Training in progress, step 2000, 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 598434152
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a8108b4c7505bf31f05a0583aabbf5fe4cfe4429dc292fc208409ab6e5fcfded
|
| 3 |
size 598434152
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1196955962
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4ee29d79e39b5eeb941ba1801f2a551f0871fde9c5f8d5db87000ea005b4bca7
|
| 3 |
size 1196955962
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f4728e4a27ef2a8c58f14bda178d8eac76290169f611c06f23f0154a1ac41085
|
| 3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1000
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f83b5db90f4185c28054d91912c7daf482661e1eee0f05c8ff078fbdacbc6754
|
| 3 |
size 1000
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 250,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -771,6 +771,770 @@
|
|
| 771 |
"eval_spearman_manhattan": 0.7526380381288565,
|
| 772 |
"eval_steps_per_second": 31.325,
|
| 773 |
"step": 1000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 774 |
}
|
| 775 |
],
|
| 776 |
"logging_steps": 10,
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9372071227741331,
|
| 5 |
"eval_steps": 250,
|
| 6 |
+
"global_step": 2000,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 771 |
"eval_spearman_manhattan": 0.7526380381288565,
|
| 772 |
"eval_steps_per_second": 31.325,
|
| 773 |
"step": 1000
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.4732895970009372,
|
| 777 |
+
"grad_norm": 6.391997814178467,
|
| 778 |
+
"learning_rate": 9.704194001874416e-06,
|
| 779 |
+
"loss": 0.6965,
|
| 780 |
+
"step": 1010
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.47797563261480785,
|
| 784 |
+
"grad_norm": 5.345996379852295,
|
| 785 |
+
"learning_rate": 9.701265229615747e-06,
|
| 786 |
+
"loss": 0.6447,
|
| 787 |
+
"step": 1020
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.48266166822867856,
|
| 791 |
+
"grad_norm": 5.60822057723999,
|
| 792 |
+
"learning_rate": 9.698336457357076e-06,
|
| 793 |
+
"loss": 0.6854,
|
| 794 |
+
"step": 1030
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.4873477038425492,
|
| 798 |
+
"grad_norm": 6.488014221191406,
|
| 799 |
+
"learning_rate": 9.695407685098408e-06,
|
| 800 |
+
"loss": 0.7089,
|
| 801 |
+
"step": 1040
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.49203373945641987,
|
| 805 |
+
"grad_norm": 5.387355804443359,
|
| 806 |
+
"learning_rate": 9.692478912839737e-06,
|
| 807 |
+
"loss": 0.6949,
|
| 808 |
+
"step": 1050
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.4967197750702905,
|
| 812 |
+
"grad_norm": 5.179281234741211,
|
| 813 |
+
"learning_rate": 9.689550140581068e-06,
|
| 814 |
+
"loss": 0.6571,
|
| 815 |
+
"step": 1060
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.5014058106841612,
|
| 819 |
+
"grad_norm": 5.786458492279053,
|
| 820 |
+
"learning_rate": 9.6866213683224e-06,
|
| 821 |
+
"loss": 0.7154,
|
| 822 |
+
"step": 1070
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.5060918462980318,
|
| 826 |
+
"grad_norm": 6.279985427856445,
|
| 827 |
+
"learning_rate": 9.68369259606373e-06,
|
| 828 |
+
"loss": 0.6757,
|
| 829 |
+
"step": 1080
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.5107778819119025,
|
| 833 |
+
"grad_norm": 4.793182849884033,
|
| 834 |
+
"learning_rate": 9.680763823805062e-06,
|
| 835 |
+
"loss": 0.7136,
|
| 836 |
+
"step": 1090
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.5154639175257731,
|
| 840 |
+
"grad_norm": 7.646529674530029,
|
| 841 |
+
"learning_rate": 9.677835051546393e-06,
|
| 842 |
+
"loss": 0.6396,
|
| 843 |
+
"step": 1100
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.5201499531396439,
|
| 847 |
+
"grad_norm": 5.7034912109375,
|
| 848 |
+
"learning_rate": 9.674906279287724e-06,
|
| 849 |
+
"loss": 0.665,
|
| 850 |
+
"step": 1110
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.5248359887535146,
|
| 854 |
+
"grad_norm": 6.54317045211792,
|
| 855 |
+
"learning_rate": 9.671977507029054e-06,
|
| 856 |
+
"loss": 0.6713,
|
| 857 |
+
"step": 1120
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.5295220243673852,
|
| 861 |
+
"grad_norm": 5.6496806144714355,
|
| 862 |
+
"learning_rate": 9.669048734770385e-06,
|
| 863 |
+
"loss": 0.6876,
|
| 864 |
+
"step": 1130
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.5342080599812559,
|
| 868 |
+
"grad_norm": 5.326486110687256,
|
| 869 |
+
"learning_rate": 9.666119962511716e-06,
|
| 870 |
+
"loss": 0.6951,
|
| 871 |
+
"step": 1140
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.5388940955951266,
|
| 875 |
+
"grad_norm": 5.124545574188232,
|
| 876 |
+
"learning_rate": 9.663191190253046e-06,
|
| 877 |
+
"loss": 0.6388,
|
| 878 |
+
"step": 1150
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.5435801312089972,
|
| 882 |
+
"grad_norm": 4.34152364730835,
|
| 883 |
+
"learning_rate": 9.660262417994377e-06,
|
| 884 |
+
"loss": 0.6322,
|
| 885 |
+
"step": 1160
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.5482661668228679,
|
| 889 |
+
"grad_norm": 8.722075462341309,
|
| 890 |
+
"learning_rate": 9.657333645735708e-06,
|
| 891 |
+
"loss": 0.6776,
|
| 892 |
+
"step": 1170
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.5529522024367385,
|
| 896 |
+
"grad_norm": 5.417623996734619,
|
| 897 |
+
"learning_rate": 9.65440487347704e-06,
|
| 898 |
+
"loss": 0.6492,
|
| 899 |
+
"step": 1180
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.5576382380506092,
|
| 903 |
+
"grad_norm": 4.369041919708252,
|
| 904 |
+
"learning_rate": 9.65147610121837e-06,
|
| 905 |
+
"loss": 0.6039,
|
| 906 |
+
"step": 1190
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.5623242736644799,
|
| 910 |
+
"grad_norm": 6.5720062255859375,
|
| 911 |
+
"learning_rate": 9.648547328959702e-06,
|
| 912 |
+
"loss": 0.6911,
|
| 913 |
+
"step": 1200
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.5670103092783505,
|
| 917 |
+
"grad_norm": 7.112950325012207,
|
| 918 |
+
"learning_rate": 9.645618556701031e-06,
|
| 919 |
+
"loss": 0.6214,
|
| 920 |
+
"step": 1210
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.5716963448922212,
|
| 924 |
+
"grad_norm": 5.643182277679443,
|
| 925 |
+
"learning_rate": 9.642689784442362e-06,
|
| 926 |
+
"loss": 0.6959,
|
| 927 |
+
"step": 1220
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.5763823805060918,
|
| 931 |
+
"grad_norm": 5.078190803527832,
|
| 932 |
+
"learning_rate": 9.639761012183694e-06,
|
| 933 |
+
"loss": 0.6633,
|
| 934 |
+
"step": 1230
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.5810684161199625,
|
| 938 |
+
"grad_norm": 5.247280120849609,
|
| 939 |
+
"learning_rate": 9.636832239925025e-06,
|
| 940 |
+
"loss": 0.6415,
|
| 941 |
+
"step": 1240
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.5857544517338332,
|
| 945 |
+
"grad_norm": 5.110747814178467,
|
| 946 |
+
"learning_rate": 9.633903467666354e-06,
|
| 947 |
+
"loss": 0.6031,
|
| 948 |
+
"step": 1250
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.5857544517338332,
|
| 952 |
+
"eval_loss": 0.06345358490943909,
|
| 953 |
+
"eval_pearson_cosine": 0.7580338914962539,
|
| 954 |
+
"eval_pearson_dot": 0.6394158052533783,
|
| 955 |
+
"eval_pearson_euclidean": 0.7521759780114508,
|
| 956 |
+
"eval_pearson_manhattan": 0.7513571158009427,
|
| 957 |
+
"eval_runtime": 44.2242,
|
| 958 |
+
"eval_samples_per_second": 33.918,
|
| 959 |
+
"eval_spearman_cosine": 0.758882658229917,
|
| 960 |
+
"eval_spearman_dot": 0.6455380162932587,
|
| 961 |
+
"eval_spearman_euclidean": 0.7604619351541958,
|
| 962 |
+
"eval_spearman_manhattan": 0.7599139087493931,
|
| 963 |
+
"eval_steps_per_second": 33.918,
|
| 964 |
+
"step": 1250
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 0.5904404873477038,
|
| 968 |
+
"grad_norm": 6.717201232910156,
|
| 969 |
+
"learning_rate": 9.630974695407685e-06,
|
| 970 |
+
"loss": 0.6553,
|
| 971 |
+
"step": 1260
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 0.5951265229615745,
|
| 975 |
+
"grad_norm": 6.948915004730225,
|
| 976 |
+
"learning_rate": 9.628045923149017e-06,
|
| 977 |
+
"loss": 0.6528,
|
| 978 |
+
"step": 1270
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 0.5998125585754451,
|
| 982 |
+
"grad_norm": 5.585124969482422,
|
| 983 |
+
"learning_rate": 9.625117150890348e-06,
|
| 984 |
+
"loss": 0.6125,
|
| 985 |
+
"step": 1280
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 0.6044985941893158,
|
| 989 |
+
"grad_norm": 4.020166397094727,
|
| 990 |
+
"learning_rate": 9.622188378631679e-06,
|
| 991 |
+
"loss": 0.5857,
|
| 992 |
+
"step": 1290
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 0.6091846298031866,
|
| 996 |
+
"grad_norm": 4.905421257019043,
|
| 997 |
+
"learning_rate": 9.619259606373008e-06,
|
| 998 |
+
"loss": 0.6128,
|
| 999 |
+
"step": 1300
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.6138706654170571,
|
| 1003 |
+
"grad_norm": 5.642446517944336,
|
| 1004 |
+
"learning_rate": 9.61633083411434e-06,
|
| 1005 |
+
"loss": 0.6177,
|
| 1006 |
+
"step": 1310
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 0.6185567010309279,
|
| 1010 |
+
"grad_norm": 5.623671531677246,
|
| 1011 |
+
"learning_rate": 9.613402061855671e-06,
|
| 1012 |
+
"loss": 0.6076,
|
| 1013 |
+
"step": 1320
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 0.6232427366447985,
|
| 1017 |
+
"grad_norm": 3.6249349117279053,
|
| 1018 |
+
"learning_rate": 9.610473289597002e-06,
|
| 1019 |
+
"loss": 0.5987,
|
| 1020 |
+
"step": 1330
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 0.6279287722586692,
|
| 1024 |
+
"grad_norm": 4.7242608070373535,
|
| 1025 |
+
"learning_rate": 9.607544517338333e-06,
|
| 1026 |
+
"loss": 0.6082,
|
| 1027 |
+
"step": 1340
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 0.6326148078725399,
|
| 1031 |
+
"grad_norm": 9.071741104125977,
|
| 1032 |
+
"learning_rate": 9.604615745079663e-06,
|
| 1033 |
+
"loss": 0.6369,
|
| 1034 |
+
"step": 1350
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 0.6373008434864105,
|
| 1038 |
+
"grad_norm": 5.471718788146973,
|
| 1039 |
+
"learning_rate": 9.601686972820994e-06,
|
| 1040 |
+
"loss": 0.6235,
|
| 1041 |
+
"step": 1360
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.6419868791002812,
|
| 1045 |
+
"grad_norm": 6.0755934715271,
|
| 1046 |
+
"learning_rate": 9.598758200562325e-06,
|
| 1047 |
+
"loss": 0.6197,
|
| 1048 |
+
"step": 1370
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 0.6466729147141518,
|
| 1052 |
+
"grad_norm": 5.650800704956055,
|
| 1053 |
+
"learning_rate": 9.595829428303656e-06,
|
| 1054 |
+
"loss": 0.5947,
|
| 1055 |
+
"step": 1380
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 0.6513589503280225,
|
| 1059 |
+
"grad_norm": 4.409568786621094,
|
| 1060 |
+
"learning_rate": 9.592900656044986e-06,
|
| 1061 |
+
"loss": 0.6632,
|
| 1062 |
+
"step": 1390
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 0.6560449859418932,
|
| 1066 |
+
"grad_norm": 6.575608730316162,
|
| 1067 |
+
"learning_rate": 9.589971883786317e-06,
|
| 1068 |
+
"loss": 0.5655,
|
| 1069 |
+
"step": 1400
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 0.6607310215557638,
|
| 1073 |
+
"grad_norm": 4.897518634796143,
|
| 1074 |
+
"learning_rate": 9.587043111527648e-06,
|
| 1075 |
+
"loss": 0.6064,
|
| 1076 |
+
"step": 1410
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 0.6654170571696345,
|
| 1080 |
+
"grad_norm": 4.505845546722412,
|
| 1081 |
+
"learning_rate": 9.58411433926898e-06,
|
| 1082 |
+
"loss": 0.6217,
|
| 1083 |
+
"step": 1420
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 0.6701030927835051,
|
| 1087 |
+
"grad_norm": 11.04179573059082,
|
| 1088 |
+
"learning_rate": 9.58118556701031e-06,
|
| 1089 |
+
"loss": 0.626,
|
| 1090 |
+
"step": 1430
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 0.6747891283973758,
|
| 1094 |
+
"grad_norm": 7.031481742858887,
|
| 1095 |
+
"learning_rate": 9.578256794751642e-06,
|
| 1096 |
+
"loss": 0.6644,
|
| 1097 |
+
"step": 1440
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 0.6794751640112465,
|
| 1101 |
+
"grad_norm": 5.177082061767578,
|
| 1102 |
+
"learning_rate": 9.575328022492971e-06,
|
| 1103 |
+
"loss": 0.5794,
|
| 1104 |
+
"step": 1450
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 0.6841611996251171,
|
| 1108 |
+
"grad_norm": 5.830789566040039,
|
| 1109 |
+
"learning_rate": 9.572399250234303e-06,
|
| 1110 |
+
"loss": 0.5962,
|
| 1111 |
+
"step": 1460
|
| 1112 |
+
},
|
| 1113 |
+
{
|
| 1114 |
+
"epoch": 0.6888472352389878,
|
| 1115 |
+
"grad_norm": 5.322279453277588,
|
| 1116 |
+
"learning_rate": 9.569470477975634e-06,
|
| 1117 |
+
"loss": 0.5528,
|
| 1118 |
+
"step": 1470
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 0.6935332708528584,
|
| 1122 |
+
"grad_norm": 5.191045761108398,
|
| 1123 |
+
"learning_rate": 9.566541705716965e-06,
|
| 1124 |
+
"loss": 0.602,
|
| 1125 |
+
"step": 1480
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 0.6982193064667291,
|
| 1129 |
+
"grad_norm": 4.832320213317871,
|
| 1130 |
+
"learning_rate": 9.563612933458294e-06,
|
| 1131 |
+
"loss": 0.5732,
|
| 1132 |
+
"step": 1490
|
| 1133 |
+
},
|
| 1134 |
+
{
|
| 1135 |
+
"epoch": 0.7029053420805998,
|
| 1136 |
+
"grad_norm": 5.9457926750183105,
|
| 1137 |
+
"learning_rate": 9.560684161199626e-06,
|
| 1138 |
+
"loss": 0.6017,
|
| 1139 |
+
"step": 1500
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 0.7029053420805998,
|
| 1143 |
+
"eval_loss": 0.059113115072250366,
|
| 1144 |
+
"eval_pearson_cosine": 0.7675747794888963,
|
| 1145 |
+
"eval_pearson_dot": 0.6475892776570333,
|
| 1146 |
+
"eval_pearson_euclidean": 0.7594640382486553,
|
| 1147 |
+
"eval_pearson_manhattan": 0.7585029707701096,
|
| 1148 |
+
"eval_runtime": 45.7613,
|
| 1149 |
+
"eval_samples_per_second": 32.779,
|
| 1150 |
+
"eval_spearman_cosine": 0.768339335776319,
|
| 1151 |
+
"eval_spearman_dot": 0.655445685087582,
|
| 1152 |
+
"eval_spearman_euclidean": 0.7680811238488432,
|
| 1153 |
+
"eval_spearman_manhattan": 0.7673055147561156,
|
| 1154 |
+
"eval_steps_per_second": 32.779,
|
| 1155 |
+
"step": 1500
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 0.7075913776944704,
|
| 1159 |
+
"grad_norm": 4.822035789489746,
|
| 1160 |
+
"learning_rate": 9.557755388940957e-06,
|
| 1161 |
+
"loss": 0.5891,
|
| 1162 |
+
"step": 1510
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 0.7122774133083412,
|
| 1166 |
+
"grad_norm": 7.0355753898620605,
|
| 1167 |
+
"learning_rate": 9.554826616682288e-06,
|
| 1168 |
+
"loss": 0.6019,
|
| 1169 |
+
"step": 1520
|
| 1170 |
+
},
|
| 1171 |
+
{
|
| 1172 |
+
"epoch": 0.7169634489222118,
|
| 1173 |
+
"grad_norm": 7.064100742340088,
|
| 1174 |
+
"learning_rate": 9.55189784442362e-06,
|
| 1175 |
+
"loss": 0.5656,
|
| 1176 |
+
"step": 1530
|
| 1177 |
+
},
|
| 1178 |
+
{
|
| 1179 |
+
"epoch": 0.7216494845360825,
|
| 1180 |
+
"grad_norm": 4.629329204559326,
|
| 1181 |
+
"learning_rate": 9.54896907216495e-06,
|
| 1182 |
+
"loss": 0.5839,
|
| 1183 |
+
"step": 1540
|
| 1184 |
+
},
|
| 1185 |
+
{
|
| 1186 |
+
"epoch": 0.7263355201499532,
|
| 1187 |
+
"grad_norm": 5.421347141265869,
|
| 1188 |
+
"learning_rate": 9.54604029990628e-06,
|
| 1189 |
+
"loss": 0.5684,
|
| 1190 |
+
"step": 1550
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"epoch": 0.7310215557638238,
|
| 1194 |
+
"grad_norm": 4.520521640777588,
|
| 1195 |
+
"learning_rate": 9.543111527647611e-06,
|
| 1196 |
+
"loss": 0.5979,
|
| 1197 |
+
"step": 1560
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 0.7357075913776945,
|
| 1201 |
+
"grad_norm": 5.172377109527588,
|
| 1202 |
+
"learning_rate": 9.540182755388942e-06,
|
| 1203 |
+
"loss": 0.5678,
|
| 1204 |
+
"step": 1570
|
| 1205 |
+
},
|
| 1206 |
+
{
|
| 1207 |
+
"epoch": 0.7403936269915652,
|
| 1208 |
+
"grad_norm": 5.090722560882568,
|
| 1209 |
+
"learning_rate": 9.537253983130272e-06,
|
| 1210 |
+
"loss": 0.556,
|
| 1211 |
+
"step": 1580
|
| 1212 |
+
},
|
| 1213 |
+
{
|
| 1214 |
+
"epoch": 0.7450796626054358,
|
| 1215 |
+
"grad_norm": 4.6714887619018555,
|
| 1216 |
+
"learning_rate": 9.534325210871603e-06,
|
| 1217 |
+
"loss": 0.564,
|
| 1218 |
+
"step": 1590
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 0.7497656982193065,
|
| 1222 |
+
"grad_norm": 4.211735248565674,
|
| 1223 |
+
"learning_rate": 9.531396438612934e-06,
|
| 1224 |
+
"loss": 0.617,
|
| 1225 |
+
"step": 1600
|
| 1226 |
+
},
|
| 1227 |
+
{
|
| 1228 |
+
"epoch": 0.7544517338331771,
|
| 1229 |
+
"grad_norm": 4.693171501159668,
|
| 1230 |
+
"learning_rate": 9.528467666354265e-06,
|
| 1231 |
+
"loss": 0.5657,
|
| 1232 |
+
"step": 1610
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 0.7591377694470478,
|
| 1236 |
+
"grad_norm": 6.890966892242432,
|
| 1237 |
+
"learning_rate": 9.525538894095597e-06,
|
| 1238 |
+
"loss": 0.5838,
|
| 1239 |
+
"step": 1620
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 0.7638238050609185,
|
| 1243 |
+
"grad_norm": 3.5127806663513184,
|
| 1244 |
+
"learning_rate": 9.522610121836928e-06,
|
| 1245 |
+
"loss": 0.5669,
|
| 1246 |
+
"step": 1630
|
| 1247 |
+
},
|
| 1248 |
+
{
|
| 1249 |
+
"epoch": 0.7685098406747891,
|
| 1250 |
+
"grad_norm": 4.389316082000732,
|
| 1251 |
+
"learning_rate": 9.519681349578259e-06,
|
| 1252 |
+
"loss": 0.5669,
|
| 1253 |
+
"step": 1640
|
| 1254 |
+
},
|
| 1255 |
+
{
|
| 1256 |
+
"epoch": 0.7731958762886598,
|
| 1257 |
+
"grad_norm": 4.59335470199585,
|
| 1258 |
+
"learning_rate": 9.516752577319588e-06,
|
| 1259 |
+
"loss": 0.604,
|
| 1260 |
+
"step": 1650
|
| 1261 |
+
},
|
| 1262 |
+
{
|
| 1263 |
+
"epoch": 0.7778819119025304,
|
| 1264 |
+
"grad_norm": 5.345147132873535,
|
| 1265 |
+
"learning_rate": 9.51382380506092e-06,
|
| 1266 |
+
"loss": 0.6132,
|
| 1267 |
+
"step": 1660
|
| 1268 |
+
},
|
| 1269 |
+
{
|
| 1270 |
+
"epoch": 0.7825679475164011,
|
| 1271 |
+
"grad_norm": 5.133398532867432,
|
| 1272 |
+
"learning_rate": 9.510895032802249e-06,
|
| 1273 |
+
"loss": 0.5539,
|
| 1274 |
+
"step": 1670
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 0.7872539831302718,
|
| 1278 |
+
"grad_norm": 7.907310962677002,
|
| 1279 |
+
"learning_rate": 9.50796626054358e-06,
|
| 1280 |
+
"loss": 0.61,
|
| 1281 |
+
"step": 1680
|
| 1282 |
+
},
|
| 1283 |
+
{
|
| 1284 |
+
"epoch": 0.7919400187441424,
|
| 1285 |
+
"grad_norm": 4.504448890686035,
|
| 1286 |
+
"learning_rate": 9.505037488284911e-06,
|
| 1287 |
+
"loss": 0.5851,
|
| 1288 |
+
"step": 1690
|
| 1289 |
+
},
|
| 1290 |
+
{
|
| 1291 |
+
"epoch": 0.7966260543580131,
|
| 1292 |
+
"grad_norm": 4.3662028312683105,
|
| 1293 |
+
"learning_rate": 9.502108716026243e-06,
|
| 1294 |
+
"loss": 0.5915,
|
| 1295 |
+
"step": 1700
|
| 1296 |
+
},
|
| 1297 |
+
{
|
| 1298 |
+
"epoch": 0.8013120899718837,
|
| 1299 |
+
"grad_norm": 5.221836566925049,
|
| 1300 |
+
"learning_rate": 9.499179943767574e-06,
|
| 1301 |
+
"loss": 0.581,
|
| 1302 |
+
"step": 1710
|
| 1303 |
+
},
|
| 1304 |
+
{
|
| 1305 |
+
"epoch": 0.8059981255857545,
|
| 1306 |
+
"grad_norm": 6.357667446136475,
|
| 1307 |
+
"learning_rate": 9.496251171508905e-06,
|
| 1308 |
+
"loss": 0.5937,
|
| 1309 |
+
"step": 1720
|
| 1310 |
+
},
|
| 1311 |
+
{
|
| 1312 |
+
"epoch": 0.8106841611996252,
|
| 1313 |
+
"grad_norm": 6.262212753295898,
|
| 1314 |
+
"learning_rate": 9.493322399250236e-06,
|
| 1315 |
+
"loss": 0.606,
|
| 1316 |
+
"step": 1730
|
| 1317 |
+
},
|
| 1318 |
+
{
|
| 1319 |
+
"epoch": 0.8153701968134958,
|
| 1320 |
+
"grad_norm": 4.363849639892578,
|
| 1321 |
+
"learning_rate": 9.490393626991566e-06,
|
| 1322 |
+
"loss": 0.5524,
|
| 1323 |
+
"step": 1740
|
| 1324 |
+
},
|
| 1325 |
+
{
|
| 1326 |
+
"epoch": 0.8200562324273665,
|
| 1327 |
+
"grad_norm": 5.514476299285889,
|
| 1328 |
+
"learning_rate": 9.487464854732897e-06,
|
| 1329 |
+
"loss": 0.5611,
|
| 1330 |
+
"step": 1750
|
| 1331 |
+
},
|
| 1332 |
+
{
|
| 1333 |
+
"epoch": 0.8200562324273665,
|
| 1334 |
+
"eval_loss": 0.05879165977239609,
|
| 1335 |
+
"eval_pearson_cosine": 0.7714099892705395,
|
| 1336 |
+
"eval_pearson_dot": 0.6462212772089089,
|
| 1337 |
+
"eval_pearson_euclidean": 0.7641084348061273,
|
| 1338 |
+
"eval_pearson_manhattan": 0.7629885828620147,
|
| 1339 |
+
"eval_runtime": 43.6421,
|
| 1340 |
+
"eval_samples_per_second": 34.37,
|
| 1341 |
+
"eval_spearman_cosine": 0.7720168259371313,
|
| 1342 |
+
"eval_spearman_dot": 0.6536245076677092,
|
| 1343 |
+
"eval_spearman_euclidean": 0.7726348092699838,
|
| 1344 |
+
"eval_spearman_manhattan": 0.7716062900578692,
|
| 1345 |
+
"eval_steps_per_second": 34.37,
|
| 1346 |
+
"step": 1750
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 0.8247422680412371,
|
| 1350 |
+
"grad_norm": 6.260695457458496,
|
| 1351 |
+
"learning_rate": 9.484536082474226e-06,
|
| 1352 |
+
"loss": 0.5566,
|
| 1353 |
+
"step": 1760
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.8294283036551078,
|
| 1357 |
+
"grad_norm": 4.187561511993408,
|
| 1358 |
+
"learning_rate": 9.481607310215558e-06,
|
| 1359 |
+
"loss": 0.5077,
|
| 1360 |
+
"step": 1770
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 0.8341143392689785,
|
| 1364 |
+
"grad_norm": 4.611522197723389,
|
| 1365 |
+
"learning_rate": 9.478678537956889e-06,
|
| 1366 |
+
"loss": 0.5449,
|
| 1367 |
+
"step": 1780
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.8388003748828491,
|
| 1371 |
+
"grad_norm": 12.466484069824219,
|
| 1372 |
+
"learning_rate": 9.47574976569822e-06,
|
| 1373 |
+
"loss": 0.5744,
|
| 1374 |
+
"step": 1790
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 0.8434864104967198,
|
| 1378 |
+
"grad_norm": 4.683777332305908,
|
| 1379 |
+
"learning_rate": 9.472820993439551e-06,
|
| 1380 |
+
"loss": 0.5102,
|
| 1381 |
+
"step": 1800
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.8481724461105904,
|
| 1385 |
+
"grad_norm": 5.541889190673828,
|
| 1386 |
+
"learning_rate": 9.469892221180882e-06,
|
| 1387 |
+
"loss": 0.5589,
|
| 1388 |
+
"step": 1810
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 0.8528584817244611,
|
| 1392 |
+
"grad_norm": 8.524742126464844,
|
| 1393 |
+
"learning_rate": 9.466963448922214e-06,
|
| 1394 |
+
"loss": 0.5872,
|
| 1395 |
+
"step": 1820
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.8575445173383318,
|
| 1399 |
+
"grad_norm": 7.117620944976807,
|
| 1400 |
+
"learning_rate": 9.464034676663543e-06,
|
| 1401 |
+
"loss": 0.5484,
|
| 1402 |
+
"step": 1830
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 0.8622305529522024,
|
| 1406 |
+
"grad_norm": 5.3457841873168945,
|
| 1407 |
+
"learning_rate": 9.461105904404874e-06,
|
| 1408 |
+
"loss": 0.5624,
|
| 1409 |
+
"step": 1840
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.8669165885660731,
|
| 1413 |
+
"grad_norm": 4.375561714172363,
|
| 1414 |
+
"learning_rate": 9.458177132146204e-06,
|
| 1415 |
+
"loss": 0.525,
|
| 1416 |
+
"step": 1850
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 0.8716026241799437,
|
| 1420 |
+
"grad_norm": 4.6026082038879395,
|
| 1421 |
+
"learning_rate": 9.455248359887535e-06,
|
| 1422 |
+
"loss": 0.5855,
|
| 1423 |
+
"step": 1860
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 0.8762886597938144,
|
| 1427 |
+
"grad_norm": 5.399001121520996,
|
| 1428 |
+
"learning_rate": 9.452319587628866e-06,
|
| 1429 |
+
"loss": 0.5775,
|
| 1430 |
+
"step": 1870
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 0.8809746954076851,
|
| 1434 |
+
"grad_norm": 3.9378573894500732,
|
| 1435 |
+
"learning_rate": 9.449390815370197e-06,
|
| 1436 |
+
"loss": 0.5068,
|
| 1437 |
+
"step": 1880
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 0.8856607310215557,
|
| 1441 |
+
"grad_norm": 5.515146255493164,
|
| 1442 |
+
"learning_rate": 9.446462043111529e-06,
|
| 1443 |
+
"loss": 0.5718,
|
| 1444 |
+
"step": 1890
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 0.8903467666354264,
|
| 1448 |
+
"grad_norm": 4.8671345710754395,
|
| 1449 |
+
"learning_rate": 9.44353327085286e-06,
|
| 1450 |
+
"loss": 0.5552,
|
| 1451 |
+
"step": 1900
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 0.895032802249297,
|
| 1455 |
+
"grad_norm": 5.388006210327148,
|
| 1456 |
+
"learning_rate": 9.440604498594191e-06,
|
| 1457 |
+
"loss": 0.5854,
|
| 1458 |
+
"step": 1910
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 0.8997188378631678,
|
| 1462 |
+
"grad_norm": 6.608395099639893,
|
| 1463 |
+
"learning_rate": 9.43767572633552e-06,
|
| 1464 |
+
"loss": 0.5459,
|
| 1465 |
+
"step": 1920
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 0.9044048734770385,
|
| 1469 |
+
"grad_norm": 4.6435160636901855,
|
| 1470 |
+
"learning_rate": 9.434746954076852e-06,
|
| 1471 |
+
"loss": 0.529,
|
| 1472 |
+
"step": 1930
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 0.9090909090909091,
|
| 1476 |
+
"grad_norm": 4.642300605773926,
|
| 1477 |
+
"learning_rate": 9.431818181818183e-06,
|
| 1478 |
+
"loss": 0.5255,
|
| 1479 |
+
"step": 1940
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 0.9137769447047798,
|
| 1483 |
+
"grad_norm": 5.40919828414917,
|
| 1484 |
+
"learning_rate": 9.428889409559512e-06,
|
| 1485 |
+
"loss": 0.5605,
|
| 1486 |
+
"step": 1950
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 0.9184629803186504,
|
| 1490 |
+
"grad_norm": 4.9874467849731445,
|
| 1491 |
+
"learning_rate": 9.425960637300844e-06,
|
| 1492 |
+
"loss": 0.5798,
|
| 1493 |
+
"step": 1960
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 0.9231490159325211,
|
| 1497 |
+
"grad_norm": 4.9304094314575195,
|
| 1498 |
+
"learning_rate": 9.423031865042175e-06,
|
| 1499 |
+
"loss": 0.5576,
|
| 1500 |
+
"step": 1970
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 0.9278350515463918,
|
| 1504 |
+
"grad_norm": 5.080467224121094,
|
| 1505 |
+
"learning_rate": 9.420103092783506e-06,
|
| 1506 |
+
"loss": 0.5221,
|
| 1507 |
+
"step": 1980
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 0.9325210871602624,
|
| 1511 |
+
"grad_norm": 5.083141326904297,
|
| 1512 |
+
"learning_rate": 9.417174320524837e-06,
|
| 1513 |
+
"loss": 0.6041,
|
| 1514 |
+
"step": 1990
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 0.9372071227741331,
|
| 1518 |
+
"grad_norm": 3.8194010257720947,
|
| 1519 |
+
"learning_rate": 9.414245548266168e-06,
|
| 1520 |
+
"loss": 0.5439,
|
| 1521 |
+
"step": 2000
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 0.9372071227741331,
|
| 1525 |
+
"eval_loss": 0.058015577495098114,
|
| 1526 |
+
"eval_pearson_cosine": 0.7772706274362164,
|
| 1527 |
+
"eval_pearson_dot": 0.6518150260238968,
|
| 1528 |
+
"eval_pearson_euclidean": 0.7681856098914253,
|
| 1529 |
+
"eval_pearson_manhattan": 0.7668726914631314,
|
| 1530 |
+
"eval_runtime": 45.6952,
|
| 1531 |
+
"eval_samples_per_second": 32.826,
|
| 1532 |
+
"eval_spearman_cosine": 0.7781983730395821,
|
| 1533 |
+
"eval_spearman_dot": 0.6578238148510893,
|
| 1534 |
+
"eval_spearman_euclidean": 0.7779674226973379,
|
| 1535 |
+
"eval_spearman_manhattan": 0.7766391726420421,
|
| 1536 |
+
"eval_steps_per_second": 32.826,
|
| 1537 |
+
"step": 2000
|
| 1538 |
}
|
| 1539 |
],
|
| 1540 |
"logging_steps": 10,
|