Training in progress, step 150, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 671149168
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2d1c9c9f8dc11c7c0f329f44cb7ff15f4e7bb7db0d26d770ea3d51a21c881def
|
| 3 |
size 671149168
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1342555602
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6ae8fbc4490a46de5bf9a24502d5562604936b27e9a4a88e091f185d6b80f4b9
|
| 3 |
size 1342555602
|
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:eedd2298fd16372c6fac7072766f3f115f4a30f98acc788a9a1d7929c2bc3710
|
| 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:f4c9c807f0681c8b7e53ada9b6ec3dba530d303de7da0d0a0562a3d8d0bbba08
|
| 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": 50,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -731,6 +731,364 @@
|
|
| 731 |
"eval_samples_per_second": 12.285,
|
| 732 |
"eval_steps_per_second": 6.143,
|
| 733 |
"step": 100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 734 |
}
|
| 735 |
],
|
| 736 |
"logging_steps": 1,
|
|
@@ -759,7 +1117,7 @@
|
|
| 759 |
"attributes": {}
|
| 760 |
}
|
| 761 |
},
|
| 762 |
-
"total_flos":
|
| 763 |
"train_batch_size": 8,
|
| 764 |
"trial_name": null,
|
| 765 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.06682530045509338,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-150",
|
| 4 |
+
"epoch": 0.012836695834492201,
|
| 5 |
"eval_steps": 50,
|
| 6 |
+
"global_step": 150,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 731 |
"eval_samples_per_second": 12.285,
|
| 732 |
"eval_steps_per_second": 6.143,
|
| 733 |
"step": 100
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 0.00864337519522475,
|
| 737 |
+
"grad_norm": 0.929148256778717,
|
| 738 |
+
"learning_rate": 5.782172325201155e-05,
|
| 739 |
+
"loss": 0.0787,
|
| 740 |
+
"step": 101
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 0.008728953167454697,
|
| 744 |
+
"grad_norm": 1.4181785583496094,
|
| 745 |
+
"learning_rate": 5.695865504800327e-05,
|
| 746 |
+
"loss": 0.1108,
|
| 747 |
+
"step": 102
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.008814531139684645,
|
| 751 |
+
"grad_norm": 0.9560567736625671,
|
| 752 |
+
"learning_rate": 5.6093467170257374e-05,
|
| 753 |
+
"loss": 0.0688,
|
| 754 |
+
"step": 103
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 0.008900109111914594,
|
| 758 |
+
"grad_norm": 0.8583462834358215,
|
| 759 |
+
"learning_rate": 5.522642316338268e-05,
|
| 760 |
+
"loss": 0.0556,
|
| 761 |
+
"step": 104
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.008985687084144541,
|
| 765 |
+
"grad_norm": 0.39183780550956726,
|
| 766 |
+
"learning_rate": 5.435778713738292e-05,
|
| 767 |
+
"loss": 0.0349,
|
| 768 |
+
"step": 105
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 0.009071265056374489,
|
| 772 |
+
"grad_norm": 0.6475428342819214,
|
| 773 |
+
"learning_rate": 5.348782368720626e-05,
|
| 774 |
+
"loss": 0.0571,
|
| 775 |
+
"step": 106
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 0.009156843028604438,
|
| 779 |
+
"grad_norm": 1.966285228729248,
|
| 780 |
+
"learning_rate": 5.26167978121472e-05,
|
| 781 |
+
"loss": 0.0628,
|
| 782 |
+
"step": 107
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 0.009242421000834385,
|
| 786 |
+
"grad_norm": 0.6283954381942749,
|
| 787 |
+
"learning_rate": 5.174497483512506e-05,
|
| 788 |
+
"loss": 0.0513,
|
| 789 |
+
"step": 108
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.009327998973064333,
|
| 793 |
+
"grad_norm": 1.4355676174163818,
|
| 794 |
+
"learning_rate": 5.0872620321864185e-05,
|
| 795 |
+
"loss": 0.081,
|
| 796 |
+
"step": 109
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 0.009413576945294282,
|
| 800 |
+
"grad_norm": 0.5498899817466736,
|
| 801 |
+
"learning_rate": 5e-05,
|
| 802 |
+
"loss": 0.0425,
|
| 803 |
+
"step": 110
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 0.00949915491752423,
|
| 807 |
+
"grad_norm": 0.4436624348163605,
|
| 808 |
+
"learning_rate": 4.912737967813583e-05,
|
| 809 |
+
"loss": 0.0435,
|
| 810 |
+
"step": 111
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 0.009584732889754177,
|
| 814 |
+
"grad_norm": 0.4409253001213074,
|
| 815 |
+
"learning_rate": 4.825502516487497e-05,
|
| 816 |
+
"loss": 0.0414,
|
| 817 |
+
"step": 112
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 0.009670310861984126,
|
| 821 |
+
"grad_norm": 0.7499750256538391,
|
| 822 |
+
"learning_rate": 4.738320218785281e-05,
|
| 823 |
+
"loss": 0.0553,
|
| 824 |
+
"step": 113
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 0.009755888834214074,
|
| 828 |
+
"grad_norm": 0.9011760354042053,
|
| 829 |
+
"learning_rate": 4.6512176312793736e-05,
|
| 830 |
+
"loss": 0.0564,
|
| 831 |
+
"step": 114
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 0.009841466806444021,
|
| 835 |
+
"grad_norm": 0.8393090963363647,
|
| 836 |
+
"learning_rate": 4.564221286261709e-05,
|
| 837 |
+
"loss": 0.0519,
|
| 838 |
+
"step": 115
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 0.009927044778673969,
|
| 842 |
+
"grad_norm": 0.5188331604003906,
|
| 843 |
+
"learning_rate": 4.477357683661734e-05,
|
| 844 |
+
"loss": 0.0506,
|
| 845 |
+
"step": 116
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 0.010012622750903918,
|
| 849 |
+
"grad_norm": 0.35314175486564636,
|
| 850 |
+
"learning_rate": 4.390653282974264e-05,
|
| 851 |
+
"loss": 0.0344,
|
| 852 |
+
"step": 117
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 0.010098200723133865,
|
| 856 |
+
"grad_norm": 0.4411436915397644,
|
| 857 |
+
"learning_rate": 4.3041344951996746e-05,
|
| 858 |
+
"loss": 0.0347,
|
| 859 |
+
"step": 118
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 0.010183778695363813,
|
| 863 |
+
"grad_norm": 0.8208513855934143,
|
| 864 |
+
"learning_rate": 4.2178276747988446e-05,
|
| 865 |
+
"loss": 0.0406,
|
| 866 |
+
"step": 119
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 0.010269356667593762,
|
| 870 |
+
"grad_norm": 0.5493667721748352,
|
| 871 |
+
"learning_rate": 4.131759111665349e-05,
|
| 872 |
+
"loss": 0.0318,
|
| 873 |
+
"step": 120
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.01035493463982371,
|
| 877 |
+
"grad_norm": 0.5189446210861206,
|
| 878 |
+
"learning_rate": 4.045955023117276e-05,
|
| 879 |
+
"loss": 0.0581,
|
| 880 |
+
"step": 121
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 0.010440512612053657,
|
| 884 |
+
"grad_norm": 0.6042659282684326,
|
| 885 |
+
"learning_rate": 3.960441545911204e-05,
|
| 886 |
+
"loss": 0.0582,
|
| 887 |
+
"step": 122
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 0.010526090584283606,
|
| 891 |
+
"grad_norm": 0.9619970917701721,
|
| 892 |
+
"learning_rate": 3.875244728280676e-05,
|
| 893 |
+
"loss": 0.0774,
|
| 894 |
+
"step": 123
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 0.010611668556513553,
|
| 898 |
+
"grad_norm": 0.48345574736595154,
|
| 899 |
+
"learning_rate": 3.790390522001662e-05,
|
| 900 |
+
"loss": 0.0299,
|
| 901 |
+
"step": 124
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 0.010697246528743501,
|
| 905 |
+
"grad_norm": 0.46458688378334045,
|
| 906 |
+
"learning_rate": 3.705904774487396e-05,
|
| 907 |
+
"loss": 0.0238,
|
| 908 |
+
"step": 125
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 0.01078282450097345,
|
| 912 |
+
"grad_norm": 0.6511420607566833,
|
| 913 |
+
"learning_rate": 3.6218132209150045e-05,
|
| 914 |
+
"loss": 0.0427,
|
| 915 |
+
"step": 126
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 0.010868402473203398,
|
| 919 |
+
"grad_norm": 0.670028567314148,
|
| 920 |
+
"learning_rate": 3.5381414763863166e-05,
|
| 921 |
+
"loss": 0.0475,
|
| 922 |
+
"step": 127
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 0.010953980445433345,
|
| 926 |
+
"grad_norm": 0.3459213674068451,
|
| 927 |
+
"learning_rate": 3.4549150281252636e-05,
|
| 928 |
+
"loss": 0.0312,
|
| 929 |
+
"step": 128
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 0.011039558417663294,
|
| 933 |
+
"grad_norm": 2.4077601432800293,
|
| 934 |
+
"learning_rate": 3.372159227714218e-05,
|
| 935 |
+
"loss": 0.0705,
|
| 936 |
+
"step": 129
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 0.011125136389893242,
|
| 940 |
+
"grad_norm": 1.3302983045578003,
|
| 941 |
+
"learning_rate": 3.289899283371657e-05,
|
| 942 |
+
"loss": 0.083,
|
| 943 |
+
"step": 130
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 0.01121071436212319,
|
| 947 |
+
"grad_norm": 0.5050893425941467,
|
| 948 |
+
"learning_rate": 3.2081602522734986e-05,
|
| 949 |
+
"loss": 0.054,
|
| 950 |
+
"step": 131
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 0.011296292334353137,
|
| 954 |
+
"grad_norm": 0.4147576093673706,
|
| 955 |
+
"learning_rate": 3.12696703292044e-05,
|
| 956 |
+
"loss": 0.0394,
|
| 957 |
+
"step": 132
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 0.011381870306583086,
|
| 961 |
+
"grad_norm": 0.5236956477165222,
|
| 962 |
+
"learning_rate": 3.046344357553632e-05,
|
| 963 |
+
"loss": 0.0435,
|
| 964 |
+
"step": 133
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 0.011467448278813033,
|
| 968 |
+
"grad_norm": 0.6349552273750305,
|
| 969 |
+
"learning_rate": 2.9663167846209998e-05,
|
| 970 |
+
"loss": 0.0658,
|
| 971 |
+
"step": 134
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 0.01155302625104298,
|
| 975 |
+
"grad_norm": 0.6823920607566833,
|
| 976 |
+
"learning_rate": 2.886908691296504e-05,
|
| 977 |
+
"loss": 0.0482,
|
| 978 |
+
"step": 135
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 0.01163860422327293,
|
| 982 |
+
"grad_norm": 0.48261919617652893,
|
| 983 |
+
"learning_rate": 2.8081442660546125e-05,
|
| 984 |
+
"loss": 0.0283,
|
| 985 |
+
"step": 136
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 0.011724182195502877,
|
| 989 |
+
"grad_norm": 0.28987106680870056,
|
| 990 |
+
"learning_rate": 2.7300475013022663e-05,
|
| 991 |
+
"loss": 0.04,
|
| 992 |
+
"step": 137
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 0.011809760167732825,
|
| 996 |
+
"grad_norm": 0.3148164749145508,
|
| 997 |
+
"learning_rate": 2.6526421860705473e-05,
|
| 998 |
+
"loss": 0.03,
|
| 999 |
+
"step": 138
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.011895338139962774,
|
| 1003 |
+
"grad_norm": 0.4744351804256439,
|
| 1004 |
+
"learning_rate": 2.575951898768315e-05,
|
| 1005 |
+
"loss": 0.0392,
|
| 1006 |
+
"step": 139
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 0.011980916112192722,
|
| 1010 |
+
"grad_norm": 0.7566235065460205,
|
| 1011 |
+
"learning_rate": 2.500000000000001e-05,
|
| 1012 |
+
"loss": 0.0636,
|
| 1013 |
+
"step": 140
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 0.012066494084422669,
|
| 1017 |
+
"grad_norm": 0.4504815638065338,
|
| 1018 |
+
"learning_rate": 2.4248096254497288e-05,
|
| 1019 |
+
"loss": 0.0375,
|
| 1020 |
+
"step": 141
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 0.012152072056652618,
|
| 1024 |
+
"grad_norm": 0.5619352459907532,
|
| 1025 |
+
"learning_rate": 2.350403678833976e-05,
|
| 1026 |
+
"loss": 0.0547,
|
| 1027 |
+
"step": 142
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 0.012237650028882566,
|
| 1031 |
+
"grad_norm": 0.4695350229740143,
|
| 1032 |
+
"learning_rate": 2.2768048249248648e-05,
|
| 1033 |
+
"loss": 0.0372,
|
| 1034 |
+
"step": 143
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 0.012323228001112513,
|
| 1038 |
+
"grad_norm": 0.35198646783828735,
|
| 1039 |
+
"learning_rate": 2.2040354826462668e-05,
|
| 1040 |
+
"loss": 0.0196,
|
| 1041 |
+
"step": 144
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.012408805973342462,
|
| 1045 |
+
"grad_norm": 0.35350337624549866,
|
| 1046 |
+
"learning_rate": 2.132117818244771e-05,
|
| 1047 |
+
"loss": 0.0342,
|
| 1048 |
+
"step": 145
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 0.01249438394557241,
|
| 1052 |
+
"grad_norm": 0.7969871163368225,
|
| 1053 |
+
"learning_rate": 2.061073738537635e-05,
|
| 1054 |
+
"loss": 0.0294,
|
| 1055 |
+
"step": 146
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 0.012579961917802357,
|
| 1059 |
+
"grad_norm": 0.5979835987091064,
|
| 1060 |
+
"learning_rate": 1.9909248842397584e-05,
|
| 1061 |
+
"loss": 0.037,
|
| 1062 |
+
"step": 147
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 0.012665539890032306,
|
| 1066 |
+
"grad_norm": 0.6548674702644348,
|
| 1067 |
+
"learning_rate": 1.9216926233717085e-05,
|
| 1068 |
+
"loss": 0.0412,
|
| 1069 |
+
"step": 148
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 0.012751117862262254,
|
| 1073 |
+
"grad_norm": 0.693615734577179,
|
| 1074 |
+
"learning_rate": 1.8533980447508137e-05,
|
| 1075 |
+
"loss": 0.0249,
|
| 1076 |
+
"step": 149
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 0.012836695834492201,
|
| 1080 |
+
"grad_norm": 0.5284988284111023,
|
| 1081 |
+
"learning_rate": 1.7860619515673033e-05,
|
| 1082 |
+
"loss": 0.033,
|
| 1083 |
+
"step": 150
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 0.012836695834492201,
|
| 1087 |
+
"eval_loss": 0.06682530045509338,
|
| 1088 |
+
"eval_runtime": 1602.9258,
|
| 1089 |
+
"eval_samples_per_second": 12.278,
|
| 1090 |
+
"eval_steps_per_second": 6.139,
|
| 1091 |
+
"step": 150
|
| 1092 |
}
|
| 1093 |
],
|
| 1094 |
"logging_steps": 1,
|
|
|
|
| 1117 |
"attributes": {}
|
| 1118 |
}
|
| 1119 |
},
|
| 1120 |
+
"total_flos": 2.262770368118784e+17,
|
| 1121 |
"train_batch_size": 8,
|
| 1122 |
"trial_name": null,
|
| 1123 |
"trial_params": null
|