Training in progress, step 691, 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 791869518
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:79f312030784e0c4c1ac477ec8be9baccaf31bb453a5f1f0ba47bae3a11d6736
|
| 3 |
size 791869518
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2375752250
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b9f0413ff5d7932d1e3cf4853d666b874dcafb75ec0e3ed0aec08553a6ec61db
|
| 3 |
size 2375752250
|
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 sha256:68d8c53b42f31b6c7313464394859eb2afcdd967a1a813faffd1e0be60216485
|
| 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": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -715,6 +715,272 @@
|
|
| 715 |
"eval_samples_per_second": 573.792,
|
| 716 |
"eval_steps_per_second": 35.866,
|
| 717 |
"step": 500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 718 |
}
|
| 719 |
],
|
| 720 |
"logging_steps": 5,
|
|
@@ -729,12 +995,12 @@
|
|
| 729 |
"should_evaluate": false,
|
| 730 |
"should_log": false,
|
| 731 |
"should_save": true,
|
| 732 |
-
"should_training_stop":
|
| 733 |
},
|
| 734 |
"attributes": {}
|
| 735 |
}
|
| 736 |
},
|
| 737 |
-
"total_flos": 2.
|
| 738 |
"train_batch_size": 4,
|
| 739 |
"trial_name": null,
|
| 740 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.999909559555033,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 691,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 715 |
"eval_samples_per_second": 573.792,
|
| 716 |
"eval_steps_per_second": 35.866,
|
| 717 |
"step": 500
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.730758795333273,
|
| 721 |
+
"grad_norm": 154.0,
|
| 722 |
+
"learning_rate": 2.995169082125604e-06,
|
| 723 |
+
"loss": 92.6857,
|
| 724 |
+
"step": 505
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.7379940309306322,
|
| 728 |
+
"grad_norm": 148.625,
|
| 729 |
+
"learning_rate": 2.914653784219002e-06,
|
| 730 |
+
"loss": 94.1288,
|
| 731 |
+
"step": 510
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.7452292665279913,
|
| 735 |
+
"grad_norm": 141.625,
|
| 736 |
+
"learning_rate": 2.8341384863123995e-06,
|
| 737 |
+
"loss": 93.0597,
|
| 738 |
+
"step": 515
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.7524645021253504,
|
| 742 |
+
"grad_norm": 146.375,
|
| 743 |
+
"learning_rate": 2.7536231884057974e-06,
|
| 744 |
+
"loss": 94.0807,
|
| 745 |
+
"step": 520
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.7596997377227096,
|
| 749 |
+
"grad_norm": 141.875,
|
| 750 |
+
"learning_rate": 2.6731078904991954e-06,
|
| 751 |
+
"loss": 95.1949,
|
| 752 |
+
"step": 525
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.7669349733200688,
|
| 756 |
+
"grad_norm": 142.25,
|
| 757 |
+
"learning_rate": 2.5925925925925925e-06,
|
| 758 |
+
"loss": 94.323,
|
| 759 |
+
"step": 530
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.7741702089174278,
|
| 763 |
+
"grad_norm": 137.125,
|
| 764 |
+
"learning_rate": 2.5120772946859904e-06,
|
| 765 |
+
"loss": 92.8978,
|
| 766 |
+
"step": 535
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.781405444514787,
|
| 770 |
+
"grad_norm": 155.0,
|
| 771 |
+
"learning_rate": 2.4315619967793884e-06,
|
| 772 |
+
"loss": 92.656,
|
| 773 |
+
"step": 540
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.7886406801121462,
|
| 777 |
+
"grad_norm": 136.875,
|
| 778 |
+
"learning_rate": 2.351046698872786e-06,
|
| 779 |
+
"loss": 94.4373,
|
| 780 |
+
"step": 545
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.7958759157095053,
|
| 784 |
+
"grad_norm": 137.375,
|
| 785 |
+
"learning_rate": 2.270531400966184e-06,
|
| 786 |
+
"loss": 93.7375,
|
| 787 |
+
"step": 550
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.8031111513068644,
|
| 791 |
+
"grad_norm": 141.125,
|
| 792 |
+
"learning_rate": 2.1900161030595814e-06,
|
| 793 |
+
"loss": 93.2835,
|
| 794 |
+
"step": 555
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.8103463869042236,
|
| 798 |
+
"grad_norm": 136.125,
|
| 799 |
+
"learning_rate": 2.109500805152979e-06,
|
| 800 |
+
"loss": 92.7297,
|
| 801 |
+
"step": 560
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.8175816225015827,
|
| 805 |
+
"grad_norm": 132.0,
|
| 806 |
+
"learning_rate": 2.028985507246377e-06,
|
| 807 |
+
"loss": 93.2055,
|
| 808 |
+
"step": 565
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.8248168580989419,
|
| 812 |
+
"grad_norm": 142.0,
|
| 813 |
+
"learning_rate": 1.948470209339775e-06,
|
| 814 |
+
"loss": 92.6126,
|
| 815 |
+
"step": 570
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.832052093696301,
|
| 819 |
+
"grad_norm": 128.375,
|
| 820 |
+
"learning_rate": 1.8679549114331724e-06,
|
| 821 |
+
"loss": 91.9927,
|
| 822 |
+
"step": 575
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.8392873292936601,
|
| 826 |
+
"grad_norm": 142.625,
|
| 827 |
+
"learning_rate": 1.7874396135265702e-06,
|
| 828 |
+
"loss": 92.6083,
|
| 829 |
+
"step": 580
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.8465225648910193,
|
| 833 |
+
"grad_norm": 142.5,
|
| 834 |
+
"learning_rate": 1.7069243156199681e-06,
|
| 835 |
+
"loss": 93.0809,
|
| 836 |
+
"step": 585
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.8537578004883783,
|
| 840 |
+
"grad_norm": 131.625,
|
| 841 |
+
"learning_rate": 1.6264090177133656e-06,
|
| 842 |
+
"loss": 90.4466,
|
| 843 |
+
"step": 590
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.8609930360857375,
|
| 847 |
+
"grad_norm": 153.0,
|
| 848 |
+
"learning_rate": 1.5458937198067634e-06,
|
| 849 |
+
"loss": 90.9484,
|
| 850 |
+
"step": 595
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.8682282716830967,
|
| 854 |
+
"grad_norm": 141.75,
|
| 855 |
+
"learning_rate": 1.4653784219001613e-06,
|
| 856 |
+
"loss": 92.5591,
|
| 857 |
+
"step": 600
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.8754635072804559,
|
| 861 |
+
"grad_norm": 149.25,
|
| 862 |
+
"learning_rate": 1.3848631239935589e-06,
|
| 863 |
+
"loss": 93.0069,
|
| 864 |
+
"step": 605
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.8826987428778149,
|
| 868 |
+
"grad_norm": 131.625,
|
| 869 |
+
"learning_rate": 1.3043478260869566e-06,
|
| 870 |
+
"loss": 92.2291,
|
| 871 |
+
"step": 610
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.8899339784751741,
|
| 875 |
+
"grad_norm": 129.875,
|
| 876 |
+
"learning_rate": 1.2238325281803544e-06,
|
| 877 |
+
"loss": 91.3298,
|
| 878 |
+
"step": 615
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.8971692140725332,
|
| 882 |
+
"grad_norm": 139.25,
|
| 883 |
+
"learning_rate": 1.1433172302737521e-06,
|
| 884 |
+
"loss": 92.7737,
|
| 885 |
+
"step": 620
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.9044044496698924,
|
| 889 |
+
"grad_norm": 134.375,
|
| 890 |
+
"learning_rate": 1.0628019323671499e-06,
|
| 891 |
+
"loss": 93.0011,
|
| 892 |
+
"step": 625
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.9116396852672515,
|
| 896 |
+
"grad_norm": 131.625,
|
| 897 |
+
"learning_rate": 9.822866344605476e-07,
|
| 898 |
+
"loss": 92.2996,
|
| 899 |
+
"step": 630
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.9188749208646106,
|
| 903 |
+
"grad_norm": 136.75,
|
| 904 |
+
"learning_rate": 9.017713365539453e-07,
|
| 905 |
+
"loss": 92.7781,
|
| 906 |
+
"step": 635
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.9261101564619698,
|
| 910 |
+
"grad_norm": 139.75,
|
| 911 |
+
"learning_rate": 8.212560386473431e-07,
|
| 912 |
+
"loss": 91.0231,
|
| 913 |
+
"step": 640
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.933345392059329,
|
| 917 |
+
"grad_norm": 136.875,
|
| 918 |
+
"learning_rate": 7.407407407407407e-07,
|
| 919 |
+
"loss": 91.6645,
|
| 920 |
+
"step": 645
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.940580627656688,
|
| 924 |
+
"grad_norm": 144.875,
|
| 925 |
+
"learning_rate": 6.602254428341386e-07,
|
| 926 |
+
"loss": 90.7734,
|
| 927 |
+
"step": 650
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.9478158632540472,
|
| 931 |
+
"grad_norm": 142.75,
|
| 932 |
+
"learning_rate": 5.797101449275363e-07,
|
| 933 |
+
"loss": 91.3177,
|
| 934 |
+
"step": 655
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.9550510988514064,
|
| 938 |
+
"grad_norm": 148.75,
|
| 939 |
+
"learning_rate": 4.991948470209341e-07,
|
| 940 |
+
"loss": 90.913,
|
| 941 |
+
"step": 660
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.9622863344487654,
|
| 945 |
+
"grad_norm": 128.125,
|
| 946 |
+
"learning_rate": 4.1867954911433176e-07,
|
| 947 |
+
"loss": 90.6037,
|
| 948 |
+
"step": 665
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.9695215700461246,
|
| 952 |
+
"grad_norm": 132.25,
|
| 953 |
+
"learning_rate": 3.3816425120772945e-07,
|
| 954 |
+
"loss": 91.3471,
|
| 955 |
+
"step": 670
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.9767568056434838,
|
| 959 |
+
"grad_norm": 126.4375,
|
| 960 |
+
"learning_rate": 2.5764895330112725e-07,
|
| 961 |
+
"loss": 91.4777,
|
| 962 |
+
"step": 675
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.9839920412408429,
|
| 966 |
+
"grad_norm": 139.0,
|
| 967 |
+
"learning_rate": 1.7713365539452497e-07,
|
| 968 |
+
"loss": 92.0473,
|
| 969 |
+
"step": 680
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.991227276838202,
|
| 973 |
+
"grad_norm": 134.875,
|
| 974 |
+
"learning_rate": 9.661835748792271e-08,
|
| 975 |
+
"loss": 90.7339,
|
| 976 |
+
"step": 685
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.9984625124355612,
|
| 980 |
+
"grad_norm": 139.375,
|
| 981 |
+
"learning_rate": 1.6103059581320453e-08,
|
| 982 |
+
"loss": 92.0409,
|
| 983 |
+
"step": 690
|
| 984 |
}
|
| 985 |
],
|
| 986 |
"logging_steps": 5,
|
|
|
|
| 995 |
"should_evaluate": false,
|
| 996 |
"should_log": false,
|
| 997 |
"should_save": true,
|
| 998 |
+
"should_training_stop": true
|
| 999 |
},
|
| 1000 |
"attributes": {}
|
| 1001 |
}
|
| 1002 |
},
|
| 1003 |
+
"total_flos": 2.993659372963365e+18,
|
| 1004 |
"train_batch_size": 4,
|
| 1005 |
"trial_name": null,
|
| 1006 |
"trial_params": null
|