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 628216
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e2b843e151cf6cc050775016450368ab902a8c5210bcf1e434a77e4e5db56396
|
| 3 |
size 628216
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 352122
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f627aa887a52e41a3875178e7cfd439b0d0e0b932a590286b92421354b0669b7
|
| 3 |
size 352122
|
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 sha256:1123d437e2018100b779616cd1029668a10695d67192092e06b2bcb9892a29fa
|
| 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 sha256:2d094abeb22730ed8a1a30db0af3a1ac1bd1a9d1fcc8794319a4b828d3c7261c
|
| 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": 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": 132.837,
|
| 732 |
"eval_steps_per_second": 33.268,
|
| 733 |
"step": 100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 734 |
}
|
| 735 |
],
|
| 736 |
"logging_steps": 1,
|
|
@@ -759,7 +1117,7 @@
|
|
| 759 |
"attributes": {}
|
| 760 |
}
|
| 761 |
},
|
| 762 |
-
"total_flos":
|
| 763 |
"train_batch_size": 4,
|
| 764 |
"trial_name": null,
|
| 765 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 10.709113121032715,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-150",
|
| 4 |
+
"epoch": 0.055699962866691426,
|
| 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": 132.837,
|
| 732 |
"eval_steps_per_second": 33.268,
|
| 733 |
"step": 100
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 0.03750464166357222,
|
| 737 |
+
"grad_norm": 0.30814334750175476,
|
| 738 |
+
"learning_rate": 5.246999999999999e-05,
|
| 739 |
+
"loss": 10.7375,
|
| 740 |
+
"step": 101
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 0.037875974749350165,
|
| 744 |
+
"grad_norm": 0.34333688020706177,
|
| 745 |
+
"learning_rate": 5.194e-05,
|
| 746 |
+
"loss": 10.7405,
|
| 747 |
+
"step": 102
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.03824730783512811,
|
| 751 |
+
"grad_norm": 0.396445631980896,
|
| 752 |
+
"learning_rate": 5.141e-05,
|
| 753 |
+
"loss": 10.7225,
|
| 754 |
+
"step": 103
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 0.038618640920906055,
|
| 758 |
+
"grad_norm": 0.3750787079334259,
|
| 759 |
+
"learning_rate": 5.088e-05,
|
| 760 |
+
"loss": 10.7264,
|
| 761 |
+
"step": 104
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.038989974006684,
|
| 765 |
+
"grad_norm": 0.30554020404815674,
|
| 766 |
+
"learning_rate": 5.035e-05,
|
| 767 |
+
"loss": 10.7261,
|
| 768 |
+
"step": 105
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 0.03936130709246194,
|
| 772 |
+
"grad_norm": 0.35283979773521423,
|
| 773 |
+
"learning_rate": 4.9819999999999994e-05,
|
| 774 |
+
"loss": 10.7309,
|
| 775 |
+
"step": 106
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 0.03973264017823988,
|
| 779 |
+
"grad_norm": 0.39950183033943176,
|
| 780 |
+
"learning_rate": 4.929e-05,
|
| 781 |
+
"loss": 10.7223,
|
| 782 |
+
"step": 107
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 0.04010397326401782,
|
| 786 |
+
"grad_norm": 0.38336852192878723,
|
| 787 |
+
"learning_rate": 4.876e-05,
|
| 788 |
+
"loss": 10.7209,
|
| 789 |
+
"step": 108
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.040475306349795764,
|
| 793 |
+
"grad_norm": 0.362358421087265,
|
| 794 |
+
"learning_rate": 4.823e-05,
|
| 795 |
+
"loss": 10.735,
|
| 796 |
+
"step": 109
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 0.04084663943557371,
|
| 800 |
+
"grad_norm": 0.397513747215271,
|
| 801 |
+
"learning_rate": 4.7699999999999994e-05,
|
| 802 |
+
"loss": 10.7304,
|
| 803 |
+
"step": 110
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 0.041217972521351655,
|
| 807 |
+
"grad_norm": 0.4068267047405243,
|
| 808 |
+
"learning_rate": 4.717e-05,
|
| 809 |
+
"loss": 10.7297,
|
| 810 |
+
"step": 111
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 0.0415893056071296,
|
| 814 |
+
"grad_norm": 0.38471511006355286,
|
| 815 |
+
"learning_rate": 4.6639999999999994e-05,
|
| 816 |
+
"loss": 10.754,
|
| 817 |
+
"step": 112
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 0.04196063869290754,
|
| 821 |
+
"grad_norm": 0.3469901978969574,
|
| 822 |
+
"learning_rate": 4.611e-05,
|
| 823 |
+
"loss": 10.7255,
|
| 824 |
+
"step": 113
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 0.04233197177868548,
|
| 828 |
+
"grad_norm": 0.3917114734649658,
|
| 829 |
+
"learning_rate": 4.558e-05,
|
| 830 |
+
"loss": 10.72,
|
| 831 |
+
"step": 114
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 0.04270330486446342,
|
| 835 |
+
"grad_norm": 0.3135025203227997,
|
| 836 |
+
"learning_rate": 4.505e-05,
|
| 837 |
+
"loss": 10.7204,
|
| 838 |
+
"step": 115
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 0.043074637950241364,
|
| 842 |
+
"grad_norm": 0.32310202717781067,
|
| 843 |
+
"learning_rate": 4.4519999999999994e-05,
|
| 844 |
+
"loss": 10.7334,
|
| 845 |
+
"step": 116
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 0.04344597103601931,
|
| 849 |
+
"grad_norm": 0.316651314496994,
|
| 850 |
+
"learning_rate": 4.399e-05,
|
| 851 |
+
"loss": 10.7357,
|
| 852 |
+
"step": 117
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 0.043817304121797254,
|
| 856 |
+
"grad_norm": 0.3423415422439575,
|
| 857 |
+
"learning_rate": 4.346e-05,
|
| 858 |
+
"loss": 10.7195,
|
| 859 |
+
"step": 118
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 0.044188637207575196,
|
| 863 |
+
"grad_norm": 0.3235597610473633,
|
| 864 |
+
"learning_rate": 4.293e-05,
|
| 865 |
+
"loss": 10.7321,
|
| 866 |
+
"step": 119
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 0.04455997029335314,
|
| 870 |
+
"grad_norm": 0.33004501461982727,
|
| 871 |
+
"learning_rate": 4.2399999999999994e-05,
|
| 872 |
+
"loss": 10.7148,
|
| 873 |
+
"step": 120
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.04493130337913108,
|
| 877 |
+
"grad_norm": 0.3902532756328583,
|
| 878 |
+
"learning_rate": 4.187e-05,
|
| 879 |
+
"loss": 10.7344,
|
| 880 |
+
"step": 121
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 0.04530263646490902,
|
| 884 |
+
"grad_norm": 0.30236899852752686,
|
| 885 |
+
"learning_rate": 4.134e-05,
|
| 886 |
+
"loss": 10.7194,
|
| 887 |
+
"step": 122
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 0.04567396955068696,
|
| 891 |
+
"grad_norm": 0.38607534766197205,
|
| 892 |
+
"learning_rate": 4.081e-05,
|
| 893 |
+
"loss": 10.7046,
|
| 894 |
+
"step": 123
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 0.04604530263646491,
|
| 898 |
+
"grad_norm": 0.3628384470939636,
|
| 899 |
+
"learning_rate": 4.028e-05,
|
| 900 |
+
"loss": 10.7198,
|
| 901 |
+
"step": 124
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 0.046416635722242854,
|
| 905 |
+
"grad_norm": 0.36593976616859436,
|
| 906 |
+
"learning_rate": 3.975e-05,
|
| 907 |
+
"loss": 10.7281,
|
| 908 |
+
"step": 125
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 0.046787968808020795,
|
| 912 |
+
"grad_norm": 0.3433733880519867,
|
| 913 |
+
"learning_rate": 3.9219999999999994e-05,
|
| 914 |
+
"loss": 10.7148,
|
| 915 |
+
"step": 126
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 0.04715930189379874,
|
| 919 |
+
"grad_norm": 0.37441202998161316,
|
| 920 |
+
"learning_rate": 3.869e-05,
|
| 921 |
+
"loss": 10.7132,
|
| 922 |
+
"step": 127
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 0.04753063497957668,
|
| 926 |
+
"grad_norm": 0.3574247658252716,
|
| 927 |
+
"learning_rate": 3.816e-05,
|
| 928 |
+
"loss": 10.7207,
|
| 929 |
+
"step": 128
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 0.04790196806535462,
|
| 933 |
+
"grad_norm": 0.3976617157459259,
|
| 934 |
+
"learning_rate": 3.763e-05,
|
| 935 |
+
"loss": 10.7027,
|
| 936 |
+
"step": 129
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 0.04827330115113257,
|
| 940 |
+
"grad_norm": 0.4094492495059967,
|
| 941 |
+
"learning_rate": 3.7099999999999994e-05,
|
| 942 |
+
"loss": 10.7168,
|
| 943 |
+
"step": 130
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 0.04864463423691051,
|
| 947 |
+
"grad_norm": 0.3910907506942749,
|
| 948 |
+
"learning_rate": 3.657e-05,
|
| 949 |
+
"loss": 10.6894,
|
| 950 |
+
"step": 131
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 0.04901596732268845,
|
| 954 |
+
"grad_norm": 0.347520112991333,
|
| 955 |
+
"learning_rate": 3.604e-05,
|
| 956 |
+
"loss": 10.7075,
|
| 957 |
+
"step": 132
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 0.049387300408466395,
|
| 961 |
+
"grad_norm": 0.33360084891319275,
|
| 962 |
+
"learning_rate": 3.551e-05,
|
| 963 |
+
"loss": 10.7175,
|
| 964 |
+
"step": 133
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 0.049758633494244336,
|
| 968 |
+
"grad_norm": 0.3098675608634949,
|
| 969 |
+
"learning_rate": 3.498e-05,
|
| 970 |
+
"loss": 10.6943,
|
| 971 |
+
"step": 134
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 0.05012996658002228,
|
| 975 |
+
"grad_norm": 0.417607843875885,
|
| 976 |
+
"learning_rate": 3.445e-05,
|
| 977 |
+
"loss": 10.696,
|
| 978 |
+
"step": 135
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 0.05050129966580022,
|
| 982 |
+
"grad_norm": 0.37847384810447693,
|
| 983 |
+
"learning_rate": 3.392e-05,
|
| 984 |
+
"loss": 10.7031,
|
| 985 |
+
"step": 136
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 0.05087263275157817,
|
| 989 |
+
"grad_norm": 0.34361228346824646,
|
| 990 |
+
"learning_rate": 3.339e-05,
|
| 991 |
+
"loss": 10.714,
|
| 992 |
+
"step": 137
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 0.05124396583735611,
|
| 996 |
+
"grad_norm": 0.4933507740497589,
|
| 997 |
+
"learning_rate": 3.286e-05,
|
| 998 |
+
"loss": 10.6758,
|
| 999 |
+
"step": 138
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.05161529892313405,
|
| 1003 |
+
"grad_norm": 0.412986695766449,
|
| 1004 |
+
"learning_rate": 3.233e-05,
|
| 1005 |
+
"loss": 10.6963,
|
| 1006 |
+
"step": 139
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 0.051986632008911994,
|
| 1010 |
+
"grad_norm": 0.43772485852241516,
|
| 1011 |
+
"learning_rate": 3.1799999999999994e-05,
|
| 1012 |
+
"loss": 10.7149,
|
| 1013 |
+
"step": 140
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 0.052357965094689936,
|
| 1017 |
+
"grad_norm": 0.37518948316574097,
|
| 1018 |
+
"learning_rate": 3.1270000000000004e-05,
|
| 1019 |
+
"loss": 10.6951,
|
| 1020 |
+
"step": 141
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 0.05272929818046788,
|
| 1024 |
+
"grad_norm": 0.36650022864341736,
|
| 1025 |
+
"learning_rate": 3.074e-05,
|
| 1026 |
+
"loss": 10.6925,
|
| 1027 |
+
"step": 142
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 0.05310063126624582,
|
| 1031 |
+
"grad_norm": 0.4543534219264984,
|
| 1032 |
+
"learning_rate": 3.0209999999999997e-05,
|
| 1033 |
+
"loss": 10.683,
|
| 1034 |
+
"step": 143
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 0.05347196435202377,
|
| 1038 |
+
"grad_norm": 0.47826236486434937,
|
| 1039 |
+
"learning_rate": 2.9679999999999997e-05,
|
| 1040 |
+
"loss": 10.7077,
|
| 1041 |
+
"step": 144
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.05384329743780171,
|
| 1045 |
+
"grad_norm": 0.3722932040691376,
|
| 1046 |
+
"learning_rate": 2.915e-05,
|
| 1047 |
+
"loss": 10.6916,
|
| 1048 |
+
"step": 145
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 0.05421463052357965,
|
| 1052 |
+
"grad_norm": 0.5447331666946411,
|
| 1053 |
+
"learning_rate": 2.8619999999999997e-05,
|
| 1054 |
+
"loss": 10.7065,
|
| 1055 |
+
"step": 146
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 0.05458596360935759,
|
| 1059 |
+
"grad_norm": 0.42991727590560913,
|
| 1060 |
+
"learning_rate": 2.8089999999999997e-05,
|
| 1061 |
+
"loss": 10.6734,
|
| 1062 |
+
"step": 147
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 0.054957296695135535,
|
| 1066 |
+
"grad_norm": 0.5424541234970093,
|
| 1067 |
+
"learning_rate": 2.756e-05,
|
| 1068 |
+
"loss": 10.6609,
|
| 1069 |
+
"step": 148
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 0.05532862978091348,
|
| 1073 |
+
"grad_norm": 0.6233406066894531,
|
| 1074 |
+
"learning_rate": 2.703e-05,
|
| 1075 |
+
"loss": 10.6865,
|
| 1076 |
+
"step": 149
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 0.055699962866691426,
|
| 1080 |
+
"grad_norm": 0.635688066482544,
|
| 1081 |
+
"learning_rate": 2.6499999999999997e-05,
|
| 1082 |
+
"loss": 10.6352,
|
| 1083 |
+
"step": 150
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 0.055699962866691426,
|
| 1087 |
+
"eval_loss": 10.709113121032715,
|
| 1088 |
+
"eval_runtime": 8.5126,
|
| 1089 |
+
"eval_samples_per_second": 133.215,
|
| 1090 |
+
"eval_steps_per_second": 33.362,
|
| 1091 |
+
"step": 150
|
| 1092 |
}
|
| 1093 |
],
|
| 1094 |
"logging_steps": 1,
|
|
|
|
| 1117 |
"attributes": {}
|
| 1118 |
}
|
| 1119 |
},
|
| 1120 |
+
"total_flos": 25616292249600.0,
|
| 1121 |
"train_batch_size": 4,
|
| 1122 |
"trial_name": null,
|
| 1123 |
"trial_params": null
|