Training in progress, step 174, 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 97307544
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:abcde8ac3d04c98a861549359d1224345d51b37788f3b8a385d055e42467481e
|
| 3 |
size 97307544
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 194840426
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e12dbbc77c83e3643e10bdd747b43283d299a4a0443c375284bff3cb8b034d78
|
| 3 |
size 194840426
|
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 sha256:6885c98f9944031b1d47a617f1a2d46af56909da93ca8c4ac4a873f90d3142fe
|
| 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 sha256:3901384dd9ab7f4272cbe89ec0e7d7be7b55f7e04d725cfcd750d27555d4c8c0
|
| 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 sha256:1cfc363eda5dfe78796b361134c848de53d3bd2047f481ddb99265e158e573b4
|
| 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": 58,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -843,6 +843,420 @@
|
|
| 843 |
"eval_samples_per_second": 8.853,
|
| 844 |
"eval_steps_per_second": 2.23,
|
| 845 |
"step": 116
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 846 |
}
|
| 847 |
],
|
| 848 |
"logging_steps": 1,
|
|
@@ -862,7 +1276,7 @@
|
|
| 862 |
"attributes": {}
|
| 863 |
}
|
| 864 |
},
|
| 865 |
-
"total_flos":
|
| 866 |
"train_batch_size": 2,
|
| 867 |
"trial_name": null,
|
| 868 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.754880694143167,
|
| 5 |
"eval_steps": 58,
|
| 6 |
+
"global_step": 174,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 843 |
"eval_samples_per_second": 8.853,
|
| 844 |
"eval_steps_per_second": 2.23,
|
| 845 |
"step": 116
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 0.5075921908893709,
|
| 849 |
+
"grad_norm": 1.3170753717422485,
|
| 850 |
+
"learning_rate": 0.00013907311284892736,
|
| 851 |
+
"loss": 2.9572,
|
| 852 |
+
"step": 117
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 0.5119305856832972,
|
| 856 |
+
"grad_norm": 1.5243107080459595,
|
| 857 |
+
"learning_rate": 0.00013746065934159123,
|
| 858 |
+
"loss": 3.3082,
|
| 859 |
+
"step": 118
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 0.5162689804772235,
|
| 863 |
+
"grad_norm": 1.5845880508422852,
|
| 864 |
+
"learning_rate": 0.00013583679495453,
|
| 865 |
+
"loss": 3.4819,
|
| 866 |
+
"step": 119
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 0.5206073752711496,
|
| 870 |
+
"grad_norm": 1.66307532787323,
|
| 871 |
+
"learning_rate": 0.00013420201433256689,
|
| 872 |
+
"loss": 3.1131,
|
| 873 |
+
"step": 120
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.5249457700650759,
|
| 877 |
+
"grad_norm": 1.6470588445663452,
|
| 878 |
+
"learning_rate": 0.00013255681544571568,
|
| 879 |
+
"loss": 3.2847,
|
| 880 |
+
"step": 121
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 0.5292841648590022,
|
| 884 |
+
"grad_norm": 2.1118075847625732,
|
| 885 |
+
"learning_rate": 0.00013090169943749476,
|
| 886 |
+
"loss": 3.4669,
|
| 887 |
+
"step": 122
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 0.5336225596529284,
|
| 891 |
+
"grad_norm": 2.056396722793579,
|
| 892 |
+
"learning_rate": 0.00012923717047227368,
|
| 893 |
+
"loss": 3.1136,
|
| 894 |
+
"step": 123
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 0.5379609544468547,
|
| 898 |
+
"grad_norm": 2.2389657497406006,
|
| 899 |
+
"learning_rate": 0.0001275637355816999,
|
| 900 |
+
"loss": 2.9323,
|
| 901 |
+
"step": 124
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 0.5422993492407809,
|
| 905 |
+
"grad_norm": 2.863621711730957,
|
| 906 |
+
"learning_rate": 0.00012588190451025207,
|
| 907 |
+
"loss": 2.9585,
|
| 908 |
+
"step": 125
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 0.5466377440347071,
|
| 912 |
+
"grad_norm": 0.8712321519851685,
|
| 913 |
+
"learning_rate": 0.00012419218955996676,
|
| 914 |
+
"loss": 3.1439,
|
| 915 |
+
"step": 126
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 0.5509761388286334,
|
| 919 |
+
"grad_norm": 1.0713740587234497,
|
| 920 |
+
"learning_rate": 0.0001224951054343865,
|
| 921 |
+
"loss": 3.2213,
|
| 922 |
+
"step": 127
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 0.5553145336225597,
|
| 926 |
+
"grad_norm": 1.104315996170044,
|
| 927 |
+
"learning_rate": 0.00012079116908177593,
|
| 928 |
+
"loss": 3.4522,
|
| 929 |
+
"step": 128
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 0.559652928416486,
|
| 933 |
+
"grad_norm": 1.0883917808532715,
|
| 934 |
+
"learning_rate": 0.00011908089953765449,
|
| 935 |
+
"loss": 3.3503,
|
| 936 |
+
"step": 129
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 0.5639913232104121,
|
| 940 |
+
"grad_norm": 1.0000834465026855,
|
| 941 |
+
"learning_rate": 0.00011736481776669306,
|
| 942 |
+
"loss": 3.4036,
|
| 943 |
+
"step": 130
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 0.5683297180043384,
|
| 947 |
+
"grad_norm": 0.8869354128837585,
|
| 948 |
+
"learning_rate": 0.0001156434465040231,
|
| 949 |
+
"loss": 3.2749,
|
| 950 |
+
"step": 131
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 0.5726681127982647,
|
| 954 |
+
"grad_norm": 0.8651937246322632,
|
| 955 |
+
"learning_rate": 0.00011391731009600654,
|
| 956 |
+
"loss": 3.3679,
|
| 957 |
+
"step": 132
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 0.5770065075921909,
|
| 961 |
+
"grad_norm": 0.9174556136131287,
|
| 962 |
+
"learning_rate": 0.00011218693434051475,
|
| 963 |
+
"loss": 3.311,
|
| 964 |
+
"step": 133
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 0.5813449023861171,
|
| 968 |
+
"grad_norm": 0.930533230304718,
|
| 969 |
+
"learning_rate": 0.00011045284632676536,
|
| 970 |
+
"loss": 3.3761,
|
| 971 |
+
"step": 134
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 0.5856832971800434,
|
| 975 |
+
"grad_norm": 0.9851680994033813,
|
| 976 |
+
"learning_rate": 0.00010871557427476583,
|
| 977 |
+
"loss": 3.2752,
|
| 978 |
+
"step": 135
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 0.5900216919739696,
|
| 982 |
+
"grad_norm": 0.9633740782737732,
|
| 983 |
+
"learning_rate": 0.00010697564737441252,
|
| 984 |
+
"loss": 3.2373,
|
| 985 |
+
"step": 136
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 0.5943600867678959,
|
| 989 |
+
"grad_norm": 1.132585048675537,
|
| 990 |
+
"learning_rate": 0.0001052335956242944,
|
| 991 |
+
"loss": 3.2323,
|
| 992 |
+
"step": 137
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 0.5986984815618221,
|
| 996 |
+
"grad_norm": 1.1232091188430786,
|
| 997 |
+
"learning_rate": 0.00010348994967025012,
|
| 998 |
+
"loss": 3.2874,
|
| 999 |
+
"step": 138
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.6030368763557483,
|
| 1003 |
+
"grad_norm": 1.2559125423431396,
|
| 1004 |
+
"learning_rate": 0.00010174524064372837,
|
| 1005 |
+
"loss": 3.2367,
|
| 1006 |
+
"step": 139
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 0.6073752711496746,
|
| 1010 |
+
"grad_norm": 1.2623041868209839,
|
| 1011 |
+
"learning_rate": 0.0001,
|
| 1012 |
+
"loss": 3.2243,
|
| 1013 |
+
"step": 140
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 0.6117136659436009,
|
| 1017 |
+
"grad_norm": 1.3554457426071167,
|
| 1018 |
+
"learning_rate": 9.825475935627165e-05,
|
| 1019 |
+
"loss": 3.4802,
|
| 1020 |
+
"step": 141
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 0.6160520607375272,
|
| 1024 |
+
"grad_norm": 1.4170132875442505,
|
| 1025 |
+
"learning_rate": 9.651005032974994e-05,
|
| 1026 |
+
"loss": 3.354,
|
| 1027 |
+
"step": 142
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 0.6203904555314533,
|
| 1031 |
+
"grad_norm": 1.4309097528457642,
|
| 1032 |
+
"learning_rate": 9.476640437570562e-05,
|
| 1033 |
+
"loss": 3.1352,
|
| 1034 |
+
"step": 143
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 0.6247288503253796,
|
| 1038 |
+
"grad_norm": 1.5829153060913086,
|
| 1039 |
+
"learning_rate": 9.302435262558747e-05,
|
| 1040 |
+
"loss": 3.2455,
|
| 1041 |
+
"step": 144
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.6290672451193059,
|
| 1045 |
+
"grad_norm": 1.8210502862930298,
|
| 1046 |
+
"learning_rate": 9.128442572523417e-05,
|
| 1047 |
+
"loss": 3.2991,
|
| 1048 |
+
"step": 145
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 0.6334056399132321,
|
| 1052 |
+
"grad_norm": 1.842761516571045,
|
| 1053 |
+
"learning_rate": 8.954715367323468e-05,
|
| 1054 |
+
"loss": 3.2255,
|
| 1055 |
+
"step": 146
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 0.6377440347071583,
|
| 1059 |
+
"grad_norm": 1.9258646965026855,
|
| 1060 |
+
"learning_rate": 8.781306565948528e-05,
|
| 1061 |
+
"loss": 3.1397,
|
| 1062 |
+
"step": 147
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 0.6420824295010846,
|
| 1066 |
+
"grad_norm": 2.1189215183258057,
|
| 1067 |
+
"learning_rate": 8.608268990399349e-05,
|
| 1068 |
+
"loss": 3.0414,
|
| 1069 |
+
"step": 148
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 0.6464208242950108,
|
| 1073 |
+
"grad_norm": 2.4063761234283447,
|
| 1074 |
+
"learning_rate": 8.435655349597689e-05,
|
| 1075 |
+
"loss": 2.8524,
|
| 1076 |
+
"step": 149
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 0.6507592190889371,
|
| 1080 |
+
"grad_norm": 3.6420836448669434,
|
| 1081 |
+
"learning_rate": 8.263518223330697e-05,
|
| 1082 |
+
"loss": 3.0156,
|
| 1083 |
+
"step": 150
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 0.6550976138828634,
|
| 1087 |
+
"grad_norm": 0.7080674171447754,
|
| 1088 |
+
"learning_rate": 8.091910046234552e-05,
|
| 1089 |
+
"loss": 3.1636,
|
| 1090 |
+
"step": 151
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 0.6594360086767896,
|
| 1094 |
+
"grad_norm": 0.798520565032959,
|
| 1095 |
+
"learning_rate": 7.920883091822408e-05,
|
| 1096 |
+
"loss": 3.212,
|
| 1097 |
+
"step": 152
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 0.6637744034707158,
|
| 1101 |
+
"grad_norm": 0.8640486001968384,
|
| 1102 |
+
"learning_rate": 7.750489456561352e-05,
|
| 1103 |
+
"loss": 3.1644,
|
| 1104 |
+
"step": 153
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 0.6681127982646421,
|
| 1108 |
+
"grad_norm": 0.870906412601471,
|
| 1109 |
+
"learning_rate": 7.580781044003324e-05,
|
| 1110 |
+
"loss": 3.1876,
|
| 1111 |
+
"step": 154
|
| 1112 |
+
},
|
| 1113 |
+
{
|
| 1114 |
+
"epoch": 0.6724511930585684,
|
| 1115 |
+
"grad_norm": 0.8581348061561584,
|
| 1116 |
+
"learning_rate": 7.411809548974792e-05,
|
| 1117 |
+
"loss": 3.2739,
|
| 1118 |
+
"step": 155
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 0.6767895878524945,
|
| 1122 |
+
"grad_norm": 0.8691614270210266,
|
| 1123 |
+
"learning_rate": 7.243626441830009e-05,
|
| 1124 |
+
"loss": 3.2444,
|
| 1125 |
+
"step": 156
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 0.6811279826464208,
|
| 1129 |
+
"grad_norm": 0.9455673098564148,
|
| 1130 |
+
"learning_rate": 7.076282952772633e-05,
|
| 1131 |
+
"loss": 3.3004,
|
| 1132 |
+
"step": 157
|
| 1133 |
+
},
|
| 1134 |
+
{
|
| 1135 |
+
"epoch": 0.6854663774403471,
|
| 1136 |
+
"grad_norm": 0.8873337507247925,
|
| 1137 |
+
"learning_rate": 6.909830056250527e-05,
|
| 1138 |
+
"loss": 3.1778,
|
| 1139 |
+
"step": 158
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 0.6898047722342733,
|
| 1143 |
+
"grad_norm": 0.910775363445282,
|
| 1144 |
+
"learning_rate": 6.744318455428436e-05,
|
| 1145 |
+
"loss": 3.1346,
|
| 1146 |
+
"step": 159
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 0.6941431670281996,
|
| 1150 |
+
"grad_norm": 0.9872409105300903,
|
| 1151 |
+
"learning_rate": 6.579798566743314e-05,
|
| 1152 |
+
"loss": 3.1665,
|
| 1153 |
+
"step": 160
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"epoch": 0.6984815618221258,
|
| 1157 |
+
"grad_norm": 1.0516481399536133,
|
| 1158 |
+
"learning_rate": 6.416320504546997e-05,
|
| 1159 |
+
"loss": 3.3064,
|
| 1160 |
+
"step": 161
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 0.702819956616052,
|
| 1164 |
+
"grad_norm": 1.0263571739196777,
|
| 1165 |
+
"learning_rate": 6.25393406584088e-05,
|
| 1166 |
+
"loss": 3.3698,
|
| 1167 |
+
"step": 162
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 0.7071583514099783,
|
| 1171 |
+
"grad_norm": 1.1050878763198853,
|
| 1172 |
+
"learning_rate": 6.092688715107264e-05,
|
| 1173 |
+
"loss": 3.2436,
|
| 1174 |
+
"step": 163
|
| 1175 |
+
},
|
| 1176 |
+
{
|
| 1177 |
+
"epoch": 0.7114967462039046,
|
| 1178 |
+
"grad_norm": 1.1121841669082642,
|
| 1179 |
+
"learning_rate": 5.9326335692419995e-05,
|
| 1180 |
+
"loss": 2.9433,
|
| 1181 |
+
"step": 164
|
| 1182 |
+
},
|
| 1183 |
+
{
|
| 1184 |
+
"epoch": 0.7158351409978309,
|
| 1185 |
+
"grad_norm": 1.2424358129501343,
|
| 1186 |
+
"learning_rate": 5.773817382593008e-05,
|
| 1187 |
+
"loss": 3.3616,
|
| 1188 |
+
"step": 165
|
| 1189 |
+
},
|
| 1190 |
+
{
|
| 1191 |
+
"epoch": 0.720173535791757,
|
| 1192 |
+
"grad_norm": 1.1899327039718628,
|
| 1193 |
+
"learning_rate": 5.616288532109225e-05,
|
| 1194 |
+
"loss": 3.0392,
|
| 1195 |
+
"step": 166
|
| 1196 |
+
},
|
| 1197 |
+
{
|
| 1198 |
+
"epoch": 0.7245119305856833,
|
| 1199 |
+
"grad_norm": 1.3395730257034302,
|
| 1200 |
+
"learning_rate": 5.4600950026045326e-05,
|
| 1201 |
+
"loss": 3.0905,
|
| 1202 |
+
"step": 167
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 0.7288503253796096,
|
| 1206 |
+
"grad_norm": 1.4268842935562134,
|
| 1207 |
+
"learning_rate": 5.305284372141095e-05,
|
| 1208 |
+
"loss": 3.1247,
|
| 1209 |
+
"step": 168
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 0.7331887201735358,
|
| 1213 |
+
"grad_norm": 1.5514875650405884,
|
| 1214 |
+
"learning_rate": 5.15190379753663e-05,
|
| 1215 |
+
"loss": 3.3772,
|
| 1216 |
+
"step": 169
|
| 1217 |
+
},
|
| 1218 |
+
{
|
| 1219 |
+
"epoch": 0.737527114967462,
|
| 1220 |
+
"grad_norm": 1.8371058702468872,
|
| 1221 |
+
"learning_rate": 5.000000000000002e-05,
|
| 1222 |
+
"loss": 2.9262,
|
| 1223 |
+
"step": 170
|
| 1224 |
+
},
|
| 1225 |
+
{
|
| 1226 |
+
"epoch": 0.7418655097613883,
|
| 1227 |
+
"grad_norm": 1.7641676664352417,
|
| 1228 |
+
"learning_rate": 4.8496192508994576e-05,
|
| 1229 |
+
"loss": 3.0113,
|
| 1230 |
+
"step": 171
|
| 1231 |
+
},
|
| 1232 |
+
{
|
| 1233 |
+
"epoch": 0.7462039045553145,
|
| 1234 |
+
"grad_norm": 1.8325039148330688,
|
| 1235 |
+
"learning_rate": 4.700807357667952e-05,
|
| 1236 |
+
"loss": 3.0551,
|
| 1237 |
+
"step": 172
|
| 1238 |
+
},
|
| 1239 |
+
{
|
| 1240 |
+
"epoch": 0.7505422993492408,
|
| 1241 |
+
"grad_norm": 1.9740185737609863,
|
| 1242 |
+
"learning_rate": 4.5536096498497295e-05,
|
| 1243 |
+
"loss": 3.1479,
|
| 1244 |
+
"step": 173
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 0.754880694143167,
|
| 1248 |
+
"grad_norm": 2.327420234680176,
|
| 1249 |
+
"learning_rate": 4.4080709652925336e-05,
|
| 1250 |
+
"loss": 3.2149,
|
| 1251 |
+
"step": 174
|
| 1252 |
+
},
|
| 1253 |
+
{
|
| 1254 |
+
"epoch": 0.754880694143167,
|
| 1255 |
+
"eval_loss": 3.163884162902832,
|
| 1256 |
+
"eval_runtime": 43.9914,
|
| 1257 |
+
"eval_samples_per_second": 8.843,
|
| 1258 |
+
"eval_steps_per_second": 2.228,
|
| 1259 |
+
"step": 174
|
| 1260 |
}
|
| 1261 |
],
|
| 1262 |
"logging_steps": 1,
|
|
|
|
| 1276 |
"attributes": {}
|
| 1277 |
}
|
| 1278 |
},
|
| 1279 |
+
"total_flos": 3.8904213574936166e+17,
|
| 1280 |
"train_batch_size": 2,
|
| 1281 |
"trial_name": null,
|
| 1282 |
"trial_params": null
|