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 295488936
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a665c434fe452b4e51fd428905a0019f6c066a612c0cf32fd74f5aaa622a9207
|
| 3 |
size 295488936
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 150486964
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:82299186248e194fa4b3a491654ca02a597d6e1928ea656828d60f908979dbaf
|
| 3 |
size 150486964
|
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 sha256:90832c7cf9c765ddb7a12506bbd270ad76e34041e867eed7c0e0ffd5d6bc2799
|
| 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:d8ce05761f46e7cf72fb17a02e3a0ca15c9d25ce3babf590eeb40568923b8bac
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 1.3634288311004639,
|
| 3 |
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
| 4 |
-
"epoch": 1.
|
| 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": 33.363,
|
| 732 |
"eval_steps_per_second": 8.5,
|
| 733 |
"step": 100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 734 |
}
|
| 735 |
],
|
| 736 |
"logging_steps": 1,
|
|
@@ -745,7 +1103,7 @@
|
|
| 745 |
"early_stopping_threshold": 0.0
|
| 746 |
},
|
| 747 |
"attributes": {
|
| 748 |
-
"early_stopping_patience_counter":
|
| 749 |
}
|
| 750 |
},
|
| 751 |
"TrainerControl": {
|
|
@@ -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": 1.3634288311004639,
|
| 3 |
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
| 4 |
+
"epoch": 1.6129032258064515,
|
| 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": 33.363,
|
| 732 |
"eval_steps_per_second": 8.5,
|
| 733 |
"step": 100
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 1.086021505376344,
|
| 737 |
+
"grad_norm": 0.9249867796897888,
|
| 738 |
+
"learning_rate": 5.330452921628497e-05,
|
| 739 |
+
"loss": 1.0458,
|
| 740 |
+
"step": 101
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 1.096774193548387,
|
| 744 |
+
"grad_norm": 1.0629762411117554,
|
| 745 |
+
"learning_rate": 5.247918773366112e-05,
|
| 746 |
+
"loss": 1.0836,
|
| 747 |
+
"step": 102
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 1.10752688172043,
|
| 751 |
+
"grad_norm": 1.1164374351501465,
|
| 752 |
+
"learning_rate": 5.165316846586541e-05,
|
| 753 |
+
"loss": 1.1097,
|
| 754 |
+
"step": 103
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 1.118279569892473,
|
| 758 |
+
"grad_norm": 1.129228115081787,
|
| 759 |
+
"learning_rate": 5.0826697238317935e-05,
|
| 760 |
+
"loss": 1.069,
|
| 761 |
+
"step": 104
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 1.129032258064516,
|
| 765 |
+
"grad_norm": 1.1376335620880127,
|
| 766 |
+
"learning_rate": 5e-05,
|
| 767 |
+
"loss": 0.9951,
|
| 768 |
+
"step": 105
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 1.139784946236559,
|
| 772 |
+
"grad_norm": 1.2229422330856323,
|
| 773 |
+
"learning_rate": 4.917330276168208e-05,
|
| 774 |
+
"loss": 1.1898,
|
| 775 |
+
"step": 106
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 1.1505376344086022,
|
| 779 |
+
"grad_norm": 1.1418484449386597,
|
| 780 |
+
"learning_rate": 4.834683153413459e-05,
|
| 781 |
+
"loss": 0.9968,
|
| 782 |
+
"step": 107
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 1.1612903225806452,
|
| 786 |
+
"grad_norm": 1.2595585584640503,
|
| 787 |
+
"learning_rate": 4.7520812266338885e-05,
|
| 788 |
+
"loss": 1.0579,
|
| 789 |
+
"step": 108
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 1.1720430107526882,
|
| 793 |
+
"grad_norm": 1.1968224048614502,
|
| 794 |
+
"learning_rate": 4.669547078371504e-05,
|
| 795 |
+
"loss": 0.9448,
|
| 796 |
+
"step": 109
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 1.1827956989247312,
|
| 800 |
+
"grad_norm": 1.3096959590911865,
|
| 801 |
+
"learning_rate": 4.5871032726383386e-05,
|
| 802 |
+
"loss": 1.0923,
|
| 803 |
+
"step": 110
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 1.1935483870967742,
|
| 807 |
+
"grad_norm": 1.3598382472991943,
|
| 808 |
+
"learning_rate": 4.504772348747687e-05,
|
| 809 |
+
"loss": 1.0318,
|
| 810 |
+
"step": 111
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 1.2043010752688172,
|
| 814 |
+
"grad_norm": 1.3797881603240967,
|
| 815 |
+
"learning_rate": 4.4225768151520694e-05,
|
| 816 |
+
"loss": 1.0698,
|
| 817 |
+
"step": 112
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 1.2150537634408602,
|
| 821 |
+
"grad_norm": 1.4478576183319092,
|
| 822 |
+
"learning_rate": 4.3405391432896555e-05,
|
| 823 |
+
"loss": 1.0424,
|
| 824 |
+
"step": 113
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 1.2258064516129032,
|
| 828 |
+
"grad_norm": 1.4821935892105103,
|
| 829 |
+
"learning_rate": 4.2586817614407895e-05,
|
| 830 |
+
"loss": 1.0264,
|
| 831 |
+
"step": 114
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 1.2365591397849462,
|
| 835 |
+
"grad_norm": 1.716293215751648,
|
| 836 |
+
"learning_rate": 4.17702704859633e-05,
|
| 837 |
+
"loss": 1.2165,
|
| 838 |
+
"step": 115
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 1.2473118279569892,
|
| 842 |
+
"grad_norm": 1.488614559173584,
|
| 843 |
+
"learning_rate": 4.095597328339452e-05,
|
| 844 |
+
"loss": 1.1289,
|
| 845 |
+
"step": 116
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 1.2580645161290323,
|
| 849 |
+
"grad_norm": 1.7371461391448975,
|
| 850 |
+
"learning_rate": 4.0144148627425993e-05,
|
| 851 |
+
"loss": 1.2733,
|
| 852 |
+
"step": 117
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 1.2688172043010753,
|
| 856 |
+
"grad_norm": 1.7669775485992432,
|
| 857 |
+
"learning_rate": 3.933501846281267e-05,
|
| 858 |
+
"loss": 1.3276,
|
| 859 |
+
"step": 118
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 1.2795698924731183,
|
| 863 |
+
"grad_norm": 1.5520764589309692,
|
| 864 |
+
"learning_rate": 3.852880399766243e-05,
|
| 865 |
+
"loss": 1.0845,
|
| 866 |
+
"step": 119
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 1.2903225806451613,
|
| 870 |
+
"grad_norm": 1.2955957651138306,
|
| 871 |
+
"learning_rate": 3.772572564296005e-05,
|
| 872 |
+
"loss": 0.9734,
|
| 873 |
+
"step": 120
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 1.3010752688172043,
|
| 877 |
+
"grad_norm": 1.396894097328186,
|
| 878 |
+
"learning_rate": 3.6926002952309016e-05,
|
| 879 |
+
"loss": 0.8713,
|
| 880 |
+
"step": 121
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 1.3118279569892473,
|
| 884 |
+
"grad_norm": 1.6373274326324463,
|
| 885 |
+
"learning_rate": 3.612985456190778e-05,
|
| 886 |
+
"loss": 0.9747,
|
| 887 |
+
"step": 122
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 1.3225806451612903,
|
| 891 |
+
"grad_norm": 1.5140986442565918,
|
| 892 |
+
"learning_rate": 3.533749813077677e-05,
|
| 893 |
+
"loss": 0.952,
|
| 894 |
+
"step": 123
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 1.3333333333333333,
|
| 898 |
+
"grad_norm": 1.687639594078064,
|
| 899 |
+
"learning_rate": 3.4549150281252636e-05,
|
| 900 |
+
"loss": 1.1532,
|
| 901 |
+
"step": 124
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 1.3440860215053765,
|
| 905 |
+
"grad_norm": 1.5184952020645142,
|
| 906 |
+
"learning_rate": 3.3765026539765834e-05,
|
| 907 |
+
"loss": 1.1347,
|
| 908 |
+
"step": 125
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 1.3548387096774195,
|
| 912 |
+
"grad_norm": 1.493153691291809,
|
| 913 |
+
"learning_rate": 3.298534127791785e-05,
|
| 914 |
+
"loss": 1.0142,
|
| 915 |
+
"step": 126
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 1.3655913978494625,
|
| 919 |
+
"grad_norm": 1.5351260900497437,
|
| 920 |
+
"learning_rate": 3.221030765387417e-05,
|
| 921 |
+
"loss": 1.096,
|
| 922 |
+
"step": 127
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 1.3763440860215055,
|
| 926 |
+
"grad_norm": 1.4562873840332031,
|
| 927 |
+
"learning_rate": 3.144013755408895e-05,
|
| 928 |
+
"loss": 0.969,
|
| 929 |
+
"step": 128
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 1.3870967741935485,
|
| 933 |
+
"grad_norm": 1.398634672164917,
|
| 934 |
+
"learning_rate": 3.0675041535377405e-05,
|
| 935 |
+
"loss": 1.0367,
|
| 936 |
+
"step": 129
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 1.3978494623655915,
|
| 940 |
+
"grad_norm": 1.3472834825515747,
|
| 941 |
+
"learning_rate": 2.991522876735154e-05,
|
| 942 |
+
"loss": 1.086,
|
| 943 |
+
"step": 130
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 1.4086021505376345,
|
| 947 |
+
"grad_norm": 1.482953429222107,
|
| 948 |
+
"learning_rate": 2.916090697523549e-05,
|
| 949 |
+
"loss": 1.1435,
|
| 950 |
+
"step": 131
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 1.4193548387096775,
|
| 954 |
+
"grad_norm": 1.5652285814285278,
|
| 955 |
+
"learning_rate": 2.8412282383075363e-05,
|
| 956 |
+
"loss": 1.135,
|
| 957 |
+
"step": 132
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 1.4301075268817205,
|
| 961 |
+
"grad_norm": 1.6983011960983276,
|
| 962 |
+
"learning_rate": 2.766955965735968e-05,
|
| 963 |
+
"loss": 1.188,
|
| 964 |
+
"step": 133
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 1.4408602150537635,
|
| 968 |
+
"grad_norm": 1.6841248273849487,
|
| 969 |
+
"learning_rate": 2.693294185106562e-05,
|
| 970 |
+
"loss": 1.1523,
|
| 971 |
+
"step": 134
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 1.4516129032258065,
|
| 975 |
+
"grad_norm": 1.623253345489502,
|
| 976 |
+
"learning_rate": 2.6202630348146324e-05,
|
| 977 |
+
"loss": 1.2135,
|
| 978 |
+
"step": 135
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 1.4623655913978495,
|
| 982 |
+
"grad_norm": 1.3781989812850952,
|
| 983 |
+
"learning_rate": 2.547882480847461e-05,
|
| 984 |
+
"loss": 0.886,
|
| 985 |
+
"step": 136
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 1.4731182795698925,
|
| 989 |
+
"grad_norm": 1.4850106239318848,
|
| 990 |
+
"learning_rate": 2.476172311325783e-05,
|
| 991 |
+
"loss": 1.0595,
|
| 992 |
+
"step": 137
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 1.4838709677419355,
|
| 996 |
+
"grad_norm": 1.6122136116027832,
|
| 997 |
+
"learning_rate": 2.405152131093926e-05,
|
| 998 |
+
"loss": 1.0925,
|
| 999 |
+
"step": 138
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 1.4946236559139785,
|
| 1003 |
+
"grad_norm": 1.4394659996032715,
|
| 1004 |
+
"learning_rate": 2.3348413563600325e-05,
|
| 1005 |
+
"loss": 0.9858,
|
| 1006 |
+
"step": 139
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 1.5053763440860215,
|
| 1010 |
+
"grad_norm": 1.6203980445861816,
|
| 1011 |
+
"learning_rate": 2.2652592093878666e-05,
|
| 1012 |
+
"loss": 1.1627,
|
| 1013 |
+
"step": 140
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 1.5161290322580645,
|
| 1017 |
+
"grad_norm": 1.4615089893341064,
|
| 1018 |
+
"learning_rate": 2.196424713241637e-05,
|
| 1019 |
+
"loss": 1.0633,
|
| 1020 |
+
"step": 141
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 1.5268817204301075,
|
| 1024 |
+
"grad_norm": 1.6260236501693726,
|
| 1025 |
+
"learning_rate": 2.128356686585282e-05,
|
| 1026 |
+
"loss": 1.1186,
|
| 1027 |
+
"step": 142
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 1.5376344086021505,
|
| 1031 |
+
"grad_norm": 1.5490525960922241,
|
| 1032 |
+
"learning_rate": 2.061073738537635e-05,
|
| 1033 |
+
"loss": 1.0727,
|
| 1034 |
+
"step": 143
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 1.5483870967741935,
|
| 1038 |
+
"grad_norm": 1.6757961511611938,
|
| 1039 |
+
"learning_rate": 1.9945942635848748e-05,
|
| 1040 |
+
"loss": 1.2063,
|
| 1041 |
+
"step": 144
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 1.5591397849462365,
|
| 1045 |
+
"grad_norm": 1.5960594415664673,
|
| 1046 |
+
"learning_rate": 1.928936436551661e-05,
|
| 1047 |
+
"loss": 1.1443,
|
| 1048 |
+
"step": 145
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 1.5698924731182795,
|
| 1052 |
+
"grad_norm": 1.5980165004730225,
|
| 1053 |
+
"learning_rate": 1.8641182076323148e-05,
|
| 1054 |
+
"loss": 1.1234,
|
| 1055 |
+
"step": 146
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 1.5806451612903225,
|
| 1059 |
+
"grad_norm": 1.5133894681930542,
|
| 1060 |
+
"learning_rate": 1.800157297483417e-05,
|
| 1061 |
+
"loss": 1.0842,
|
| 1062 |
+
"step": 147
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 1.5913978494623655,
|
| 1066 |
+
"grad_norm": 1.3797662258148193,
|
| 1067 |
+
"learning_rate": 1.7370711923791567e-05,
|
| 1068 |
+
"loss": 0.9913,
|
| 1069 |
+
"step": 148
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 1.6021505376344085,
|
| 1073 |
+
"grad_norm": 1.5195506811141968,
|
| 1074 |
+
"learning_rate": 1.6748771394307585e-05,
|
| 1075 |
+
"loss": 1.1191,
|
| 1076 |
+
"step": 149
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 1.6129032258064515,
|
| 1080 |
+
"grad_norm": 1.61488676071167,
|
| 1081 |
+
"learning_rate": 1.6135921418712956e-05,
|
| 1082 |
+
"loss": 1.1218,
|
| 1083 |
+
"step": 150
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 1.6129032258064515,
|
| 1087 |
+
"eval_loss": 1.3883932828903198,
|
| 1088 |
+
"eval_runtime": 4.7039,
|
| 1089 |
+
"eval_samples_per_second": 33.377,
|
| 1090 |
+
"eval_steps_per_second": 8.504,
|
| 1091 |
+
"step": 150
|
| 1092 |
}
|
| 1093 |
],
|
| 1094 |
"logging_steps": 1,
|
|
|
|
| 1103 |
"early_stopping_threshold": 0.0
|
| 1104 |
},
|
| 1105 |
"attributes": {
|
| 1106 |
+
"early_stopping_patience_counter": 1
|
| 1107 |
}
|
| 1108 |
},
|
| 1109 |
"TrainerControl": {
|
|
|
|
| 1117 |
"attributes": {}
|
| 1118 |
}
|
| 1119 |
},
|
| 1120 |
+
"total_flos": 4.125544026734592e+16,
|
| 1121 |
"train_batch_size": 8,
|
| 1122 |
"trial_name": null,
|
| 1123 |
"trial_params": null
|