Commit
•
c7b0544
1
Parent(s):
9429c9d
Training in progress, step 1500
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +363 -3
- pytorch_model.bin +1 -1
- runs/Feb08_07-03-50_74bc69b4becb/events.out.tfevents.1675839843.74bc69b4becb.290.8 +2 -2
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4115013
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:67681c79cd214ed9a8ee42c881c73d19f1c39d67a78279d301dd38994ad30568
|
| 3 |
size 4115013
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2329702453
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c1d3b0d701f16fe2a1ac911c75f337bfda79fe2f7f898cd1baabb210413c7dba
|
| 3 |
size 2329702453
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14575
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5f08b7042b3265d650ddd09433dd030c04a52d87e147dd0a8cbaf2372dce6fce
|
| 3 |
size 14575
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 627
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c08a9482e48e6ef3973131ed0b8d44170a3c271bf2d7cf6a402ee43fb89e77ae
|
| 3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -726,11 +726,371 @@
|
|
| 726 |
"eval_samples_per_second": 0.244,
|
| 727 |
"eval_steps_per_second": 0.244,
|
| 728 |
"step": 1000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 729 |
}
|
| 730 |
],
|
| 731 |
"max_steps": 3542,
|
| 732 |
"num_train_epochs": 7,
|
| 733 |
-
"total_flos":
|
| 734 |
"trial_name": null,
|
| 735 |
"trial_params": null
|
| 736 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.962643323881149,
|
| 5 |
+
"global_step": 1500,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 726 |
"eval_samples_per_second": 0.244,
|
| 727 |
"eval_steps_per_second": 0.244,
|
| 728 |
"step": 1000
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 1.99,
|
| 732 |
+
"learning_rate": 0.0003667439165701043,
|
| 733 |
+
"loss": 0.1462,
|
| 734 |
+
"step": 1010
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 2.02,
|
| 738 |
+
"learning_rate": 0.0003652954808806489,
|
| 739 |
+
"loss": 0.1944,
|
| 740 |
+
"step": 1020
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 2.04,
|
| 744 |
+
"learning_rate": 0.0003638470451911935,
|
| 745 |
+
"loss": 0.2296,
|
| 746 |
+
"step": 1030
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 2.06,
|
| 750 |
+
"learning_rate": 0.00036239860950173814,
|
| 751 |
+
"loss": 0.2446,
|
| 752 |
+
"step": 1040
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 2.07,
|
| 756 |
+
"learning_rate": 0.00036095017381228273,
|
| 757 |
+
"loss": 0.1448,
|
| 758 |
+
"step": 1050
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 2.09,
|
| 762 |
+
"learning_rate": 0.0003595017381228273,
|
| 763 |
+
"loss": 0.1507,
|
| 764 |
+
"step": 1060
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 2.11,
|
| 768 |
+
"learning_rate": 0.00035805330243337196,
|
| 769 |
+
"loss": 0.1636,
|
| 770 |
+
"step": 1070
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 2.13,
|
| 774 |
+
"learning_rate": 0.00035660486674391655,
|
| 775 |
+
"loss": 0.1909,
|
| 776 |
+
"step": 1080
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 2.15,
|
| 780 |
+
"learning_rate": 0.0003551564310544612,
|
| 781 |
+
"loss": 0.1895,
|
| 782 |
+
"step": 1090
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 2.17,
|
| 786 |
+
"learning_rate": 0.0003537079953650058,
|
| 787 |
+
"loss": 0.2663,
|
| 788 |
+
"step": 1100
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 2.17,
|
| 792 |
+
"eval_loss": 0.9002671241760254,
|
| 793 |
+
"eval_rouge1": 0.07948717948717948,
|
| 794 |
+
"eval_rouge2": 0.06779220779220778,
|
| 795 |
+
"eval_rougeL": 0.08782051282051281,
|
| 796 |
+
"eval_rougeLsum": 0.08333333333333333,
|
| 797 |
+
"eval_runtime": 84.9078,
|
| 798 |
+
"eval_samples_per_second": 0.236,
|
| 799 |
+
"eval_steps_per_second": 0.236,
|
| 800 |
+
"step": 1100
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 2.19,
|
| 804 |
+
"learning_rate": 0.0003522595596755504,
|
| 805 |
+
"loss": 0.1672,
|
| 806 |
+
"step": 1110
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 2.21,
|
| 810 |
+
"learning_rate": 0.00035081112398609507,
|
| 811 |
+
"loss": 0.1909,
|
| 812 |
+
"step": 1120
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 2.23,
|
| 816 |
+
"learning_rate": 0.00034936268829663966,
|
| 817 |
+
"loss": 0.1675,
|
| 818 |
+
"step": 1130
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 2.25,
|
| 822 |
+
"learning_rate": 0.00034791425260718425,
|
| 823 |
+
"loss": 0.2636,
|
| 824 |
+
"step": 1140
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 2.27,
|
| 828 |
+
"learning_rate": 0.0003464658169177289,
|
| 829 |
+
"loss": 0.2119,
|
| 830 |
+
"step": 1150
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 2.29,
|
| 834 |
+
"learning_rate": 0.0003450173812282735,
|
| 835 |
+
"loss": 0.2114,
|
| 836 |
+
"step": 1160
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 2.31,
|
| 840 |
+
"learning_rate": 0.0003435689455388181,
|
| 841 |
+
"loss": 0.1456,
|
| 842 |
+
"step": 1170
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 2.33,
|
| 846 |
+
"learning_rate": 0.0003421205098493627,
|
| 847 |
+
"loss": 0.1993,
|
| 848 |
+
"step": 1180
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 2.35,
|
| 852 |
+
"learning_rate": 0.0003406720741599073,
|
| 853 |
+
"loss": 0.1467,
|
| 854 |
+
"step": 1190
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 2.37,
|
| 858 |
+
"learning_rate": 0.0003392236384704519,
|
| 859 |
+
"loss": 0.237,
|
| 860 |
+
"step": 1200
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 2.37,
|
| 864 |
+
"eval_loss": 0.9139176607131958,
|
| 865 |
+
"eval_rouge1": 0.19904761904761903,
|
| 866 |
+
"eval_rouge2": 0.10285714285714284,
|
| 867 |
+
"eval_rougeL": 0.19511904761904764,
|
| 868 |
+
"eval_rougeLsum": 0.20619047619047615,
|
| 869 |
+
"eval_runtime": 85.9903,
|
| 870 |
+
"eval_samples_per_second": 0.233,
|
| 871 |
+
"eval_steps_per_second": 0.233,
|
| 872 |
+
"step": 1200
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 2.39,
|
| 876 |
+
"learning_rate": 0.00033777520278099654,
|
| 877 |
+
"loss": 0.1996,
|
| 878 |
+
"step": 1210
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 2.41,
|
| 882 |
+
"learning_rate": 0.00033632676709154113,
|
| 883 |
+
"loss": 0.1725,
|
| 884 |
+
"step": 1220
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 2.43,
|
| 888 |
+
"learning_rate": 0.0003348783314020857,
|
| 889 |
+
"loss": 0.2089,
|
| 890 |
+
"step": 1230
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 2.45,
|
| 894 |
+
"learning_rate": 0.00033342989571263036,
|
| 895 |
+
"loss": 0.183,
|
| 896 |
+
"step": 1240
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 2.47,
|
| 900 |
+
"learning_rate": 0.00033198146002317495,
|
| 901 |
+
"loss": 0.1631,
|
| 902 |
+
"step": 1250
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 2.49,
|
| 906 |
+
"learning_rate": 0.00033053302433371954,
|
| 907 |
+
"loss": 0.1889,
|
| 908 |
+
"step": 1260
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 2.51,
|
| 912 |
+
"learning_rate": 0.00032908458864426424,
|
| 913 |
+
"loss": 0.172,
|
| 914 |
+
"step": 1270
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 2.53,
|
| 918 |
+
"learning_rate": 0.00032763615295480883,
|
| 919 |
+
"loss": 0.1236,
|
| 920 |
+
"step": 1280
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 2.55,
|
| 924 |
+
"learning_rate": 0.0003261877172653534,
|
| 925 |
+
"loss": 0.1682,
|
| 926 |
+
"step": 1290
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 2.57,
|
| 930 |
+
"learning_rate": 0.00032473928157589806,
|
| 931 |
+
"loss": 0.2019,
|
| 932 |
+
"step": 1300
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 2.57,
|
| 936 |
+
"eval_loss": 0.920964241027832,
|
| 937 |
+
"eval_rouge1": 0.11282051282051282,
|
| 938 |
+
"eval_rouge2": 0.03636363636363636,
|
| 939 |
+
"eval_rougeL": 0.1128205128205128,
|
| 940 |
+
"eval_rougeLsum": 0.11607142857142858,
|
| 941 |
+
"eval_runtime": 82.9262,
|
| 942 |
+
"eval_samples_per_second": 0.241,
|
| 943 |
+
"eval_steps_per_second": 0.241,
|
| 944 |
+
"step": 1300
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 2.59,
|
| 948 |
+
"learning_rate": 0.00032329084588644265,
|
| 949 |
+
"loss": 0.1681,
|
| 950 |
+
"step": 1310
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 2.61,
|
| 954 |
+
"learning_rate": 0.00032184241019698724,
|
| 955 |
+
"loss": 0.2372,
|
| 956 |
+
"step": 1320
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 2.63,
|
| 960 |
+
"learning_rate": 0.0003203939745075319,
|
| 961 |
+
"loss": 0.1343,
|
| 962 |
+
"step": 1330
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 2.65,
|
| 966 |
+
"learning_rate": 0.0003189455388180765,
|
| 967 |
+
"loss": 0.2125,
|
| 968 |
+
"step": 1340
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 2.67,
|
| 972 |
+
"learning_rate": 0.0003174971031286211,
|
| 973 |
+
"loss": 0.2217,
|
| 974 |
+
"step": 1350
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 2.69,
|
| 978 |
+
"learning_rate": 0.0003160486674391657,
|
| 979 |
+
"loss": 0.1542,
|
| 980 |
+
"step": 1360
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 2.71,
|
| 984 |
+
"learning_rate": 0.0003146002317497103,
|
| 985 |
+
"loss": 0.171,
|
| 986 |
+
"step": 1370
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 2.73,
|
| 990 |
+
"learning_rate": 0.00031315179606025494,
|
| 991 |
+
"loss": 0.1808,
|
| 992 |
+
"step": 1380
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 2.75,
|
| 996 |
+
"learning_rate": 0.00031170336037079953,
|
| 997 |
+
"loss": 0.1423,
|
| 998 |
+
"step": 1390
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 2.77,
|
| 1002 |
+
"learning_rate": 0.0003102549246813441,
|
| 1003 |
+
"loss": 0.1794,
|
| 1004 |
+
"step": 1400
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 2.77,
|
| 1008 |
+
"eval_loss": 0.9037507772445679,
|
| 1009 |
+
"eval_rouge1": 0.11666666666666667,
|
| 1010 |
+
"eval_rouge2": 0.08636363636363635,
|
| 1011 |
+
"eval_rougeL": 0.11833333333333333,
|
| 1012 |
+
"eval_rougeLsum": 0.12064102564102563,
|
| 1013 |
+
"eval_runtime": 84.5851,
|
| 1014 |
+
"eval_samples_per_second": 0.236,
|
| 1015 |
+
"eval_steps_per_second": 0.236,
|
| 1016 |
+
"step": 1400
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 2.79,
|
| 1020 |
+
"learning_rate": 0.00030880648899188877,
|
| 1021 |
+
"loss": 0.2313,
|
| 1022 |
+
"step": 1410
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 2.8,
|
| 1026 |
+
"learning_rate": 0.00030735805330243336,
|
| 1027 |
+
"loss": 0.1548,
|
| 1028 |
+
"step": 1420
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 2.82,
|
| 1032 |
+
"learning_rate": 0.000305909617612978,
|
| 1033 |
+
"loss": 0.2318,
|
| 1034 |
+
"step": 1430
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 2.84,
|
| 1038 |
+
"learning_rate": 0.00030446118192352264,
|
| 1039 |
+
"loss": 0.1959,
|
| 1040 |
+
"step": 1440
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 2.86,
|
| 1044 |
+
"learning_rate": 0.00030301274623406723,
|
| 1045 |
+
"loss": 0.1438,
|
| 1046 |
+
"step": 1450
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 2.88,
|
| 1050 |
+
"learning_rate": 0.0003015643105446118,
|
| 1051 |
+
"loss": 0.1953,
|
| 1052 |
+
"step": 1460
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 2.9,
|
| 1056 |
+
"learning_rate": 0.00030011587485515647,
|
| 1057 |
+
"loss": 0.1542,
|
| 1058 |
+
"step": 1470
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 2.92,
|
| 1062 |
+
"learning_rate": 0.00029866743916570106,
|
| 1063 |
+
"loss": 0.1693,
|
| 1064 |
+
"step": 1480
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 2.94,
|
| 1068 |
+
"learning_rate": 0.00029721900347624565,
|
| 1069 |
+
"loss": 0.1836,
|
| 1070 |
+
"step": 1490
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 2.96,
|
| 1074 |
+
"learning_rate": 0.0002957705677867903,
|
| 1075 |
+
"loss": 0.1847,
|
| 1076 |
+
"step": 1500
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 2.96,
|
| 1080 |
+
"eval_loss": 0.8892697095870972,
|
| 1081 |
+
"eval_rouge1": 0.14335664335664336,
|
| 1082 |
+
"eval_rouge2": 0.13131313131313133,
|
| 1083 |
+
"eval_rougeL": 0.14375624375624377,
|
| 1084 |
+
"eval_rougeLsum": 0.14725274725274726,
|
| 1085 |
+
"eval_runtime": 86.985,
|
| 1086 |
+
"eval_samples_per_second": 0.23,
|
| 1087 |
+
"eval_steps_per_second": 0.23,
|
| 1088 |
+
"step": 1500
|
| 1089 |
}
|
| 1090 |
],
|
| 1091 |
"max_steps": 3542,
|
| 1092 |
"num_train_epochs": 7,
|
| 1093 |
+
"total_flos": 3.644099786288333e+16,
|
| 1094 |
"trial_name": null,
|
| 1095 |
"trial_params": null
|
| 1096 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2329702453
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c1d3b0d701f16fe2a1ac911c75f337bfda79fe2f7f898cd1baabb210413c7dba
|
| 3 |
size 2329702453
|
runs/Feb08_07-03-50_74bc69b4becb/events.out.tfevents.1675839843.74bc69b4becb.290.8
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f8194d28430976b9d808ff3690e18217a68d80fd2f3d19f3bcfe785482800df6
|
| 3 |
+
size 24674
|