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 48679352
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:053cb8f76fc41f5bfe9704e91836299832a2a246d762e4f05fd274b5ff20f8bb
|
| 3 |
size 48679352
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 97585002
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c32447458daa8d16702ef6f2e735f6a551622410b6f0267a1724b7b74542ab1e
|
| 3 |
size 97585002
|
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 14960
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:203ba680c133ba1e747e24ab19bbd4c6347d511c0188c7476fec2ee1a3f9ce00
|
| 3 |
size 14960
|
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 sha256:246e30b34b6000b9bd44f0e6e962677e838a6e1ba2b16a7d13880ed5e8b7b415
|
| 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:cca77b78ad60850baaae873a88d4ee09734c23eea65520af712ae8ebe4b3f78c
|
| 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:e8c9771df92c952a37068fbebb573f983700d39ed62007071fe9f51f154fc3ca
|
| 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 sha256:4e2cbf161ff6bcb4f44ffee985cadc63b2634e2ed9f01b220e474866148af092
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 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": 54.242,
|
| 748 |
"eval_steps_per_second": 14.103,
|
| 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": 0.5081304907798767,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-150",
|
| 4 |
+
"epoch": 0.8609865470852018,
|
| 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": 54.242,
|
| 748 |
"eval_steps_per_second": 14.103,
|
| 749 |
"step": 100
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 0.5797309417040358,
|
| 753 |
+
"grad_norm": 0.2608706057071686,
|
| 754 |
+
"learning_rate": 0.00014947546146846748,
|
| 755 |
+
"loss": 0.3916,
|
| 756 |
+
"step": 101
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 0.5854708520179372,
|
| 760 |
+
"grad_norm": 0.379069447517395,
|
| 761 |
+
"learning_rate": 0.0001484799584087254,
|
| 762 |
+
"loss": 0.566,
|
| 763 |
+
"step": 102
|
| 764 |
+
},
|
| 765 |
+
{
|
| 766 |
+
"epoch": 0.5912107623318386,
|
| 767 |
+
"grad_norm": 0.3914828598499298,
|
| 768 |
+
"learning_rate": 0.00014747866040878738,
|
| 769 |
+
"loss": 0.6203,
|
| 770 |
+
"step": 103
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 0.5969506726457399,
|
| 774 |
+
"grad_norm": 0.4011947512626648,
|
| 775 |
+
"learning_rate": 0.00014647171826044907,
|
| 776 |
+
"loss": 0.5886,
|
| 777 |
+
"step": 104
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 0.6026905829596413,
|
| 781 |
+
"grad_norm": 0.38338544964790344,
|
| 782 |
+
"learning_rate": 0.00014545928360549436,
|
| 783 |
+
"loss": 0.5889,
|
| 784 |
+
"step": 105
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 0.6084304932735426,
|
| 788 |
+
"grad_norm": 0.40191414952278137,
|
| 789 |
+
"learning_rate": 0.00014444150891285807,
|
| 790 |
+
"loss": 0.5612,
|
| 791 |
+
"step": 106
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 0.6141704035874439,
|
| 795 |
+
"grad_norm": 0.3976474404335022,
|
| 796 |
+
"learning_rate": 0.00014341854745566538,
|
| 797 |
+
"loss": 0.5905,
|
| 798 |
+
"step": 107
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 0.6199103139013453,
|
| 802 |
+
"grad_norm": 0.3555368185043335,
|
| 803 |
+
"learning_rate": 0.00014239055328814894,
|
| 804 |
+
"loss": 0.5735,
|
| 805 |
+
"step": 108
|
| 806 |
+
},
|
| 807 |
+
{
|
| 808 |
+
"epoch": 0.6256502242152466,
|
| 809 |
+
"grad_norm": 0.3123275935649872,
|
| 810 |
+
"learning_rate": 0.0001413576812224491,
|
| 811 |
+
"loss": 0.5211,
|
| 812 |
+
"step": 109
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 0.6313901345291479,
|
| 816 |
+
"grad_norm": 0.35772255063056946,
|
| 817 |
+
"learning_rate": 0.0001403200868052998,
|
| 818 |
+
"loss": 0.5413,
|
| 819 |
+
"step": 110
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 0.6371300448430494,
|
| 823 |
+
"grad_norm": 0.34592434763908386,
|
| 824 |
+
"learning_rate": 0.00013927792629460367,
|
| 825 |
+
"loss": 0.5764,
|
| 826 |
+
"step": 111
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 0.6428699551569507,
|
| 830 |
+
"grad_norm": 0.33390721678733826,
|
| 831 |
+
"learning_rate": 0.00013823135663590025,
|
| 832 |
+
"loss": 0.5225,
|
| 833 |
+
"step": 112
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 0.648609865470852,
|
| 837 |
+
"grad_norm": 0.21307708323001862,
|
| 838 |
+
"learning_rate": 0.00013718053543873056,
|
| 839 |
+
"loss": 0.3379,
|
| 840 |
+
"step": 113
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 0.6543497757847534,
|
| 844 |
+
"grad_norm": 0.41324618458747864,
|
| 845 |
+
"learning_rate": 0.0001361256209529016,
|
| 846 |
+
"loss": 0.538,
|
| 847 |
+
"step": 114
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 0.6600896860986547,
|
| 851 |
+
"grad_norm": 0.4129272997379303,
|
| 852 |
+
"learning_rate": 0.00013506677204465475,
|
| 853 |
+
"loss": 0.5736,
|
| 854 |
+
"step": 115
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 0.665829596412556,
|
| 858 |
+
"grad_norm": 0.39694082736968994,
|
| 859 |
+
"learning_rate": 0.00013400414817274088,
|
| 860 |
+
"loss": 0.5951,
|
| 861 |
+
"step": 116
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 0.6715695067264574,
|
| 865 |
+
"grad_norm": 0.4103195369243622,
|
| 866 |
+
"learning_rate": 0.00013293790936440633,
|
| 867 |
+
"loss": 0.5936,
|
| 868 |
+
"step": 117
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 0.6773094170403587,
|
| 872 |
+
"grad_norm": 0.3834230303764343,
|
| 873 |
+
"learning_rate": 0.00013186821619129378,
|
| 874 |
+
"loss": 0.5769,
|
| 875 |
+
"step": 118
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 0.68304932735426,
|
| 879 |
+
"grad_norm": 0.40706706047058105,
|
| 880 |
+
"learning_rate": 0.00013079522974526042,
|
| 881 |
+
"loss": 0.5666,
|
| 882 |
+
"step": 119
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 0.6887892376681615,
|
| 886 |
+
"grad_norm": 0.3616923689842224,
|
| 887 |
+
"learning_rate": 0.00012971911161411827,
|
| 888 |
+
"loss": 0.5568,
|
| 889 |
+
"step": 120
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 0.6945291479820628,
|
| 893 |
+
"grad_norm": 0.32444703578948975,
|
| 894 |
+
"learning_rate": 0.00012864002385729967,
|
| 895 |
+
"loss": 0.5424,
|
| 896 |
+
"step": 121
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 0.7002690582959641,
|
| 900 |
+
"grad_norm": 0.34600815176963806,
|
| 901 |
+
"learning_rate": 0.00012755812898145155,
|
| 902 |
+
"loss": 0.5415,
|
| 903 |
+
"step": 122
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 0.7060089686098655,
|
| 907 |
+
"grad_norm": 0.41751474142074585,
|
| 908 |
+
"learning_rate": 0.0001264735899159627,
|
| 909 |
+
"loss": 0.5645,
|
| 910 |
+
"step": 123
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 0.7117488789237668,
|
| 914 |
+
"grad_norm": 0.3468458950519562,
|
| 915 |
+
"learning_rate": 0.00012538656998842713,
|
| 916 |
+
"loss": 0.4588,
|
| 917 |
+
"step": 124
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 0.7174887892376681,
|
| 921 |
+
"grad_norm": 0.4765909016132355,
|
| 922 |
+
"learning_rate": 0.00012429723290004752,
|
| 923 |
+
"loss": 0.5565,
|
| 924 |
+
"step": 125
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 0.7174887892376681,
|
| 928 |
+
"eval_loss": 0.5193074941635132,
|
| 929 |
+
"eval_runtime": 0.9221,
|
| 930 |
+
"eval_samples_per_second": 54.225,
|
| 931 |
+
"eval_steps_per_second": 14.098,
|
| 932 |
+
"step": 125
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 0.7232286995515695,
|
| 936 |
+
"grad_norm": 0.27293744683265686,
|
| 937 |
+
"learning_rate": 0.00012320574270098254,
|
| 938 |
+
"loss": 0.3958,
|
| 939 |
+
"step": 126
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 0.7289686098654709,
|
| 943 |
+
"grad_norm": 0.37524548172950745,
|
| 944 |
+
"learning_rate": 0.00012211226376564137,
|
| 945 |
+
"loss": 0.5386,
|
| 946 |
+
"step": 127
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 0.7347085201793722,
|
| 950 |
+
"grad_norm": 0.3265777826309204,
|
| 951 |
+
"learning_rate": 0.00012101696076792946,
|
| 952 |
+
"loss": 0.5729,
|
| 953 |
+
"step": 128
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 0.7404484304932736,
|
| 957 |
+
"grad_norm": 0.3645853102207184,
|
| 958 |
+
"learning_rate": 0.00011991999865644949,
|
| 959 |
+
"loss": 0.6049,
|
| 960 |
+
"step": 129
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 0.7461883408071749,
|
| 964 |
+
"grad_norm": 0.39641687273979187,
|
| 965 |
+
"learning_rate": 0.0001188215426296605,
|
| 966 |
+
"loss": 0.5868,
|
| 967 |
+
"step": 130
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 0.7519282511210762,
|
| 971 |
+
"grad_norm": 0.3878898620605469,
|
| 972 |
+
"learning_rate": 0.00011772175811099962,
|
| 973 |
+
"loss": 0.5686,
|
| 974 |
+
"step": 131
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 0.7576681614349776,
|
| 978 |
+
"grad_norm": 0.38877856731414795,
|
| 979 |
+
"learning_rate": 0.00011662081072397009,
|
| 980 |
+
"loss": 0.5596,
|
| 981 |
+
"step": 132
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 0.7634080717488789,
|
| 985 |
+
"grad_norm": 0.3513187766075134,
|
| 986 |
+
"learning_rate": 0.00011551886626719879,
|
| 987 |
+
"loss": 0.5512,
|
| 988 |
+
"step": 133
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 0.7691479820627802,
|
| 992 |
+
"grad_norm": 0.33318498730659485,
|
| 993 |
+
"learning_rate": 0.00011441609068946764,
|
| 994 |
+
"loss": 0.5654,
|
| 995 |
+
"step": 134
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 0.7748878923766817,
|
| 999 |
+
"grad_norm": 0.38084232807159424,
|
| 1000 |
+
"learning_rate": 0.00011331265006472231,
|
| 1001 |
+
"loss": 0.5368,
|
| 1002 |
+
"step": 135
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 0.780627802690583,
|
| 1006 |
+
"grad_norm": 0.40014737844467163,
|
| 1007 |
+
"learning_rate": 0.00011220871056706212,
|
| 1008 |
+
"loss": 0.5569,
|
| 1009 |
+
"step": 136
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 0.7863677130044843,
|
| 1013 |
+
"grad_norm": 0.40615227818489075,
|
| 1014 |
+
"learning_rate": 0.0001111044384457148,
|
| 1015 |
+
"loss": 0.5602,
|
| 1016 |
+
"step": 137
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 0.7921076233183857,
|
| 1020 |
+
"grad_norm": 0.20240327715873718,
|
| 1021 |
+
"learning_rate": 0.00011000000000000002,
|
| 1022 |
+
"loss": 0.2802,
|
| 1023 |
+
"step": 138
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 0.797847533632287,
|
| 1027 |
+
"grad_norm": 0.4555722177028656,
|
| 1028 |
+
"learning_rate": 0.00010889556155428522,
|
| 1029 |
+
"loss": 0.5397,
|
| 1030 |
+
"step": 139
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"epoch": 0.8035874439461883,
|
| 1034 |
+
"grad_norm": 0.3639007806777954,
|
| 1035 |
+
"learning_rate": 0.0001077912894329379,
|
| 1036 |
+
"loss": 0.5589,
|
| 1037 |
+
"step": 140
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 0.8093273542600897,
|
| 1041 |
+
"grad_norm": 0.3477562665939331,
|
| 1042 |
+
"learning_rate": 0.00010668734993527771,
|
| 1043 |
+
"loss": 0.5665,
|
| 1044 |
+
"step": 141
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 0.815067264573991,
|
| 1048 |
+
"grad_norm": 0.32893893122673035,
|
| 1049 |
+
"learning_rate": 0.0001055839093105324,
|
| 1050 |
+
"loss": 0.6049,
|
| 1051 |
+
"step": 142
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"epoch": 0.8208071748878923,
|
| 1055 |
+
"grad_norm": 0.3630063533782959,
|
| 1056 |
+
"learning_rate": 0.00010448113373280125,
|
| 1057 |
+
"loss": 0.566,
|
| 1058 |
+
"step": 143
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 0.8265470852017938,
|
| 1062 |
+
"grad_norm": 0.4404502213001251,
|
| 1063 |
+
"learning_rate": 0.00010337918927602994,
|
| 1064 |
+
"loss": 0.5496,
|
| 1065 |
+
"step": 144
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 0.8322869955156951,
|
| 1069 |
+
"grad_norm": 0.4184599816799164,
|
| 1070 |
+
"learning_rate": 0.00010227824188900043,
|
| 1071 |
+
"loss": 0.5382,
|
| 1072 |
+
"step": 145
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 0.8380269058295964,
|
| 1076 |
+
"grad_norm": 0.3810145854949951,
|
| 1077 |
+
"learning_rate": 0.00010117845737033956,
|
| 1078 |
+
"loss": 0.5412,
|
| 1079 |
+
"step": 146
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 0.8437668161434978,
|
| 1083 |
+
"grad_norm": 0.37553566694259644,
|
| 1084 |
+
"learning_rate": 0.00010008000134355053,
|
| 1085 |
+
"loss": 0.5264,
|
| 1086 |
+
"step": 147
|
| 1087 |
+
},
|
| 1088 |
+
{
|
| 1089 |
+
"epoch": 0.8495067264573991,
|
| 1090 |
+
"grad_norm": 0.35165223479270935,
|
| 1091 |
+
"learning_rate": 9.898303923207055e-05,
|
| 1092 |
+
"loss": 0.5131,
|
| 1093 |
+
"step": 148
|
| 1094 |
+
},
|
| 1095 |
+
{
|
| 1096 |
+
"epoch": 0.8552466367713004,
|
| 1097 |
+
"grad_norm": 0.41181644797325134,
|
| 1098 |
+
"learning_rate": 9.788773623435865e-05,
|
| 1099 |
+
"loss": 0.5279,
|
| 1100 |
+
"step": 149
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 0.8609865470852018,
|
| 1104 |
+
"grad_norm": 0.47862258553504944,
|
| 1105 |
+
"learning_rate": 9.679425729901746e-05,
|
| 1106 |
+
"loss": 0.5313,
|
| 1107 |
+
"step": 150
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 0.8609865470852018,
|
| 1111 |
+
"eval_loss": 0.5081304907798767,
|
| 1112 |
+
"eval_runtime": 0.9227,
|
| 1113 |
+
"eval_samples_per_second": 54.191,
|
| 1114 |
+
"eval_steps_per_second": 14.09,
|
| 1115 |
+
"step": 150
|
| 1116 |
}
|
| 1117 |
],
|
| 1118 |
"logging_steps": 1,
|
|
|
|
| 1141 |
"attributes": {}
|
| 1142 |
}
|
| 1143 |
},
|
| 1144 |
+
"total_flos": 1.336101323447206e+18,
|
| 1145 |
"train_batch_size": 1,
|
| 1146 |
"trial_name": null,
|
| 1147 |
"trial_params": null
|