Training in progress, step 150, checkpoint
Browse files- last-checkpoint/adapter_model.safetensors +1 -1
- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +371 -5
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 335604696
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:730bf807571d846def74a46e45f99554d12b11076bcada3cac5d955ddea66db2
|
| 3 |
size 335604696
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 671466706
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ee340771dd06839064bad0beaa1caf83d161d51aec600414991284f98cf1c5fe
|
| 3 |
size 671466706
|
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 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:83bd8e032647fefdbe60f5d1ba5664c58fe9f616f3b35d81604acc0e41765fe9
|
| 3 |
size 15024
|
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 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:44ba0da6d74210066aa277337bd34fa7edae8957f15b61fd31ba24021c9d487b
|
| 3 |
size 15024
|
last-checkpoint/rng_state_2.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b9420e123c33e44748f0d832c6564860494e2ab77b99629416583c427d615008
|
| 3 |
size 15024
|
last-checkpoint/rng_state_3.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8f9cf53e40a3d9c497b339307f840ffa54e97a02b010d2c079e4c938d0d0950f
|
| 3 |
size 15024
|
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:c9aac4548b288d1967dc95faadd4d9e2138fd23b52c693b8658d543813c7dada
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 1.
|
| 3 |
-
"best_model_checkpoint": "miner_id_24/checkpoint-
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 25,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -747,6 +747,372 @@
|
|
| 747 |
"eval_samples_per_second": 29.392,
|
| 748 |
"eval_steps_per_second": 7.642,
|
| 749 |
"step": 100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 750 |
}
|
| 751 |
],
|
| 752 |
"logging_steps": 1,
|
|
@@ -775,7 +1141,7 @@
|
|
| 775 |
"attributes": {}
|
| 776 |
}
|
| 777 |
},
|
| 778 |
-
"total_flos":
|
| 779 |
"train_batch_size": 1,
|
| 780 |
"trial_name": null,
|
| 781 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 1.2113550901412964,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-150",
|
| 4 |
+
"epoch": 0.30546981894549274,
|
| 5 |
"eval_steps": 25,
|
| 6 |
+
"global_step": 150,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 747 |
"eval_samples_per_second": 29.392,
|
| 748 |
"eval_steps_per_second": 7.642,
|
| 749 |
"step": 100
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 0.20568301142329845,
|
| 753 |
+
"grad_norm": 0.6772087216377258,
|
| 754 |
+
"learning_rate": 9.443380060197387e-05,
|
| 755 |
+
"loss": 0.6919,
|
| 756 |
+
"step": 101
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 0.20771947688293504,
|
| 760 |
+
"grad_norm": 0.7789549231529236,
|
| 761 |
+
"learning_rate": 9.428955743746959e-05,
|
| 762 |
+
"loss": 0.8907,
|
| 763 |
+
"step": 102
|
| 764 |
+
},
|
| 765 |
+
{
|
| 766 |
+
"epoch": 0.20975594234257167,
|
| 767 |
+
"grad_norm": 0.45445516705513,
|
| 768 |
+
"learning_rate": 9.414359562044249e-05,
|
| 769 |
+
"loss": 1.0365,
|
| 770 |
+
"step": 103
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 0.2117924078022083,
|
| 774 |
+
"grad_norm": 0.6397705078125,
|
| 775 |
+
"learning_rate": 9.399592153573528e-05,
|
| 776 |
+
"loss": 1.0507,
|
| 777 |
+
"step": 104
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 0.2138288732618449,
|
| 781 |
+
"grad_norm": 0.8309004902839661,
|
| 782 |
+
"learning_rate": 9.384654164309083e-05,
|
| 783 |
+
"loss": 1.13,
|
| 784 |
+
"step": 105
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 0.21586533872148153,
|
| 788 |
+
"grad_norm": 0.589943528175354,
|
| 789 |
+
"learning_rate": 9.369546247686956e-05,
|
| 790 |
+
"loss": 1.2671,
|
| 791 |
+
"step": 106
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 0.21790180418111815,
|
| 795 |
+
"grad_norm": 0.5603682994842529,
|
| 796 |
+
"learning_rate": 9.354269064576366e-05,
|
| 797 |
+
"loss": 1.385,
|
| 798 |
+
"step": 107
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 0.21993826964075477,
|
| 802 |
+
"grad_norm": 0.7477754950523376,
|
| 803 |
+
"learning_rate": 9.338823283250788e-05,
|
| 804 |
+
"loss": 1.4722,
|
| 805 |
+
"step": 108
|
| 806 |
+
},
|
| 807 |
+
{
|
| 808 |
+
"epoch": 0.2219747351003914,
|
| 809 |
+
"grad_norm": 0.49757981300354004,
|
| 810 |
+
"learning_rate": 9.323209579358741e-05,
|
| 811 |
+
"loss": 1.4234,
|
| 812 |
+
"step": 109
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 0.224011200560028,
|
| 816 |
+
"grad_norm": 0.7344427108764648,
|
| 817 |
+
"learning_rate": 9.30742863589421e-05,
|
| 818 |
+
"loss": 1.4364,
|
| 819 |
+
"step": 110
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 0.2260476660196646,
|
| 823 |
+
"grad_norm": 1.003458857536316,
|
| 824 |
+
"learning_rate": 9.291481143166785e-05,
|
| 825 |
+
"loss": 1.4717,
|
| 826 |
+
"step": 111
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 0.22808413147930123,
|
| 830 |
+
"grad_norm": 0.9664032459259033,
|
| 831 |
+
"learning_rate": 9.275367798771466e-05,
|
| 832 |
+
"loss": 1.6414,
|
| 833 |
+
"step": 112
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 0.23012059693893785,
|
| 837 |
+
"grad_norm": 0.3967495560646057,
|
| 838 |
+
"learning_rate": 9.259089307558131e-05,
|
| 839 |
+
"loss": 0.6532,
|
| 840 |
+
"step": 113
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 0.23215706239857448,
|
| 844 |
+
"grad_norm": 0.44618600606918335,
|
| 845 |
+
"learning_rate": 9.242646381600722e-05,
|
| 846 |
+
"loss": 0.7917,
|
| 847 |
+
"step": 114
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 0.2341935278582111,
|
| 851 |
+
"grad_norm": 0.4544903039932251,
|
| 852 |
+
"learning_rate": 9.226039740166091e-05,
|
| 853 |
+
"loss": 0.9741,
|
| 854 |
+
"step": 115
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 0.23622999331784772,
|
| 858 |
+
"grad_norm": 0.36634865403175354,
|
| 859 |
+
"learning_rate": 9.20927010968253e-05,
|
| 860 |
+
"loss": 1.0818,
|
| 861 |
+
"step": 116
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 0.23826645877748434,
|
| 865 |
+
"grad_norm": 0.3430715799331665,
|
| 866 |
+
"learning_rate": 9.192338223708001e-05,
|
| 867 |
+
"loss": 1.1227,
|
| 868 |
+
"step": 117
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 0.24030292423712094,
|
| 872 |
+
"grad_norm": 0.34879475831985474,
|
| 873 |
+
"learning_rate": 9.17524482289805e-05,
|
| 874 |
+
"loss": 1.1969,
|
| 875 |
+
"step": 118
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 0.24233938969675756,
|
| 879 |
+
"grad_norm": 0.4282311201095581,
|
| 880 |
+
"learning_rate": 9.157990654973406e-05,
|
| 881 |
+
"loss": 1.3577,
|
| 882 |
+
"step": 119
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 0.24437585515639418,
|
| 886 |
+
"grad_norm": 0.4587807059288025,
|
| 887 |
+
"learning_rate": 9.140576474687264e-05,
|
| 888 |
+
"loss": 1.4188,
|
| 889 |
+
"step": 120
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 0.2464123206160308,
|
| 893 |
+
"grad_norm": 0.45881757140159607,
|
| 894 |
+
"learning_rate": 9.123003043792289e-05,
|
| 895 |
+
"loss": 1.4452,
|
| 896 |
+
"step": 121
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 0.24844878607566742,
|
| 900 |
+
"grad_norm": 0.4397464692592621,
|
| 901 |
+
"learning_rate": 9.105271131007274e-05,
|
| 902 |
+
"loss": 1.4655,
|
| 903 |
+
"step": 122
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 0.25048525153530404,
|
| 907 |
+
"grad_norm": 0.4731747508049011,
|
| 908 |
+
"learning_rate": 9.087381511983533e-05,
|
| 909 |
+
"loss": 1.4057,
|
| 910 |
+
"step": 123
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 0.25252171699494064,
|
| 914 |
+
"grad_norm": 0.652103066444397,
|
| 915 |
+
"learning_rate": 9.069334969270952e-05,
|
| 916 |
+
"loss": 1.5301,
|
| 917 |
+
"step": 124
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 0.2545581824545773,
|
| 921 |
+
"grad_norm": 0.5992268919944763,
|
| 922 |
+
"learning_rate": 9.051132292283771e-05,
|
| 923 |
+
"loss": 1.7445,
|
| 924 |
+
"step": 125
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 0.2545581824545773,
|
| 928 |
+
"eval_loss": 1.247846007347107,
|
| 929 |
+
"eval_runtime": 1.6992,
|
| 930 |
+
"eval_samples_per_second": 29.426,
|
| 931 |
+
"eval_steps_per_second": 7.651,
|
| 932 |
+
"step": 125
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 0.2565946479142139,
|
| 936 |
+
"grad_norm": 0.33065474033355713,
|
| 937 |
+
"learning_rate": 9.032774277266055e-05,
|
| 938 |
+
"loss": 0.6734,
|
| 939 |
+
"step": 126
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 0.25863111337385053,
|
| 943 |
+
"grad_norm": 0.33799877762794495,
|
| 944 |
+
"learning_rate": 9.014261727256849e-05,
|
| 945 |
+
"loss": 0.8156,
|
| 946 |
+
"step": 127
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 0.2606675788334871,
|
| 950 |
+
"grad_norm": 0.3140442371368408,
|
| 951 |
+
"learning_rate": 8.995595452055063e-05,
|
| 952 |
+
"loss": 1.0481,
|
| 953 |
+
"step": 128
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 0.2627040442931238,
|
| 957 |
+
"grad_norm": 0.414773553609848,
|
| 958 |
+
"learning_rate": 8.976776268184046e-05,
|
| 959 |
+
"loss": 1.0778,
|
| 960 |
+
"step": 129
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 0.26474050975276037,
|
| 964 |
+
"grad_norm": 0.42660096287727356,
|
| 965 |
+
"learning_rate": 8.957804998855866e-05,
|
| 966 |
+
"loss": 1.1496,
|
| 967 |
+
"step": 130
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 0.26677697521239696,
|
| 971 |
+
"grad_norm": 0.3320043981075287,
|
| 972 |
+
"learning_rate": 8.9386824739353e-05,
|
| 973 |
+
"loss": 1.274,
|
| 974 |
+
"step": 131
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 0.2688134406720336,
|
| 978 |
+
"grad_norm": 0.4077851474285126,
|
| 979 |
+
"learning_rate": 8.91940952990354e-05,
|
| 980 |
+
"loss": 1.3346,
|
| 981 |
+
"step": 132
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 0.2708499061316702,
|
| 985 |
+
"grad_norm": 0.4087212085723877,
|
| 986 |
+
"learning_rate": 8.899987009821588e-05,
|
| 987 |
+
"loss": 1.4256,
|
| 988 |
+
"step": 133
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 0.27288637159130685,
|
| 992 |
+
"grad_norm": 0.3933734893798828,
|
| 993 |
+
"learning_rate": 8.880415763293398e-05,
|
| 994 |
+
"loss": 1.3862,
|
| 995 |
+
"step": 134
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 0.27492283705094345,
|
| 999 |
+
"grad_norm": 0.5865826606750488,
|
| 1000 |
+
"learning_rate": 8.860696646428693e-05,
|
| 1001 |
+
"loss": 1.4127,
|
| 1002 |
+
"step": 135
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 0.2769593025105801,
|
| 1006 |
+
"grad_norm": 0.7289634346961975,
|
| 1007 |
+
"learning_rate": 8.840830521805525e-05,
|
| 1008 |
+
"loss": 1.4241,
|
| 1009 |
+
"step": 136
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 0.2789957679702167,
|
| 1013 |
+
"grad_norm": 0.40526294708251953,
|
| 1014 |
+
"learning_rate": 8.820818258432543e-05,
|
| 1015 |
+
"loss": 1.5764,
|
| 1016 |
+
"step": 137
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 0.2810322334298533,
|
| 1020 |
+
"grad_norm": 0.31064677238464355,
|
| 1021 |
+
"learning_rate": 8.800660731710981e-05,
|
| 1022 |
+
"loss": 0.5921,
|
| 1023 |
+
"step": 138
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 0.28306869888948993,
|
| 1027 |
+
"grad_norm": 0.46164336800575256,
|
| 1028 |
+
"learning_rate": 8.780358823396352e-05,
|
| 1029 |
+
"loss": 0.7685,
|
| 1030 |
+
"step": 139
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"epoch": 0.2851051643491265,
|
| 1034 |
+
"grad_norm": 0.4381145238876343,
|
| 1035 |
+
"learning_rate": 8.759913421559902e-05,
|
| 1036 |
+
"loss": 0.9196,
|
| 1037 |
+
"step": 140
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 0.2871416298087632,
|
| 1041 |
+
"grad_norm": 0.34802648425102234,
|
| 1042 |
+
"learning_rate": 8.739325420549735e-05,
|
| 1043 |
+
"loss": 1.0642,
|
| 1044 |
+
"step": 141
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 0.28917809526839977,
|
| 1048 |
+
"grad_norm": 0.4874970316886902,
|
| 1049 |
+
"learning_rate": 8.718595720951716e-05,
|
| 1050 |
+
"loss": 1.0956,
|
| 1051 |
+
"step": 142
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"epoch": 0.2912145607280364,
|
| 1055 |
+
"grad_norm": 0.6465345621109009,
|
| 1056 |
+
"learning_rate": 8.697725229550056e-05,
|
| 1057 |
+
"loss": 1.1598,
|
| 1058 |
+
"step": 143
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 0.293251026187673,
|
| 1062 |
+
"grad_norm": 0.5405471920967102,
|
| 1063 |
+
"learning_rate": 8.676714859287666e-05,
|
| 1064 |
+
"loss": 1.2878,
|
| 1065 |
+
"step": 144
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 0.29528749164730966,
|
| 1069 |
+
"grad_norm": 0.48423656821250916,
|
| 1070 |
+
"learning_rate": 8.655565529226198e-05,
|
| 1071 |
+
"loss": 1.4311,
|
| 1072 |
+
"step": 145
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 0.29732395710694626,
|
| 1076 |
+
"grad_norm": 0.6868144273757935,
|
| 1077 |
+
"learning_rate": 8.63427816450587e-05,
|
| 1078 |
+
"loss": 1.4178,
|
| 1079 |
+
"step": 146
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 0.29936042256658285,
|
| 1083 |
+
"grad_norm": 0.526288628578186,
|
| 1084 |
+
"learning_rate": 8.612853696304972e-05,
|
| 1085 |
+
"loss": 1.393,
|
| 1086 |
+
"step": 147
|
| 1087 |
+
},
|
| 1088 |
+
{
|
| 1089 |
+
"epoch": 0.3013968880262195,
|
| 1090 |
+
"grad_norm": 0.6044138669967651,
|
| 1091 |
+
"learning_rate": 8.591293061799151e-05,
|
| 1092 |
+
"loss": 1.3549,
|
| 1093 |
+
"step": 148
|
| 1094 |
+
},
|
| 1095 |
+
{
|
| 1096 |
+
"epoch": 0.3034333534858561,
|
| 1097 |
+
"grad_norm": 1.4905437231063843,
|
| 1098 |
+
"learning_rate": 8.569597204120405e-05,
|
| 1099 |
+
"loss": 1.4648,
|
| 1100 |
+
"step": 149
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 0.30546981894549274,
|
| 1104 |
+
"grad_norm": 0.777951717376709,
|
| 1105 |
+
"learning_rate": 8.547767072315835e-05,
|
| 1106 |
+
"loss": 1.694,
|
| 1107 |
+
"step": 150
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 0.30546981894549274,
|
| 1111 |
+
"eval_loss": 1.2113550901412964,
|
| 1112 |
+
"eval_runtime": 1.6972,
|
| 1113 |
+
"eval_samples_per_second": 29.46,
|
| 1114 |
+
"eval_steps_per_second": 7.66,
|
| 1115 |
+
"step": 150
|
| 1116 |
}
|
| 1117 |
],
|
| 1118 |
"logging_steps": 1,
|
|
|
|
| 1141 |
"attributes": {}
|
| 1142 |
}
|
| 1143 |
},
|
| 1144 |
+
"total_flos": 3.763436218054869e+18,
|
| 1145 |
"train_batch_size": 1,
|
| 1146 |
"trial_name": null,
|
| 1147 |
"trial_params": null
|