Training in progress, step 150, checkpoint
Browse files- last-checkpoint/adapter_model.safetensors +1 -1
- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +371 -5
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 50624
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a724b883b206a12ca637814a06169f4199e9d78ea91a4e7128a62b0bc3920f30
|
| 3 |
size 50624
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 118090
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4f9fd3bbd5fbd2985cf3aef2f0dca81d7f1e99a993ccfc741664a136baa58a0d
|
| 3 |
size 118090
|
last-checkpoint/rng_state_0.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5f45934ac600086a616e710f5906c1c7f11e577a5decec0f5ae0a2ba0933101b
|
| 3 |
size 15024
|
last-checkpoint/rng_state_1.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b14f79d6fb33a1c3ccb9ba41995139a9c9a1890c17f4d85a00a0ca975c030f83
|
| 3 |
size 15024
|
last-checkpoint/rng_state_2.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bbb4d08cea2c6de43e4475bbf090cd8adefed93f31d0faa150ee9376dc4d179c
|
| 3 |
size 15024
|
last-checkpoint/rng_state_3.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d1bd0541ca6ac4e8a53aa9ffa8aec437643cb0830712258b4896039e47e154ca
|
| 3 |
size 15024
|
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": 10.
|
| 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": 1116.397,
|
| 748 |
"eval_steps_per_second": 44.656,
|
| 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": 10.3283109664917,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-150",
|
| 4 |
+
"epoch": 0.16703786191536749,
|
| 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": 1116.397,
|
| 748 |
"eval_steps_per_second": 44.656,
|
| 749 |
"step": 100
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 0.11247216035634744,
|
| 753 |
+
"grad_norm": 0.04336141422390938,
|
| 754 |
+
"learning_rate": 0.0001599135876488549,
|
| 755 |
+
"loss": 10.3448,
|
| 756 |
+
"step": 101
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 0.11358574610244988,
|
| 760 |
+
"grad_norm": 0.029405318200588226,
|
| 761 |
+
"learning_rate": 0.00015743756320098332,
|
| 762 |
+
"loss": 10.3418,
|
| 763 |
+
"step": 102
|
| 764 |
+
},
|
| 765 |
+
{
|
| 766 |
+
"epoch": 0.11469933184855234,
|
| 767 |
+
"grad_norm": 0.024563252925872803,
|
| 768 |
+
"learning_rate": 0.0001549595053975962,
|
| 769 |
+
"loss": 10.3404,
|
| 770 |
+
"step": 103
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 0.11581291759465479,
|
| 774 |
+
"grad_norm": 0.032005004584789276,
|
| 775 |
+
"learning_rate": 0.00015248009171495378,
|
| 776 |
+
"loss": 10.3378,
|
| 777 |
+
"step": 104
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 0.11692650334075724,
|
| 781 |
+
"grad_norm": 0.027886446565389633,
|
| 782 |
+
"learning_rate": 0.00015,
|
| 783 |
+
"loss": 10.3384,
|
| 784 |
+
"step": 105
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 0.11804008908685969,
|
| 788 |
+
"grad_norm": 0.027392663061618805,
|
| 789 |
+
"learning_rate": 0.00014751990828504622,
|
| 790 |
+
"loss": 10.3359,
|
| 791 |
+
"step": 106
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 0.11915367483296214,
|
| 795 |
+
"grad_norm": 0.029057586565613747,
|
| 796 |
+
"learning_rate": 0.00014504049460240375,
|
| 797 |
+
"loss": 10.3357,
|
| 798 |
+
"step": 107
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 0.12026726057906459,
|
| 802 |
+
"grad_norm": 0.02602003701031208,
|
| 803 |
+
"learning_rate": 0.00014256243679901663,
|
| 804 |
+
"loss": 10.334,
|
| 805 |
+
"step": 108
|
| 806 |
+
},
|
| 807 |
+
{
|
| 808 |
+
"epoch": 0.12138084632516703,
|
| 809 |
+
"grad_norm": 0.025092778727412224,
|
| 810 |
+
"learning_rate": 0.00014008641235114508,
|
| 811 |
+
"loss": 10.3295,
|
| 812 |
+
"step": 109
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 0.12249443207126949,
|
| 816 |
+
"grad_norm": 0.0306704044342041,
|
| 817 |
+
"learning_rate": 0.00013761309817915014,
|
| 818 |
+
"loss": 10.3304,
|
| 819 |
+
"step": 110
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 0.12360801781737193,
|
| 823 |
+
"grad_norm": 0.03935825452208519,
|
| 824 |
+
"learning_rate": 0.00013514317046243058,
|
| 825 |
+
"loss": 10.3302,
|
| 826 |
+
"step": 111
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 0.12472160356347439,
|
| 830 |
+
"grad_norm": 0.05053841695189476,
|
| 831 |
+
"learning_rate": 0.00013267730445456208,
|
| 832 |
+
"loss": 10.3247,
|
| 833 |
+
"step": 112
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 0.12583518930957685,
|
| 837 |
+
"grad_norm": 0.03532646968960762,
|
| 838 |
+
"learning_rate": 0.00013021617429868963,
|
| 839 |
+
"loss": 10.3419,
|
| 840 |
+
"step": 113
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 0.12694877505567928,
|
| 844 |
+
"grad_norm": 0.03398346155881882,
|
| 845 |
+
"learning_rate": 0.00012776045284322368,
|
| 846 |
+
"loss": 10.341,
|
| 847 |
+
"step": 114
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 0.12806236080178174,
|
| 851 |
+
"grad_norm": 0.031128259375691414,
|
| 852 |
+
"learning_rate": 0.00012531081145788987,
|
| 853 |
+
"loss": 10.3399,
|
| 854 |
+
"step": 115
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 0.1291759465478842,
|
| 858 |
+
"grad_norm": 0.02975599467754364,
|
| 859 |
+
"learning_rate": 0.00012286791985018355,
|
| 860 |
+
"loss": 10.3378,
|
| 861 |
+
"step": 116
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 0.13028953229398663,
|
| 865 |
+
"grad_norm": 0.025660140439867973,
|
| 866 |
+
"learning_rate": 0.00012043244588227796,
|
| 867 |
+
"loss": 10.3369,
|
| 868 |
+
"step": 117
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 0.13140311804008908,
|
| 872 |
+
"grad_norm": 0.023060623556375504,
|
| 873 |
+
"learning_rate": 0.00011800505538843798,
|
| 874 |
+
"loss": 10.3345,
|
| 875 |
+
"step": 118
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 0.13251670378619154,
|
| 879 |
+
"grad_norm": 0.02799002081155777,
|
| 880 |
+
"learning_rate": 0.00011558641199298727,
|
| 881 |
+
"loss": 10.3328,
|
| 882 |
+
"step": 119
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 0.133630289532294,
|
| 886 |
+
"grad_norm": 0.024050775915384293,
|
| 887 |
+
"learning_rate": 0.00011317717692888012,
|
| 888 |
+
"loss": 10.3321,
|
| 889 |
+
"step": 120
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 0.13474387527839643,
|
| 893 |
+
"grad_norm": 0.02656245231628418,
|
| 894 |
+
"learning_rate": 0.00011077800885692702,
|
| 895 |
+
"loss": 10.3342,
|
| 896 |
+
"step": 121
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 0.1358574610244989,
|
| 900 |
+
"grad_norm": 0.02685682475566864,
|
| 901 |
+
"learning_rate": 0.00010838956368572334,
|
| 902 |
+
"loss": 10.3297,
|
| 903 |
+
"step": 122
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 0.13697104677060135,
|
| 907 |
+
"grad_norm": 0.03605301305651665,
|
| 908 |
+
"learning_rate": 0.0001060124943923303,
|
| 909 |
+
"loss": 10.3265,
|
| 910 |
+
"step": 123
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 0.13808463251670378,
|
| 914 |
+
"grad_norm": 0.04310872033238411,
|
| 915 |
+
"learning_rate": 0.0001036474508437579,
|
| 916 |
+
"loss": 10.325,
|
| 917 |
+
"step": 124
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 0.13919821826280623,
|
| 921 |
+
"grad_norm": 0.052310604602098465,
|
| 922 |
+
"learning_rate": 0.00010129507961929748,
|
| 923 |
+
"loss": 10.3216,
|
| 924 |
+
"step": 125
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 0.13919821826280623,
|
| 928 |
+
"eval_loss": 10.330706596374512,
|
| 929 |
+
"eval_runtime": 0.0484,
|
| 930 |
+
"eval_samples_per_second": 1033.941,
|
| 931 |
+
"eval_steps_per_second": 41.358,
|
| 932 |
+
"step": 125
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 0.1403118040089087,
|
| 936 |
+
"grad_norm": 0.03873632475733757,
|
| 937 |
+
"learning_rate": 9.895602383375353e-05,
|
| 938 |
+
"loss": 10.343,
|
| 939 |
+
"step": 126
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 0.14142538975501115,
|
| 943 |
+
"grad_norm": 0.03256813436746597,
|
| 944 |
+
"learning_rate": 9.663092296162251e-05,
|
| 945 |
+
"loss": 10.3388,
|
| 946 |
+
"step": 127
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 0.14253897550111358,
|
| 950 |
+
"grad_norm": 0.026527272537350655,
|
| 951 |
+
"learning_rate": 9.432041266226686e-05,
|
| 952 |
+
"loss": 10.3378,
|
| 953 |
+
"step": 128
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 0.14365256124721604,
|
| 957 |
+
"grad_norm": 0.022660735994577408,
|
| 958 |
+
"learning_rate": 9.202512460613219e-05,
|
| 959 |
+
"loss": 10.3365,
|
| 960 |
+
"step": 129
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 0.1447661469933185,
|
| 964 |
+
"grad_norm": 0.0257252287119627,
|
| 965 |
+
"learning_rate": 8.97456863020546e-05,
|
| 966 |
+
"loss": 10.3343,
|
| 967 |
+
"step": 130
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 0.14587973273942093,
|
| 971 |
+
"grad_norm": 0.02294372208416462,
|
| 972 |
+
"learning_rate": 8.748272092570646e-05,
|
| 973 |
+
"loss": 10.3345,
|
| 974 |
+
"step": 131
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 0.14699331848552338,
|
| 978 |
+
"grad_norm": 0.022150015458464622,
|
| 979 |
+
"learning_rate": 8.523684714922608e-05,
|
| 980 |
+
"loss": 10.33,
|
| 981 |
+
"step": 132
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 0.14810690423162584,
|
| 985 |
+
"grad_norm": 0.023904934525489807,
|
| 986 |
+
"learning_rate": 8.300867897207903e-05,
|
| 987 |
+
"loss": 10.3325,
|
| 988 |
+
"step": 133
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 0.1492204899777283,
|
| 992 |
+
"grad_norm": 0.025626808404922485,
|
| 993 |
+
"learning_rate": 8.079882555319684e-05,
|
| 994 |
+
"loss": 10.329,
|
| 995 |
+
"step": 134
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 0.15033407572383073,
|
| 999 |
+
"grad_norm": 0.031538087874650955,
|
| 1000 |
+
"learning_rate": 7.860789104443896e-05,
|
| 1001 |
+
"loss": 10.3266,
|
| 1002 |
+
"step": 135
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 0.1514476614699332,
|
| 1006 |
+
"grad_norm": 0.03154623880982399,
|
| 1007 |
+
"learning_rate": 7.643647442542382e-05,
|
| 1008 |
+
"loss": 10.3253,
|
| 1009 |
+
"step": 136
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 0.15256124721603564,
|
| 1013 |
+
"grad_norm": 0.04129767417907715,
|
| 1014 |
+
"learning_rate": 7.428516933977347e-05,
|
| 1015 |
+
"loss": 10.3231,
|
| 1016 |
+
"step": 137
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 0.15367483296213807,
|
| 1020 |
+
"grad_norm": 0.03668758645653725,
|
| 1021 |
+
"learning_rate": 7.215456393281776e-05,
|
| 1022 |
+
"loss": 10.3407,
|
| 1023 |
+
"step": 138
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 0.15478841870824053,
|
| 1027 |
+
"grad_norm": 0.03435783460736275,
|
| 1028 |
+
"learning_rate": 7.004524069080096e-05,
|
| 1029 |
+
"loss": 10.3408,
|
| 1030 |
+
"step": 139
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"epoch": 0.155902004454343,
|
| 1034 |
+
"grad_norm": 0.03316853567957878,
|
| 1035 |
+
"learning_rate": 6.795777628163599e-05,
|
| 1036 |
+
"loss": 10.3389,
|
| 1037 |
+
"step": 140
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 0.15701559020044542,
|
| 1041 |
+
"grad_norm": 0.025575635954737663,
|
| 1042 |
+
"learning_rate": 6.58927413972491e-05,
|
| 1043 |
+
"loss": 10.3364,
|
| 1044 |
+
"step": 141
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 0.15812917594654788,
|
| 1048 |
+
"grad_norm": 0.021810244768857956,
|
| 1049 |
+
"learning_rate": 6.385070059755846e-05,
|
| 1050 |
+
"loss": 10.3354,
|
| 1051 |
+
"step": 142
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"epoch": 0.15924276169265034,
|
| 1055 |
+
"grad_norm": 0.021209685131907463,
|
| 1056 |
+
"learning_rate": 6.183221215612904e-05,
|
| 1057 |
+
"loss": 10.3342,
|
| 1058 |
+
"step": 143
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 0.1603563474387528,
|
| 1062 |
+
"grad_norm": 0.02310410887002945,
|
| 1063 |
+
"learning_rate": 5.983782790754623e-05,
|
| 1064 |
+
"loss": 10.3325,
|
| 1065 |
+
"step": 144
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 0.16146993318485522,
|
| 1069 |
+
"grad_norm": 0.021886780858039856,
|
| 1070 |
+
"learning_rate": 5.786809309654982e-05,
|
| 1071 |
+
"loss": 10.3306,
|
| 1072 |
+
"step": 145
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 0.16258351893095768,
|
| 1076 |
+
"grad_norm": 0.025645460933446884,
|
| 1077 |
+
"learning_rate": 5.592354622896944e-05,
|
| 1078 |
+
"loss": 10.3291,
|
| 1079 |
+
"step": 146
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 0.16369710467706014,
|
| 1083 |
+
"grad_norm": 0.028998544439673424,
|
| 1084 |
+
"learning_rate": 5.40047189245025e-05,
|
| 1085 |
+
"loss": 10.3274,
|
| 1086 |
+
"step": 147
|
| 1087 |
+
},
|
| 1088 |
+
{
|
| 1089 |
+
"epoch": 0.16481069042316257,
|
| 1090 |
+
"grad_norm": 0.03274320811033249,
|
| 1091 |
+
"learning_rate": 5.211213577137469e-05,
|
| 1092 |
+
"loss": 10.3251,
|
| 1093 |
+
"step": 148
|
| 1094 |
+
},
|
| 1095 |
+
{
|
| 1096 |
+
"epoch": 0.16592427616926503,
|
| 1097 |
+
"grad_norm": 0.041816357523202896,
|
| 1098 |
+
"learning_rate": 5.024631418292274e-05,
|
| 1099 |
+
"loss": 10.3252,
|
| 1100 |
+
"step": 149
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 0.16703786191536749,
|
| 1104 |
+
"grad_norm": 0.05579761043190956,
|
| 1105 |
+
"learning_rate": 4.840776425613886e-05,
|
| 1106 |
+
"loss": 10.321,
|
| 1107 |
+
"step": 150
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 0.16703786191536749,
|
| 1111 |
+
"eval_loss": 10.3283109664917,
|
| 1112 |
+
"eval_runtime": 0.0477,
|
| 1113 |
+
"eval_samples_per_second": 1048.482,
|
| 1114 |
+
"eval_steps_per_second": 41.939,
|
| 1115 |
+
"step": 150
|
| 1116 |
}
|
| 1117 |
],
|
| 1118 |
"logging_steps": 1,
|
|
|
|
| 1141 |
"attributes": {}
|
| 1142 |
}
|
| 1143 |
},
|
| 1144 |
+
"total_flos": 69380829872128.0,
|
| 1145 |
"train_batch_size": 8,
|
| 1146 |
"trial_name": null,
|
| 1147 |
"trial_params": null
|