Training in progress, step 150, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 167832240
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:097d0b703d8fbc9474686d771aad256f69ed978695b3caa8d1bc039f12d5d3d8
|
| 3 |
size 167832240
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 335922386
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7ad92601a278ed6419846d0e437563e2c4cb75e6f537123044e986e787845ba3
|
| 3 |
size 335922386
|
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:e778428ec82a72991514a42630c9ba1873a74d309d263446700cf113414276ca
|
| 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 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e70710c409284f74d525f8db5cfaccc22a8afd29416f19c595da9242ec92d936
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 1.
|
| 3 |
-
"best_model_checkpoint": "miner_id_24/checkpoint-
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 25,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -747,6 +747,372 @@
|
|
| 747 |
"eval_samples_per_second": 7.697,
|
| 748 |
"eval_steps_per_second": 1.078,
|
| 749 |
"step": 100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 750 |
}
|
| 751 |
],
|
| 752 |
"logging_steps": 1,
|
|
@@ -775,7 +1141,7 @@
|
|
| 775 |
"attributes": {}
|
| 776 |
}
|
| 777 |
},
|
| 778 |
-
"total_flos":
|
| 779 |
"train_batch_size": 8,
|
| 780 |
"trial_name": null,
|
| 781 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 1.557321310043335,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-150",
|
| 4 |
+
"epoch": 0.023405500292568753,
|
| 5 |
"eval_steps": 25,
|
| 6 |
+
"global_step": 150,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 747 |
"eval_samples_per_second": 7.697,
|
| 748 |
"eval_steps_per_second": 1.078,
|
| 749 |
"step": 100
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 0.015759703530329627,
|
| 753 |
+
"grad_norm": 1.328065037727356,
|
| 754 |
+
"learning_rate": 0.0001599135876488549,
|
| 755 |
+
"loss": 1.7923,
|
| 756 |
+
"step": 101
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 0.015915740198946753,
|
| 760 |
+
"grad_norm": 1.02339768409729,
|
| 761 |
+
"learning_rate": 0.00015743756320098332,
|
| 762 |
+
"loss": 1.9042,
|
| 763 |
+
"step": 102
|
| 764 |
+
},
|
| 765 |
+
{
|
| 766 |
+
"epoch": 0.016071776867563878,
|
| 767 |
+
"grad_norm": 0.5130980610847473,
|
| 768 |
+
"learning_rate": 0.0001549595053975962,
|
| 769 |
+
"loss": 1.7668,
|
| 770 |
+
"step": 103
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 0.016227813536181003,
|
| 774 |
+
"grad_norm": 0.37997496128082275,
|
| 775 |
+
"learning_rate": 0.00015248009171495378,
|
| 776 |
+
"loss": 1.689,
|
| 777 |
+
"step": 104
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 0.016383850204798128,
|
| 781 |
+
"grad_norm": 0.42504414916038513,
|
| 782 |
+
"learning_rate": 0.00015,
|
| 783 |
+
"loss": 1.529,
|
| 784 |
+
"step": 105
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 0.016539886873415253,
|
| 788 |
+
"grad_norm": 0.328225702047348,
|
| 789 |
+
"learning_rate": 0.00014751990828504622,
|
| 790 |
+
"loss": 1.3804,
|
| 791 |
+
"step": 106
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 0.01669592354203238,
|
| 795 |
+
"grad_norm": 0.3386905789375305,
|
| 796 |
+
"learning_rate": 0.00014504049460240375,
|
| 797 |
+
"loss": 1.6091,
|
| 798 |
+
"step": 107
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 0.016851960210649504,
|
| 802 |
+
"grad_norm": 0.33392131328582764,
|
| 803 |
+
"learning_rate": 0.00014256243679901663,
|
| 804 |
+
"loss": 1.6571,
|
| 805 |
+
"step": 108
|
| 806 |
+
},
|
| 807 |
+
{
|
| 808 |
+
"epoch": 0.01700799687926663,
|
| 809 |
+
"grad_norm": 0.3345213830471039,
|
| 810 |
+
"learning_rate": 0.00014008641235114508,
|
| 811 |
+
"loss": 1.594,
|
| 812 |
+
"step": 109
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 0.017164033547883754,
|
| 816 |
+
"grad_norm": 0.37102460861206055,
|
| 817 |
+
"learning_rate": 0.00013761309817915014,
|
| 818 |
+
"loss": 1.7052,
|
| 819 |
+
"step": 110
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 0.017320070216500876,
|
| 823 |
+
"grad_norm": 0.36494970321655273,
|
| 824 |
+
"learning_rate": 0.00013514317046243058,
|
| 825 |
+
"loss": 1.5868,
|
| 826 |
+
"step": 111
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 0.017476106885118,
|
| 830 |
+
"grad_norm": 0.36978891491889954,
|
| 831 |
+
"learning_rate": 0.00013267730445456208,
|
| 832 |
+
"loss": 1.5605,
|
| 833 |
+
"step": 112
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 0.017632143553735127,
|
| 837 |
+
"grad_norm": 0.4322417676448822,
|
| 838 |
+
"learning_rate": 0.00013021617429868963,
|
| 839 |
+
"loss": 1.5087,
|
| 840 |
+
"step": 113
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 0.017788180222352252,
|
| 844 |
+
"grad_norm": 0.42043352127075195,
|
| 845 |
+
"learning_rate": 0.00012776045284322368,
|
| 846 |
+
"loss": 1.5209,
|
| 847 |
+
"step": 114
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 0.017944216890969377,
|
| 851 |
+
"grad_norm": 0.47093257308006287,
|
| 852 |
+
"learning_rate": 0.00012531081145788987,
|
| 853 |
+
"loss": 1.5932,
|
| 854 |
+
"step": 115
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 0.018100253559586502,
|
| 858 |
+
"grad_norm": 0.3943566083908081,
|
| 859 |
+
"learning_rate": 0.00012286791985018355,
|
| 860 |
+
"loss": 1.5031,
|
| 861 |
+
"step": 116
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 0.018256290228203628,
|
| 865 |
+
"grad_norm": 0.4569840431213379,
|
| 866 |
+
"learning_rate": 0.00012043244588227796,
|
| 867 |
+
"loss": 1.6201,
|
| 868 |
+
"step": 117
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 0.018412326896820753,
|
| 872 |
+
"grad_norm": 0.3882908225059509,
|
| 873 |
+
"learning_rate": 0.00011800505538843798,
|
| 874 |
+
"loss": 1.441,
|
| 875 |
+
"step": 118
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 0.018568363565437878,
|
| 879 |
+
"grad_norm": 0.4978281557559967,
|
| 880 |
+
"learning_rate": 0.00011558641199298727,
|
| 881 |
+
"loss": 1.4181,
|
| 882 |
+
"step": 119
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 0.018724400234055003,
|
| 886 |
+
"grad_norm": 0.4600917100906372,
|
| 887 |
+
"learning_rate": 0.00011317717692888012,
|
| 888 |
+
"loss": 1.4694,
|
| 889 |
+
"step": 120
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 0.01888043690267213,
|
| 893 |
+
"grad_norm": 0.5189599990844727,
|
| 894 |
+
"learning_rate": 0.00011077800885692702,
|
| 895 |
+
"loss": 1.4932,
|
| 896 |
+
"step": 121
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 0.019036473571289254,
|
| 900 |
+
"grad_norm": 0.5141446590423584,
|
| 901 |
+
"learning_rate": 0.00010838956368572334,
|
| 902 |
+
"loss": 1.3281,
|
| 903 |
+
"step": 122
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 0.01919251023990638,
|
| 907 |
+
"grad_norm": 0.5593545436859131,
|
| 908 |
+
"learning_rate": 0.0001060124943923303,
|
| 909 |
+
"loss": 1.2175,
|
| 910 |
+
"step": 123
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 0.019348546908523504,
|
| 914 |
+
"grad_norm": 0.5619649291038513,
|
| 915 |
+
"learning_rate": 0.0001036474508437579,
|
| 916 |
+
"loss": 1.3246,
|
| 917 |
+
"step": 124
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 0.01950458357714063,
|
| 921 |
+
"grad_norm": 0.4860003590583801,
|
| 922 |
+
"learning_rate": 0.00010129507961929748,
|
| 923 |
+
"loss": 1.356,
|
| 924 |
+
"step": 125
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 0.01950458357714063,
|
| 928 |
+
"eval_loss": 1.5037603378295898,
|
| 929 |
+
"eval_runtime": 6.4994,
|
| 930 |
+
"eval_samples_per_second": 7.693,
|
| 931 |
+
"eval_steps_per_second": 1.077,
|
| 932 |
+
"step": 125
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 0.019660620245757755,
|
| 936 |
+
"grad_norm": 0.6618039011955261,
|
| 937 |
+
"learning_rate": 9.895602383375353e-05,
|
| 938 |
+
"loss": 1.241,
|
| 939 |
+
"step": 126
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 0.019816656914374876,
|
| 943 |
+
"grad_norm": 0.5603771209716797,
|
| 944 |
+
"learning_rate": 9.663092296162251e-05,
|
| 945 |
+
"loss": 1.3383,
|
| 946 |
+
"step": 127
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 0.019972693582992,
|
| 950 |
+
"grad_norm": 0.5711013078689575,
|
| 951 |
+
"learning_rate": 9.432041266226686e-05,
|
| 952 |
+
"loss": 1.3882,
|
| 953 |
+
"step": 128
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 0.020128730251609127,
|
| 957 |
+
"grad_norm": 0.5455312132835388,
|
| 958 |
+
"learning_rate": 9.202512460613219e-05,
|
| 959 |
+
"loss": 1.1994,
|
| 960 |
+
"step": 129
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 0.020284766920226252,
|
| 964 |
+
"grad_norm": 0.5478842854499817,
|
| 965 |
+
"learning_rate": 8.97456863020546e-05,
|
| 966 |
+
"loss": 1.3298,
|
| 967 |
+
"step": 130
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 0.020440803588843377,
|
| 971 |
+
"grad_norm": 0.612348735332489,
|
| 972 |
+
"learning_rate": 8.748272092570646e-05,
|
| 973 |
+
"loss": 1.3007,
|
| 974 |
+
"step": 131
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 0.020596840257460503,
|
| 978 |
+
"grad_norm": 0.5542769432067871,
|
| 979 |
+
"learning_rate": 8.523684714922608e-05,
|
| 980 |
+
"loss": 1.211,
|
| 981 |
+
"step": 132
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 0.020752876926077628,
|
| 985 |
+
"grad_norm": 0.6410621404647827,
|
| 986 |
+
"learning_rate": 8.300867897207903e-05,
|
| 987 |
+
"loss": 1.3215,
|
| 988 |
+
"step": 133
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 0.020908913594694753,
|
| 992 |
+
"grad_norm": 0.6674242615699768,
|
| 993 |
+
"learning_rate": 8.079882555319684e-05,
|
| 994 |
+
"loss": 1.3031,
|
| 995 |
+
"step": 134
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 0.021064950263311878,
|
| 999 |
+
"grad_norm": 0.6528021097183228,
|
| 1000 |
+
"learning_rate": 7.860789104443896e-05,
|
| 1001 |
+
"loss": 1.3276,
|
| 1002 |
+
"step": 135
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 0.021220986931929003,
|
| 1006 |
+
"grad_norm": 0.7368160486221313,
|
| 1007 |
+
"learning_rate": 7.643647442542382e-05,
|
| 1008 |
+
"loss": 1.2318,
|
| 1009 |
+
"step": 136
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 0.02137702360054613,
|
| 1013 |
+
"grad_norm": 0.7098979949951172,
|
| 1014 |
+
"learning_rate": 7.428516933977347e-05,
|
| 1015 |
+
"loss": 1.3272,
|
| 1016 |
+
"step": 137
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 0.021533060269163254,
|
| 1020 |
+
"grad_norm": 0.680216908454895,
|
| 1021 |
+
"learning_rate": 7.215456393281776e-05,
|
| 1022 |
+
"loss": 1.2541,
|
| 1023 |
+
"step": 138
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 0.02168909693778038,
|
| 1027 |
+
"grad_norm": 0.7274788618087769,
|
| 1028 |
+
"learning_rate": 7.004524069080096e-05,
|
| 1029 |
+
"loss": 1.0468,
|
| 1030 |
+
"step": 139
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"epoch": 0.021845133606397504,
|
| 1034 |
+
"grad_norm": 0.7748696804046631,
|
| 1035 |
+
"learning_rate": 6.795777628163599e-05,
|
| 1036 |
+
"loss": 1.0636,
|
| 1037 |
+
"step": 140
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 0.02200117027501463,
|
| 1041 |
+
"grad_norm": 0.6825678944587708,
|
| 1042 |
+
"learning_rate": 6.58927413972491e-05,
|
| 1043 |
+
"loss": 0.9245,
|
| 1044 |
+
"step": 141
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 0.022157206943631755,
|
| 1048 |
+
"grad_norm": 0.7998738884925842,
|
| 1049 |
+
"learning_rate": 6.385070059755846e-05,
|
| 1050 |
+
"loss": 0.9596,
|
| 1051 |
+
"step": 142
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"epoch": 0.02231324361224888,
|
| 1055 |
+
"grad_norm": 0.7875250577926636,
|
| 1056 |
+
"learning_rate": 6.183221215612904e-05,
|
| 1057 |
+
"loss": 0.9371,
|
| 1058 |
+
"step": 143
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 0.022469280280866002,
|
| 1062 |
+
"grad_norm": 0.9212265610694885,
|
| 1063 |
+
"learning_rate": 5.983782790754623e-05,
|
| 1064 |
+
"loss": 0.721,
|
| 1065 |
+
"step": 144
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 0.022625316949483127,
|
| 1069 |
+
"grad_norm": 0.8048818111419678,
|
| 1070 |
+
"learning_rate": 5.786809309654982e-05,
|
| 1071 |
+
"loss": 0.7062,
|
| 1072 |
+
"step": 145
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 0.022781353618100252,
|
| 1076 |
+
"grad_norm": 1.0022319555282593,
|
| 1077 |
+
"learning_rate": 5.592354622896944e-05,
|
| 1078 |
+
"loss": 0.6178,
|
| 1079 |
+
"step": 146
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 0.022937390286717377,
|
| 1083 |
+
"grad_norm": 0.9216979742050171,
|
| 1084 |
+
"learning_rate": 5.40047189245025e-05,
|
| 1085 |
+
"loss": 0.7871,
|
| 1086 |
+
"step": 147
|
| 1087 |
+
},
|
| 1088 |
+
{
|
| 1089 |
+
"epoch": 0.023093426955334503,
|
| 1090 |
+
"grad_norm": 1.163275957107544,
|
| 1091 |
+
"learning_rate": 5.211213577137469e-05,
|
| 1092 |
+
"loss": 0.5207,
|
| 1093 |
+
"step": 148
|
| 1094 |
+
},
|
| 1095 |
+
{
|
| 1096 |
+
"epoch": 0.023249463623951628,
|
| 1097 |
+
"grad_norm": 1.1899170875549316,
|
| 1098 |
+
"learning_rate": 5.024631418292274e-05,
|
| 1099 |
+
"loss": 0.751,
|
| 1100 |
+
"step": 149
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 0.023405500292568753,
|
| 1104 |
+
"grad_norm": 1.1365642547607422,
|
| 1105 |
+
"learning_rate": 4.840776425613886e-05,
|
| 1106 |
+
"loss": 0.4787,
|
| 1107 |
+
"step": 150
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 0.023405500292568753,
|
| 1111 |
+
"eval_loss": 1.557321310043335,
|
| 1112 |
+
"eval_runtime": 6.503,
|
| 1113 |
+
"eval_samples_per_second": 7.689,
|
| 1114 |
+
"eval_steps_per_second": 1.076,
|
| 1115 |
+
"step": 150
|
| 1116 |
}
|
| 1117 |
],
|
| 1118 |
"logging_steps": 1,
|
|
|
|
| 1141 |
"attributes": {}
|
| 1142 |
}
|
| 1143 |
},
|
| 1144 |
+
"total_flos": 2.364765716348928e+17,
|
| 1145 |
"train_batch_size": 8,
|
| 1146 |
"trial_name": null,
|
| 1147 |
"trial_params": null
|