6875,
|
| 20749 |
+
"learning_rate": 0.00048548965589452015,
|
| 20750 |
+
"loss": 16.94,
|
| 20751 |
+
"step": 59260
|
| 20752 |
+
},
|
| 20753 |
+
{
|
| 20754 |
+
"epoch": 0.08781233520374003,
|
| 20755 |
+
"grad_norm": 5.71875,
|
| 20756 |
+
"learning_rate": 0.0004854847169595126,
|
| 20757 |
+
"loss": 16.8507,
|
| 20758 |
+
"step": 59280
|
| 20759 |
+
},
|
| 20760 |
+
{
|
| 20761 |
+
"epoch": 0.08784196149766842,
|
| 20762 |
+
"grad_norm": 6.5,
|
| 20763 |
+
"learning_rate": 0.00048547977802450504,
|
| 20764 |
+
"loss": 16.9175,
|
| 20765 |
+
"step": 59300
|
| 20766 |
+
},
|
| 20767 |
+
{
|
| 20768 |
+
"epoch": 0.0878715877915968,
|
| 20769 |
+
"grad_norm": 6.78125,
|
| 20770 |
+
"learning_rate": 0.0004854748390894975,
|
| 20771 |
+
"loss": 16.9454,
|
| 20772 |
+
"step": 59320
|
| 20773 |
+
},
|
| 20774 |
+
{
|
| 20775 |
+
"epoch": 0.08790121408552519,
|
| 20776 |
+
"grad_norm": 6.84375,
|
| 20777 |
+
"learning_rate": 0.0004854699001544899,
|
| 20778 |
+
"loss": 16.9354,
|
| 20779 |
+
"step": 59340
|
| 20780 |
+
},
|
| 20781 |
+
{
|
| 20782 |
+
"epoch": 0.08793084037945358,
|
| 20783 |
+
"grad_norm": 7.375,
|
| 20784 |
+
"learning_rate": 0.0004854649612194823,
|
| 20785 |
+
"loss": 16.8951,
|
| 20786 |
+
"step": 59360
|
| 20787 |
+
},
|
| 20788 |
+
{
|
| 20789 |
+
"epoch": 0.08796046667338196,
|
| 20790 |
+
"grad_norm": 7.625,
|
| 20791 |
+
"learning_rate": 0.0004854600222844748,
|
| 20792 |
+
"loss": 16.9231,
|
| 20793 |
+
"step": 59380
|
| 20794 |
+
},
|
| 20795 |
+
{
|
| 20796 |
+
"epoch": 0.08799009296731035,
|
| 20797 |
+
"grad_norm": 6.5,
|
| 20798 |
+
"learning_rate": 0.0004854550833494672,
|
| 20799 |
+
"loss": 16.8769,
|
| 20800 |
+
"step": 59400
|
| 20801 |
+
},
|
| 20802 |
+
{
|
| 20803 |
+
"epoch": 0.08801971926123874,
|
| 20804 |
+
"grad_norm": 7.71875,
|
| 20805 |
+
"learning_rate": 0.0004854501444144596,
|
| 20806 |
+
"loss": 16.9411,
|
| 20807 |
+
"step": 59420
|
| 20808 |
+
},
|
| 20809 |
+
{
|
| 20810 |
+
"epoch": 0.08804934555516712,
|
| 20811 |
+
"grad_norm": 6.96875,
|
| 20812 |
+
"learning_rate": 0.00048544520547945207,
|
| 20813 |
+
"loss": 16.943,
|
| 20814 |
+
"step": 59440
|
| 20815 |
+
},
|
| 20816 |
+
{
|
| 20817 |
+
"epoch": 0.08807897184909551,
|
| 20818 |
+
"grad_norm": 6.75,
|
| 20819 |
+
"learning_rate": 0.0004854402665444445,
|
| 20820 |
+
"loss": 16.9327,
|
| 20821 |
+
"step": 59460
|
| 20822 |
+
},
|
| 20823 |
+
{
|
| 20824 |
+
"epoch": 0.0881085981430239,
|
| 20825 |
+
"grad_norm": 6.8125,
|
| 20826 |
+
"learning_rate": 0.0004854353276094369,
|
| 20827 |
+
"loss": 16.9585,
|
| 20828 |
+
"step": 59480
|
| 20829 |
+
},
|
| 20830 |
+
{
|
| 20831 |
+
"epoch": 0.08813822443695228,
|
| 20832 |
+
"grad_norm": 7.5,
|
| 20833 |
+
"learning_rate": 0.00048543038867442936,
|
| 20834 |
+
"loss": 16.9142,
|
| 20835 |
+
"step": 59500
|
| 20836 |
+
},
|
| 20837 |
+
{
|
| 20838 |
+
"epoch": 0.08816785073088067,
|
| 20839 |
+
"grad_norm": 6.84375,
|
| 20840 |
+
"learning_rate": 0.0004854254497394218,
|
| 20841 |
+
"loss": 16.8786,
|
| 20842 |
+
"step": 59520
|
| 20843 |
+
},
|
| 20844 |
+
{
|
| 20845 |
+
"epoch": 0.08819747702480905,
|
| 20846 |
+
"grad_norm": 7.1875,
|
| 20847 |
+
"learning_rate": 0.00048542051080441425,
|
| 20848 |
+
"loss": 16.9315,
|
| 20849 |
+
"step": 59540
|
| 20850 |
+
},
|
| 20851 |
+
{
|
| 20852 |
+
"epoch": 0.08822710331873744,
|
| 20853 |
+
"grad_norm": 6.9375,
|
| 20854 |
+
"learning_rate": 0.00048541557186940665,
|
| 20855 |
+
"loss": 16.9105,
|
| 20856 |
+
"step": 59560
|
| 20857 |
+
},
|
| 20858 |
+
{
|
| 20859 |
+
"epoch": 0.08825672961266583,
|
| 20860 |
+
"grad_norm": 6.1875,
|
| 20861 |
+
"learning_rate": 0.0004854106329343991,
|
| 20862 |
+
"loss": 16.9476,
|
| 20863 |
+
"step": 59580
|
| 20864 |
+
},
|
| 20865 |
+
{
|
| 20866 |
+
"epoch": 0.08828635590659423,
|
| 20867 |
+
"grad_norm": 7.5,
|
| 20868 |
+
"learning_rate": 0.00048540569399939154,
|
| 20869 |
+
"loss": 16.9046,
|
| 20870 |
+
"step": 59600
|
| 20871 |
+
},
|
| 20872 |
+
{
|
| 20873 |
+
"epoch": 0.08831598220052261,
|
| 20874 |
+
"grad_norm": 7.4375,
|
| 20875 |
+
"learning_rate": 0.000485400755064384,
|
| 20876 |
+
"loss": 16.9677,
|
| 20877 |
+
"step": 59620
|
| 20878 |
+
},
|
| 20879 |
+
{
|
| 20880 |
+
"epoch": 0.088345608494451,
|
| 20881 |
+
"grad_norm": 7.25,
|
| 20882 |
+
"learning_rate": 0.0004853958161293764,
|
| 20883 |
+
"loss": 16.8664,
|
| 20884 |
+
"step": 59640
|
| 20885 |
+
},
|
| 20886 |
+
{
|
| 20887 |
+
"epoch": 0.08837523478837939,
|
| 20888 |
+
"grad_norm": 6.6875,
|
| 20889 |
+
"learning_rate": 0.00048539087719436883,
|
| 20890 |
+
"loss": 16.9334,
|
| 20891 |
+
"step": 59660
|
| 20892 |
+
},
|
| 20893 |
+
{
|
| 20894 |
+
"epoch": 0.08840486108230777,
|
| 20895 |
+
"grad_norm": 7.375,
|
| 20896 |
+
"learning_rate": 0.0004853859382593613,
|
| 20897 |
+
"loss": 16.8932,
|
| 20898 |
+
"step": 59680
|
| 20899 |
+
},
|
| 20900 |
+
{
|
| 20901 |
+
"epoch": 0.08843448737623616,
|
| 20902 |
+
"grad_norm": 6.96875,
|
| 20903 |
+
"learning_rate": 0.0004853809993243537,
|
| 20904 |
+
"loss": 16.9439,
|
| 20905 |
+
"step": 59700
|
| 20906 |
+
},
|
| 20907 |
+
{
|
| 20908 |
+
"epoch": 0.08846411367016455,
|
| 20909 |
+
"grad_norm": 6.625,
|
| 20910 |
+
"learning_rate": 0.0004853760603893461,
|
| 20911 |
+
"loss": 16.9137,
|
| 20912 |
+
"step": 59720
|
| 20913 |
+
},
|
| 20914 |
+
{
|
| 20915 |
+
"epoch": 0.08849373996409293,
|
| 20916 |
+
"grad_norm": 6.1875,
|
| 20917 |
+
"learning_rate": 0.00048537112145433857,
|
| 20918 |
+
"loss": 16.9407,
|
| 20919 |
+
"step": 59740
|
| 20920 |
+
},
|
| 20921 |
+
{
|
| 20922 |
+
"epoch": 0.08852336625802132,
|
| 20923 |
+
"grad_norm": 7.28125,
|
| 20924 |
+
"learning_rate": 0.000485366182519331,
|
| 20925 |
+
"loss": 16.9089,
|
| 20926 |
+
"step": 59760
|
| 20927 |
+
},
|
| 20928 |
+
{
|
| 20929 |
+
"epoch": 0.0885529925519497,
|
| 20930 |
+
"grad_norm": 6.8125,
|
| 20931 |
+
"learning_rate": 0.0004853612435843234,
|
| 20932 |
+
"loss": 16.9287,
|
| 20933 |
+
"step": 59780
|
| 20934 |
+
},
|
| 20935 |
+
{
|
| 20936 |
+
"epoch": 0.08858261884587809,
|
| 20937 |
+
"grad_norm": 6.875,
|
| 20938 |
+
"learning_rate": 0.00048535630464931586,
|
| 20939 |
+
"loss": 16.8928,
|
| 20940 |
+
"step": 59800
|
| 20941 |
+
},
|
| 20942 |
+
{
|
| 20943 |
+
"epoch": 0.08861224513980648,
|
| 20944 |
+
"grad_norm": 7.1875,
|
| 20945 |
+
"learning_rate": 0.0004853513657143083,
|
| 20946 |
+
"loss": 16.8844,
|
| 20947 |
+
"step": 59820
|
| 20948 |
+
},
|
| 20949 |
+
{
|
| 20950 |
+
"epoch": 0.08864187143373486,
|
| 20951 |
+
"grad_norm": 6.375,
|
| 20952 |
+
"learning_rate": 0.00048534642677930075,
|
| 20953 |
+
"loss": 16.8664,
|
| 20954 |
+
"step": 59840
|
| 20955 |
+
},
|
| 20956 |
+
{
|
| 20957 |
+
"epoch": 0.08867149772766325,
|
| 20958 |
+
"grad_norm": 6.5,
|
| 20959 |
+
"learning_rate": 0.00048534148784429315,
|
| 20960 |
+
"loss": 16.936,
|
| 20961 |
+
"step": 59860
|
| 20962 |
+
},
|
| 20963 |
+
{
|
| 20964 |
+
"epoch": 0.08870112402159164,
|
| 20965 |
+
"grad_norm": 6.84375,
|
| 20966 |
+
"learning_rate": 0.0004853365489092856,
|
| 20967 |
+
"loss": 16.9358,
|
| 20968 |
+
"step": 59880
|
| 20969 |
+
},
|
| 20970 |
+
{
|
| 20971 |
+
"epoch": 0.08873075031552002,
|
| 20972 |
+
"grad_norm": 7.03125,
|
| 20973 |
+
"learning_rate": 0.00048533160997427804,
|
| 20974 |
+
"loss": 16.9482,
|
| 20975 |
+
"step": 59900
|
| 20976 |
+
},
|
| 20977 |
+
{
|
| 20978 |
+
"epoch": 0.08876037660944842,
|
| 20979 |
+
"grad_norm": 7.46875,
|
| 20980 |
+
"learning_rate": 0.0004853266710392705,
|
| 20981 |
+
"loss": 16.8417,
|
| 20982 |
+
"step": 59920
|
| 20983 |
+
},
|
| 20984 |
+
{
|
| 20985 |
+
"epoch": 0.08879000290337681,
|
| 20986 |
+
"grad_norm": 7.3125,
|
| 20987 |
+
"learning_rate": 0.0004853217321042629,
|
| 20988 |
+
"loss": 16.869,
|
| 20989 |
+
"step": 59940
|
| 20990 |
+
},
|
| 20991 |
+
{
|
| 20992 |
+
"epoch": 0.0888196291973052,
|
| 20993 |
+
"grad_norm": 5.65625,
|
| 20994 |
+
"learning_rate": 0.00048531679316925533,
|
| 20995 |
+
"loss": 16.8701,
|
| 20996 |
+
"step": 59960
|
| 20997 |
+
},
|
| 20998 |
+
{
|
| 20999 |
+
"epoch": 0.08884925549123358,
|
| 21000 |
+
"grad_norm": 6.46875,
|
| 21001 |
+
"learning_rate": 0.0004853118542342478,
|
| 21002 |
+
"loss": 16.9125,
|
| 21003 |
+
"step": 59980
|
| 21004 |
+
},
|
| 21005 |
+
{
|
| 21006 |
+
"epoch": 0.08887888178516197,
|
| 21007 |
+
"grad_norm": 7.625,
|
| 21008 |
+
"learning_rate": 0.00048530691529924023,
|
| 21009 |
+
"loss": 16.8648,
|
| 21010 |
+
"step": 60000
|
| 21011 |
}
|
| 21012 |
],
|
| 21013 |
"logging_steps": 20,
|
|
|
|
| 21027 |
"attributes": {}
|
| 21028 |
}
|
| 21029 |
},
|
| 21030 |
+
"total_flos": 4.411273302804057e+19,
|
| 21031 |
"train_batch_size": 48,
|
| 21032 |
"trial_name": null,
|
| 21033 |
"trial_params": null
|