Training in progress, step 1500, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1304192904
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:95ceecdd0b1aa2dbf1ec2f23a4ddd928595c382511d085f0d1663c9722b61ee1
|
| 3 |
size 1304192904
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2608620781
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c6a4cdb23fbf57119940af942e16735f7e6ed513337f644de9af3a2da6bc01e6
|
| 3 |
size 2608620781
|
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:a0dde6cfb71c791201a1b9da1c3a5b4ebadc80456fb340adc64cdc8144e3ec77
|
| 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 sha256:94619124ebef073ef434567921b91695bdc23ddab6d107310abf209634914efe
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.2986587882041931,
|
| 3 |
"best_model_checkpoint": "./results/checkpoint-180",
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 20,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -807,6 +807,406 @@
|
|
| 807 |
"eval_samples_per_second": 9.897,
|
| 808 |
"eval_steps_per_second": 2.523,
|
| 809 |
"step": 1000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 810 |
}
|
| 811 |
],
|
| 812 |
"logging_steps": 20,
|
|
@@ -826,7 +1226,7 @@
|
|
| 826 |
"attributes": {}
|
| 827 |
}
|
| 828 |
},
|
| 829 |
-
"total_flos":
|
| 830 |
"train_batch_size": 4,
|
| 831 |
"trial_name": null,
|
| 832 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.2986587882041931,
|
| 3 |
"best_model_checkpoint": "./results/checkpoint-180",
|
| 4 |
+
"epoch": 4.531722054380665,
|
| 5 |
"eval_steps": 20,
|
| 6 |
+
"global_step": 1500,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 807 |
"eval_samples_per_second": 9.897,
|
| 808 |
"eval_steps_per_second": 2.523,
|
| 809 |
"step": 1000
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 3.081570996978852,
|
| 813 |
+
"grad_norm": 0.047077979892492294,
|
| 814 |
+
"learning_rate": 7.673716012084593e-06,
|
| 815 |
+
"loss": 0.2093,
|
| 816 |
+
"step": 1020
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 3.081570996978852,
|
| 820 |
+
"eval_accuracy": 0.9019607843137255,
|
| 821 |
+
"eval_loss": 0.4630826711654663,
|
| 822 |
+
"eval_runtime": 16.4745,
|
| 823 |
+
"eval_samples_per_second": 9.287,
|
| 824 |
+
"eval_steps_per_second": 2.367,
|
| 825 |
+
"step": 1020
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 3.1419939577039275,
|
| 829 |
+
"grad_norm": 0.07947070896625519,
|
| 830 |
+
"learning_rate": 7.432024169184291e-06,
|
| 831 |
+
"loss": 0.2436,
|
| 832 |
+
"step": 1040
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 3.1419939577039275,
|
| 836 |
+
"eval_accuracy": 0.869281045751634,
|
| 837 |
+
"eval_loss": 0.5888116359710693,
|
| 838 |
+
"eval_runtime": 15.2662,
|
| 839 |
+
"eval_samples_per_second": 10.022,
|
| 840 |
+
"eval_steps_per_second": 2.555,
|
| 841 |
+
"step": 1040
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 3.202416918429003,
|
| 845 |
+
"grad_norm": 1.2857632637023926,
|
| 846 |
+
"learning_rate": 7.190332326283988e-06,
|
| 847 |
+
"loss": 0.1375,
|
| 848 |
+
"step": 1060
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 3.202416918429003,
|
| 852 |
+
"eval_accuracy": 0.8888888888888888,
|
| 853 |
+
"eval_loss": 0.6457459926605225,
|
| 854 |
+
"eval_runtime": 15.6557,
|
| 855 |
+
"eval_samples_per_second": 9.773,
|
| 856 |
+
"eval_steps_per_second": 2.491,
|
| 857 |
+
"step": 1060
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 3.2628398791540785,
|
| 861 |
+
"grad_norm": 0.029293788596987724,
|
| 862 |
+
"learning_rate": 6.948640483383686e-06,
|
| 863 |
+
"loss": 0.0049,
|
| 864 |
+
"step": 1080
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 3.2628398791540785,
|
| 868 |
+
"eval_accuracy": 0.8888888888888888,
|
| 869 |
+
"eval_loss": 0.6600757837295532,
|
| 870 |
+
"eval_runtime": 15.5566,
|
| 871 |
+
"eval_samples_per_second": 9.835,
|
| 872 |
+
"eval_steps_per_second": 2.507,
|
| 873 |
+
"step": 1080
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 3.323262839879154,
|
| 877 |
+
"grad_norm": 0.01973886974155903,
|
| 878 |
+
"learning_rate": 6.706948640483384e-06,
|
| 879 |
+
"loss": 0.0089,
|
| 880 |
+
"step": 1100
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 3.323262839879154,
|
| 884 |
+
"eval_accuracy": 0.8823529411764706,
|
| 885 |
+
"eval_loss": 0.6461706161499023,
|
| 886 |
+
"eval_runtime": 15.4515,
|
| 887 |
+
"eval_samples_per_second": 9.902,
|
| 888 |
+
"eval_steps_per_second": 2.524,
|
| 889 |
+
"step": 1100
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 3.38368580060423,
|
| 893 |
+
"grad_norm": 0.0038618145044893026,
|
| 894 |
+
"learning_rate": 6.465256797583082e-06,
|
| 895 |
+
"loss": 0.0616,
|
| 896 |
+
"step": 1120
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 3.38368580060423,
|
| 900 |
+
"eval_accuracy": 0.8888888888888888,
|
| 901 |
+
"eval_loss": 0.6607339978218079,
|
| 902 |
+
"eval_runtime": 15.5198,
|
| 903 |
+
"eval_samples_per_second": 9.858,
|
| 904 |
+
"eval_steps_per_second": 2.513,
|
| 905 |
+
"step": 1120
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 3.4441087613293053,
|
| 909 |
+
"grad_norm": 0.009797470644116402,
|
| 910 |
+
"learning_rate": 6.22356495468278e-06,
|
| 911 |
+
"loss": 0.006,
|
| 912 |
+
"step": 1140
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 3.4441087613293053,
|
| 916 |
+
"eval_accuracy": 0.9019607843137255,
|
| 917 |
+
"eval_loss": 0.6243405938148499,
|
| 918 |
+
"eval_runtime": 15.5129,
|
| 919 |
+
"eval_samples_per_second": 9.863,
|
| 920 |
+
"eval_steps_per_second": 2.514,
|
| 921 |
+
"step": 1140
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 3.504531722054381,
|
| 925 |
+
"grad_norm": 0.01924210786819458,
|
| 926 |
+
"learning_rate": 5.981873111782478e-06,
|
| 927 |
+
"loss": 0.1769,
|
| 928 |
+
"step": 1160
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 3.504531722054381,
|
| 932 |
+
"eval_accuracy": 0.9019607843137255,
|
| 933 |
+
"eval_loss": 0.5256864428520203,
|
| 934 |
+
"eval_runtime": 15.4982,
|
| 935 |
+
"eval_samples_per_second": 9.872,
|
| 936 |
+
"eval_steps_per_second": 2.516,
|
| 937 |
+
"step": 1160
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 3.5649546827794563,
|
| 941 |
+
"grad_norm": 0.06478149443864822,
|
| 942 |
+
"learning_rate": 5.7401812688821754e-06,
|
| 943 |
+
"loss": 0.0044,
|
| 944 |
+
"step": 1180
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 3.5649546827794563,
|
| 948 |
+
"eval_accuracy": 0.9084967320261438,
|
| 949 |
+
"eval_loss": 0.5507912039756775,
|
| 950 |
+
"eval_runtime": 15.4829,
|
| 951 |
+
"eval_samples_per_second": 9.882,
|
| 952 |
+
"eval_steps_per_second": 2.519,
|
| 953 |
+
"step": 1180
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 3.6253776435045317,
|
| 957 |
+
"grad_norm": 0.14462168514728546,
|
| 958 |
+
"learning_rate": 5.498489425981873e-06,
|
| 959 |
+
"loss": 0.2295,
|
| 960 |
+
"step": 1200
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 3.6253776435045317,
|
| 964 |
+
"eval_accuracy": 0.9150326797385621,
|
| 965 |
+
"eval_loss": 0.48460787534713745,
|
| 966 |
+
"eval_runtime": 15.4689,
|
| 967 |
+
"eval_samples_per_second": 9.891,
|
| 968 |
+
"eval_steps_per_second": 2.521,
|
| 969 |
+
"step": 1200
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 3.685800604229607,
|
| 973 |
+
"grad_norm": 0.004326341208070517,
|
| 974 |
+
"learning_rate": 5.2567975830815706e-06,
|
| 975 |
+
"loss": 0.1175,
|
| 976 |
+
"step": 1220
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 3.685800604229607,
|
| 980 |
+
"eval_accuracy": 0.9019607843137255,
|
| 981 |
+
"eval_loss": 0.4763535261154175,
|
| 982 |
+
"eval_runtime": 15.4639,
|
| 983 |
+
"eval_samples_per_second": 9.894,
|
| 984 |
+
"eval_steps_per_second": 2.522,
|
| 985 |
+
"step": 1220
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 3.7462235649546827,
|
| 989 |
+
"grad_norm": 0.016803044825792313,
|
| 990 |
+
"learning_rate": 5.01510574018127e-06,
|
| 991 |
+
"loss": 0.0746,
|
| 992 |
+
"step": 1240
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 3.7462235649546827,
|
| 996 |
+
"eval_accuracy": 0.9019607843137255,
|
| 997 |
+
"eval_loss": 0.4760640561580658,
|
| 998 |
+
"eval_runtime": 15.4735,
|
| 999 |
+
"eval_samples_per_second": 9.888,
|
| 1000 |
+
"eval_steps_per_second": 2.52,
|
| 1001 |
+
"step": 1240
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 3.806646525679758,
|
| 1005 |
+
"grad_norm": 0.024552155286073685,
|
| 1006 |
+
"learning_rate": 4.773413897280967e-06,
|
| 1007 |
+
"loss": 0.0222,
|
| 1008 |
+
"step": 1260
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 3.806646525679758,
|
| 1012 |
+
"eval_accuracy": 0.9019607843137255,
|
| 1013 |
+
"eval_loss": 0.48361214995384216,
|
| 1014 |
+
"eval_runtime": 15.4614,
|
| 1015 |
+
"eval_samples_per_second": 9.896,
|
| 1016 |
+
"eval_steps_per_second": 2.522,
|
| 1017 |
+
"step": 1260
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 3.8670694864048336,
|
| 1021 |
+
"grad_norm": 0.04030178114771843,
|
| 1022 |
+
"learning_rate": 4.531722054380665e-06,
|
| 1023 |
+
"loss": 0.0012,
|
| 1024 |
+
"step": 1280
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 3.8670694864048336,
|
| 1028 |
+
"eval_accuracy": 0.9215686274509803,
|
| 1029 |
+
"eval_loss": 0.4774629771709442,
|
| 1030 |
+
"eval_runtime": 15.4388,
|
| 1031 |
+
"eval_samples_per_second": 9.91,
|
| 1032 |
+
"eval_steps_per_second": 2.526,
|
| 1033 |
+
"step": 1280
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 3.9274924471299095,
|
| 1037 |
+
"grad_norm": 0.030293526127934456,
|
| 1038 |
+
"learning_rate": 4.2900302114803626e-06,
|
| 1039 |
+
"loss": 0.2131,
|
| 1040 |
+
"step": 1300
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 3.9274924471299095,
|
| 1044 |
+
"eval_accuracy": 0.9019607843137255,
|
| 1045 |
+
"eval_loss": 0.46071678400039673,
|
| 1046 |
+
"eval_runtime": 15.4357,
|
| 1047 |
+
"eval_samples_per_second": 9.912,
|
| 1048 |
+
"eval_steps_per_second": 2.527,
|
| 1049 |
+
"step": 1300
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 3.987915407854985,
|
| 1053 |
+
"grad_norm": 0.04355171322822571,
|
| 1054 |
+
"learning_rate": 4.048338368580061e-06,
|
| 1055 |
+
"loss": 0.0006,
|
| 1056 |
+
"step": 1320
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 3.987915407854985,
|
| 1060 |
+
"eval_accuracy": 0.9084967320261438,
|
| 1061 |
+
"eval_loss": 0.4934905767440796,
|
| 1062 |
+
"eval_runtime": 15.4993,
|
| 1063 |
+
"eval_samples_per_second": 9.871,
|
| 1064 |
+
"eval_steps_per_second": 2.516,
|
| 1065 |
+
"step": 1320
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 4.04833836858006,
|
| 1069 |
+
"grad_norm": 0.023308318108320236,
|
| 1070 |
+
"learning_rate": 3.8066465256797586e-06,
|
| 1071 |
+
"loss": 0.0758,
|
| 1072 |
+
"step": 1340
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 4.04833836858006,
|
| 1076 |
+
"eval_accuracy": 0.9019607843137255,
|
| 1077 |
+
"eval_loss": 0.4591919183731079,
|
| 1078 |
+
"eval_runtime": 15.4907,
|
| 1079 |
+
"eval_samples_per_second": 9.877,
|
| 1080 |
+
"eval_steps_per_second": 2.518,
|
| 1081 |
+
"step": 1340
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 4.108761329305136,
|
| 1085 |
+
"grad_norm": 0.007429028861224651,
|
| 1086 |
+
"learning_rate": 3.564954682779456e-06,
|
| 1087 |
+
"loss": 0.1466,
|
| 1088 |
+
"step": 1360
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 4.108761329305136,
|
| 1092 |
+
"eval_accuracy": 0.9084967320261438,
|
| 1093 |
+
"eval_loss": 0.4464338719844818,
|
| 1094 |
+
"eval_runtime": 15.4771,
|
| 1095 |
+
"eval_samples_per_second": 9.886,
|
| 1096 |
+
"eval_steps_per_second": 2.52,
|
| 1097 |
+
"step": 1360
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 4.169184290030212,
|
| 1101 |
+
"grad_norm": 0.019125748425722122,
|
| 1102 |
+
"learning_rate": 3.3232628398791546e-06,
|
| 1103 |
+
"loss": 0.0488,
|
| 1104 |
+
"step": 1380
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 4.169184290030212,
|
| 1108 |
+
"eval_accuracy": 0.9084967320261438,
|
| 1109 |
+
"eval_loss": 0.4816044867038727,
|
| 1110 |
+
"eval_runtime": 15.4856,
|
| 1111 |
+
"eval_samples_per_second": 9.88,
|
| 1112 |
+
"eval_steps_per_second": 2.518,
|
| 1113 |
+
"step": 1380
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 4.229607250755287,
|
| 1117 |
+
"grad_norm": 0.02935463935136795,
|
| 1118 |
+
"learning_rate": 3.081570996978852e-06,
|
| 1119 |
+
"loss": 0.0014,
|
| 1120 |
+
"step": 1400
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"epoch": 4.229607250755287,
|
| 1124 |
+
"eval_accuracy": 0.9150326797385621,
|
| 1125 |
+
"eval_loss": 0.4570343494415283,
|
| 1126 |
+
"eval_runtime": 15.452,
|
| 1127 |
+
"eval_samples_per_second": 9.902,
|
| 1128 |
+
"eval_steps_per_second": 2.524,
|
| 1129 |
+
"step": 1400
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 4.290030211480363,
|
| 1133 |
+
"grad_norm": 0.05864783003926277,
|
| 1134 |
+
"learning_rate": 2.83987915407855e-06,
|
| 1135 |
+
"loss": 0.082,
|
| 1136 |
+
"step": 1420
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 4.290030211480363,
|
| 1140 |
+
"eval_accuracy": 0.9215686274509803,
|
| 1141 |
+
"eval_loss": 0.45447495579719543,
|
| 1142 |
+
"eval_runtime": 15.4821,
|
| 1143 |
+
"eval_samples_per_second": 9.882,
|
| 1144 |
+
"eval_steps_per_second": 2.519,
|
| 1145 |
+
"step": 1420
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 4.350453172205438,
|
| 1149 |
+
"grad_norm": 1.1889474391937256,
|
| 1150 |
+
"learning_rate": 2.598187311178248e-06,
|
| 1151 |
+
"loss": 0.0009,
|
| 1152 |
+
"step": 1440
|
| 1153 |
+
},
|
| 1154 |
+
{
|
| 1155 |
+
"epoch": 4.350453172205438,
|
| 1156 |
+
"eval_accuracy": 0.9150326797385621,
|
| 1157 |
+
"eval_loss": 0.4721324145793915,
|
| 1158 |
+
"eval_runtime": 15.4932,
|
| 1159 |
+
"eval_samples_per_second": 9.875,
|
| 1160 |
+
"eval_steps_per_second": 2.517,
|
| 1161 |
+
"step": 1440
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 4.410876132930514,
|
| 1165 |
+
"grad_norm": 0.017764601856470108,
|
| 1166 |
+
"learning_rate": 2.3564954682779457e-06,
|
| 1167 |
+
"loss": 0.0008,
|
| 1168 |
+
"step": 1460
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 4.410876132930514,
|
| 1172 |
+
"eval_accuracy": 0.9215686274509803,
|
| 1173 |
+
"eval_loss": 0.4873809814453125,
|
| 1174 |
+
"eval_runtime": 15.477,
|
| 1175 |
+
"eval_samples_per_second": 9.886,
|
| 1176 |
+
"eval_steps_per_second": 2.52,
|
| 1177 |
+
"step": 1460
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 4.471299093655589,
|
| 1181 |
+
"grad_norm": 0.016238484531641006,
|
| 1182 |
+
"learning_rate": 2.1148036253776437e-06,
|
| 1183 |
+
"loss": 0.0014,
|
| 1184 |
+
"step": 1480
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 4.471299093655589,
|
| 1188 |
+
"eval_accuracy": 0.9150326797385621,
|
| 1189 |
+
"eval_loss": 0.5002758502960205,
|
| 1190 |
+
"eval_runtime": 15.4881,
|
| 1191 |
+
"eval_samples_per_second": 9.879,
|
| 1192 |
+
"eval_steps_per_second": 2.518,
|
| 1193 |
+
"step": 1480
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 4.531722054380665,
|
| 1197 |
+
"grad_norm": 0.037868522107601166,
|
| 1198 |
+
"learning_rate": 1.8731117824773415e-06,
|
| 1199 |
+
"loss": 0.1612,
|
| 1200 |
+
"step": 1500
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 4.531722054380665,
|
| 1204 |
+
"eval_accuracy": 0.9150326797385621,
|
| 1205 |
+
"eval_loss": 0.5064195394515991,
|
| 1206 |
+
"eval_runtime": 15.5013,
|
| 1207 |
+
"eval_samples_per_second": 9.87,
|
| 1208 |
+
"eval_steps_per_second": 2.516,
|
| 1209 |
+
"step": 1500
|
| 1210 |
}
|
| 1211 |
],
|
| 1212 |
"logging_steps": 20,
|
|
|
|
| 1226 |
"attributes": {}
|
| 1227 |
}
|
| 1228 |
},
|
| 1229 |
+
"total_flos": 4844949162060756.0,
|
| 1230 |
"train_batch_size": 4,
|
| 1231 |
"trial_name": null,
|
| 1232 |
"trial_params": null
|