Training in progress, epoch 4
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +288 -3
- pytorch_model.bin +1 -1
- runs/Feb20_18-29-06_ubuntu-2004/events.out.tfevents.1676885357.ubuntu-2004.887393.0 +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 236491269
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5ef39ac23e005dc178e9ef1a544aa5b8f96467e8469680a8607d2d7347b1ee53
|
| 3 |
size 236491269
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 118253458
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e2079a756a8358ae3a535c523dc50111795059680977ed08b4832ffbac8ef5fc
|
| 3 |
size 118253458
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15597
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8af9d4596051180f9613336aed3a4246c78a50ebaf3faba7d98ece3fdb0a943a
|
| 3 |
size 15597
|
last-checkpoint/scaler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 557
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ccbda19fc21cde44b0ae7a422108e69de01877a51e50220752bf822b9a78b1f9
|
| 3 |
size 557
|
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:c5962a4375a7ac9a133f1b777607905c970b63f4d098090eca341092be76e05b
|
| 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,
|
|
@@ -855,11 +855,296 @@
|
|
| 855 |
"eval_samples_per_second": 603.314,
|
| 856 |
"eval_steps_per_second": 37.707,
|
| 857 |
"step": 68820
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 858 |
}
|
| 859 |
],
|
| 860 |
"max_steps": 321160,
|
| 861 |
"num_train_epochs": 14,
|
| 862 |
-
"total_flos":
|
| 863 |
"trial_name": null,
|
| 864 |
"trial_params": null
|
| 865 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 4.0,
|
| 5 |
+
"global_step": 91760,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 855 |
"eval_samples_per_second": 603.314,
|
| 856 |
"eval_steps_per_second": 37.707,
|
| 857 |
"step": 68820
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 3.01,
|
| 861 |
+
"learning_rate": 7.93173726521318e-05,
|
| 862 |
+
"loss": 1.8202,
|
| 863 |
+
"step": 69000
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 3.03,
|
| 867 |
+
"learning_rate": 7.916011423251602e-05,
|
| 868 |
+
"loss": 1.8172,
|
| 869 |
+
"step": 69500
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 3.05,
|
| 873 |
+
"learning_rate": 7.900285581290023e-05,
|
| 874 |
+
"loss": 1.8126,
|
| 875 |
+
"step": 70000
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 3.07,
|
| 879 |
+
"learning_rate": 7.884591191012367e-05,
|
| 880 |
+
"loss": 1.8141,
|
| 881 |
+
"step": 70500
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 3.1,
|
| 885 |
+
"learning_rate": 7.868865349050788e-05,
|
| 886 |
+
"loss": 1.8052,
|
| 887 |
+
"step": 71000
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 3.12,
|
| 891 |
+
"learning_rate": 7.85313950708921e-05,
|
| 892 |
+
"loss": 1.8075,
|
| 893 |
+
"step": 71500
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 3.14,
|
| 897 |
+
"learning_rate": 7.83741366512763e-05,
|
| 898 |
+
"loss": 1.8115,
|
| 899 |
+
"step": 72000
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 3.16,
|
| 903 |
+
"learning_rate": 7.821719274849975e-05,
|
| 904 |
+
"loss": 1.8076,
|
| 905 |
+
"step": 72500
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 3.18,
|
| 909 |
+
"learning_rate": 7.805993432888397e-05,
|
| 910 |
+
"loss": 1.8078,
|
| 911 |
+
"step": 73000
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 3.2,
|
| 915 |
+
"learning_rate": 7.790267590926819e-05,
|
| 916 |
+
"loss": 1.8015,
|
| 917 |
+
"step": 73500
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 3.23,
|
| 921 |
+
"learning_rate": 7.77454174896524e-05,
|
| 922 |
+
"loss": 1.8043,
|
| 923 |
+
"step": 74000
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 3.25,
|
| 927 |
+
"learning_rate": 7.758847358687584e-05,
|
| 928 |
+
"loss": 1.8002,
|
| 929 |
+
"step": 74500
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 3.27,
|
| 933 |
+
"learning_rate": 7.743121516726006e-05,
|
| 934 |
+
"loss": 1.7954,
|
| 935 |
+
"step": 75000
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 3.29,
|
| 939 |
+
"learning_rate": 7.727395674764428e-05,
|
| 940 |
+
"loss": 1.7936,
|
| 941 |
+
"step": 75500
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 3.31,
|
| 945 |
+
"learning_rate": 7.711669832802849e-05,
|
| 946 |
+
"loss": 1.7903,
|
| 947 |
+
"step": 76000
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 3.33,
|
| 951 |
+
"learning_rate": 7.695975442525193e-05,
|
| 952 |
+
"loss": 1.7951,
|
| 953 |
+
"step": 76500
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 3.36,
|
| 957 |
+
"learning_rate": 7.680249600563615e-05,
|
| 958 |
+
"loss": 1.7946,
|
| 959 |
+
"step": 77000
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 3.38,
|
| 963 |
+
"learning_rate": 7.664523758602035e-05,
|
| 964 |
+
"loss": 1.7946,
|
| 965 |
+
"step": 77500
|
| 966 |
+
},
|
| 967 |
+
{
|
| 968 |
+
"epoch": 3.4,
|
| 969 |
+
"learning_rate": 7.648797916640458e-05,
|
| 970 |
+
"loss": 1.7902,
|
| 971 |
+
"step": 78000
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 3.42,
|
| 975 |
+
"learning_rate": 7.633103526362802e-05,
|
| 976 |
+
"loss": 1.7905,
|
| 977 |
+
"step": 78500
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 3.44,
|
| 981 |
+
"learning_rate": 7.617377684401223e-05,
|
| 982 |
+
"loss": 1.7898,
|
| 983 |
+
"step": 79000
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 3.47,
|
| 987 |
+
"learning_rate": 7.601651842439644e-05,
|
| 988 |
+
"loss": 1.7885,
|
| 989 |
+
"step": 79500
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 3.49,
|
| 993 |
+
"learning_rate": 7.585926000478067e-05,
|
| 994 |
+
"loss": 1.7852,
|
| 995 |
+
"step": 80000
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 3.51,
|
| 999 |
+
"learning_rate": 7.57023161020041e-05,
|
| 1000 |
+
"loss": 1.7815,
|
| 1001 |
+
"step": 80500
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 3.53,
|
| 1005 |
+
"learning_rate": 7.554505768238832e-05,
|
| 1006 |
+
"loss": 1.7833,
|
| 1007 |
+
"step": 81000
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 3.55,
|
| 1011 |
+
"learning_rate": 7.538779926277253e-05,
|
| 1012 |
+
"loss": 1.7815,
|
| 1013 |
+
"step": 81500
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 3.57,
|
| 1017 |
+
"learning_rate": 7.523054084315676e-05,
|
| 1018 |
+
"loss": 1.7778,
|
| 1019 |
+
"step": 82000
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 3.6,
|
| 1023 |
+
"learning_rate": 7.507359694038019e-05,
|
| 1024 |
+
"loss": 1.7811,
|
| 1025 |
+
"step": 82500
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 3.62,
|
| 1029 |
+
"learning_rate": 7.491633852076441e-05,
|
| 1030 |
+
"loss": 1.7786,
|
| 1031 |
+
"step": 83000
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 3.64,
|
| 1035 |
+
"learning_rate": 7.475908010114862e-05,
|
| 1036 |
+
"loss": 1.7767,
|
| 1037 |
+
"step": 83500
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 3.66,
|
| 1041 |
+
"learning_rate": 7.460182168153283e-05,
|
| 1042 |
+
"loss": 1.7804,
|
| 1043 |
+
"step": 84000
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 3.68,
|
| 1047 |
+
"learning_rate": 7.444487777875628e-05,
|
| 1048 |
+
"loss": 1.7716,
|
| 1049 |
+
"step": 84500
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 3.71,
|
| 1053 |
+
"learning_rate": 7.428761935914049e-05,
|
| 1054 |
+
"loss": 1.7777,
|
| 1055 |
+
"step": 85000
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 3.73,
|
| 1059 |
+
"learning_rate": 7.41303609395247e-05,
|
| 1060 |
+
"loss": 1.7712,
|
| 1061 |
+
"step": 85500
|
| 1062 |
+
},
|
| 1063 |
+
{
|
| 1064 |
+
"epoch": 3.75,
|
| 1065 |
+
"learning_rate": 7.397310251990892e-05,
|
| 1066 |
+
"loss": 1.7678,
|
| 1067 |
+
"step": 86000
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 3.77,
|
| 1071 |
+
"learning_rate": 7.381615861713237e-05,
|
| 1072 |
+
"loss": 1.7702,
|
| 1073 |
+
"step": 86500
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 3.79,
|
| 1077 |
+
"learning_rate": 7.365890019751658e-05,
|
| 1078 |
+
"loss": 1.7701,
|
| 1079 |
+
"step": 87000
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 3.81,
|
| 1083 |
+
"learning_rate": 7.350164177790079e-05,
|
| 1084 |
+
"loss": 1.7689,
|
| 1085 |
+
"step": 87500
|
| 1086 |
+
},
|
| 1087 |
+
{
|
| 1088 |
+
"epoch": 3.84,
|
| 1089 |
+
"learning_rate": 7.334438335828501e-05,
|
| 1090 |
+
"loss": 1.7665,
|
| 1091 |
+
"step": 88000
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 3.86,
|
| 1095 |
+
"learning_rate": 7.318743945550846e-05,
|
| 1096 |
+
"loss": 1.7711,
|
| 1097 |
+
"step": 88500
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 3.88,
|
| 1101 |
+
"learning_rate": 7.303018103589267e-05,
|
| 1102 |
+
"loss": 1.7626,
|
| 1103 |
+
"step": 89000
|
| 1104 |
+
},
|
| 1105 |
+
{
|
| 1106 |
+
"epoch": 3.9,
|
| 1107 |
+
"learning_rate": 7.287292261627688e-05,
|
| 1108 |
+
"loss": 1.7628,
|
| 1109 |
+
"step": 89500
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 3.92,
|
| 1113 |
+
"learning_rate": 7.271566419666109e-05,
|
| 1114 |
+
"loss": 1.7589,
|
| 1115 |
+
"step": 90000
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 3.95,
|
| 1119 |
+
"learning_rate": 7.255872029388455e-05,
|
| 1120 |
+
"loss": 1.7614,
|
| 1121 |
+
"step": 90500
|
| 1122 |
+
},
|
| 1123 |
+
{
|
| 1124 |
+
"epoch": 3.97,
|
| 1125 |
+
"learning_rate": 7.240146187426874e-05,
|
| 1126 |
+
"loss": 1.7646,
|
| 1127 |
+
"step": 91000
|
| 1128 |
+
},
|
| 1129 |
+
{
|
| 1130 |
+
"epoch": 3.99,
|
| 1131 |
+
"learning_rate": 7.224420345465297e-05,
|
| 1132 |
+
"loss": 1.7636,
|
| 1133 |
+
"step": 91500
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 4.0,
|
| 1137 |
+
"eval_accuracy": 0.6662888180155826,
|
| 1138 |
+
"eval_loss": 1.6273692846298218,
|
| 1139 |
+
"eval_runtime": 294.4726,
|
| 1140 |
+
"eval_samples_per_second": 604.307,
|
| 1141 |
+
"eval_steps_per_second": 37.769,
|
| 1142 |
+
"step": 91760
|
| 1143 |
}
|
| 1144 |
],
|
| 1145 |
"max_steps": 321160,
|
| 1146 |
"num_train_epochs": 14,
|
| 1147 |
+
"total_flos": 6.9770786168245e+17,
|
| 1148 |
"trial_name": null,
|
| 1149 |
"trial_params": null
|
| 1150 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 118253458
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e2079a756a8358ae3a535c523dc50111795059680977ed08b4832ffbac8ef5fc
|
| 3 |
size 118253458
|
runs/Feb20_18-29-06_ubuntu-2004/events.out.tfevents.1676885357.ubuntu-2004.887393.0
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 sha256:0c61cb2a0b744c6498ef70bdac9f8c45f62963b3650e88b2e9078f86270e723f
|
| 3 |
+
size 34268
|