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 78480072
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c827c21dcd3a257819246a55c11b3f50909e9233dcfebd2814a25bd3ee845ac3
|
| 3 |
size 78480072
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 157104826
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:68052fd8b96c1f2271f1b7eff022a919e3355f62ce1a8e7e2f099d3fa9d51815
|
| 3 |
size 157104826
|
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 sha256:502e686da367d3f37771f4b324ac8e96576dc0d12a4d01dd2b6dd1a0e08ee790
|
| 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:c293ea2ced33e6b1a9a6d31cc9d0df0ce2794a92d3016ca4577e7bf7d0183635
|
| 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 sha256:77d4a73ace90f0be2d58c57db7ec4e9dc9586b6130ee4f221abc20fcb20f9193
|
| 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:cd52b163a28bcfe6d938bfe3e9051ccaeb68b57c36b5805f8c7ca75b025892ec
|
| 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:f80d648856420cec2afc4a26fe030d14fe1888f66711c6de8ea302f1ee36d8b9
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 2.
|
| 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": 71.931,
|
| 748 |
"eval_steps_per_second": 18.702,
|
| 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": 2.4083755016326904,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-150",
|
| 4 |
+
"epoch": 1.474427891260943,
|
| 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": 71.931,
|
| 748 |
"eval_steps_per_second": 18.702,
|
| 749 |
"step": 100
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 0.9927814467823683,
|
| 753 |
+
"grad_norm": 0.9641188383102417,
|
| 754 |
+
"learning_rate": 0.00016227631426330124,
|
| 755 |
+
"loss": 2.2486,
|
| 756 |
+
"step": 101
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 1.0026109660574412,
|
| 760 |
+
"grad_norm": 1.2361067533493042,
|
| 761 |
+
"learning_rate": 0.00016149049941099528,
|
| 762 |
+
"loss": 3.1568,
|
| 763 |
+
"step": 102
|
| 764 |
+
},
|
| 765 |
+
{
|
| 766 |
+
"epoch": 1.0124404853325142,
|
| 767 |
+
"grad_norm": 0.6794304251670837,
|
| 768 |
+
"learning_rate": 0.00016069880522572597,
|
| 769 |
+
"loss": 2.0051,
|
| 770 |
+
"step": 103
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 1.0222700046075872,
|
| 774 |
+
"grad_norm": 0.7373532056808472,
|
| 775 |
+
"learning_rate": 0.00015990132210540707,
|
| 776 |
+
"loss": 2.1212,
|
| 777 |
+
"step": 104
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 1.03209952388266,
|
| 781 |
+
"grad_norm": 0.7815002202987671,
|
| 782 |
+
"learning_rate": 0.00015909814110894938,
|
| 783 |
+
"loss": 2.1963,
|
| 784 |
+
"step": 105
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 1.041929043157733,
|
| 788 |
+
"grad_norm": 0.8411288261413574,
|
| 789 |
+
"learning_rate": 0.00015828935394586365,
|
| 790 |
+
"loss": 2.108,
|
| 791 |
+
"step": 106
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 1.051758562432806,
|
| 795 |
+
"grad_norm": 0.9140182137489319,
|
| 796 |
+
"learning_rate": 0.00015747505296578884,
|
| 797 |
+
"loss": 2.014,
|
| 798 |
+
"step": 107
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 1.0615880817078789,
|
| 802 |
+
"grad_norm": 0.8995840549468994,
|
| 803 |
+
"learning_rate": 0.0001566553311479473,
|
| 804 |
+
"loss": 2.1216,
|
| 805 |
+
"step": 108
|
| 806 |
+
},
|
| 807 |
+
{
|
| 808 |
+
"epoch": 1.071417600982952,
|
| 809 |
+
"grad_norm": 0.8572644591331482,
|
| 810 |
+
"learning_rate": 0.0001558302820905281,
|
| 811 |
+
"loss": 2.1224,
|
| 812 |
+
"step": 109
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 1.081247120258025,
|
| 816 |
+
"grad_norm": 0.8983514904975891,
|
| 817 |
+
"learning_rate": 0.000155,
|
| 818 |
+
"loss": 2.0613,
|
| 819 |
+
"step": 110
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 1.0910766395330977,
|
| 823 |
+
"grad_norm": 1.0163862705230713,
|
| 824 |
+
"learning_rate": 0.00015416457968035443,
|
| 825 |
+
"loss": 2.0615,
|
| 826 |
+
"step": 111
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 1.1009061588081708,
|
| 830 |
+
"grad_norm": 1.1525602340698242,
|
| 831 |
+
"learning_rate": 0.0001533241165222805,
|
| 832 |
+
"loss": 2.0906,
|
| 833 |
+
"step": 112
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 1.1107356780832438,
|
| 837 |
+
"grad_norm": 1.3764214515686035,
|
| 838 |
+
"learning_rate": 0.00015247870649227308,
|
| 839 |
+
"loss": 2.1388,
|
| 840 |
+
"step": 113
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 1.1205651973583166,
|
| 844 |
+
"grad_norm": 1.391831398010254,
|
| 845 |
+
"learning_rate": 0.0001516284461216752,
|
| 846 |
+
"loss": 1.7508,
|
| 847 |
+
"step": 114
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 1.1303947166333896,
|
| 851 |
+
"grad_norm": 1.578629970550537,
|
| 852 |
+
"learning_rate": 0.00015077343249565554,
|
| 853 |
+
"loss": 2.4968,
|
| 854 |
+
"step": 115
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 1.1402242359084627,
|
| 858 |
+
"grad_norm": 1.0895462036132812,
|
| 859 |
+
"learning_rate": 0.0001499137632421232,
|
| 860 |
+
"loss": 2.0435,
|
| 861 |
+
"step": 116
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 1.1500537551835355,
|
| 865 |
+
"grad_norm": 1.0212132930755615,
|
| 866 |
+
"learning_rate": 0.00014904953652058022,
|
| 867 |
+
"loss": 2.0891,
|
| 868 |
+
"step": 117
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 1.1598832744586085,
|
| 872 |
+
"grad_norm": 0.9461895227432251,
|
| 873 |
+
"learning_rate": 0.00014818085101091336,
|
| 874 |
+
"loss": 2.1364,
|
| 875 |
+
"step": 118
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 1.1697127937336815,
|
| 879 |
+
"grad_norm": 0.8605825901031494,
|
| 880 |
+
"learning_rate": 0.0001473078059021266,
|
| 881 |
+
"loss": 2.0956,
|
| 882 |
+
"step": 119
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 1.1795423130087543,
|
| 886 |
+
"grad_norm": 1.0641827583312988,
|
| 887 |
+
"learning_rate": 0.00014643050088101545,
|
| 888 |
+
"loss": 1.984,
|
| 889 |
+
"step": 120
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 1.1893718322838274,
|
| 893 |
+
"grad_norm": 0.9965870380401611,
|
| 894 |
+
"learning_rate": 0.00014554903612078448,
|
| 895 |
+
"loss": 2.0469,
|
| 896 |
+
"step": 121
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 1.1992013515589004,
|
| 900 |
+
"grad_norm": 1.0630478858947754,
|
| 901 |
+
"learning_rate": 0.00014466351226960917,
|
| 902 |
+
"loss": 2.0305,
|
| 903 |
+
"step": 122
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 1.2090308708339732,
|
| 907 |
+
"grad_norm": 1.062567949295044,
|
| 908 |
+
"learning_rate": 0.0001437740304391437,
|
| 909 |
+
"loss": 2.024,
|
| 910 |
+
"step": 123
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 1.2188603901090462,
|
| 914 |
+
"grad_norm": 1.1082484722137451,
|
| 915 |
+
"learning_rate": 0.0001428806921929756,
|
| 916 |
+
"loss": 2.0846,
|
| 917 |
+
"step": 124
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 1.2286899093841193,
|
| 921 |
+
"grad_norm": 1.236946702003479,
|
| 922 |
+
"learning_rate": 0.000141983599535029,
|
| 923 |
+
"loss": 1.9621,
|
| 924 |
+
"step": 125
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 1.2286899093841193,
|
| 928 |
+
"eval_loss": 2.4299097061157227,
|
| 929 |
+
"eval_runtime": 0.6964,
|
| 930 |
+
"eval_samples_per_second": 71.798,
|
| 931 |
+
"eval_steps_per_second": 18.667,
|
| 932 |
+
"step": 125
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 1.238519428659192,
|
| 936 |
+
"grad_norm": 1.6171234846115112,
|
| 937 |
+
"learning_rate": 0.00014108285489791768,
|
| 938 |
+
"loss": 2.2414,
|
| 939 |
+
"step": 126
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 1.248348947934265,
|
| 943 |
+
"grad_norm": 2.209141254425049,
|
| 944 |
+
"learning_rate": 0.0001401785611312488,
|
| 945 |
+
"loss": 2.4781,
|
| 946 |
+
"step": 127
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 1.2581784672093381,
|
| 950 |
+
"grad_norm": 1.0709174871444702,
|
| 951 |
+
"learning_rate": 0.00013927082148987925,
|
| 952 |
+
"loss": 1.9901,
|
| 953 |
+
"step": 128
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 1.268007986484411,
|
| 957 |
+
"grad_norm": 1.1437026262283325,
|
| 958 |
+
"learning_rate": 0.0001383597396221259,
|
| 959 |
+
"loss": 1.9849,
|
| 960 |
+
"step": 129
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 1.277837505759484,
|
| 964 |
+
"grad_norm": 1.181343674659729,
|
| 965 |
+
"learning_rate": 0.00013744541955793045,
|
| 966 |
+
"loss": 2.0997,
|
| 967 |
+
"step": 130
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 1.287667025034557,
|
| 971 |
+
"grad_norm": 1.113682508468628,
|
| 972 |
+
"learning_rate": 0.0001365279656969814,
|
| 973 |
+
"loss": 2.0418,
|
| 974 |
+
"step": 131
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 1.2974965443096298,
|
| 978 |
+
"grad_norm": 1.067321538925171,
|
| 979 |
+
"learning_rate": 0.0001356074827967929,
|
| 980 |
+
"loss": 2.0363,
|
| 981 |
+
"step": 132
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 1.3073260635847028,
|
| 985 |
+
"grad_norm": 0.9680085182189941,
|
| 986 |
+
"learning_rate": 0.00013468407596074376,
|
| 987 |
+
"loss": 2.0136,
|
| 988 |
+
"step": 133
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 1.3171555828597756,
|
| 992 |
+
"grad_norm": 1.076326608657837,
|
| 993 |
+
"learning_rate": 0.0001337578506260759,
|
| 994 |
+
"loss": 2.03,
|
| 995 |
+
"step": 134
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 1.3269851021348487,
|
| 999 |
+
"grad_norm": 1.0561034679412842,
|
| 1000 |
+
"learning_rate": 0.00013282891255185565,
|
| 1001 |
+
"loss": 1.9895,
|
| 1002 |
+
"step": 135
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 1.3368146214099217,
|
| 1006 |
+
"grad_norm": 1.1942148208618164,
|
| 1007 |
+
"learning_rate": 0.0001318973678068978,
|
| 1008 |
+
"loss": 2.0359,
|
| 1009 |
+
"step": 136
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 1.3466441406849947,
|
| 1013 |
+
"grad_norm": 1.1791845560073853,
|
| 1014 |
+
"learning_rate": 0.00013096332275765407,
|
| 1015 |
+
"loss": 2.0042,
|
| 1016 |
+
"step": 137
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 1.3564736599600675,
|
| 1020 |
+
"grad_norm": 1.4035441875457764,
|
| 1021 |
+
"learning_rate": 0.00013002688405606828,
|
| 1022 |
+
"loss": 2.1086,
|
| 1023 |
+
"step": 138
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 1.3663031792351406,
|
| 1027 |
+
"grad_norm": 1.4087142944335938,
|
| 1028 |
+
"learning_rate": 0.00012908815862739835,
|
| 1029 |
+
"loss": 1.7052,
|
| 1030 |
+
"step": 139
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"epoch": 1.3761326985102134,
|
| 1034 |
+
"grad_norm": 1.3538085222244263,
|
| 1035 |
+
"learning_rate": 0.00012814725365800698,
|
| 1036 |
+
"loss": 2.5688,
|
| 1037 |
+
"step": 140
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 1.3859622177852864,
|
| 1041 |
+
"grad_norm": 0.9382008910179138,
|
| 1042 |
+
"learning_rate": 0.00012720427658312352,
|
| 1043 |
+
"loss": 2.0208,
|
| 1044 |
+
"step": 141
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 1.3957917370603594,
|
| 1048 |
+
"grad_norm": 0.8642036318778992,
|
| 1049 |
+
"learning_rate": 0.0001262593350745759,
|
| 1050 |
+
"loss": 2.0409,
|
| 1051 |
+
"step": 142
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"epoch": 1.4056212563354324,
|
| 1055 |
+
"grad_norm": 0.9334009289741516,
|
| 1056 |
+
"learning_rate": 0.00012531253702849696,
|
| 1057 |
+
"loss": 2.028,
|
| 1058 |
+
"step": 143
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 1.4154507756105053,
|
| 1062 |
+
"grad_norm": 0.9900059700012207,
|
| 1063 |
+
"learning_rate": 0.00012436399055300415,
|
| 1064 |
+
"loss": 2.0542,
|
| 1065 |
+
"step": 144
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 1.4252802948855783,
|
| 1069 |
+
"grad_norm": 1.1152311563491821,
|
| 1070 |
+
"learning_rate": 0.0001234138039558557,
|
| 1071 |
+
"loss": 2.0503,
|
| 1072 |
+
"step": 145
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 1.435109814160651,
|
| 1076 |
+
"grad_norm": 1.132704496383667,
|
| 1077 |
+
"learning_rate": 0.00012246208573208367,
|
| 1078 |
+
"loss": 2.019,
|
| 1079 |
+
"step": 146
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 1.4449393334357241,
|
| 1083 |
+
"grad_norm": 1.0074613094329834,
|
| 1084 |
+
"learning_rate": 0.00012150894455160555,
|
| 1085 |
+
"loss": 1.9423,
|
| 1086 |
+
"step": 147
|
| 1087 |
+
},
|
| 1088 |
+
{
|
| 1089 |
+
"epoch": 1.4547688527107971,
|
| 1090 |
+
"grad_norm": 1.2089931964874268,
|
| 1091 |
+
"learning_rate": 0.00012055448924681618,
|
| 1092 |
+
"loss": 2.0784,
|
| 1093 |
+
"step": 148
|
| 1094 |
+
},
|
| 1095 |
+
{
|
| 1096 |
+
"epoch": 1.4645983719858702,
|
| 1097 |
+
"grad_norm": 1.1703325510025024,
|
| 1098 |
+
"learning_rate": 0.00011959882880016083,
|
| 1099 |
+
"loss": 1.9828,
|
| 1100 |
+
"step": 149
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 1.474427891260943,
|
| 1104 |
+
"grad_norm": 1.3632087707519531,
|
| 1105 |
+
"learning_rate": 0.00011864207233169136,
|
| 1106 |
+
"loss": 2.1095,
|
| 1107 |
+
"step": 150
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 1.474427891260943,
|
| 1111 |
+
"eval_loss": 2.4083755016326904,
|
| 1112 |
+
"eval_runtime": 0.6963,
|
| 1113 |
+
"eval_samples_per_second": 71.812,
|
| 1114 |
+
"eval_steps_per_second": 18.671,
|
| 1115 |
+
"step": 150
|
| 1116 |
}
|
| 1117 |
],
|
| 1118 |
"logging_steps": 1,
|
|
|
|
| 1141 |
"attributes": {}
|
| 1142 |
}
|
| 1143 |
},
|
| 1144 |
+
"total_flos": 9.444243315621888e+17,
|
| 1145 |
"train_batch_size": 1,
|
| 1146 |
"trial_name": null,
|
| 1147 |
"trial_params": null
|