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 671149168
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:534550b1993aac826c8bec08efc7427902b771347f6110818e42f6b7079e34c4
|
| 3 |
size 671149168
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1342555602
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:163946c9c0a7404af0fb1af7ac9b8b3e77a65cd96952f1cec17d9cd93a77268c
|
| 3 |
size 1342555602
|
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 sha256:5307d22aa1a177d12d3717bbba20e29c997ee293f9e1cc39ab3319ef8ba7b43e
|
| 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:dfd59dca009004df561617f8f6994512d029a952a68609cac24b36df5a0757ce
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "miner_id_24/checkpoint-
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 50,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -731,6 +731,364 @@
|
|
| 731 |
"eval_samples_per_second": 6.963,
|
| 732 |
"eval_steps_per_second": 3.482,
|
| 733 |
"step": 100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 734 |
}
|
| 735 |
],
|
| 736 |
"logging_steps": 1,
|
|
@@ -759,7 +1117,7 @@
|
|
| 759 |
"attributes": {}
|
| 760 |
}
|
| 761 |
},
|
| 762 |
-
"total_flos":
|
| 763 |
"train_batch_size": 8,
|
| 764 |
"trial_name": null,
|
| 765 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.06637585908174515,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-150",
|
| 4 |
+
"epoch": 0.043044694741373124,
|
| 5 |
"eval_steps": 50,
|
| 6 |
+
"global_step": 150,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 731 |
"eval_samples_per_second": 6.963,
|
| 732 |
"eval_steps_per_second": 3.482,
|
| 733 |
"step": 100
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 0.028983427792524573,
|
| 737 |
+
"grad_norm": 0.6289970874786377,
|
| 738 |
+
"learning_rate": 6.279213887972179e-05,
|
| 739 |
+
"loss": 0.2776,
|
| 740 |
+
"step": 101
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 0.029270392424133724,
|
| 744 |
+
"grad_norm": 0.4327123761177063,
|
| 745 |
+
"learning_rate": 6.189675975213094e-05,
|
| 746 |
+
"loss": 0.2454,
|
| 747 |
+
"step": 102
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.02955735705574288,
|
| 751 |
+
"grad_norm": 0.31198781728744507,
|
| 752 |
+
"learning_rate": 6.099731789198344e-05,
|
| 753 |
+
"loss": 0.3004,
|
| 754 |
+
"step": 103
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 0.029844321687352033,
|
| 758 |
+
"grad_norm": 0.24795642495155334,
|
| 759 |
+
"learning_rate": 6.009412045785051e-05,
|
| 760 |
+
"loss": 0.2992,
|
| 761 |
+
"step": 104
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.030131286318961188,
|
| 765 |
+
"grad_norm": 0.2529444396495819,
|
| 766 |
+
"learning_rate": 5.918747589082853e-05,
|
| 767 |
+
"loss": 0.3179,
|
| 768 |
+
"step": 105
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 0.030418250950570342,
|
| 772 |
+
"grad_norm": 0.2385726273059845,
|
| 773 |
+
"learning_rate": 5.82776938092065e-05,
|
| 774 |
+
"loss": 0.2885,
|
| 775 |
+
"step": 106
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 0.030705215582179497,
|
| 779 |
+
"grad_norm": 0.3763389587402344,
|
| 780 |
+
"learning_rate": 5.736508490273188e-05,
|
| 781 |
+
"loss": 0.2945,
|
| 782 |
+
"step": 107
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 0.03099218021378865,
|
| 786 |
+
"grad_norm": 0.3574504852294922,
|
| 787 |
+
"learning_rate": 5.644996082651017e-05,
|
| 788 |
+
"loss": 0.3193,
|
| 789 |
+
"step": 108
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.0312791448453978,
|
| 793 |
+
"grad_norm": 0.2397194802761078,
|
| 794 |
+
"learning_rate": 5.553263409457504e-05,
|
| 795 |
+
"loss": 0.3078,
|
| 796 |
+
"step": 109
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 0.03156610947700696,
|
| 800 |
+
"grad_norm": 0.2164476364850998,
|
| 801 |
+
"learning_rate": 5.4613417973165106e-05,
|
| 802 |
+
"loss": 0.2868,
|
| 803 |
+
"step": 110
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 0.03185307410861611,
|
| 807 |
+
"grad_norm": 0.3787127435207367,
|
| 808 |
+
"learning_rate": 5.3692626373743706e-05,
|
| 809 |
+
"loss": 0.2738,
|
| 810 |
+
"step": 111
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 0.032140038740225266,
|
| 814 |
+
"grad_norm": 0.24689379334449768,
|
| 815 |
+
"learning_rate": 5.27705737457985e-05,
|
| 816 |
+
"loss": 0.283,
|
| 817 |
+
"step": 112
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 0.03242700337183442,
|
| 821 |
+
"grad_norm": 0.26295608282089233,
|
| 822 |
+
"learning_rate": 5.184757496945726e-05,
|
| 823 |
+
"loss": 0.283,
|
| 824 |
+
"step": 113
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 0.032713968003443575,
|
| 828 |
+
"grad_norm": 0.1907181441783905,
|
| 829 |
+
"learning_rate": 5.092394524795649e-05,
|
| 830 |
+
"loss": 0.2788,
|
| 831 |
+
"step": 114
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 0.03300093263505273,
|
| 835 |
+
"grad_norm": 0.20249591767787933,
|
| 836 |
+
"learning_rate": 5e-05,
|
| 837 |
+
"loss": 0.2666,
|
| 838 |
+
"step": 115
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 0.033287897266661884,
|
| 842 |
+
"grad_norm": 0.280271053314209,
|
| 843 |
+
"learning_rate": 4.907605475204352e-05,
|
| 844 |
+
"loss": 0.2414,
|
| 845 |
+
"step": 116
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 0.03357486189827104,
|
| 849 |
+
"grad_norm": 0.25560441613197327,
|
| 850 |
+
"learning_rate": 4.8152425030542766e-05,
|
| 851 |
+
"loss": 0.2671,
|
| 852 |
+
"step": 117
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 0.03386182652988019,
|
| 856 |
+
"grad_norm": 0.22025573253631592,
|
| 857 |
+
"learning_rate": 4.72294262542015e-05,
|
| 858 |
+
"loss": 0.2634,
|
| 859 |
+
"step": 118
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 0.03414879116148935,
|
| 863 |
+
"grad_norm": 0.22071503102779388,
|
| 864 |
+
"learning_rate": 4.6307373626256306e-05,
|
| 865 |
+
"loss": 0.2807,
|
| 866 |
+
"step": 119
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 0.0344357557930985,
|
| 870 |
+
"grad_norm": 0.2339547574520111,
|
| 871 |
+
"learning_rate": 4.5386582026834906e-05,
|
| 872 |
+
"loss": 0.3041,
|
| 873 |
+
"step": 120
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.034722720424707657,
|
| 877 |
+
"grad_norm": 0.24428895115852356,
|
| 878 |
+
"learning_rate": 4.446736590542497e-05,
|
| 879 |
+
"loss": 0.2918,
|
| 880 |
+
"step": 121
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 0.03500968505631681,
|
| 884 |
+
"grad_norm": 0.2549816966056824,
|
| 885 |
+
"learning_rate": 4.3550039173489845e-05,
|
| 886 |
+
"loss": 0.2667,
|
| 887 |
+
"step": 122
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 0.035296649687925966,
|
| 891 |
+
"grad_norm": 0.29650628566741943,
|
| 892 |
+
"learning_rate": 4.2634915097268115e-05,
|
| 893 |
+
"loss": 0.2566,
|
| 894 |
+
"step": 123
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 0.03558361431953512,
|
| 898 |
+
"grad_norm": 0.24224285781383514,
|
| 899 |
+
"learning_rate": 4.1722306190793495e-05,
|
| 900 |
+
"loss": 0.2607,
|
| 901 |
+
"step": 124
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 0.035870578951144275,
|
| 905 |
+
"grad_norm": 0.35612723231315613,
|
| 906 |
+
"learning_rate": 4.0812524109171476e-05,
|
| 907 |
+
"loss": 0.2404,
|
| 908 |
+
"step": 125
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 0.03615754358275342,
|
| 912 |
+
"grad_norm": 0.3032487630844116,
|
| 913 |
+
"learning_rate": 3.99058795421495e-05,
|
| 914 |
+
"loss": 0.2661,
|
| 915 |
+
"step": 126
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 0.03644450821436258,
|
| 919 |
+
"grad_norm": 0.33981555700302124,
|
| 920 |
+
"learning_rate": 3.9002682108016585e-05,
|
| 921 |
+
"loss": 0.2189,
|
| 922 |
+
"step": 127
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 0.03673147284597173,
|
| 926 |
+
"grad_norm": 0.33926525712013245,
|
| 927 |
+
"learning_rate": 3.8103240247869075e-05,
|
| 928 |
+
"loss": 0.2906,
|
| 929 |
+
"step": 128
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 0.037018437477580886,
|
| 933 |
+
"grad_norm": 0.3139205574989319,
|
| 934 |
+
"learning_rate": 3.720786112027822e-05,
|
| 935 |
+
"loss": 0.2836,
|
| 936 |
+
"step": 129
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 0.03730540210919004,
|
| 940 |
+
"grad_norm": 0.4507588744163513,
|
| 941 |
+
"learning_rate": 3.631685049639586e-05,
|
| 942 |
+
"loss": 0.296,
|
| 943 |
+
"step": 130
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 0.037592366740799195,
|
| 947 |
+
"grad_norm": 0.328153520822525,
|
| 948 |
+
"learning_rate": 3.543051265553377e-05,
|
| 949 |
+
"loss": 0.2721,
|
| 950 |
+
"step": 131
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 0.03787933137240835,
|
| 954 |
+
"grad_norm": 0.5082656145095825,
|
| 955 |
+
"learning_rate": 3.4549150281252636e-05,
|
| 956 |
+
"loss": 0.2613,
|
| 957 |
+
"step": 132
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 0.038166296004017504,
|
| 961 |
+
"grad_norm": 0.4505540132522583,
|
| 962 |
+
"learning_rate": 3.367306435799584e-05,
|
| 963 |
+
"loss": 0.2407,
|
| 964 |
+
"step": 133
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 0.03845326063562666,
|
| 968 |
+
"grad_norm": 0.4038177728652954,
|
| 969 |
+
"learning_rate": 3.2802554068303596e-05,
|
| 970 |
+
"loss": 0.215,
|
| 971 |
+
"step": 134
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 0.03874022526723581,
|
| 975 |
+
"grad_norm": 0.3410555124282837,
|
| 976 |
+
"learning_rate": 3.1937916690642356e-05,
|
| 977 |
+
"loss": 0.2292,
|
| 978 |
+
"step": 135
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 0.03902718989884497,
|
| 982 |
+
"grad_norm": 0.4864601790904999,
|
| 983 |
+
"learning_rate": 3.107944749788449e-05,
|
| 984 |
+
"loss": 0.2465,
|
| 985 |
+
"step": 136
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 0.03931415453045412,
|
| 989 |
+
"grad_norm": 0.6895772218704224,
|
| 990 |
+
"learning_rate": 3.0227439656472877e-05,
|
| 991 |
+
"loss": 0.2501,
|
| 992 |
+
"step": 137
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 0.03960111916206328,
|
| 996 |
+
"grad_norm": 0.4328419864177704,
|
| 997 |
+
"learning_rate": 2.9382184126304834e-05,
|
| 998 |
+
"loss": 0.2526,
|
| 999 |
+
"step": 138
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.03988808379367243,
|
| 1003 |
+
"grad_norm": 0.47423994541168213,
|
| 1004 |
+
"learning_rate": 2.8543969561369556e-05,
|
| 1005 |
+
"loss": 0.242,
|
| 1006 |
+
"step": 139
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 0.040175048425281586,
|
| 1010 |
+
"grad_norm": 0.39731431007385254,
|
| 1011 |
+
"learning_rate": 2.771308221117309e-05,
|
| 1012 |
+
"loss": 0.1844,
|
| 1013 |
+
"step": 140
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 0.04046201305689074,
|
| 1017 |
+
"grad_norm": 0.5587954521179199,
|
| 1018 |
+
"learning_rate": 2.688980582298435e-05,
|
| 1019 |
+
"loss": 0.2735,
|
| 1020 |
+
"step": 141
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 0.040748977688499895,
|
| 1024 |
+
"grad_norm": 0.47387251257896423,
|
| 1025 |
+
"learning_rate": 2.607442154493568e-05,
|
| 1026 |
+
"loss": 0.2045,
|
| 1027 |
+
"step": 142
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 0.04103594232010905,
|
| 1031 |
+
"grad_norm": 0.5877320766448975,
|
| 1032 |
+
"learning_rate": 2.5267207830011068e-05,
|
| 1033 |
+
"loss": 0.2564,
|
| 1034 |
+
"step": 143
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 0.041322906951718204,
|
| 1038 |
+
"grad_norm": 0.5738049149513245,
|
| 1039 |
+
"learning_rate": 2.446844034095466e-05,
|
| 1040 |
+
"loss": 0.3058,
|
| 1041 |
+
"step": 144
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.04160987158332736,
|
| 1045 |
+
"grad_norm": 0.5666738152503967,
|
| 1046 |
+
"learning_rate": 2.3678391856132204e-05,
|
| 1047 |
+
"loss": 0.2889,
|
| 1048 |
+
"step": 145
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 0.041896836214936506,
|
| 1052 |
+
"grad_norm": 0.6741418838500977,
|
| 1053 |
+
"learning_rate": 2.2897332176377528e-05,
|
| 1054 |
+
"loss": 0.2702,
|
| 1055 |
+
"step": 146
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 0.04218380084654566,
|
| 1059 |
+
"grad_norm": 0.5714048743247986,
|
| 1060 |
+
"learning_rate": 2.2125528032855724e-05,
|
| 1061 |
+
"loss": 0.1961,
|
| 1062 |
+
"step": 147
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 0.042470765478154815,
|
| 1066 |
+
"grad_norm": 1.3949394226074219,
|
| 1067 |
+
"learning_rate": 2.136324299597474e-05,
|
| 1068 |
+
"loss": 0.1444,
|
| 1069 |
+
"step": 148
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 0.04275773010976397,
|
| 1073 |
+
"grad_norm": 0.38774827122688293,
|
| 1074 |
+
"learning_rate": 2.061073738537635e-05,
|
| 1075 |
+
"loss": 0.1532,
|
| 1076 |
+
"step": 149
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 0.043044694741373124,
|
| 1080 |
+
"grad_norm": 0.7958654165267944,
|
| 1081 |
+
"learning_rate": 1.9868268181037185e-05,
|
| 1082 |
+
"loss": 0.2234,
|
| 1083 |
+
"step": 150
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 0.043044694741373124,
|
| 1087 |
+
"eval_loss": 0.06637585908174515,
|
| 1088 |
+
"eval_runtime": 842.6363,
|
| 1089 |
+
"eval_samples_per_second": 6.965,
|
| 1090 |
+
"eval_steps_per_second": 3.483,
|
| 1091 |
+
"step": 150
|
| 1092 |
}
|
| 1093 |
],
|
| 1094 |
"logging_steps": 1,
|
|
|
|
| 1117 |
"attributes": {}
|
| 1118 |
}
|
| 1119 |
},
|
| 1120 |
+
"total_flos": 3.849388976725033e+17,
|
| 1121 |
"train_batch_size": 8,
|
| 1122 |
"trial_name": null,
|
| 1123 |
"trial_params": null
|