End of training
Browse files- all_results.json +11 -11
- eval_results.json +7 -7
- train_results.json +5 -5
- trainer_state.json +482 -14
all_results.json
CHANGED
|
@@ -1,15 +1,15 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_bleu":
|
| 4 |
-
"eval_gen_len":
|
| 5 |
-
"eval_loss": 0.
|
| 6 |
-
"eval_runtime":
|
| 7 |
"eval_samples": 12422,
|
| 8 |
-
"eval_samples_per_second": 3.
|
| 9 |
-
"eval_steps_per_second": 0.
|
| 10 |
-
"train_loss":
|
| 11 |
-
"train_runtime":
|
| 12 |
"train_samples": 62107,
|
| 13 |
-
"train_samples_per_second":
|
| 14 |
-
"train_steps_per_second": 0.
|
| 15 |
}
|
| 1 |
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"eval_bleu": 36.7184,
|
| 4 |
+
"eval_gen_len": 64.6249,
|
| 5 |
+
"eval_loss": 0.6334519386291504,
|
| 6 |
+
"eval_runtime": 3498.0158,
|
| 7 |
"eval_samples": 12422,
|
| 8 |
+
"eval_samples_per_second": 3.551,
|
| 9 |
+
"eval_steps_per_second": 0.222,
|
| 10 |
+
"train_loss": 0.3320594994939522,
|
| 11 |
+
"train_runtime": 31593.7732,
|
| 12 |
"train_samples": 62107,
|
| 13 |
+
"train_samples_per_second": 9.829,
|
| 14 |
+
"train_steps_per_second": 0.614
|
| 15 |
}
|
eval_results.json
CHANGED
|
@@ -1,10 +1,10 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_bleu":
|
| 4 |
-
"eval_gen_len":
|
| 5 |
-
"eval_loss": 0.
|
| 6 |
-
"eval_runtime":
|
| 7 |
"eval_samples": 12422,
|
| 8 |
-
"eval_samples_per_second": 3.
|
| 9 |
-
"eval_steps_per_second": 0.
|
| 10 |
}
|
| 1 |
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"eval_bleu": 36.7184,
|
| 4 |
+
"eval_gen_len": 64.6249,
|
| 5 |
+
"eval_loss": 0.6334519386291504,
|
| 6 |
+
"eval_runtime": 3498.0158,
|
| 7 |
"eval_samples": 12422,
|
| 8 |
+
"eval_samples_per_second": 3.551,
|
| 9 |
+
"eval_steps_per_second": 0.222
|
| 10 |
}
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"train_loss":
|
| 4 |
-
"train_runtime":
|
| 5 |
"train_samples": 62107,
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
| 1 |
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"train_loss": 0.3320594994939522,
|
| 4 |
+
"train_runtime": 31593.7732,
|
| 5 |
"train_samples": 62107,
|
| 6 |
+
"train_samples_per_second": 9.829,
|
| 7 |
+
"train_steps_per_second": 0.614
|
| 8 |
}
|
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,
|
|
@@ -699,23 +699,491 @@
|
|
| 699 |
},
|
| 700 |
{
|
| 701 |
"epoch": 2.99,
|
| 702 |
-
"learning_rate":
|
| 703 |
-
"loss": 0.
|
| 704 |
"step": 11600
|
| 705 |
},
|
| 706 |
{
|
| 707 |
-
"epoch": 3.
|
| 708 |
-
"
|
| 709 |
-
"
|
| 710 |
-
"
|
| 711 |
-
|
| 712 |
-
|
| 713 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 714 |
}
|
| 715 |
],
|
| 716 |
-
"max_steps":
|
| 717 |
-
"num_train_epochs":
|
| 718 |
-
"total_flos":
|
| 719 |
"trial_name": null,
|
| 720 |
"trial_params": null
|
| 721 |
}
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"global_step": 19410,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 699 |
},
|
| 700 |
{
|
| 701 |
"epoch": 2.99,
|
| 702 |
+
"learning_rate": 2.0118495620814015e-05,
|
| 703 |
+
"loss": 0.8823,
|
| 704 |
"step": 11600
|
| 705 |
},
|
| 706 |
{
|
| 707 |
+
"epoch": 3.01,
|
| 708 |
+
"learning_rate": 1.9860896445131376e-05,
|
| 709 |
+
"loss": 0.8469,
|
| 710 |
+
"step": 11700
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 3.04,
|
| 714 |
+
"learning_rate": 1.960329726944874e-05,
|
| 715 |
+
"loss": 0.8762,
|
| 716 |
+
"step": 11800
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 3.07,
|
| 720 |
+
"learning_rate": 1.93456980937661e-05,
|
| 721 |
+
"loss": 0.8434,
|
| 722 |
+
"step": 11900
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 3.09,
|
| 726 |
+
"learning_rate": 1.9088098918083462e-05,
|
| 727 |
+
"loss": 0.856,
|
| 728 |
+
"step": 12000
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 3.12,
|
| 732 |
+
"learning_rate": 1.8830499742400827e-05,
|
| 733 |
+
"loss": 0.8453,
|
| 734 |
+
"step": 12100
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 3.14,
|
| 738 |
+
"learning_rate": 1.8572900566718188e-05,
|
| 739 |
+
"loss": 0.8447,
|
| 740 |
+
"step": 12200
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 3.17,
|
| 744 |
+
"learning_rate": 1.831530139103555e-05,
|
| 745 |
+
"loss": 0.8621,
|
| 746 |
+
"step": 12300
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 3.19,
|
| 750 |
+
"learning_rate": 1.8057702215352913e-05,
|
| 751 |
+
"loss": 0.8375,
|
| 752 |
+
"step": 12400
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 3.22,
|
| 756 |
+
"learning_rate": 1.7800103039670274e-05,
|
| 757 |
+
"loss": 0.8614,
|
| 758 |
+
"step": 12500
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 3.25,
|
| 762 |
+
"learning_rate": 1.7542503863987635e-05,
|
| 763 |
+
"loss": 0.8449,
|
| 764 |
+
"step": 12600
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 3.27,
|
| 768 |
+
"learning_rate": 1.7284904688305e-05,
|
| 769 |
+
"loss": 0.8578,
|
| 770 |
+
"step": 12700
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 3.3,
|
| 774 |
+
"learning_rate": 1.702730551262236e-05,
|
| 775 |
+
"loss": 0.8627,
|
| 776 |
+
"step": 12800
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 3.32,
|
| 780 |
+
"learning_rate": 1.676970633693972e-05,
|
| 781 |
+
"loss": 0.8396,
|
| 782 |
+
"step": 12900
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 3.35,
|
| 786 |
+
"learning_rate": 1.6512107161257085e-05,
|
| 787 |
+
"loss": 0.8391,
|
| 788 |
+
"step": 13000
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 3.37,
|
| 792 |
+
"learning_rate": 1.6254507985574446e-05,
|
| 793 |
+
"loss": 0.8475,
|
| 794 |
+
"step": 13100
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 3.4,
|
| 798 |
+
"learning_rate": 1.5996908809891807e-05,
|
| 799 |
+
"loss": 0.8225,
|
| 800 |
+
"step": 13200
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 3.43,
|
| 804 |
+
"learning_rate": 1.573930963420917e-05,
|
| 805 |
+
"loss": 0.8395,
|
| 806 |
+
"step": 13300
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 3.45,
|
| 810 |
+
"learning_rate": 1.5481710458526533e-05,
|
| 811 |
+
"loss": 0.8366,
|
| 812 |
+
"step": 13400
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 3.48,
|
| 816 |
+
"learning_rate": 1.5224111282843895e-05,
|
| 817 |
+
"loss": 0.8371,
|
| 818 |
+
"step": 13500
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 3.5,
|
| 822 |
+
"learning_rate": 1.4966512107161256e-05,
|
| 823 |
+
"loss": 0.8294,
|
| 824 |
+
"step": 13600
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 3.53,
|
| 828 |
+
"learning_rate": 1.4708912931478619e-05,
|
| 829 |
+
"loss": 0.83,
|
| 830 |
+
"step": 13700
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 3.55,
|
| 834 |
+
"learning_rate": 1.4451313755795981e-05,
|
| 835 |
+
"loss": 0.8357,
|
| 836 |
+
"step": 13800
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 3.58,
|
| 840 |
+
"learning_rate": 1.4193714580113342e-05,
|
| 841 |
+
"loss": 0.8355,
|
| 842 |
+
"step": 13900
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 3.61,
|
| 846 |
+
"learning_rate": 1.3936115404430705e-05,
|
| 847 |
+
"loss": 0.8592,
|
| 848 |
+
"step": 14000
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 3.63,
|
| 852 |
+
"learning_rate": 1.367851622874807e-05,
|
| 853 |
+
"loss": 0.811,
|
| 854 |
+
"step": 14100
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 3.66,
|
| 858 |
+
"learning_rate": 1.3420917053065432e-05,
|
| 859 |
+
"loss": 0.8269,
|
| 860 |
+
"step": 14200
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 3.68,
|
| 864 |
+
"learning_rate": 1.3163317877382795e-05,
|
| 865 |
+
"loss": 0.8447,
|
| 866 |
+
"step": 14300
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 3.71,
|
| 870 |
+
"learning_rate": 1.2905718701700156e-05,
|
| 871 |
+
"loss": 0.8463,
|
| 872 |
+
"step": 14400
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 3.74,
|
| 876 |
+
"learning_rate": 1.2648119526017518e-05,
|
| 877 |
+
"loss": 0.8257,
|
| 878 |
+
"step": 14500
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 3.76,
|
| 882 |
+
"learning_rate": 1.239052035033488e-05,
|
| 883 |
+
"loss": 0.8134,
|
| 884 |
+
"step": 14600
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 3.79,
|
| 888 |
+
"learning_rate": 1.2132921174652242e-05,
|
| 889 |
+
"loss": 0.826,
|
| 890 |
+
"step": 14700
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 3.81,
|
| 894 |
+
"learning_rate": 1.1875321998969603e-05,
|
| 895 |
+
"loss": 0.8358,
|
| 896 |
+
"step": 14800
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 3.84,
|
| 900 |
+
"learning_rate": 1.1617722823286967e-05,
|
| 901 |
+
"loss": 0.8237,
|
| 902 |
+
"step": 14900
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 3.86,
|
| 906 |
+
"learning_rate": 1.1360123647604328e-05,
|
| 907 |
+
"loss": 0.8314,
|
| 908 |
+
"step": 15000
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 3.89,
|
| 912 |
+
"learning_rate": 1.110252447192169e-05,
|
| 913 |
+
"loss": 0.8022,
|
| 914 |
+
"step": 15100
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 3.92,
|
| 918 |
+
"learning_rate": 1.0844925296239053e-05,
|
| 919 |
+
"loss": 0.8039,
|
| 920 |
+
"step": 15200
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 3.94,
|
| 924 |
+
"learning_rate": 1.0587326120556414e-05,
|
| 925 |
+
"loss": 0.8209,
|
| 926 |
+
"step": 15300
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 3.97,
|
| 930 |
+
"learning_rate": 1.0329726944873777e-05,
|
| 931 |
+
"loss": 0.8108,
|
| 932 |
+
"step": 15400
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 3.99,
|
| 936 |
+
"learning_rate": 1.007212776919114e-05,
|
| 937 |
+
"loss": 0.8068,
|
| 938 |
+
"step": 15500
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 4.02,
|
| 942 |
+
"learning_rate": 9.8145285935085e-06,
|
| 943 |
+
"loss": 0.8114,
|
| 944 |
+
"step": 15600
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 4.04,
|
| 948 |
+
"learning_rate": 9.556929417825863e-06,
|
| 949 |
+
"loss": 0.796,
|
| 950 |
+
"step": 15700
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 4.07,
|
| 954 |
+
"learning_rate": 9.299330242143226e-06,
|
| 955 |
+
"loss": 0.8125,
|
| 956 |
+
"step": 15800
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 4.1,
|
| 960 |
+
"learning_rate": 9.041731066460587e-06,
|
| 961 |
+
"loss": 0.7814,
|
| 962 |
+
"step": 15900
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 4.12,
|
| 966 |
+
"learning_rate": 8.78413189077795e-06,
|
| 967 |
+
"loss": 0.8087,
|
| 968 |
+
"step": 16000
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 4.15,
|
| 972 |
+
"learning_rate": 8.526532715095312e-06,
|
| 973 |
+
"loss": 0.7925,
|
| 974 |
+
"step": 16100
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 4.17,
|
| 978 |
+
"learning_rate": 8.268933539412673e-06,
|
| 979 |
+
"loss": 0.7946,
|
| 980 |
+
"step": 16200
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 4.2,
|
| 984 |
+
"learning_rate": 8.011334363730036e-06,
|
| 985 |
+
"loss": 0.8019,
|
| 986 |
+
"step": 16300
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 4.22,
|
| 990 |
+
"learning_rate": 7.753735188047398e-06,
|
| 991 |
+
"loss": 0.7974,
|
| 992 |
+
"step": 16400
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 4.25,
|
| 996 |
+
"learning_rate": 7.496136012364761e-06,
|
| 997 |
+
"loss": 0.7763,
|
| 998 |
+
"step": 16500
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 4.28,
|
| 1002 |
+
"learning_rate": 7.238536836682124e-06,
|
| 1003 |
+
"loss": 0.8158,
|
| 1004 |
+
"step": 16600
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 4.3,
|
| 1008 |
+
"learning_rate": 6.9809376609994855e-06,
|
| 1009 |
+
"loss": 0.8042,
|
| 1010 |
+
"step": 16700
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 4.33,
|
| 1014 |
+
"learning_rate": 6.723338485316847e-06,
|
| 1015 |
+
"loss": 0.7932,
|
| 1016 |
+
"step": 16800
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 4.35,
|
| 1020 |
+
"learning_rate": 6.46573930963421e-06,
|
| 1021 |
+
"loss": 0.7899,
|
| 1022 |
+
"step": 16900
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 4.38,
|
| 1026 |
+
"learning_rate": 6.208140133951572e-06,
|
| 1027 |
+
"loss": 0.7974,
|
| 1028 |
+
"step": 17000
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 4.4,
|
| 1032 |
+
"learning_rate": 5.9505409582689335e-06,
|
| 1033 |
+
"loss": 0.8083,
|
| 1034 |
+
"step": 17100
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 4.43,
|
| 1038 |
+
"learning_rate": 5.692941782586296e-06,
|
| 1039 |
+
"loss": 0.7924,
|
| 1040 |
+
"step": 17200
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 4.46,
|
| 1044 |
+
"learning_rate": 5.435342606903658e-06,
|
| 1045 |
+
"loss": 0.7591,
|
| 1046 |
+
"step": 17300
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 4.48,
|
| 1050 |
+
"learning_rate": 5.17774343122102e-06,
|
| 1051 |
+
"loss": 0.8039,
|
| 1052 |
+
"step": 17400
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 4.51,
|
| 1056 |
+
"learning_rate": 4.9201442555383824e-06,
|
| 1057 |
+
"loss": 0.7864,
|
| 1058 |
+
"step": 17500
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 4.53,
|
| 1062 |
+
"learning_rate": 4.662545079855744e-06,
|
| 1063 |
+
"loss": 0.779,
|
| 1064 |
+
"step": 17600
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 4.56,
|
| 1068 |
+
"learning_rate": 4.404945904173107e-06,
|
| 1069 |
+
"loss": 0.7983,
|
| 1070 |
+
"step": 17700
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 4.59,
|
| 1074 |
+
"learning_rate": 4.1473467284904695e-06,
|
| 1075 |
+
"loss": 0.7849,
|
| 1076 |
+
"step": 17800
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 4.61,
|
| 1080 |
+
"learning_rate": 3.889747552807831e-06,
|
| 1081 |
+
"loss": 0.7977,
|
| 1082 |
+
"step": 17900
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 4.64,
|
| 1086 |
+
"learning_rate": 3.6321483771251936e-06,
|
| 1087 |
+
"loss": 0.7929,
|
| 1088 |
+
"step": 18000
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 4.66,
|
| 1092 |
+
"learning_rate": 3.3745492014425554e-06,
|
| 1093 |
+
"loss": 0.7761,
|
| 1094 |
+
"step": 18100
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 4.69,
|
| 1098 |
+
"learning_rate": 3.116950025759918e-06,
|
| 1099 |
+
"loss": 0.7998,
|
| 1100 |
+
"step": 18200
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 4.71,
|
| 1104 |
+
"learning_rate": 2.85935085007728e-06,
|
| 1105 |
+
"loss": 0.7863,
|
| 1106 |
+
"step": 18300
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 4.74,
|
| 1110 |
+
"learning_rate": 2.601751674394642e-06,
|
| 1111 |
+
"loss": 0.7726,
|
| 1112 |
+
"step": 18400
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 4.77,
|
| 1116 |
+
"learning_rate": 2.3441524987120042e-06,
|
| 1117 |
+
"loss": 0.7742,
|
| 1118 |
+
"step": 18500
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 4.79,
|
| 1122 |
+
"learning_rate": 2.0865533230293665e-06,
|
| 1123 |
+
"loss": 0.782,
|
| 1124 |
+
"step": 18600
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 4.82,
|
| 1128 |
+
"learning_rate": 1.8289541473467287e-06,
|
| 1129 |
+
"loss": 0.7836,
|
| 1130 |
+
"step": 18700
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 4.84,
|
| 1134 |
+
"learning_rate": 1.5713549716640907e-06,
|
| 1135 |
+
"loss": 0.7859,
|
| 1136 |
+
"step": 18800
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 4.87,
|
| 1140 |
+
"learning_rate": 1.313755795981453e-06,
|
| 1141 |
+
"loss": 0.8002,
|
| 1142 |
+
"step": 18900
|
| 1143 |
+
},
|
| 1144 |
+
{
|
| 1145 |
+
"epoch": 4.89,
|
| 1146 |
+
"learning_rate": 1.0561566202988151e-06,
|
| 1147 |
+
"loss": 0.7903,
|
| 1148 |
+
"step": 19000
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 4.92,
|
| 1152 |
+
"learning_rate": 7.985574446161774e-07,
|
| 1153 |
+
"loss": 0.7888,
|
| 1154 |
+
"step": 19100
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 4.95,
|
| 1158 |
+
"learning_rate": 5.409582689335394e-07,
|
| 1159 |
+
"loss": 0.7848,
|
| 1160 |
+
"step": 19200
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 4.97,
|
| 1164 |
+
"learning_rate": 2.8335909325090165e-07,
|
| 1165 |
+
"loss": 0.7853,
|
| 1166 |
+
"step": 19300
|
| 1167 |
+
},
|
| 1168 |
+
{
|
| 1169 |
+
"epoch": 5.0,
|
| 1170 |
+
"learning_rate": 2.5759917568263784e-08,
|
| 1171 |
+
"loss": 0.7858,
|
| 1172 |
+
"step": 19400
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 5.0,
|
| 1176 |
+
"step": 19410,
|
| 1177 |
+
"total_flos": 1.0472274521715917e+17,
|
| 1178 |
+
"train_loss": 0.3320594994939522,
|
| 1179 |
+
"train_runtime": 31593.7732,
|
| 1180 |
+
"train_samples_per_second": 9.829,
|
| 1181 |
+
"train_steps_per_second": 0.614
|
| 1182 |
}
|
| 1183 |
],
|
| 1184 |
+
"max_steps": 19410,
|
| 1185 |
+
"num_train_epochs": 5,
|
| 1186 |
+
"total_flos": 1.0472274521715917e+17,
|
| 1187 |
"trial_name": null,
|
| 1188 |
"trial_params": null
|
| 1189 |
}
|