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 323014168
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5a49dc6f89920d427480b9b77d480771cc7f0b0bfa683a26a359ff2ce3ba2c68
|
| 3 |
size 323014168
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 164464564
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:65d60037cd6f702b04bd102ee3adf9b73ca2e0f00096e84cfc4e101e63821500
|
| 3 |
size 164464564
|
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:dc9ea7f4294b5a941dc55b6e5e8ff8969a7e24970e0af3f67a607cbf43766431
|
| 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 sha256:9a2c66bb4d12d3f5744da06cc31c7eb24188fe0a7bf31f80d1b18d6ac974b973
|
| 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": 2.94,
|
| 732 |
"eval_steps_per_second": 2.94,
|
| 733 |
"step": 100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 734 |
}
|
| 735 |
],
|
| 736 |
"logging_steps": 1,
|
|
@@ -759,7 +1117,7 @@
|
|
| 759 |
"attributes": {}
|
| 760 |
}
|
| 761 |
},
|
| 762 |
-
"total_flos":
|
| 763 |
"train_batch_size": 1,
|
| 764 |
"trial_name": null,
|
| 765 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.42699772119522095,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-150",
|
| 4 |
+
"epoch": 0.2546148949713558,
|
| 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": 2.94,
|
| 732 |
"eval_steps_per_second": 2.94,
|
| 733 |
"step": 100
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 0.1714406959473796,
|
| 737 |
+
"grad_norm": 0.33816632628440857,
|
| 738 |
+
"learning_rate": 0.0002937891172275147,
|
| 739 |
+
"loss": 0.6861,
|
| 740 |
+
"step": 101
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 0.17313812858052197,
|
| 744 |
+
"grad_norm": 0.24974839389324188,
|
| 745 |
+
"learning_rate": 0.00029365284045804077,
|
| 746 |
+
"loss": 0.7581,
|
| 747 |
+
"step": 102
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.17483556121366434,
|
| 751 |
+
"grad_norm": 0.389892041683197,
|
| 752 |
+
"learning_rate": 0.00029351511710605825,
|
| 753 |
+
"loss": 0.8517,
|
| 754 |
+
"step": 103
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 0.1765329938468067,
|
| 758 |
+
"grad_norm": 0.21865390241146088,
|
| 759 |
+
"learning_rate": 0.0002933759485584397,
|
| 760 |
+
"loss": 0.7927,
|
| 761 |
+
"step": 104
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.17823042647994908,
|
| 765 |
+
"grad_norm": 0.2867435812950134,
|
| 766 |
+
"learning_rate": 0.00029323533621661106,
|
| 767 |
+
"loss": 0.8931,
|
| 768 |
+
"step": 105
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 0.17992785911309145,
|
| 772 |
+
"grad_norm": 0.19504129886627197,
|
| 773 |
+
"learning_rate": 0.0002930932814965369,
|
| 774 |
+
"loss": 0.5056,
|
| 775 |
+
"step": 106
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 0.18162529174623382,
|
| 779 |
+
"grad_norm": 0.2704707980155945,
|
| 780 |
+
"learning_rate": 0.00029294978582870666,
|
| 781 |
+
"loss": 0.7927,
|
| 782 |
+
"step": 107
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 0.1833227243793762,
|
| 786 |
+
"grad_norm": 0.20052890479564667,
|
| 787 |
+
"learning_rate": 0.0002928048506581202,
|
| 788 |
+
"loss": 0.6507,
|
| 789 |
+
"step": 108
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.18502015701251856,
|
| 793 |
+
"grad_norm": 0.20652854442596436,
|
| 794 |
+
"learning_rate": 0.00029265847744427303,
|
| 795 |
+
"loss": 0.6928,
|
| 796 |
+
"step": 109
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 0.18671758964566093,
|
| 800 |
+
"grad_norm": 0.2864634096622467,
|
| 801 |
+
"learning_rate": 0.00029251066766114176,
|
| 802 |
+
"loss": 1.0405,
|
| 803 |
+
"step": 110
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 0.1884150222788033,
|
| 807 |
+
"grad_norm": 0.2000068873167038,
|
| 808 |
+
"learning_rate": 0.0002923614227971694,
|
| 809 |
+
"loss": 0.5787,
|
| 810 |
+
"step": 111
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 0.19011245491194567,
|
| 814 |
+
"grad_norm": 0.16141685843467712,
|
| 815 |
+
"learning_rate": 0.0002922107443552499,
|
| 816 |
+
"loss": 0.4154,
|
| 817 |
+
"step": 112
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 0.19180988754508804,
|
| 821 |
+
"grad_norm": 0.2669724225997925,
|
| 822 |
+
"learning_rate": 0.00029205863385271363,
|
| 823 |
+
"loss": 0.9767,
|
| 824 |
+
"step": 113
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 0.1935073201782304,
|
| 828 |
+
"grad_norm": 0.7105275988578796,
|
| 829 |
+
"learning_rate": 0.00029190509282131153,
|
| 830 |
+
"loss": 0.6763,
|
| 831 |
+
"step": 114
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 0.1952047528113728,
|
| 835 |
+
"grad_norm": 0.23595799505710602,
|
| 836 |
+
"learning_rate": 0.00029175012280720024,
|
| 837 |
+
"loss": 0.6856,
|
| 838 |
+
"step": 115
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 0.19690218544451518,
|
| 842 |
+
"grad_norm": 0.23921440541744232,
|
| 843 |
+
"learning_rate": 0.00029159372537092596,
|
| 844 |
+
"loss": 0.7075,
|
| 845 |
+
"step": 116
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 0.19859961807765755,
|
| 849 |
+
"grad_norm": 0.21551960706710815,
|
| 850 |
+
"learning_rate": 0.0002914359020874092,
|
| 851 |
+
"loss": 0.6004,
|
| 852 |
+
"step": 117
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 0.20029705071079992,
|
| 856 |
+
"grad_norm": 0.20390333235263824,
|
| 857 |
+
"learning_rate": 0.0002912766545459287,
|
| 858 |
+
"loss": 0.57,
|
| 859 |
+
"step": 118
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 0.2019944833439423,
|
| 863 |
+
"grad_norm": 0.15612931549549103,
|
| 864 |
+
"learning_rate": 0.0002911159843501053,
|
| 865 |
+
"loss": 0.2055,
|
| 866 |
+
"step": 119
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 0.20369191597708466,
|
| 870 |
+
"grad_norm": 0.17460142076015472,
|
| 871 |
+
"learning_rate": 0.0002909538931178862,
|
| 872 |
+
"loss": 0.371,
|
| 873 |
+
"step": 120
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.20538934861022703,
|
| 877 |
+
"grad_norm": 0.18853937089443207,
|
| 878 |
+
"learning_rate": 0.00029079038248152835,
|
| 879 |
+
"loss": 0.4252,
|
| 880 |
+
"step": 121
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 0.2070867812433694,
|
| 884 |
+
"grad_norm": 0.14426594972610474,
|
| 885 |
+
"learning_rate": 0.0002906254540875819,
|
| 886 |
+
"loss": 0.2658,
|
| 887 |
+
"step": 122
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 0.20878421387651178,
|
| 891 |
+
"grad_norm": 0.16134832799434662,
|
| 892 |
+
"learning_rate": 0.0002904591095968741,
|
| 893 |
+
"loss": 0.297,
|
| 894 |
+
"step": 123
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 0.21048164650965415,
|
| 898 |
+
"grad_norm": 0.3797933757305145,
|
| 899 |
+
"learning_rate": 0.00029029135068449195,
|
| 900 |
+
"loss": 0.2837,
|
| 901 |
+
"step": 124
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 0.21217907914279652,
|
| 905 |
+
"grad_norm": 0.038109440356492996,
|
| 906 |
+
"learning_rate": 0.000290122179039766,
|
| 907 |
+
"loss": 0.0149,
|
| 908 |
+
"step": 125
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 0.2138765117759389,
|
| 912 |
+
"grad_norm": 0.11762002855539322,
|
| 913 |
+
"learning_rate": 0.00028995159636625276,
|
| 914 |
+
"loss": 0.0684,
|
| 915 |
+
"step": 126
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 0.21557394440908126,
|
| 919 |
+
"grad_norm": 0.02665620669722557,
|
| 920 |
+
"learning_rate": 0.00028977960438171784,
|
| 921 |
+
"loss": 0.0044,
|
| 922 |
+
"step": 127
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 0.21727137704222363,
|
| 926 |
+
"grad_norm": 0.03071051463484764,
|
| 927 |
+
"learning_rate": 0.0002896062048181186,
|
| 928 |
+
"loss": 0.0018,
|
| 929 |
+
"step": 128
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 0.218968809675366,
|
| 933 |
+
"grad_norm": 0.009578248485922813,
|
| 934 |
+
"learning_rate": 0.00028943139942158683,
|
| 935 |
+
"loss": 0.0004,
|
| 936 |
+
"step": 129
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 0.22066624230850837,
|
| 940 |
+
"grad_norm": 0.0018459237180650234,
|
| 941 |
+
"learning_rate": 0.0002892551899524109,
|
| 942 |
+
"loss": 0.0001,
|
| 943 |
+
"step": 130
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 0.22236367494165074,
|
| 947 |
+
"grad_norm": 0.09641125798225403,
|
| 948 |
+
"learning_rate": 0.0002890775781850181,
|
| 949 |
+
"loss": 0.0588,
|
| 950 |
+
"step": 131
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 0.22406110757479314,
|
| 954 |
+
"grad_norm": 0.008955306373536587,
|
| 955 |
+
"learning_rate": 0.000288898565907957,
|
| 956 |
+
"loss": 0.0002,
|
| 957 |
+
"step": 132
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 0.2257585402079355,
|
| 961 |
+
"grad_norm": 0.4112979471683502,
|
| 962 |
+
"learning_rate": 0.0002887181549238793,
|
| 963 |
+
"loss": 0.0037,
|
| 964 |
+
"step": 133
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 0.22745597284107788,
|
| 968 |
+
"grad_norm": 0.0008860170491971076,
|
| 969 |
+
"learning_rate": 0.00028853634704952165,
|
| 970 |
+
"loss": 0.0001,
|
| 971 |
+
"step": 134
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 0.22915340547422025,
|
| 975 |
+
"grad_norm": 0.03983623534440994,
|
| 976 |
+
"learning_rate": 0.0002883531441156872,
|
| 977 |
+
"loss": 0.0014,
|
| 978 |
+
"step": 135
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 0.23085083810736262,
|
| 982 |
+
"grad_norm": 0.13147315382957458,
|
| 983 |
+
"learning_rate": 0.00028816854796722747,
|
| 984 |
+
"loss": 0.0039,
|
| 985 |
+
"step": 136
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 0.232548270740505,
|
| 989 |
+
"grad_norm": 0.027041589841246605,
|
| 990 |
+
"learning_rate": 0.00028798256046302375,
|
| 991 |
+
"loss": 0.003,
|
| 992 |
+
"step": 137
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 0.23424570337364736,
|
| 996 |
+
"grad_norm": 0.012492002919316292,
|
| 997 |
+
"learning_rate": 0.000287795183475968,
|
| 998 |
+
"loss": 0.0006,
|
| 999 |
+
"step": 138
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.23594313600678973,
|
| 1003 |
+
"grad_norm": 0.004202733281999826,
|
| 1004 |
+
"learning_rate": 0.00028760641889294446,
|
| 1005 |
+
"loss": 0.0002,
|
| 1006 |
+
"step": 139
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 0.2376405686399321,
|
| 1010 |
+
"grad_norm": 0.004685190040618181,
|
| 1011 |
+
"learning_rate": 0.0002874162686148104,
|
| 1012 |
+
"loss": 0.0003,
|
| 1013 |
+
"step": 140
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 0.23933800127307447,
|
| 1017 |
+
"grad_norm": 0.009362437762320042,
|
| 1018 |
+
"learning_rate": 0.000287224734556377,
|
| 1019 |
+
"loss": 0.0007,
|
| 1020 |
+
"step": 141
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 0.24103543390621684,
|
| 1024 |
+
"grad_norm": 0.0981183648109436,
|
| 1025 |
+
"learning_rate": 0.0002870318186463901,
|
| 1026 |
+
"loss": 0.0042,
|
| 1027 |
+
"step": 142
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 0.24273286653935922,
|
| 1031 |
+
"grad_norm": 0.015274147503077984,
|
| 1032 |
+
"learning_rate": 0.00028683752282751074,
|
| 1033 |
+
"loss": 0.0007,
|
| 1034 |
+
"step": 143
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 0.24443029917250159,
|
| 1038 |
+
"grad_norm": 0.00900458823889494,
|
| 1039 |
+
"learning_rate": 0.0002866418490562957,
|
| 1040 |
+
"loss": 0.0007,
|
| 1041 |
+
"step": 144
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.24612773180564396,
|
| 1045 |
+
"grad_norm": 0.01067203190177679,
|
| 1046 |
+
"learning_rate": 0.00028644479930317775,
|
| 1047 |
+
"loss": 0.0006,
|
| 1048 |
+
"step": 145
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 0.24782516443878633,
|
| 1052 |
+
"grad_norm": 0.022083261981606483,
|
| 1053 |
+
"learning_rate": 0.0002862463755524455,
|
| 1054 |
+
"loss": 0.0006,
|
| 1055 |
+
"step": 146
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 0.2495225970719287,
|
| 1059 |
+
"grad_norm": 0.003914229571819305,
|
| 1060 |
+
"learning_rate": 0.00028604657980222417,
|
| 1061 |
+
"loss": 0.0003,
|
| 1062 |
+
"step": 147
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 0.25122002970507107,
|
| 1066 |
+
"grad_norm": 0.005544353276491165,
|
| 1067 |
+
"learning_rate": 0.0002858454140644546,
|
| 1068 |
+
"loss": 0.0004,
|
| 1069 |
+
"step": 148
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 0.25291746233821344,
|
| 1073 |
+
"grad_norm": 0.006152280140668154,
|
| 1074 |
+
"learning_rate": 0.00028564288036487357,
|
| 1075 |
+
"loss": 0.0005,
|
| 1076 |
+
"step": 149
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 0.2546148949713558,
|
| 1080 |
+
"grad_norm": 0.04355669021606445,
|
| 1081 |
+
"learning_rate": 0.00028543898074299317,
|
| 1082 |
+
"loss": 0.0053,
|
| 1083 |
+
"step": 150
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 0.2546148949713558,
|
| 1087 |
+
"eval_loss": 0.42699772119522095,
|
| 1088 |
+
"eval_runtime": 65.6214,
|
| 1089 |
+
"eval_samples_per_second": 2.941,
|
| 1090 |
+
"eval_steps_per_second": 2.941,
|
| 1091 |
+
"step": 150
|
| 1092 |
}
|
| 1093 |
],
|
| 1094 |
"logging_steps": 1,
|
|
|
|
| 1117 |
"attributes": {}
|
| 1118 |
}
|
| 1119 |
},
|
| 1120 |
+
"total_flos": 9.72786272651182e+16,
|
| 1121 |
"train_batch_size": 1,
|
| 1122 |
"trial_name": null,
|
| 1123 |
"trial_params": null
|