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 sha256:44aec1a9f6fb805307490320ba258806ffb9df86e0b51cecd88a53ffa9c2793b
|
| 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 sha256:64a509044d1dcefabaf2c7facc6cc5233470eca302ff577918adbad27d810998
|
| 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 sha256:368b1f478bd952ee39af7166d592b9b8d2fbbd092ece63cd293da03d59e4b9fc
|
| 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:f4c9c807f0681c8b7e53ada9b6ec3dba530d303de7da0d0a0562a3d8d0bbba08
|
| 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": 9.965,
|
| 732 |
"eval_steps_per_second": 4.983,
|
| 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": 0.11594025045633316,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-150",
|
| 4 |
+
"epoch": 0.01722949689869056,
|
| 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": 9.965,
|
| 732 |
"eval_steps_per_second": 4.983,
|
| 733 |
"step": 100
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 0.011601194578451643,
|
| 737 |
+
"grad_norm": 2.6634979248046875,
|
| 738 |
+
"learning_rate": 5.782172325201155e-05,
|
| 739 |
+
"loss": 0.6536,
|
| 740 |
+
"step": 101
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 0.01171605789110958,
|
| 744 |
+
"grad_norm": 2.7935872077941895,
|
| 745 |
+
"learning_rate": 5.695865504800327e-05,
|
| 746 |
+
"loss": 0.8657,
|
| 747 |
+
"step": 102
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.011830921203767516,
|
| 751 |
+
"grad_norm": 3.1238162517547607,
|
| 752 |
+
"learning_rate": 5.6093467170257374e-05,
|
| 753 |
+
"loss": 0.6678,
|
| 754 |
+
"step": 103
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 0.011945784516425454,
|
| 758 |
+
"grad_norm": 3.002263069152832,
|
| 759 |
+
"learning_rate": 5.522642316338268e-05,
|
| 760 |
+
"loss": 0.6514,
|
| 761 |
+
"step": 104
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.012060647829083391,
|
| 765 |
+
"grad_norm": 2.975006580352783,
|
| 766 |
+
"learning_rate": 5.435778713738292e-05,
|
| 767 |
+
"loss": 0.4484,
|
| 768 |
+
"step": 105
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 0.012175511141741327,
|
| 772 |
+
"grad_norm": 2.8138067722320557,
|
| 773 |
+
"learning_rate": 5.348782368720626e-05,
|
| 774 |
+
"loss": 0.5668,
|
| 775 |
+
"step": 106
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 0.012290374454399264,
|
| 779 |
+
"grad_norm": 2.3226609230041504,
|
| 780 |
+
"learning_rate": 5.26167978121472e-05,
|
| 781 |
+
"loss": 0.4671,
|
| 782 |
+
"step": 107
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 0.012405237767057202,
|
| 786 |
+
"grad_norm": 3.791348934173584,
|
| 787 |
+
"learning_rate": 5.174497483512506e-05,
|
| 788 |
+
"loss": 0.6958,
|
| 789 |
+
"step": 108
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.01252010107971514,
|
| 793 |
+
"grad_norm": 2.7212183475494385,
|
| 794 |
+
"learning_rate": 5.0872620321864185e-05,
|
| 795 |
+
"loss": 0.6117,
|
| 796 |
+
"step": 109
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 0.012634964392373075,
|
| 800 |
+
"grad_norm": 3.5150516033172607,
|
| 801 |
+
"learning_rate": 5e-05,
|
| 802 |
+
"loss": 0.822,
|
| 803 |
+
"step": 110
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 0.012749827705031013,
|
| 807 |
+
"grad_norm": 2.905332088470459,
|
| 808 |
+
"learning_rate": 4.912737967813583e-05,
|
| 809 |
+
"loss": 0.6823,
|
| 810 |
+
"step": 111
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 0.01286469101768895,
|
| 814 |
+
"grad_norm": 3.329963207244873,
|
| 815 |
+
"learning_rate": 4.825502516487497e-05,
|
| 816 |
+
"loss": 0.559,
|
| 817 |
+
"step": 112
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 0.012979554330346888,
|
| 821 |
+
"grad_norm": 3.3605265617370605,
|
| 822 |
+
"learning_rate": 4.738320218785281e-05,
|
| 823 |
+
"loss": 0.5544,
|
| 824 |
+
"step": 113
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 0.013094417643004824,
|
| 828 |
+
"grad_norm": 3.592366933822632,
|
| 829 |
+
"learning_rate": 4.6512176312793736e-05,
|
| 830 |
+
"loss": 0.5781,
|
| 831 |
+
"step": 114
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 0.013209280955662761,
|
| 835 |
+
"grad_norm": 3.577732563018799,
|
| 836 |
+
"learning_rate": 4.564221286261709e-05,
|
| 837 |
+
"loss": 0.6123,
|
| 838 |
+
"step": 115
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 0.013324144268320699,
|
| 842 |
+
"grad_norm": 4.342945575714111,
|
| 843 |
+
"learning_rate": 4.477357683661734e-05,
|
| 844 |
+
"loss": 0.7269,
|
| 845 |
+
"step": 116
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 0.013439007580978636,
|
| 849 |
+
"grad_norm": 2.921304941177368,
|
| 850 |
+
"learning_rate": 4.390653282974264e-05,
|
| 851 |
+
"loss": 0.5198,
|
| 852 |
+
"step": 117
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 0.013553870893636572,
|
| 856 |
+
"grad_norm": 3.515984058380127,
|
| 857 |
+
"learning_rate": 4.3041344951996746e-05,
|
| 858 |
+
"loss": 0.9182,
|
| 859 |
+
"step": 118
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 0.01366873420629451,
|
| 863 |
+
"grad_norm": 2.688448190689087,
|
| 864 |
+
"learning_rate": 4.2178276747988446e-05,
|
| 865 |
+
"loss": 0.6087,
|
| 866 |
+
"step": 119
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 0.013783597518952447,
|
| 870 |
+
"grad_norm": 2.6708593368530273,
|
| 871 |
+
"learning_rate": 4.131759111665349e-05,
|
| 872 |
+
"loss": 0.5885,
|
| 873 |
+
"step": 120
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.013898460831610384,
|
| 877 |
+
"grad_norm": 2.5848822593688965,
|
| 878 |
+
"learning_rate": 4.045955023117276e-05,
|
| 879 |
+
"loss": 0.5533,
|
| 880 |
+
"step": 121
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 0.01401332414426832,
|
| 884 |
+
"grad_norm": 3.2022759914398193,
|
| 885 |
+
"learning_rate": 3.960441545911204e-05,
|
| 886 |
+
"loss": 0.5861,
|
| 887 |
+
"step": 122
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 0.014128187456926258,
|
| 891 |
+
"grad_norm": 2.4787240028381348,
|
| 892 |
+
"learning_rate": 3.875244728280676e-05,
|
| 893 |
+
"loss": 0.4025,
|
| 894 |
+
"step": 123
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 0.014243050769584195,
|
| 898 |
+
"grad_norm": 3.095510959625244,
|
| 899 |
+
"learning_rate": 3.790390522001662e-05,
|
| 900 |
+
"loss": 0.5104,
|
| 901 |
+
"step": 124
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 0.014357914082242133,
|
| 905 |
+
"grad_norm": 3.846745491027832,
|
| 906 |
+
"learning_rate": 3.705904774487396e-05,
|
| 907 |
+
"loss": 0.5936,
|
| 908 |
+
"step": 125
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 0.014472777394900068,
|
| 912 |
+
"grad_norm": 2.9915177822113037,
|
| 913 |
+
"learning_rate": 3.6218132209150045e-05,
|
| 914 |
+
"loss": 0.5739,
|
| 915 |
+
"step": 126
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 0.014587640707558006,
|
| 919 |
+
"grad_norm": 2.5920958518981934,
|
| 920 |
+
"learning_rate": 3.5381414763863166e-05,
|
| 921 |
+
"loss": 0.4191,
|
| 922 |
+
"step": 127
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 0.014702504020215943,
|
| 926 |
+
"grad_norm": 2.4326400756835938,
|
| 927 |
+
"learning_rate": 3.4549150281252636e-05,
|
| 928 |
+
"loss": 0.437,
|
| 929 |
+
"step": 128
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 0.014817367332873881,
|
| 933 |
+
"grad_norm": 2.664111614227295,
|
| 934 |
+
"learning_rate": 3.372159227714218e-05,
|
| 935 |
+
"loss": 0.4107,
|
| 936 |
+
"step": 129
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 0.014932230645531817,
|
| 940 |
+
"grad_norm": 3.015989303588867,
|
| 941 |
+
"learning_rate": 3.289899283371657e-05,
|
| 942 |
+
"loss": 0.6345,
|
| 943 |
+
"step": 130
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 0.015047093958189754,
|
| 947 |
+
"grad_norm": 2.8984575271606445,
|
| 948 |
+
"learning_rate": 3.2081602522734986e-05,
|
| 949 |
+
"loss": 0.5547,
|
| 950 |
+
"step": 131
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 0.015161957270847692,
|
| 954 |
+
"grad_norm": 3.772346019744873,
|
| 955 |
+
"learning_rate": 3.12696703292044e-05,
|
| 956 |
+
"loss": 0.6239,
|
| 957 |
+
"step": 132
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 0.015276820583505627,
|
| 961 |
+
"grad_norm": 3.629082441329956,
|
| 962 |
+
"learning_rate": 3.046344357553632e-05,
|
| 963 |
+
"loss": 0.5739,
|
| 964 |
+
"step": 133
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 0.015391683896163565,
|
| 968 |
+
"grad_norm": 3.2363765239715576,
|
| 969 |
+
"learning_rate": 2.9663167846209998e-05,
|
| 970 |
+
"loss": 0.661,
|
| 971 |
+
"step": 134
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 0.015506547208821502,
|
| 975 |
+
"grad_norm": 2.6455376148223877,
|
| 976 |
+
"learning_rate": 2.886908691296504e-05,
|
| 977 |
+
"loss": 0.4586,
|
| 978 |
+
"step": 135
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 0.01562141052147944,
|
| 982 |
+
"grad_norm": 2.9570345878601074,
|
| 983 |
+
"learning_rate": 2.8081442660546125e-05,
|
| 984 |
+
"loss": 0.6333,
|
| 985 |
+
"step": 136
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 0.015736273834137376,
|
| 989 |
+
"grad_norm": 2.019033670425415,
|
| 990 |
+
"learning_rate": 2.7300475013022663e-05,
|
| 991 |
+
"loss": 0.3232,
|
| 992 |
+
"step": 137
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 0.015851137146795313,
|
| 996 |
+
"grad_norm": 2.6063356399536133,
|
| 997 |
+
"learning_rate": 2.6526421860705473e-05,
|
| 998 |
+
"loss": 0.4487,
|
| 999 |
+
"step": 138
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.01596600045945325,
|
| 1003 |
+
"grad_norm": 3.5841784477233887,
|
| 1004 |
+
"learning_rate": 2.575951898768315e-05,
|
| 1005 |
+
"loss": 0.6579,
|
| 1006 |
+
"step": 139
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 0.01608086377211119,
|
| 1010 |
+
"grad_norm": 3.1793031692504883,
|
| 1011 |
+
"learning_rate": 2.500000000000001e-05,
|
| 1012 |
+
"loss": 0.6123,
|
| 1013 |
+
"step": 140
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 0.016195727084769126,
|
| 1017 |
+
"grad_norm": 1.9112600088119507,
|
| 1018 |
+
"learning_rate": 2.4248096254497288e-05,
|
| 1019 |
+
"loss": 0.2844,
|
| 1020 |
+
"step": 141
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 0.016310590397427063,
|
| 1024 |
+
"grad_norm": 2.6747708320617676,
|
| 1025 |
+
"learning_rate": 2.350403678833976e-05,
|
| 1026 |
+
"loss": 0.4366,
|
| 1027 |
+
"step": 142
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 0.016425453710084997,
|
| 1031 |
+
"grad_norm": 2.7817370891571045,
|
| 1032 |
+
"learning_rate": 2.2768048249248648e-05,
|
| 1033 |
+
"loss": 0.4206,
|
| 1034 |
+
"step": 143
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 0.016540317022742935,
|
| 1038 |
+
"grad_norm": 3.0754709243774414,
|
| 1039 |
+
"learning_rate": 2.2040354826462668e-05,
|
| 1040 |
+
"loss": 0.4934,
|
| 1041 |
+
"step": 144
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.016655180335400872,
|
| 1045 |
+
"grad_norm": 2.9075064659118652,
|
| 1046 |
+
"learning_rate": 2.132117818244771e-05,
|
| 1047 |
+
"loss": 0.3818,
|
| 1048 |
+
"step": 145
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 0.01677004364805881,
|
| 1052 |
+
"grad_norm": 3.9040424823760986,
|
| 1053 |
+
"learning_rate": 2.061073738537635e-05,
|
| 1054 |
+
"loss": 0.6472,
|
| 1055 |
+
"step": 146
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 0.016884906960716747,
|
| 1059 |
+
"grad_norm": 2.7987887859344482,
|
| 1060 |
+
"learning_rate": 1.9909248842397584e-05,
|
| 1061 |
+
"loss": 0.3802,
|
| 1062 |
+
"step": 147
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 0.016999770273374685,
|
| 1066 |
+
"grad_norm": 3.3494410514831543,
|
| 1067 |
+
"learning_rate": 1.9216926233717085e-05,
|
| 1068 |
+
"loss": 0.5155,
|
| 1069 |
+
"step": 148
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 0.017114633586032622,
|
| 1073 |
+
"grad_norm": 2.892005681991577,
|
| 1074 |
+
"learning_rate": 1.8533980447508137e-05,
|
| 1075 |
+
"loss": 0.385,
|
| 1076 |
+
"step": 149
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 0.01722949689869056,
|
| 1080 |
+
"grad_norm": 2.724477529525757,
|
| 1081 |
+
"learning_rate": 1.7860619515673033e-05,
|
| 1082 |
+
"loss": 0.5024,
|
| 1083 |
+
"step": 150
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 0.01722949689869056,
|
| 1087 |
+
"eval_loss": 0.11594025045633316,
|
| 1088 |
+
"eval_runtime": 1471.5665,
|
| 1089 |
+
"eval_samples_per_second": 9.964,
|
| 1090 |
+
"eval_steps_per_second": 4.982,
|
| 1091 |
+
"step": 150
|
| 1092 |
}
|
| 1093 |
],
|
| 1094 |
"logging_steps": 1,
|
|
|
|
| 1117 |
"attributes": {}
|
| 1118 |
}
|
| 1119 |
},
|
| 1120 |
+
"total_flos": 2.146497013481472e+17,
|
| 1121 |
"train_batch_size": 8,
|
| 1122 |
"trial_name": null,
|
| 1123 |
"trial_params": null
|