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 410636248
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ee4e2d84e38cb73fc215ea160b72d8c65fb8ef814b9ce18e21001c4fceb2971e
|
| 3 |
size 410636248
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 821393658
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:db5189682206216f1eb6c749f032237c2b81ba6a5a04045dadba360a7ff157fd
|
| 3 |
size 821393658
|
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 sha256:70171b5cf4c5d65f8d1801780619a5ef6eaa49858f51f2d188c1b4ae2878778d
|
| 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 sha256:0db746135b039e0910ffb0031dacdf1ae5245ec4309f44b2f467d1af6778d5b2
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.20959021151065826,
|
| 3 |
"best_model_checkpoint": "./results/checkpoint-640",
|
| 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": 34.023,
|
| 808 |
"eval_steps_per_second": 8.619,
|
| 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": 0.20959021151065826,
|
| 3 |
"best_model_checkpoint": "./results/checkpoint-640",
|
| 4 |
+
"epoch": 4.615384615384615,
|
| 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": 34.023,
|
| 808 |
"eval_steps_per_second": 8.619,
|
| 809 |
"step": 1000
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 3.1384615384615384,
|
| 813 |
+
"grad_norm": 0.00659064669162035,
|
| 814 |
+
"learning_rate": 7.446153846153846e-06,
|
| 815 |
+
"loss": 0.0003,
|
| 816 |
+
"step": 1020
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 3.1384615384615384,
|
| 820 |
+
"eval_accuracy": 0.9133333333333333,
|
| 821 |
+
"eval_loss": 0.49057698249816895,
|
| 822 |
+
"eval_runtime": 4.386,
|
| 823 |
+
"eval_samples_per_second": 34.2,
|
| 824 |
+
"eval_steps_per_second": 8.664,
|
| 825 |
+
"step": 1020
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 3.2,
|
| 829 |
+
"grad_norm": 0.043470922857522964,
|
| 830 |
+
"learning_rate": 7.2000000000000005e-06,
|
| 831 |
+
"loss": 0.0003,
|
| 832 |
+
"step": 1040
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 3.2,
|
| 836 |
+
"eval_accuracy": 0.9133333333333333,
|
| 837 |
+
"eval_loss": 0.48904499411582947,
|
| 838 |
+
"eval_runtime": 4.5644,
|
| 839 |
+
"eval_samples_per_second": 32.863,
|
| 840 |
+
"eval_steps_per_second": 8.325,
|
| 841 |
+
"step": 1040
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 3.2615384615384615,
|
| 845 |
+
"grad_norm": 0.005845973733812571,
|
| 846 |
+
"learning_rate": 6.953846153846154e-06,
|
| 847 |
+
"loss": 0.0642,
|
| 848 |
+
"step": 1060
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 3.2615384615384615,
|
| 852 |
+
"eval_accuracy": 0.9333333333333333,
|
| 853 |
+
"eval_loss": 0.34622737765312195,
|
| 854 |
+
"eval_runtime": 4.642,
|
| 855 |
+
"eval_samples_per_second": 32.313,
|
| 856 |
+
"eval_steps_per_second": 8.186,
|
| 857 |
+
"step": 1060
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 3.3230769230769233,
|
| 861 |
+
"grad_norm": 0.015024982392787933,
|
| 862 |
+
"learning_rate": 6.707692307692308e-06,
|
| 863 |
+
"loss": 0.0003,
|
| 864 |
+
"step": 1080
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 3.3230769230769233,
|
| 868 |
+
"eval_accuracy": 0.9466666666666667,
|
| 869 |
+
"eval_loss": 0.3094027638435364,
|
| 870 |
+
"eval_runtime": 4.5041,
|
| 871 |
+
"eval_samples_per_second": 33.303,
|
| 872 |
+
"eval_steps_per_second": 8.437,
|
| 873 |
+
"step": 1080
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 3.3846153846153846,
|
| 877 |
+
"grad_norm": 0.004358809906989336,
|
| 878 |
+
"learning_rate": 6.461538461538463e-06,
|
| 879 |
+
"loss": 0.0003,
|
| 880 |
+
"step": 1100
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 3.3846153846153846,
|
| 884 |
+
"eval_accuracy": 0.94,
|
| 885 |
+
"eval_loss": 0.32816219329833984,
|
| 886 |
+
"eval_runtime": 4.3854,
|
| 887 |
+
"eval_samples_per_second": 34.204,
|
| 888 |
+
"eval_steps_per_second": 8.665,
|
| 889 |
+
"step": 1100
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 3.4461538461538463,
|
| 893 |
+
"grad_norm": 0.003102461341768503,
|
| 894 |
+
"learning_rate": 6.215384615384615e-06,
|
| 895 |
+
"loss": 0.1037,
|
| 896 |
+
"step": 1120
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 3.4461538461538463,
|
| 900 |
+
"eval_accuracy": 0.9333333333333333,
|
| 901 |
+
"eval_loss": 0.38093501329421997,
|
| 902 |
+
"eval_runtime": 4.3086,
|
| 903 |
+
"eval_samples_per_second": 34.814,
|
| 904 |
+
"eval_steps_per_second": 8.82,
|
| 905 |
+
"step": 1120
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 3.5076923076923077,
|
| 909 |
+
"grad_norm": 1.403334379196167,
|
| 910 |
+
"learning_rate": 5.9692307692307695e-06,
|
| 911 |
+
"loss": 0.0006,
|
| 912 |
+
"step": 1140
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 3.5076923076923077,
|
| 916 |
+
"eval_accuracy": 0.9266666666666666,
|
| 917 |
+
"eval_loss": 0.44484424591064453,
|
| 918 |
+
"eval_runtime": 4.3328,
|
| 919 |
+
"eval_samples_per_second": 34.62,
|
| 920 |
+
"eval_steps_per_second": 8.77,
|
| 921 |
+
"step": 1140
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 3.569230769230769,
|
| 925 |
+
"grad_norm": 0.0068647353909909725,
|
| 926 |
+
"learning_rate": 5.723076923076923e-06,
|
| 927 |
+
"loss": 0.0942,
|
| 928 |
+
"step": 1160
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 3.569230769230769,
|
| 932 |
+
"eval_accuracy": 0.8866666666666667,
|
| 933 |
+
"eval_loss": 0.6030946969985962,
|
| 934 |
+
"eval_runtime": 4.4045,
|
| 935 |
+
"eval_samples_per_second": 34.056,
|
| 936 |
+
"eval_steps_per_second": 8.627,
|
| 937 |
+
"step": 1160
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 3.6307692307692307,
|
| 941 |
+
"grad_norm": 0.00668348977342248,
|
| 942 |
+
"learning_rate": 5.476923076923077e-06,
|
| 943 |
+
"loss": 0.0003,
|
| 944 |
+
"step": 1180
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 3.6307692307692307,
|
| 948 |
+
"eval_accuracy": 0.8866666666666667,
|
| 949 |
+
"eval_loss": 0.4964194595813751,
|
| 950 |
+
"eval_runtime": 4.4815,
|
| 951 |
+
"eval_samples_per_second": 33.471,
|
| 952 |
+
"eval_steps_per_second": 8.479,
|
| 953 |
+
"step": 1180
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 3.6923076923076925,
|
| 957 |
+
"grad_norm": 0.009669807739555836,
|
| 958 |
+
"learning_rate": 5.230769230769232e-06,
|
| 959 |
+
"loss": 0.0007,
|
| 960 |
+
"step": 1200
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 3.6923076923076925,
|
| 964 |
+
"eval_accuracy": 0.8866666666666667,
|
| 965 |
+
"eval_loss": 0.5268967151641846,
|
| 966 |
+
"eval_runtime": 4.5142,
|
| 967 |
+
"eval_samples_per_second": 33.228,
|
| 968 |
+
"eval_steps_per_second": 8.418,
|
| 969 |
+
"step": 1200
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 3.753846153846154,
|
| 973 |
+
"grad_norm": 0.00334552931599319,
|
| 974 |
+
"learning_rate": 4.984615384615385e-06,
|
| 975 |
+
"loss": 0.0887,
|
| 976 |
+
"step": 1220
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 3.753846153846154,
|
| 980 |
+
"eval_accuracy": 0.8866666666666667,
|
| 981 |
+
"eval_loss": 0.49135467410087585,
|
| 982 |
+
"eval_runtime": 4.4888,
|
| 983 |
+
"eval_samples_per_second": 33.417,
|
| 984 |
+
"eval_steps_per_second": 8.466,
|
| 985 |
+
"step": 1220
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 3.815384615384615,
|
| 989 |
+
"grad_norm": 0.005591992288827896,
|
| 990 |
+
"learning_rate": 4.738461538461539e-06,
|
| 991 |
+
"loss": 0.0003,
|
| 992 |
+
"step": 1240
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 3.815384615384615,
|
| 996 |
+
"eval_accuracy": 0.9266666666666666,
|
| 997 |
+
"eval_loss": 0.395882248878479,
|
| 998 |
+
"eval_runtime": 4.4355,
|
| 999 |
+
"eval_samples_per_second": 33.818,
|
| 1000 |
+
"eval_steps_per_second": 8.567,
|
| 1001 |
+
"step": 1240
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 3.876923076923077,
|
| 1005 |
+
"grad_norm": 0.02592817321419716,
|
| 1006 |
+
"learning_rate": 4.492307692307693e-06,
|
| 1007 |
+
"loss": 0.0008,
|
| 1008 |
+
"step": 1260
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 3.876923076923077,
|
| 1012 |
+
"eval_accuracy": 0.9266666666666666,
|
| 1013 |
+
"eval_loss": 0.42400792241096497,
|
| 1014 |
+
"eval_runtime": 4.4143,
|
| 1015 |
+
"eval_samples_per_second": 33.98,
|
| 1016 |
+
"eval_steps_per_second": 8.608,
|
| 1017 |
+
"step": 1260
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 3.9384615384615387,
|
| 1021 |
+
"grad_norm": 0.0067848521284759045,
|
| 1022 |
+
"learning_rate": 4.246153846153846e-06,
|
| 1023 |
+
"loss": 0.0003,
|
| 1024 |
+
"step": 1280
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 3.9384615384615387,
|
| 1028 |
+
"eval_accuracy": 0.92,
|
| 1029 |
+
"eval_loss": 0.43341755867004395,
|
| 1030 |
+
"eval_runtime": 4.3946,
|
| 1031 |
+
"eval_samples_per_second": 34.133,
|
| 1032 |
+
"eval_steps_per_second": 8.647,
|
| 1033 |
+
"step": 1280
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 4.0,
|
| 1037 |
+
"grad_norm": 0.004882505163550377,
|
| 1038 |
+
"learning_rate": 4.000000000000001e-06,
|
| 1039 |
+
"loss": 0.0003,
|
| 1040 |
+
"step": 1300
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 4.0,
|
| 1044 |
+
"eval_accuracy": 0.9266666666666666,
|
| 1045 |
+
"eval_loss": 0.42421114444732666,
|
| 1046 |
+
"eval_runtime": 4.4076,
|
| 1047 |
+
"eval_samples_per_second": 34.032,
|
| 1048 |
+
"eval_steps_per_second": 8.621,
|
| 1049 |
+
"step": 1300
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 4.061538461538461,
|
| 1053 |
+
"grad_norm": 0.006306629162281752,
|
| 1054 |
+
"learning_rate": 3.753846153846154e-06,
|
| 1055 |
+
"loss": 0.0002,
|
| 1056 |
+
"step": 1320
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 4.061538461538461,
|
| 1060 |
+
"eval_accuracy": 0.9266666666666666,
|
| 1061 |
+
"eval_loss": 0.42182713747024536,
|
| 1062 |
+
"eval_runtime": 4.4367,
|
| 1063 |
+
"eval_samples_per_second": 33.809,
|
| 1064 |
+
"eval_steps_per_second": 8.565,
|
| 1065 |
+
"step": 1320
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 4.123076923076923,
|
| 1069 |
+
"grad_norm": 0.10213489085435867,
|
| 1070 |
+
"learning_rate": 3.507692307692308e-06,
|
| 1071 |
+
"loss": 0.0003,
|
| 1072 |
+
"step": 1340
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 4.123076923076923,
|
| 1076 |
+
"eval_accuracy": 0.9266666666666666,
|
| 1077 |
+
"eval_loss": 0.41865241527557373,
|
| 1078 |
+
"eval_runtime": 4.4189,
|
| 1079 |
+
"eval_samples_per_second": 33.945,
|
| 1080 |
+
"eval_steps_per_second": 8.599,
|
| 1081 |
+
"step": 1340
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 4.184615384615385,
|
| 1085 |
+
"grad_norm": 0.007508518174290657,
|
| 1086 |
+
"learning_rate": 3.2615384615384615e-06,
|
| 1087 |
+
"loss": 0.0002,
|
| 1088 |
+
"step": 1360
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 4.184615384615385,
|
| 1092 |
+
"eval_accuracy": 0.9266666666666666,
|
| 1093 |
+
"eval_loss": 0.41028958559036255,
|
| 1094 |
+
"eval_runtime": 4.491,
|
| 1095 |
+
"eval_samples_per_second": 33.4,
|
| 1096 |
+
"eval_steps_per_second": 8.461,
|
| 1097 |
+
"step": 1360
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 4.246153846153846,
|
| 1101 |
+
"grad_norm": 0.004084484186023474,
|
| 1102 |
+
"learning_rate": 3.0153846153846154e-06,
|
| 1103 |
+
"loss": 0.0002,
|
| 1104 |
+
"step": 1380
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 4.246153846153846,
|
| 1108 |
+
"eval_accuracy": 0.9266666666666666,
|
| 1109 |
+
"eval_loss": 0.4090527892112732,
|
| 1110 |
+
"eval_runtime": 4.4734,
|
| 1111 |
+
"eval_samples_per_second": 33.532,
|
| 1112 |
+
"eval_steps_per_second": 8.495,
|
| 1113 |
+
"step": 1380
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 4.3076923076923075,
|
| 1117 |
+
"grad_norm": 0.00797939207404852,
|
| 1118 |
+
"learning_rate": 2.7692307692307697e-06,
|
| 1119 |
+
"loss": 0.0002,
|
| 1120 |
+
"step": 1400
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"epoch": 4.3076923076923075,
|
| 1124 |
+
"eval_accuracy": 0.9266666666666666,
|
| 1125 |
+
"eval_loss": 0.4111497402191162,
|
| 1126 |
+
"eval_runtime": 4.4612,
|
| 1127 |
+
"eval_samples_per_second": 33.624,
|
| 1128 |
+
"eval_steps_per_second": 8.518,
|
| 1129 |
+
"step": 1400
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 4.36923076923077,
|
| 1133 |
+
"grad_norm": 0.0033812555484473705,
|
| 1134 |
+
"learning_rate": 2.523076923076923e-06,
|
| 1135 |
+
"loss": 0.0003,
|
| 1136 |
+
"step": 1420
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 4.36923076923077,
|
| 1140 |
+
"eval_accuracy": 0.9266666666666666,
|
| 1141 |
+
"eval_loss": 0.40916740894317627,
|
| 1142 |
+
"eval_runtime": 4.4676,
|
| 1143 |
+
"eval_samples_per_second": 33.575,
|
| 1144 |
+
"eval_steps_per_second": 8.506,
|
| 1145 |
+
"step": 1420
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 4.430769230769231,
|
| 1149 |
+
"grad_norm": 0.005078181624412537,
|
| 1150 |
+
"learning_rate": 2.276923076923077e-06,
|
| 1151 |
+
"loss": 0.0003,
|
| 1152 |
+
"step": 1440
|
| 1153 |
+
},
|
| 1154 |
+
{
|
| 1155 |
+
"epoch": 4.430769230769231,
|
| 1156 |
+
"eval_accuracy": 0.9333333333333333,
|
| 1157 |
+
"eval_loss": 0.3990814685821533,
|
| 1158 |
+
"eval_runtime": 4.4277,
|
| 1159 |
+
"eval_samples_per_second": 33.877,
|
| 1160 |
+
"eval_steps_per_second": 8.582,
|
| 1161 |
+
"step": 1440
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 4.492307692307692,
|
| 1165 |
+
"grad_norm": 0.003911417443305254,
|
| 1166 |
+
"learning_rate": 2.030769230769231e-06,
|
| 1167 |
+
"loss": 0.0002,
|
| 1168 |
+
"step": 1460
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 4.492307692307692,
|
| 1172 |
+
"eval_accuracy": 0.9333333333333333,
|
| 1173 |
+
"eval_loss": 0.39907512068748474,
|
| 1174 |
+
"eval_runtime": 4.4194,
|
| 1175 |
+
"eval_samples_per_second": 33.941,
|
| 1176 |
+
"eval_steps_per_second": 8.598,
|
| 1177 |
+
"step": 1460
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 4.553846153846154,
|
| 1181 |
+
"grad_norm": 0.005002380348742008,
|
| 1182 |
+
"learning_rate": 1.7846153846153846e-06,
|
| 1183 |
+
"loss": 0.0002,
|
| 1184 |
+
"step": 1480
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 4.553846153846154,
|
| 1188 |
+
"eval_accuracy": 0.9333333333333333,
|
| 1189 |
+
"eval_loss": 0.39858585596084595,
|
| 1190 |
+
"eval_runtime": 4.4069,
|
| 1191 |
+
"eval_samples_per_second": 34.037,
|
| 1192 |
+
"eval_steps_per_second": 8.623,
|
| 1193 |
+
"step": 1480
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 4.615384615384615,
|
| 1197 |
+
"grad_norm": 0.005623374599963427,
|
| 1198 |
+
"learning_rate": 1.5384615384615387e-06,
|
| 1199 |
+
"loss": 0.0004,
|
| 1200 |
+
"step": 1500
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 4.615384615384615,
|
| 1204 |
+
"eval_accuracy": 0.9333333333333333,
|
| 1205 |
+
"eval_loss": 0.4055434763431549,
|
| 1206 |
+
"eval_runtime": 4.4211,
|
| 1207 |
+
"eval_samples_per_second": 33.928,
|
| 1208 |
+
"eval_steps_per_second": 8.595,
|
| 1209 |
+
"step": 1500
|
| 1210 |
}
|
| 1211 |
],
|
| 1212 |
"logging_steps": 20,
|
|
|
|
| 1226 |
"attributes": {}
|
| 1227 |
}
|
| 1228 |
},
|
| 1229 |
+
"total_flos": 1380510818592000.0,
|
| 1230 |
"train_batch_size": 4,
|
| 1231 |
"trial_name": null,
|
| 1232 |
"trial_params": null
|