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 13587864
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d3d7811f0d3c91eb0559d6dd57dbab4cbf46345245cf1dada768a60472fe8396
|
| 3 |
size 13587864
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 27273018
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3da6d858e7d81bec94e9df9f841ded71cbba3baa78c5d5662bbc2267370154ae
|
| 3 |
size 27273018
|
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:f8c9d729ce54890d2b004e8818490177e5625467f75e54adee6318c935eb7ad9
|
| 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:eea2c85c433dc178f7297992565db28a1eab3bd318e64c50f31cc218f4874305
|
| 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 sha256:824a76a21878d4877c2046d8ad58c4e61f8b4afa79156f487f81a3613095e08d
|
| 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 sha256:4174057fda88174f282bba24bb30a94ae554b6014d600262e9ee53ba95563faf
|
| 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 sha256:9bab2e2e6d5938b4266045afdacf5782a91c8e156838fe5f46422cf8b6d4d279
|
| 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":
|
| 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": 178.583,
|
| 748 |
"eval_steps_per_second": 46.431,
|
| 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": 1.7033360004425049,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-150",
|
| 4 |
+
"epoch": 1.1439466158245948,
|
| 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": 178.583,
|
| 748 |
"eval_steps_per_second": 46.431,
|
| 749 |
"step": 100
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 0.7702573879885606,
|
| 753 |
+
"grad_norm": 0.5027046203613281,
|
| 754 |
+
"learning_rate": 0.00021970757739067358,
|
| 755 |
+
"loss": 1.6627,
|
| 756 |
+
"step": 101
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 0.7778836987607245,
|
| 760 |
+
"grad_norm": 0.4292294681072235,
|
| 761 |
+
"learning_rate": 0.00021818892540824148,
|
| 762 |
+
"loss": 1.6495,
|
| 763 |
+
"step": 102
|
| 764 |
+
},
|
| 765 |
+
{
|
| 766 |
+
"epoch": 0.7855100095328885,
|
| 767 |
+
"grad_norm": 0.37569937109947205,
|
| 768 |
+
"learning_rate": 0.00021666226336928708,
|
| 769 |
+
"loss": 1.6692,
|
| 770 |
+
"step": 103
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 0.7931363203050524,
|
| 774 |
+
"grad_norm": 0.3786998391151428,
|
| 775 |
+
"learning_rate": 0.00021512782118349806,
|
| 776 |
+
"loss": 1.6581,
|
| 777 |
+
"step": 104
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 0.8007626310772163,
|
| 781 |
+
"grad_norm": 0.36832037568092346,
|
| 782 |
+
"learning_rate": 0.0002135858299322234,
|
| 783 |
+
"loss": 1.6714,
|
| 784 |
+
"step": 105
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 0.8083889418493804,
|
| 788 |
+
"grad_norm": 0.336896687746048,
|
| 789 |
+
"learning_rate": 0.00021203652183367363,
|
| 790 |
+
"loss": 1.7207,
|
| 791 |
+
"step": 106
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 0.8160152526215443,
|
| 795 |
+
"grad_norm": 0.35588911175727844,
|
| 796 |
+
"learning_rate": 0.00021048013020794968,
|
| 797 |
+
"loss": 1.7085,
|
| 798 |
+
"step": 107
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 0.8236415633937083,
|
| 802 |
+
"grad_norm": 0.4056905508041382,
|
| 803 |
+
"learning_rate": 0.00020891688944190548,
|
| 804 |
+
"loss": 1.7094,
|
| 805 |
+
"step": 108
|
| 806 |
+
},
|
| 807 |
+
{
|
| 808 |
+
"epoch": 0.8312678741658722,
|
| 809 |
+
"grad_norm": 0.40606462955474854,
|
| 810 |
+
"learning_rate": 0.00020734703495385037,
|
| 811 |
+
"loss": 1.7239,
|
| 812 |
+
"step": 109
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 0.8388941849380362,
|
| 816 |
+
"grad_norm": 0.40182796120643616,
|
| 817 |
+
"learning_rate": 0.0002057708031580958,
|
| 818 |
+
"loss": 1.7333,
|
| 819 |
+
"step": 110
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 0.8465204957102002,
|
| 823 |
+
"grad_norm": 0.44995224475860596,
|
| 824 |
+
"learning_rate": 0.00020418843142935237,
|
| 825 |
+
"loss": 1.7049,
|
| 826 |
+
"step": 111
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 0.8541468064823642,
|
| 830 |
+
"grad_norm": 0.4388667047023773,
|
| 831 |
+
"learning_rate": 0.00020260015806698213,
|
| 832 |
+
"loss": 1.783,
|
| 833 |
+
"step": 112
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 0.8617731172545281,
|
| 837 |
+
"grad_norm": 0.44865381717681885,
|
| 838 |
+
"learning_rate": 0.00020100622225911128,
|
| 839 |
+
"loss": 1.7508,
|
| 840 |
+
"step": 113
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 0.8693994280266921,
|
| 844 |
+
"grad_norm": 0.4294881522655487,
|
| 845 |
+
"learning_rate": 0.00019940686404660947,
|
| 846 |
+
"loss": 1.6571,
|
| 847 |
+
"step": 114
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 0.877025738798856,
|
| 851 |
+
"grad_norm": 0.3841921091079712,
|
| 852 |
+
"learning_rate": 0.00019780232428694063,
|
| 853 |
+
"loss": 1.695,
|
| 854 |
+
"step": 115
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 0.8846520495710201,
|
| 858 |
+
"grad_norm": 0.3785157799720764,
|
| 859 |
+
"learning_rate": 0.0001961928446178906,
|
| 860 |
+
"loss": 1.6545,
|
| 861 |
+
"step": 116
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 0.892278360343184,
|
| 865 |
+
"grad_norm": 0.33887144923210144,
|
| 866 |
+
"learning_rate": 0.00019457866742117737,
|
| 867 |
+
"loss": 1.6715,
|
| 868 |
+
"step": 117
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 0.899904671115348,
|
| 872 |
+
"grad_norm": 0.32863056659698486,
|
| 873 |
+
"learning_rate": 0.00019296003578594948,
|
| 874 |
+
"loss": 1.6952,
|
| 875 |
+
"step": 118
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 0.9075309818875119,
|
| 879 |
+
"grad_norm": 0.3387095034122467,
|
| 880 |
+
"learning_rate": 0.00019133719347217733,
|
| 881 |
+
"loss": 1.6291,
|
| 882 |
+
"step": 119
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 0.9151572926596759,
|
| 886 |
+
"grad_norm": 0.3665367066860199,
|
| 887 |
+
"learning_rate": 0.00018971038487394402,
|
| 888 |
+
"loss": 1.7321,
|
| 889 |
+
"step": 120
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 0.9227836034318398,
|
| 893 |
+
"grad_norm": 0.3495505452156067,
|
| 894 |
+
"learning_rate": 0.00018807985498264066,
|
| 895 |
+
"loss": 1.6587,
|
| 896 |
+
"step": 121
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 0.9304099142040038,
|
| 900 |
+
"grad_norm": 0.40355828404426575,
|
| 901 |
+
"learning_rate": 0.00018644584935007127,
|
| 902 |
+
"loss": 1.7027,
|
| 903 |
+
"step": 122
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 0.9380362249761678,
|
| 907 |
+
"grad_norm": 0.4357530474662781,
|
| 908 |
+
"learning_rate": 0.0001848086140514738,
|
| 909 |
+
"loss": 1.7724,
|
| 910 |
+
"step": 123
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 0.9456625357483317,
|
| 914 |
+
"grad_norm": 0.44958412647247314,
|
| 915 |
+
"learning_rate": 0.000183168395648462,
|
| 916 |
+
"loss": 1.7454,
|
| 917 |
+
"step": 124
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 0.9532888465204957,
|
| 921 |
+
"grad_norm": 0.5644071102142334,
|
| 922 |
+
"learning_rate": 0.00018152544115189416,
|
| 923 |
+
"loss": 1.8156,
|
| 924 |
+
"step": 125
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 0.9532888465204957,
|
| 928 |
+
"eval_loss": 1.7262933254241943,
|
| 929 |
+
"eval_runtime": 0.2797,
|
| 930 |
+
"eval_samples_per_second": 178.792,
|
| 931 |
+
"eval_steps_per_second": 46.486,
|
| 932 |
+
"step": 125
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 0.9609151572926596,
|
| 936 |
+
"grad_norm": 0.45155230164527893,
|
| 937 |
+
"learning_rate": 0.0001798799979846742,
|
| 938 |
+
"loss": 1.6338,
|
| 939 |
+
"step": 126
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 0.9685414680648237,
|
| 943 |
+
"grad_norm": 0.41884180903434753,
|
| 944 |
+
"learning_rate": 0.00017823231394449072,
|
| 945 |
+
"loss": 1.6829,
|
| 946 |
+
"step": 127
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 0.9761677788369876,
|
| 950 |
+
"grad_norm": 0.3723445534706116,
|
| 951 |
+
"learning_rate": 0.0001765826371664994,
|
| 952 |
+
"loss": 1.6707,
|
| 953 |
+
"step": 128
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 0.9837940896091516,
|
| 957 |
+
"grad_norm": 0.3832674026489258,
|
| 958 |
+
"learning_rate": 0.00017493121608595511,
|
| 959 |
+
"loss": 1.7397,
|
| 960 |
+
"step": 129
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 0.9914204003813155,
|
| 964 |
+
"grad_norm": 0.37408822774887085,
|
| 965 |
+
"learning_rate": 0.00017327829940079817,
|
| 966 |
+
"loss": 1.6765,
|
| 967 |
+
"step": 130
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 0.9990467111534795,
|
| 971 |
+
"grad_norm": 0.42527204751968384,
|
| 972 |
+
"learning_rate": 0.00017162413603420142,
|
| 973 |
+
"loss": 1.791,
|
| 974 |
+
"step": 131
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 1.0066730219256435,
|
| 978 |
+
"grad_norm": 1.3834341764450073,
|
| 979 |
+
"learning_rate": 0.00016996897509708345,
|
| 980 |
+
"loss": 3.4039,
|
| 981 |
+
"step": 132
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 1.0142993326978074,
|
| 985 |
+
"grad_norm": 0.43991145491600037,
|
| 986 |
+
"learning_rate": 0.00016831306585059317,
|
| 987 |
+
"loss": 1.6506,
|
| 988 |
+
"step": 133
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 1.0219256434699715,
|
| 992 |
+
"grad_norm": 0.37817224860191345,
|
| 993 |
+
"learning_rate": 0.0001666566576685722,
|
| 994 |
+
"loss": 1.5943,
|
| 995 |
+
"step": 134
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 1.0295519542421354,
|
| 999 |
+
"grad_norm": 0.34133297204971313,
|
| 1000 |
+
"learning_rate": 0.000165,
|
| 1001 |
+
"loss": 1.5756,
|
| 1002 |
+
"step": 135
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 1.0371782650142993,
|
| 1006 |
+
"grad_norm": 0.32997646927833557,
|
| 1007 |
+
"learning_rate": 0.0001633433423314278,
|
| 1008 |
+
"loss": 1.6236,
|
| 1009 |
+
"step": 136
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 1.0448045757864632,
|
| 1013 |
+
"grad_norm": 0.3591316342353821,
|
| 1014 |
+
"learning_rate": 0.00016168693414940683,
|
| 1015 |
+
"loss": 1.6221,
|
| 1016 |
+
"step": 137
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 1.0524308865586272,
|
| 1020 |
+
"grad_norm": 0.3701683580875397,
|
| 1021 |
+
"learning_rate": 0.00016003102490291655,
|
| 1022 |
+
"loss": 1.6099,
|
| 1023 |
+
"step": 138
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 1.0600571973307913,
|
| 1027 |
+
"grad_norm": 0.3921620845794678,
|
| 1028 |
+
"learning_rate": 0.00015837586396579858,
|
| 1029 |
+
"loss": 1.6507,
|
| 1030 |
+
"step": 139
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"epoch": 1.0676835081029552,
|
| 1034 |
+
"grad_norm": 0.411425918340683,
|
| 1035 |
+
"learning_rate": 0.00015672170059920183,
|
| 1036 |
+
"loss": 1.6658,
|
| 1037 |
+
"step": 140
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 1.0753098188751191,
|
| 1041 |
+
"grad_norm": 0.4283716082572937,
|
| 1042 |
+
"learning_rate": 0.00015506878391404488,
|
| 1043 |
+
"loss": 1.6525,
|
| 1044 |
+
"step": 141
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 1.082936129647283,
|
| 1048 |
+
"grad_norm": 0.43306857347488403,
|
| 1049 |
+
"learning_rate": 0.00015341736283350064,
|
| 1050 |
+
"loss": 1.6808,
|
| 1051 |
+
"step": 142
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"epoch": 1.0905624404194472,
|
| 1055 |
+
"grad_norm": 0.46868017315864563,
|
| 1056 |
+
"learning_rate": 0.0001517676860555093,
|
| 1057 |
+
"loss": 1.7022,
|
| 1058 |
+
"step": 143
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 1.098188751191611,
|
| 1062 |
+
"grad_norm": 0.3939070403575897,
|
| 1063 |
+
"learning_rate": 0.0001501200020153258,
|
| 1064 |
+
"loss": 1.608,
|
| 1065 |
+
"step": 144
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 1.105815061963775,
|
| 1069 |
+
"grad_norm": 0.5079172253608704,
|
| 1070 |
+
"learning_rate": 0.00014847455884810581,
|
| 1071 |
+
"loss": 1.664,
|
| 1072 |
+
"step": 145
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 1.113441372735939,
|
| 1076 |
+
"grad_norm": 0.4701906740665436,
|
| 1077 |
+
"learning_rate": 0.00014683160435153796,
|
| 1078 |
+
"loss": 1.5924,
|
| 1079 |
+
"step": 146
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 1.121067683508103,
|
| 1083 |
+
"grad_norm": 0.4438985288143158,
|
| 1084 |
+
"learning_rate": 0.00014519138594852615,
|
| 1085 |
+
"loss": 1.6186,
|
| 1086 |
+
"step": 147
|
| 1087 |
+
},
|
| 1088 |
+
{
|
| 1089 |
+
"epoch": 1.128693994280267,
|
| 1090 |
+
"grad_norm": 0.40085965394973755,
|
| 1091 |
+
"learning_rate": 0.00014355415064992873,
|
| 1092 |
+
"loss": 1.6421,
|
| 1093 |
+
"step": 148
|
| 1094 |
+
},
|
| 1095 |
+
{
|
| 1096 |
+
"epoch": 1.1363203050524309,
|
| 1097 |
+
"grad_norm": 0.3875059485435486,
|
| 1098 |
+
"learning_rate": 0.00014192014501735934,
|
| 1099 |
+
"loss": 1.5903,
|
| 1100 |
+
"step": 149
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 1.1439466158245948,
|
| 1104 |
+
"grad_norm": 0.3794068992137909,
|
| 1105 |
+
"learning_rate": 0.00014028961512605598,
|
| 1106 |
+
"loss": 1.6741,
|
| 1107 |
+
"step": 150
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 1.1439466158245948,
|
| 1111 |
+
"eval_loss": 1.7033360004425049,
|
| 1112 |
+
"eval_runtime": 0.2798,
|
| 1113 |
+
"eval_samples_per_second": 178.678,
|
| 1114 |
+
"eval_steps_per_second": 46.456,
|
| 1115 |
+
"step": 150
|
| 1116 |
}
|
| 1117 |
],
|
| 1118 |
"logging_steps": 1,
|
|
|
|
| 1141 |
"attributes": {}
|
| 1142 |
}
|
| 1143 |
},
|
| 1144 |
+
"total_flos": 6.66420413202432e+16,
|
| 1145 |
"train_batch_size": 1,
|
| 1146 |
"trial_name": null,
|
| 1147 |
"trial_params": null
|