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:d8531674f361d182c891832698f501d99806f4a54ed644f913a7d6cceb4fcd09
|
| 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:dd3900014829cff936e288455c77cc8b24c817e5bdea4b3c8b0a9a2a3b7ae871
|
| 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 sha256:57ce7f83dafbabb337ab4f899de43a8d1e2ad1723ca17b896a002cebd19940f6
|
| 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 sha256:303407244c6d788bc550e7a7560bf135b9af5a2f148beb7dd1c9b2a263c088ce
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "./results/checkpoint-
|
| 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": 10.737,
|
| 808 |
"eval_steps_per_second": 2.72,
|
| 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": 0.2884907126426697,
|
| 3 |
+
"best_model_checkpoint": "./results/checkpoint-1440",
|
| 4 |
+
"epoch": 4.601226993865031,
|
| 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": 10.737,
|
| 808 |
"eval_steps_per_second": 2.72,
|
| 809 |
"step": 1000
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 3.128834355828221,
|
| 813 |
+
"grad_norm": 0.021293368190526962,
|
| 814 |
+
"learning_rate": 7.484662576687118e-06,
|
| 815 |
+
"loss": 0.1619,
|
| 816 |
+
"step": 1020
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 3.128834355828221,
|
| 820 |
+
"eval_accuracy": 0.9133333333333333,
|
| 821 |
+
"eval_loss": 0.4180934429168701,
|
| 822 |
+
"eval_runtime": 14.3308,
|
| 823 |
+
"eval_samples_per_second": 10.467,
|
| 824 |
+
"eval_steps_per_second": 2.652,
|
| 825 |
+
"step": 1020
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 3.190184049079755,
|
| 829 |
+
"grad_norm": 14.229204177856445,
|
| 830 |
+
"learning_rate": 7.239263803680983e-06,
|
| 831 |
+
"loss": 0.1849,
|
| 832 |
+
"step": 1040
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 3.190184049079755,
|
| 836 |
+
"eval_accuracy": 0.92,
|
| 837 |
+
"eval_loss": 0.47268736362457275,
|
| 838 |
+
"eval_runtime": 13.9315,
|
| 839 |
+
"eval_samples_per_second": 10.767,
|
| 840 |
+
"eval_steps_per_second": 2.728,
|
| 841 |
+
"step": 1040
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 3.2515337423312882,
|
| 845 |
+
"grad_norm": 0.017998775467276573,
|
| 846 |
+
"learning_rate": 6.993865030674847e-06,
|
| 847 |
+
"loss": 0.1949,
|
| 848 |
+
"step": 1060
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 3.2515337423312882,
|
| 852 |
+
"eval_accuracy": 0.8933333333333333,
|
| 853 |
+
"eval_loss": 0.3345566689968109,
|
| 854 |
+
"eval_runtime": 14.0413,
|
| 855 |
+
"eval_samples_per_second": 10.683,
|
| 856 |
+
"eval_steps_per_second": 2.706,
|
| 857 |
+
"step": 1060
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 3.312883435582822,
|
| 861 |
+
"grad_norm": 0.020114585757255554,
|
| 862 |
+
"learning_rate": 6.748466257668712e-06,
|
| 863 |
+
"loss": 0.1796,
|
| 864 |
+
"step": 1080
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 3.312883435582822,
|
| 868 |
+
"eval_accuracy": 0.9266666666666666,
|
| 869 |
+
"eval_loss": 0.3471291661262512,
|
| 870 |
+
"eval_runtime": 13.9741,
|
| 871 |
+
"eval_samples_per_second": 10.734,
|
| 872 |
+
"eval_steps_per_second": 2.719,
|
| 873 |
+
"step": 1080
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 3.374233128834356,
|
| 877 |
+
"grad_norm": 0.013905039988458157,
|
| 878 |
+
"learning_rate": 6.503067484662578e-06,
|
| 879 |
+
"loss": 0.086,
|
| 880 |
+
"step": 1100
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 3.374233128834356,
|
| 884 |
+
"eval_accuracy": 0.8866666666666667,
|
| 885 |
+
"eval_loss": 0.4089130759239197,
|
| 886 |
+
"eval_runtime": 13.9473,
|
| 887 |
+
"eval_samples_per_second": 10.755,
|
| 888 |
+
"eval_steps_per_second": 2.725,
|
| 889 |
+
"step": 1100
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 3.4355828220858897,
|
| 893 |
+
"grad_norm": 0.009700474329292774,
|
| 894 |
+
"learning_rate": 6.257668711656443e-06,
|
| 895 |
+
"loss": 0.0187,
|
| 896 |
+
"step": 1120
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 3.4355828220858897,
|
| 900 |
+
"eval_accuracy": 0.92,
|
| 901 |
+
"eval_loss": 0.3867844045162201,
|
| 902 |
+
"eval_runtime": 14.013,
|
| 903 |
+
"eval_samples_per_second": 10.704,
|
| 904 |
+
"eval_steps_per_second": 2.712,
|
| 905 |
+
"step": 1120
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 3.4969325153374236,
|
| 909 |
+
"grad_norm": 0.003781616687774658,
|
| 910 |
+
"learning_rate": 6.012269938650307e-06,
|
| 911 |
+
"loss": 0.0768,
|
| 912 |
+
"step": 1140
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 3.4969325153374236,
|
| 916 |
+
"eval_accuracy": 0.9266666666666666,
|
| 917 |
+
"eval_loss": 0.4095223546028137,
|
| 918 |
+
"eval_runtime": 13.9902,
|
| 919 |
+
"eval_samples_per_second": 10.722,
|
| 920 |
+
"eval_steps_per_second": 2.716,
|
| 921 |
+
"step": 1140
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 3.558282208588957,
|
| 925 |
+
"grad_norm": 0.21029236912727356,
|
| 926 |
+
"learning_rate": 5.766871165644172e-06,
|
| 927 |
+
"loss": 0.0008,
|
| 928 |
+
"step": 1160
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 3.558282208588957,
|
| 932 |
+
"eval_accuracy": 0.9066666666666666,
|
| 933 |
+
"eval_loss": 0.3779890835285187,
|
| 934 |
+
"eval_runtime": 13.9578,
|
| 935 |
+
"eval_samples_per_second": 10.747,
|
| 936 |
+
"eval_steps_per_second": 2.722,
|
| 937 |
+
"step": 1160
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 3.6196319018404908,
|
| 941 |
+
"grad_norm": 0.032502181828022,
|
| 942 |
+
"learning_rate": 5.521472392638038e-06,
|
| 943 |
+
"loss": 0.183,
|
| 944 |
+
"step": 1180
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 3.6196319018404908,
|
| 948 |
+
"eval_accuracy": 0.9,
|
| 949 |
+
"eval_loss": 0.3827475905418396,
|
| 950 |
+
"eval_runtime": 13.933,
|
| 951 |
+
"eval_samples_per_second": 10.766,
|
| 952 |
+
"eval_steps_per_second": 2.727,
|
| 953 |
+
"step": 1180
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 3.6809815950920246,
|
| 957 |
+
"grad_norm": 0.0289248526096344,
|
| 958 |
+
"learning_rate": 5.276073619631902e-06,
|
| 959 |
+
"loss": 0.204,
|
| 960 |
+
"step": 1200
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 3.6809815950920246,
|
| 964 |
+
"eval_accuracy": 0.9,
|
| 965 |
+
"eval_loss": 0.5132840871810913,
|
| 966 |
+
"eval_runtime": 13.9107,
|
| 967 |
+
"eval_samples_per_second": 10.783,
|
| 968 |
+
"eval_steps_per_second": 2.732,
|
| 969 |
+
"step": 1200
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 3.7423312883435584,
|
| 973 |
+
"grad_norm": 1.0068583488464355,
|
| 974 |
+
"learning_rate": 5.030674846625767e-06,
|
| 975 |
+
"loss": 0.0758,
|
| 976 |
+
"step": 1220
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 3.7423312883435584,
|
| 980 |
+
"eval_accuracy": 0.9133333333333333,
|
| 981 |
+
"eval_loss": 0.4279702305793762,
|
| 982 |
+
"eval_runtime": 13.8908,
|
| 983 |
+
"eval_samples_per_second": 10.799,
|
| 984 |
+
"eval_steps_per_second": 2.736,
|
| 985 |
+
"step": 1220
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 3.8036809815950923,
|
| 989 |
+
"grad_norm": 0.0101453373208642,
|
| 990 |
+
"learning_rate": 4.785276073619632e-06,
|
| 991 |
+
"loss": 0.0237,
|
| 992 |
+
"step": 1240
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 3.8036809815950923,
|
| 996 |
+
"eval_accuracy": 0.92,
|
| 997 |
+
"eval_loss": 0.3941916823387146,
|
| 998 |
+
"eval_runtime": 13.8887,
|
| 999 |
+
"eval_samples_per_second": 10.8,
|
| 1000 |
+
"eval_steps_per_second": 2.736,
|
| 1001 |
+
"step": 1240
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 3.8650306748466257,
|
| 1005 |
+
"grad_norm": 182.59510803222656,
|
| 1006 |
+
"learning_rate": 4.539877300613497e-06,
|
| 1007 |
+
"loss": 0.2143,
|
| 1008 |
+
"step": 1260
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 3.8650306748466257,
|
| 1012 |
+
"eval_accuracy": 0.9066666666666666,
|
| 1013 |
+
"eval_loss": 0.36801090836524963,
|
| 1014 |
+
"eval_runtime": 13.8946,
|
| 1015 |
+
"eval_samples_per_second": 10.796,
|
| 1016 |
+
"eval_steps_per_second": 2.735,
|
| 1017 |
+
"step": 1260
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 3.9263803680981595,
|
| 1021 |
+
"grad_norm": 0.03958132117986679,
|
| 1022 |
+
"learning_rate": 4.294478527607362e-06,
|
| 1023 |
+
"loss": 0.0106,
|
| 1024 |
+
"step": 1280
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 3.9263803680981595,
|
| 1028 |
+
"eval_accuracy": 0.8866666666666667,
|
| 1029 |
+
"eval_loss": 0.5633125901222229,
|
| 1030 |
+
"eval_runtime": 13.9747,
|
| 1031 |
+
"eval_samples_per_second": 10.734,
|
| 1032 |
+
"eval_steps_per_second": 2.719,
|
| 1033 |
+
"step": 1280
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 3.9877300613496933,
|
| 1037 |
+
"grad_norm": 140.984375,
|
| 1038 |
+
"learning_rate": 4.049079754601227e-06,
|
| 1039 |
+
"loss": 0.2221,
|
| 1040 |
+
"step": 1300
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 3.9877300613496933,
|
| 1044 |
+
"eval_accuracy": 0.92,
|
| 1045 |
+
"eval_loss": 0.38154712319374084,
|
| 1046 |
+
"eval_runtime": 13.996,
|
| 1047 |
+
"eval_samples_per_second": 10.717,
|
| 1048 |
+
"eval_steps_per_second": 2.715,
|
| 1049 |
+
"step": 1300
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 4.049079754601227,
|
| 1053 |
+
"grad_norm": 0.0037327792961150408,
|
| 1054 |
+
"learning_rate": 3.8036809815950928e-06,
|
| 1055 |
+
"loss": 0.0212,
|
| 1056 |
+
"step": 1320
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 4.049079754601227,
|
| 1060 |
+
"eval_accuracy": 0.9266666666666666,
|
| 1061 |
+
"eval_loss": 0.4598991274833679,
|
| 1062 |
+
"eval_runtime": 13.9374,
|
| 1063 |
+
"eval_samples_per_second": 10.762,
|
| 1064 |
+
"eval_steps_per_second": 2.726,
|
| 1065 |
+
"step": 1320
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 4.110429447852761,
|
| 1069 |
+
"grad_norm": 0.010530122555792332,
|
| 1070 |
+
"learning_rate": 3.5582822085889574e-06,
|
| 1071 |
+
"loss": 0.1678,
|
| 1072 |
+
"step": 1340
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 4.110429447852761,
|
| 1076 |
+
"eval_accuracy": 0.92,
|
| 1077 |
+
"eval_loss": 0.34579145908355713,
|
| 1078 |
+
"eval_runtime": 13.9042,
|
| 1079 |
+
"eval_samples_per_second": 10.788,
|
| 1080 |
+
"eval_steps_per_second": 2.733,
|
| 1081 |
+
"step": 1340
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 4.171779141104294,
|
| 1085 |
+
"grad_norm": 0.015701429918408394,
|
| 1086 |
+
"learning_rate": 3.312883435582822e-06,
|
| 1087 |
+
"loss": 0.1153,
|
| 1088 |
+
"step": 1360
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 4.171779141104294,
|
| 1092 |
+
"eval_accuracy": 0.92,
|
| 1093 |
+
"eval_loss": 0.3261447250843048,
|
| 1094 |
+
"eval_runtime": 13.9236,
|
| 1095 |
+
"eval_samples_per_second": 10.773,
|
| 1096 |
+
"eval_steps_per_second": 2.729,
|
| 1097 |
+
"step": 1360
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 4.233128834355828,
|
| 1101 |
+
"grad_norm": 0.011384344659745693,
|
| 1102 |
+
"learning_rate": 3.0674846625766875e-06,
|
| 1103 |
+
"loss": 0.0006,
|
| 1104 |
+
"step": 1380
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 4.233128834355828,
|
| 1108 |
+
"eval_accuracy": 0.9133333333333333,
|
| 1109 |
+
"eval_loss": 0.3404422998428345,
|
| 1110 |
+
"eval_runtime": 13.9552,
|
| 1111 |
+
"eval_samples_per_second": 10.749,
|
| 1112 |
+
"eval_steps_per_second": 2.723,
|
| 1113 |
+
"step": 1380
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 4.294478527607362,
|
| 1117 |
+
"grad_norm": 0.08929850906133652,
|
| 1118 |
+
"learning_rate": 2.822085889570552e-06,
|
| 1119 |
+
"loss": 0.0193,
|
| 1120 |
+
"step": 1400
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"epoch": 4.294478527607362,
|
| 1124 |
+
"eval_accuracy": 0.92,
|
| 1125 |
+
"eval_loss": 0.3601679503917694,
|
| 1126 |
+
"eval_runtime": 13.9574,
|
| 1127 |
+
"eval_samples_per_second": 10.747,
|
| 1128 |
+
"eval_steps_per_second": 2.723,
|
| 1129 |
+
"step": 1400
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 4.355828220858895,
|
| 1133 |
+
"grad_norm": 129.2814483642578,
|
| 1134 |
+
"learning_rate": 2.5766871165644175e-06,
|
| 1135 |
+
"loss": 0.0994,
|
| 1136 |
+
"step": 1420
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 4.355828220858895,
|
| 1140 |
+
"eval_accuracy": 0.94,
|
| 1141 |
+
"eval_loss": 0.33025145530700684,
|
| 1142 |
+
"eval_runtime": 13.9627,
|
| 1143 |
+
"eval_samples_per_second": 10.743,
|
| 1144 |
+
"eval_steps_per_second": 2.722,
|
| 1145 |
+
"step": 1420
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 4.41717791411043,
|
| 1149 |
+
"grad_norm": 0.024497592821717262,
|
| 1150 |
+
"learning_rate": 2.331288343558282e-06,
|
| 1151 |
+
"loss": 0.0032,
|
| 1152 |
+
"step": 1440
|
| 1153 |
+
},
|
| 1154 |
+
{
|
| 1155 |
+
"epoch": 4.41717791411043,
|
| 1156 |
+
"eval_accuracy": 0.94,
|
| 1157 |
+
"eval_loss": 0.2884907126426697,
|
| 1158 |
+
"eval_runtime": 13.9317,
|
| 1159 |
+
"eval_samples_per_second": 10.767,
|
| 1160 |
+
"eval_steps_per_second": 2.728,
|
| 1161 |
+
"step": 1440
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 4.478527607361963,
|
| 1165 |
+
"grad_norm": 0.009228991344571114,
|
| 1166 |
+
"learning_rate": 2.085889570552147e-06,
|
| 1167 |
+
"loss": 0.0008,
|
| 1168 |
+
"step": 1460
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 4.478527607361963,
|
| 1172 |
+
"eval_accuracy": 0.92,
|
| 1173 |
+
"eval_loss": 0.31121641397476196,
|
| 1174 |
+
"eval_runtime": 13.9417,
|
| 1175 |
+
"eval_samples_per_second": 10.759,
|
| 1176 |
+
"eval_steps_per_second": 2.726,
|
| 1177 |
+
"step": 1460
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 4.539877300613497,
|
| 1181 |
+
"grad_norm": 0.22681556642055511,
|
| 1182 |
+
"learning_rate": 1.8404907975460124e-06,
|
| 1183 |
+
"loss": 0.0823,
|
| 1184 |
+
"step": 1480
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 4.539877300613497,
|
| 1188 |
+
"eval_accuracy": 0.9266666666666666,
|
| 1189 |
+
"eval_loss": 0.3145321011543274,
|
| 1190 |
+
"eval_runtime": 13.9075,
|
| 1191 |
+
"eval_samples_per_second": 10.786,
|
| 1192 |
+
"eval_steps_per_second": 2.732,
|
| 1193 |
+
"step": 1480
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 4.601226993865031,
|
| 1197 |
+
"grad_norm": 0.010360241867601871,
|
| 1198 |
+
"learning_rate": 1.5950920245398775e-06,
|
| 1199 |
+
"loss": 0.0086,
|
| 1200 |
+
"step": 1500
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 4.601226993865031,
|
| 1204 |
+
"eval_accuracy": 0.94,
|
| 1205 |
+
"eval_loss": 0.2954442799091339,
|
| 1206 |
+
"eval_runtime": 14.0025,
|
| 1207 |
+
"eval_samples_per_second": 10.712,
|
| 1208 |
+
"eval_steps_per_second": 2.714,
|
| 1209 |
+
"step": 1500
|
| 1210 |
}
|
| 1211 |
],
|
| 1212 |
"logging_steps": 20,
|
|
|
|
| 1226 |
"attributes": {}
|
| 1227 |
}
|
| 1228 |
},
|
| 1229 |
+
"total_flos": 4859676225851160.0,
|
| 1230 |
"train_batch_size": 4,
|
| 1231 |
"trial_name": null,
|
| 1232 |
"trial_params": null
|