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 767856
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:68ce69cbbb7eda1684f8e4b647cbf1ca20f612aa80bd5a7622634a561ea86cde
|
| 3 |
size 767856
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1601338
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9b88c0ce4ccb86cf3672fe1d79a86a918a6b76333503be58bcb3f59c7779c8ef
|
| 3 |
size 1601338
|
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 14512
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cc3a31a11ca5cfbebd4465844ec0aac986b9c7664d8e19621ce7f146bef85200
|
| 3 |
size 14512
|
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 14512
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4e98d969b50546a6457ae05f133a63e9a444a80e20591144e4ff1d00857620af
|
| 3 |
size 14512
|
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 sha256:128efb8a98caf4df21dfdfcef7946b561e6794b7432b36b07a7c31e3fed817b6
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 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": 40.455,
|
| 732 |
"eval_steps_per_second": 10.174,
|
| 733 |
"step": 100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 734 |
}
|
| 735 |
],
|
| 736 |
"logging_steps": 1,
|
|
@@ -750,7 +1108,7 @@
|
|
| 750 |
"attributes": {}
|
| 751 |
}
|
| 752 |
},
|
| 753 |
-
"total_flos":
|
| 754 |
"train_batch_size": 2,
|
| 755 |
"trial_name": null,
|
| 756 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.7580543272267846,
|
| 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": 40.455,
|
| 732 |
"eval_steps_per_second": 10.174,
|
| 733 |
"step": 100
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 0.5104232469993683,
|
| 737 |
+
"grad_norm": 1.6569247245788574,
|
| 738 |
+
"learning_rate": 7.312691451204178e-05,
|
| 739 |
+
"loss": 8.9028,
|
| 740 |
+
"step": 101
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 0.5154769425142135,
|
| 744 |
+
"grad_norm": 1.122266173362732,
|
| 745 |
+
"learning_rate": 7.217431291229067e-05,
|
| 746 |
+
"loss": 8.8732,
|
| 747 |
+
"step": 102
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.5205306380290587,
|
| 751 |
+
"grad_norm": 0.9974745512008667,
|
| 752 |
+
"learning_rate": 7.121158389495186e-05,
|
| 753 |
+
"loss": 8.9486,
|
| 754 |
+
"step": 103
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 0.525584333543904,
|
| 758 |
+
"grad_norm": 1.1596142053604126,
|
| 759 |
+
"learning_rate": 7.023916715611969e-05,
|
| 760 |
+
"loss": 8.7343,
|
| 761 |
+
"step": 104
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.5306380290587492,
|
| 765 |
+
"grad_norm": 1.1720257997512817,
|
| 766 |
+
"learning_rate": 6.925750681644953e-05,
|
| 767 |
+
"loss": 8.7557,
|
| 768 |
+
"step": 105
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 0.5356917245735945,
|
| 772 |
+
"grad_norm": 1.1216539144515991,
|
| 773 |
+
"learning_rate": 6.826705121831976e-05,
|
| 774 |
+
"loss": 8.7399,
|
| 775 |
+
"step": 106
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 0.5407454200884396,
|
| 779 |
+
"grad_norm": 1.0456095933914185,
|
| 780 |
+
"learning_rate": 6.726825272106538e-05,
|
| 781 |
+
"loss": 8.8259,
|
| 782 |
+
"step": 107
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 0.5457991156032849,
|
| 786 |
+
"grad_norm": 1.1412315368652344,
|
| 787 |
+
"learning_rate": 6.626156749437736e-05,
|
| 788 |
+
"loss": 8.7779,
|
| 789 |
+
"step": 108
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.5508528111181301,
|
| 793 |
+
"grad_norm": 1.144679069519043,
|
| 794 |
+
"learning_rate": 6.524745530996137e-05,
|
| 795 |
+
"loss": 8.7377,
|
| 796 |
+
"step": 109
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 0.5559065066329754,
|
| 800 |
+
"grad_norm": 1.1518090963363647,
|
| 801 |
+
"learning_rate": 6.422637933155162e-05,
|
| 802 |
+
"loss": 8.5458,
|
| 803 |
+
"step": 110
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 0.5609602021478206,
|
| 807 |
+
"grad_norm": 1.0327682495117188,
|
| 808 |
+
"learning_rate": 6.319880590337549e-05,
|
| 809 |
+
"loss": 8.7034,
|
| 810 |
+
"step": 111
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 0.5660138976626659,
|
| 814 |
+
"grad_norm": 0.9186742901802063,
|
| 815 |
+
"learning_rate": 6.216520433716545e-05,
|
| 816 |
+
"loss": 8.7843,
|
| 817 |
+
"step": 112
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 0.5710675931775111,
|
| 821 |
+
"grad_norm": 0.9329281449317932,
|
| 822 |
+
"learning_rate": 6.112604669781572e-05,
|
| 823 |
+
"loss": 8.7471,
|
| 824 |
+
"step": 113
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 0.5761212886923562,
|
| 828 |
+
"grad_norm": 1.0598094463348389,
|
| 829 |
+
"learning_rate": 6.008180758778167e-05,
|
| 830 |
+
"loss": 8.6698,
|
| 831 |
+
"step": 114
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 0.5811749842072015,
|
| 835 |
+
"grad_norm": 1.1156866550445557,
|
| 836 |
+
"learning_rate": 5.903296393031995e-05,
|
| 837 |
+
"loss": 8.6572,
|
| 838 |
+
"step": 115
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 0.5862286797220467,
|
| 842 |
+
"grad_norm": 1.0410085916519165,
|
| 843 |
+
"learning_rate": 5.7979994751668964e-05,
|
| 844 |
+
"loss": 8.505,
|
| 845 |
+
"step": 116
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 0.591282375236892,
|
| 849 |
+
"grad_norm": 1.126705288887024,
|
| 850 |
+
"learning_rate": 5.69233809622687e-05,
|
| 851 |
+
"loss": 8.7812,
|
| 852 |
+
"step": 117
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 0.5963360707517372,
|
| 856 |
+
"grad_norm": 1.1464685201644897,
|
| 857 |
+
"learning_rate": 5.58636051371201e-05,
|
| 858 |
+
"loss": 8.5813,
|
| 859 |
+
"step": 118
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 0.6013897662665825,
|
| 863 |
+
"grad_norm": 1.146330714225769,
|
| 864 |
+
"learning_rate": 5.480115129538409e-05,
|
| 865 |
+
"loss": 8.4167,
|
| 866 |
+
"step": 119
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 0.6064434617814277,
|
| 870 |
+
"grad_norm": 1.079012393951416,
|
| 871 |
+
"learning_rate": 5.373650467932122e-05,
|
| 872 |
+
"loss": 8.5148,
|
| 873 |
+
"step": 120
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.6114971572962729,
|
| 877 |
+
"grad_norm": 1.281872272491455,
|
| 878 |
+
"learning_rate": 5.267015153267245e-05,
|
| 879 |
+
"loss": 8.4182,
|
| 880 |
+
"step": 121
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 0.6165508528111181,
|
| 884 |
+
"grad_norm": 1.1823097467422485,
|
| 885 |
+
"learning_rate": 5.1602578878582776e-05,
|
| 886 |
+
"loss": 8.6779,
|
| 887 |
+
"step": 122
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 0.6216045483259633,
|
| 891 |
+
"grad_norm": 1.620906114578247,
|
| 892 |
+
"learning_rate": 5.053427429716867e-05,
|
| 893 |
+
"loss": 8.8053,
|
| 894 |
+
"step": 123
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 0.6266582438408086,
|
| 898 |
+
"grad_norm": 1.704972505569458,
|
| 899 |
+
"learning_rate": 4.9465725702831346e-05,
|
| 900 |
+
"loss": 8.9209,
|
| 901 |
+
"step": 124
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 0.6317119393556538,
|
| 905 |
+
"grad_norm": 2.0735604763031006,
|
| 906 |
+
"learning_rate": 4.839742112141724e-05,
|
| 907 |
+
"loss": 8.7427,
|
| 908 |
+
"step": 125
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 0.6367656348704991,
|
| 912 |
+
"grad_norm": 1.3401007652282715,
|
| 913 |
+
"learning_rate": 4.732984846732755e-05,
|
| 914 |
+
"loss": 8.7623,
|
| 915 |
+
"step": 126
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 0.6418193303853443,
|
| 919 |
+
"grad_norm": 1.1091989278793335,
|
| 920 |
+
"learning_rate": 4.626349532067879e-05,
|
| 921 |
+
"loss": 8.7094,
|
| 922 |
+
"step": 127
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 0.6468730259001895,
|
| 926 |
+
"grad_norm": 1.1784418821334839,
|
| 927 |
+
"learning_rate": 4.5198848704615914e-05,
|
| 928 |
+
"loss": 8.5668,
|
| 929 |
+
"step": 128
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 0.6519267214150347,
|
| 933 |
+
"grad_norm": 1.323731541633606,
|
| 934 |
+
"learning_rate": 4.4136394862879914e-05,
|
| 935 |
+
"loss": 8.4429,
|
| 936 |
+
"step": 129
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 0.65698041692988,
|
| 940 |
+
"grad_norm": 0.8502984642982483,
|
| 941 |
+
"learning_rate": 4.307661903773129e-05,
|
| 942 |
+
"loss": 8.7092,
|
| 943 |
+
"step": 130
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 0.6620341124447252,
|
| 947 |
+
"grad_norm": 1.1920008659362793,
|
| 948 |
+
"learning_rate": 4.2020005248331054e-05,
|
| 949 |
+
"loss": 8.4987,
|
| 950 |
+
"step": 131
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 0.6670878079595705,
|
| 954 |
+
"grad_norm": 1.0251978635787964,
|
| 955 |
+
"learning_rate": 4.096703606968006e-05,
|
| 956 |
+
"loss": 8.6157,
|
| 957 |
+
"step": 132
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 0.6721415034744157,
|
| 961 |
+
"grad_norm": 1.0642647743225098,
|
| 962 |
+
"learning_rate": 3.991819241221835e-05,
|
| 963 |
+
"loss": 8.4535,
|
| 964 |
+
"step": 133
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 0.677195198989261,
|
| 968 |
+
"grad_norm": 1.3170267343521118,
|
| 969 |
+
"learning_rate": 3.887395330218429e-05,
|
| 970 |
+
"loss": 8.4171,
|
| 971 |
+
"step": 134
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 0.6822488945041061,
|
| 975 |
+
"grad_norm": 1.0994036197662354,
|
| 976 |
+
"learning_rate": 3.783479566283457e-05,
|
| 977 |
+
"loss": 8.6795,
|
| 978 |
+
"step": 135
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 0.6873025900189513,
|
| 982 |
+
"grad_norm": 1.2040021419525146,
|
| 983 |
+
"learning_rate": 3.680119409662452e-05,
|
| 984 |
+
"loss": 8.5518,
|
| 985 |
+
"step": 136
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 0.6923562855337966,
|
| 989 |
+
"grad_norm": 1.1834477186203003,
|
| 990 |
+
"learning_rate": 3.5773620668448384e-05,
|
| 991 |
+
"loss": 8.6813,
|
| 992 |
+
"step": 137
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 0.6974099810486418,
|
| 996 |
+
"grad_norm": 0.9281287789344788,
|
| 997 |
+
"learning_rate": 3.4752544690038647e-05,
|
| 998 |
+
"loss": 8.535,
|
| 999 |
+
"step": 138
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.7024636765634871,
|
| 1003 |
+
"grad_norm": 1.0375516414642334,
|
| 1004 |
+
"learning_rate": 3.373843250562265e-05,
|
| 1005 |
+
"loss": 8.5263,
|
| 1006 |
+
"step": 139
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 0.7075173720783323,
|
| 1010 |
+
"grad_norm": 0.9735792279243469,
|
| 1011 |
+
"learning_rate": 3.273174727893463e-05,
|
| 1012 |
+
"loss": 8.4796,
|
| 1013 |
+
"step": 140
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 0.7125710675931776,
|
| 1017 |
+
"grad_norm": 1.0425305366516113,
|
| 1018 |
+
"learning_rate": 3.173294878168025e-05,
|
| 1019 |
+
"loss": 8.4304,
|
| 1020 |
+
"step": 141
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 0.7176247631080227,
|
| 1024 |
+
"grad_norm": 1.076398491859436,
|
| 1025 |
+
"learning_rate": 3.074249318355046e-05,
|
| 1026 |
+
"loss": 8.4417,
|
| 1027 |
+
"step": 142
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 0.722678458622868,
|
| 1031 |
+
"grad_norm": 1.0114437341690063,
|
| 1032 |
+
"learning_rate": 2.976083284388031e-05,
|
| 1033 |
+
"loss": 8.3947,
|
| 1034 |
+
"step": 143
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 0.7277321541377132,
|
| 1038 |
+
"grad_norm": 1.0746240615844727,
|
| 1039 |
+
"learning_rate": 2.8788416105048122e-05,
|
| 1040 |
+
"loss": 8.3048,
|
| 1041 |
+
"step": 144
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.7327858496525584,
|
| 1045 |
+
"grad_norm": 1.0370659828186035,
|
| 1046 |
+
"learning_rate": 2.7825687087709328e-05,
|
| 1047 |
+
"loss": 8.3032,
|
| 1048 |
+
"step": 145
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 0.7378395451674037,
|
| 1052 |
+
"grad_norm": 1.1819736957550049,
|
| 1053 |
+
"learning_rate": 2.687308548795825e-05,
|
| 1054 |
+
"loss": 8.3238,
|
| 1055 |
+
"step": 146
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 0.7428932406822489,
|
| 1059 |
+
"grad_norm": 1.3127453327178955,
|
| 1060 |
+
"learning_rate": 2.5931046376510877e-05,
|
| 1061 |
+
"loss": 8.5473,
|
| 1062 |
+
"step": 147
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 0.7479469361970941,
|
| 1066 |
+
"grad_norm": 1.3957887887954712,
|
| 1067 |
+
"learning_rate": 2.500000000000001e-05,
|
| 1068 |
+
"loss": 8.4965,
|
| 1069 |
+
"step": 148
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 0.7530006317119393,
|
| 1073 |
+
"grad_norm": 1.6841113567352295,
|
| 1074 |
+
"learning_rate": 2.4080371584473748e-05,
|
| 1075 |
+
"loss": 8.5345,
|
| 1076 |
+
"step": 149
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 0.7580543272267846,
|
| 1080 |
+
"grad_norm": 2.3189311027526855,
|
| 1081 |
+
"learning_rate": 2.317258114118686e-05,
|
| 1082 |
+
"loss": 8.6134,
|
| 1083 |
+
"step": 150
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 0.7580543272267846,
|
| 1087 |
+
"eval_loss": 8.470457077026367,
|
| 1088 |
+
"eval_runtime": 8.309,
|
| 1089 |
+
"eval_samples_per_second": 40.198,
|
| 1090 |
+
"eval_steps_per_second": 10.11,
|
| 1091 |
+
"step": 150
|
| 1092 |
}
|
| 1093 |
],
|
| 1094 |
"logging_steps": 1,
|
|
|
|
| 1108 |
"attributes": {}
|
| 1109 |
}
|
| 1110 |
},
|
| 1111 |
+
"total_flos": 169820248080384.0,
|
| 1112 |
"train_batch_size": 2,
|
| 1113 |
"trial_name": null,
|
| 1114 |
"trial_params": null
|