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 50503544
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c143c42a4063e9e6fbea2ebbe9c02df6f80698f18813772b4b5c98f9248249e9
|
| 3 |
size 50503544
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 101184122
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b0e09fb5c6720dc558c523e23c997a5d16d04dc2794435654bc7c25355e27bfa
|
| 3 |
size 101184122
|
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:f1ea6d2abfec74017454f40a9100b440d5fc7363ae27950f7b451e76805ee6ac
|
| 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:fe23725d0f11173bf91cd02a1243888f0bd7f88a0c1003bf3e3f8a4146e8aa94
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 1.
|
| 3 |
-
"best_model_checkpoint": "miner_id_24/checkpoint-
|
| 4 |
-
"epoch": 1.
|
| 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": 17.66,
|
| 748 |
"eval_steps_per_second": 2.472,
|
| 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": 1.2822918891906738,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-150",
|
| 4 |
+
"epoch": 1.7122507122507122,
|
| 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": 17.66,
|
| 748 |
"eval_steps_per_second": 2.472,
|
| 749 |
"step": 100
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 1.1538461538461537,
|
| 753 |
+
"grad_norm": 1.0093574523925781,
|
| 754 |
+
"learning_rate": 0.00012737635542579392,
|
| 755 |
+
"loss": 0.9741,
|
| 756 |
+
"step": 101
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 1.1652421652421652,
|
| 760 |
+
"grad_norm": 1.1475558280944824,
|
| 761 |
+
"learning_rate": 0.00012457425986158547,
|
| 762 |
+
"loss": 1.1514,
|
| 763 |
+
"step": 102
|
| 764 |
+
},
|
| 765 |
+
{
|
| 766 |
+
"epoch": 1.1766381766381766,
|
| 767 |
+
"grad_norm": 1.0175673961639404,
|
| 768 |
+
"learning_rate": 0.00012178127064470495,
|
| 769 |
+
"loss": 0.892,
|
| 770 |
+
"step": 103
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 1.188034188034188,
|
| 774 |
+
"grad_norm": 1.1485775709152222,
|
| 775 |
+
"learning_rate": 0.00011899838809725704,
|
| 776 |
+
"loss": 0.9361,
|
| 777 |
+
"step": 104
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 1.1994301994301995,
|
| 781 |
+
"grad_norm": 1.1438003778457642,
|
| 782 |
+
"learning_rate": 0.00011622660892159588,
|
| 783 |
+
"loss": 1.0521,
|
| 784 |
+
"step": 105
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 1.210826210826211,
|
| 788 |
+
"grad_norm": 1.055317997932434,
|
| 789 |
+
"learning_rate": 0.0001134669258433512,
|
| 790 |
+
"loss": 0.7935,
|
| 791 |
+
"step": 106
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 1.2222222222222223,
|
| 795 |
+
"grad_norm": 1.357569932937622,
|
| 796 |
+
"learning_rate": 0.00011072032725587898,
|
| 797 |
+
"loss": 0.7351,
|
| 798 |
+
"step": 107
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 1.2336182336182335,
|
| 802 |
+
"grad_norm": 2.4943761825561523,
|
| 803 |
+
"learning_rate": 0.00010798779686626394,
|
| 804 |
+
"loss": 1.2773,
|
| 805 |
+
"step": 108
|
| 806 |
+
},
|
| 807 |
+
{
|
| 808 |
+
"epoch": 1.245014245014245,
|
| 809 |
+
"grad_norm": 1.9703893661499023,
|
| 810 |
+
"learning_rate": 0.0001052703133430002,
|
| 811 |
+
"loss": 1.7024,
|
| 812 |
+
"step": 109
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 1.2564102564102564,
|
| 816 |
+
"grad_norm": 1.2065763473510742,
|
| 817 |
+
"learning_rate": 0.00010256884996547639,
|
| 818 |
+
"loss": 1.7203,
|
| 819 |
+
"step": 110
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 1.2678062678062678,
|
| 823 |
+
"grad_norm": 1.4649949073791504,
|
| 824 |
+
"learning_rate": 9.988437427539152e-05,
|
| 825 |
+
"loss": 1.7926,
|
| 826 |
+
"step": 111
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 1.2792022792022792,
|
| 830 |
+
"grad_norm": 1.2466754913330078,
|
| 831 |
+
"learning_rate": 9.721784773022504e-05,
|
| 832 |
+
"loss": 1.805,
|
| 833 |
+
"step": 112
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 1.2905982905982907,
|
| 837 |
+
"grad_norm": 1.2706060409545898,
|
| 838 |
+
"learning_rate": 9.457022535888646e-05,
|
| 839 |
+
"loss": 1.4421,
|
| 840 |
+
"step": 113
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 1.301994301994302,
|
| 844 |
+
"grad_norm": 1.3075103759765625,
|
| 845 |
+
"learning_rate": 9.194245541966741e-05,
|
| 846 |
+
"loss": 1.3973,
|
| 847 |
+
"step": 114
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 1.3133903133903133,
|
| 851 |
+
"grad_norm": 1.1189782619476318,
|
| 852 |
+
"learning_rate": 8.933547906061846e-05,
|
| 853 |
+
"loss": 1.4012,
|
| 854 |
+
"step": 115
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 1.3247863247863247,
|
| 858 |
+
"grad_norm": 1.4372056722640991,
|
| 859 |
+
"learning_rate": 8.675022998247239e-05,
|
| 860 |
+
"loss": 1.4232,
|
| 861 |
+
"step": 116
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 1.3361823361823362,
|
| 865 |
+
"grad_norm": 1.2321964502334595,
|
| 866 |
+
"learning_rate": 8.418763410423521e-05,
|
| 867 |
+
"loss": 1.1983,
|
| 868 |
+
"step": 117
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 1.3475783475783476,
|
| 872 |
+
"grad_norm": 1.393195390701294,
|
| 873 |
+
"learning_rate": 8.164860923156377e-05,
|
| 874 |
+
"loss": 1.1489,
|
| 875 |
+
"step": 118
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 1.358974358974359,
|
| 879 |
+
"grad_norm": 1.1735514402389526,
|
| 880 |
+
"learning_rate": 7.913406472804938e-05,
|
| 881 |
+
"loss": 1.1197,
|
| 882 |
+
"step": 119
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 1.3703703703703702,
|
| 886 |
+
"grad_norm": 1.2319945096969604,
|
| 887 |
+
"learning_rate": 7.664490118952502e-05,
|
| 888 |
+
"loss": 1.2014,
|
| 889 |
+
"step": 120
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 1.381766381766382,
|
| 893 |
+
"grad_norm": 1.0852819681167603,
|
| 894 |
+
"learning_rate": 7.418201012151291e-05,
|
| 895 |
+
"loss": 0.957,
|
| 896 |
+
"step": 121
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 1.393162393162393,
|
| 900 |
+
"grad_norm": 1.0578720569610596,
|
| 901 |
+
"learning_rate": 7.174627361992732e-05,
|
| 902 |
+
"loss": 0.9002,
|
| 903 |
+
"step": 122
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 1.4045584045584045,
|
| 907 |
+
"grad_norm": 1.19394052028656,
|
| 908 |
+
"learning_rate": 6.933856405514818e-05,
|
| 909 |
+
"loss": 0.869,
|
| 910 |
+
"step": 123
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 1.415954415954416,
|
| 914 |
+
"grad_norm": 1.4179712533950806,
|
| 915 |
+
"learning_rate": 6.695974375957732e-05,
|
| 916 |
+
"loss": 0.8395,
|
| 917 |
+
"step": 124
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 1.4273504273504274,
|
| 921 |
+
"grad_norm": 1.5434173345565796,
|
| 922 |
+
"learning_rate": 6.461066471879014e-05,
|
| 923 |
+
"loss": 0.9276,
|
| 924 |
+
"step": 125
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 1.4273504273504274,
|
| 928 |
+
"eval_loss": 1.3488426208496094,
|
| 929 |
+
"eval_runtime": 2.8312,
|
| 930 |
+
"eval_samples_per_second": 17.661,
|
| 931 |
+
"eval_steps_per_second": 2.472,
|
| 932 |
+
"step": 125
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 1.4387464387464388,
|
| 936 |
+
"grad_norm": 1.3119511604309082,
|
| 937 |
+
"learning_rate": 6.229216826639293e-05,
|
| 938 |
+
"loss": 0.864,
|
| 939 |
+
"step": 126
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 1.45014245014245,
|
| 943 |
+
"grad_norm": 1.39320707321167,
|
| 944 |
+
"learning_rate": 6.000508478269568e-05,
|
| 945 |
+
"loss": 0.8115,
|
| 946 |
+
"step": 127
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 1.4615384615384617,
|
| 950 |
+
"grad_norm": 1.4658546447753906,
|
| 951 |
+
"learning_rate": 5.775023339730696e-05,
|
| 952 |
+
"loss": 0.7579,
|
| 953 |
+
"step": 128
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 1.4729344729344729,
|
| 957 |
+
"grad_norm": 2.2543859481811523,
|
| 958 |
+
"learning_rate": 5.552842169575929e-05,
|
| 959 |
+
"loss": 0.8667,
|
| 960 |
+
"step": 129
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 1.4843304843304843,
|
| 964 |
+
"grad_norm": 1.626423716545105,
|
| 965 |
+
"learning_rate": 5.3340445430268436e-05,
|
| 966 |
+
"loss": 1.4114,
|
| 967 |
+
"step": 130
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 1.4957264957264957,
|
| 971 |
+
"grad_norm": 1.1121342182159424,
|
| 972 |
+
"learning_rate": 5.118708823473095e-05,
|
| 973 |
+
"loss": 1.5799,
|
| 974 |
+
"step": 131
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 1.5071225071225072,
|
| 978 |
+
"grad_norm": 1.16105318069458,
|
| 979 |
+
"learning_rate": 4.906912134406216e-05,
|
| 980 |
+
"loss": 1.4849,
|
| 981 |
+
"step": 132
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 1.5185185185185186,
|
| 985 |
+
"grad_norm": 1.185447335243225,
|
| 986 |
+
"learning_rate": 4.6987303317974865e-05,
|
| 987 |
+
"loss": 1.4004,
|
| 988 |
+
"step": 133
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 1.5299145299145298,
|
| 992 |
+
"grad_norm": 1.2638546228408813,
|
| 993 |
+
"learning_rate": 4.4942379769297414e-05,
|
| 994 |
+
"loss": 1.3315,
|
| 995 |
+
"step": 134
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 1.5413105413105415,
|
| 999 |
+
"grad_norm": 1.316292405128479,
|
| 1000 |
+
"learning_rate": 4.293508309692913e-05,
|
| 1001 |
+
"loss": 1.3905,
|
| 1002 |
+
"step": 135
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 1.5527065527065527,
|
| 1006 |
+
"grad_norm": 1.37898850440979,
|
| 1007 |
+
"learning_rate": 4.096613222352843e-05,
|
| 1008 |
+
"loss": 1.2715,
|
| 1009 |
+
"step": 136
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 1.564102564102564,
|
| 1013 |
+
"grad_norm": 1.1590007543563843,
|
| 1014 |
+
"learning_rate": 3.90362323380269e-05,
|
| 1015 |
+
"loss": 1.0867,
|
| 1016 |
+
"step": 137
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 1.5754985754985755,
|
| 1020 |
+
"grad_norm": 1.10092031955719,
|
| 1021 |
+
"learning_rate": 3.714607464306281e-05,
|
| 1022 |
+
"loss": 1.0965,
|
| 1023 |
+
"step": 138
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 1.5868945868945867,
|
| 1027 |
+
"grad_norm": 2.0354859828948975,
|
| 1028 |
+
"learning_rate": 3.529633610742382e-05,
|
| 1029 |
+
"loss": 0.9744,
|
| 1030 |
+
"step": 139
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"epoch": 1.5982905982905984,
|
| 1034 |
+
"grad_norm": 1.2980939149856567,
|
| 1035 |
+
"learning_rate": 3.348767922358719e-05,
|
| 1036 |
+
"loss": 1.0778,
|
| 1037 |
+
"step": 140
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 1.6096866096866096,
|
| 1041 |
+
"grad_norm": 1.143785834312439,
|
| 1042 |
+
"learning_rate": 3.172075177044513e-05,
|
| 1043 |
+
"loss": 1.0259,
|
| 1044 |
+
"step": 141
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 1.6210826210826212,
|
| 1048 |
+
"grad_norm": 1.204784870147705,
|
| 1049 |
+
"learning_rate": 2.9996186581299824e-05,
|
| 1050 |
+
"loss": 0.9,
|
| 1051 |
+
"step": 142
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"epoch": 1.6324786324786325,
|
| 1055 |
+
"grad_norm": 1.0703641176223755,
|
| 1056 |
+
"learning_rate": 2.831460131721116e-05,
|
| 1057 |
+
"loss": 0.8159,
|
| 1058 |
+
"step": 143
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 1.6438746438746439,
|
| 1062 |
+
"grad_norm": 1.161806583404541,
|
| 1063 |
+
"learning_rate": 2.6676598245778498e-05,
|
| 1064 |
+
"loss": 0.9118,
|
| 1065 |
+
"step": 144
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 1.6552706552706553,
|
| 1069 |
+
"grad_norm": 1.3269273042678833,
|
| 1070 |
+
"learning_rate": 2.5082764025435865e-05,
|
| 1071 |
+
"loss": 1.0347,
|
| 1072 |
+
"step": 145
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 1.6666666666666665,
|
| 1076 |
+
"grad_norm": 1.4473638534545898,
|
| 1077 |
+
"learning_rate": 2.353366949533736e-05,
|
| 1078 |
+
"loss": 1.0452,
|
| 1079 |
+
"step": 146
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 1.6780626780626782,
|
| 1083 |
+
"grad_norm": 1.5314830541610718,
|
| 1084 |
+
"learning_rate": 2.20298694709085e-05,
|
| 1085 |
+
"loss": 0.888,
|
| 1086 |
+
"step": 147
|
| 1087 |
+
},
|
| 1088 |
+
{
|
| 1089 |
+
"epoch": 1.6894586894586894,
|
| 1090 |
+
"grad_norm": 1.3223233222961426,
|
| 1091 |
+
"learning_rate": 2.0571902545136565e-05,
|
| 1092 |
+
"loss": 0.7846,
|
| 1093 |
+
"step": 148
|
| 1094 |
+
},
|
| 1095 |
+
{
|
| 1096 |
+
"epoch": 1.7008547008547008,
|
| 1097 |
+
"grad_norm": 1.436808705329895,
|
| 1098 |
+
"learning_rate": 1.9160290895670937e-05,
|
| 1099 |
+
"loss": 0.6303,
|
| 1100 |
+
"step": 149
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 1.7122507122507122,
|
| 1104 |
+
"grad_norm": 2.25252103805542,
|
| 1105 |
+
"learning_rate": 1.7795540097802668e-05,
|
| 1106 |
+
"loss": 1.0496,
|
| 1107 |
+
"step": 150
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 1.7122507122507122,
|
| 1111 |
+
"eval_loss": 1.2822918891906738,
|
| 1112 |
+
"eval_runtime": 2.5321,
|
| 1113 |
+
"eval_samples_per_second": 19.747,
|
| 1114 |
+
"eval_steps_per_second": 2.765,
|
| 1115 |
+
"step": 150
|
| 1116 |
}
|
| 1117 |
],
|
| 1118 |
"logging_steps": 1,
|
|
|
|
| 1141 |
"attributes": {}
|
| 1142 |
}
|
| 1143 |
},
|
| 1144 |
+
"total_flos": 3.669377994561946e+16,
|
| 1145 |
"train_batch_size": 8,
|
| 1146 |
"trial_name": null,
|
| 1147 |
"trial_params": null
|