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 +363 -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 639691872
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ecd25bc0d8b6223f33a9ebb632af1df6ae79e5198e08fe8cf1162acb95c50ff2
|
| 3 |
size 639691872
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 325339796
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c593b78fc1f7ddfb817772a3d38dab0573600c151f0b676eecd59b9226f4501c
|
| 3 |
size 325339796
|
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 sha256:0a281cc93722f15ec32a06d9f11692716a9a11cc0f6bf5f7a0bc6e6bf13b1b6f
|
| 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 sha256:1b1d43a8747327f7c1327922026b4e877587bbb70dc6be7afcb3459f85b29e07
|
| 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:f12374625999f55ba1d4306fe1d7c0b29c805b83a14ddf9ef70935cde59c8ebc
|
| 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 sha256:7eae386689c6a32d53d558422f5eaaed1e0da12f4e3b928830fde7d811574233
|
| 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:d8ce05761f46e7cf72fb17a02e3a0ca15c9d25ce3babf590eeb40568923b8bac
|
| 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": 84.012,
|
| 732 |
"eval_steps_per_second": 5.252,
|
| 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": 0.36475056409835815,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-150",
|
| 4 |
+
"epoch": 0.051190171487074485,
|
| 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": 84.012,
|
| 732 |
"eval_steps_per_second": 5.252,
|
| 733 |
"step": 100
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 0.034468048801296815,
|
| 737 |
+
"grad_norm": 0.16129793226718903,
|
| 738 |
+
"learning_rate": 5.330452921628497e-05,
|
| 739 |
+
"loss": 0.4731,
|
| 740 |
+
"step": 101
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 0.034809316611210644,
|
| 744 |
+
"grad_norm": 0.2253504991531372,
|
| 745 |
+
"learning_rate": 5.247918773366112e-05,
|
| 746 |
+
"loss": 0.5473,
|
| 747 |
+
"step": 102
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.035150584421124474,
|
| 751 |
+
"grad_norm": 0.2580241858959198,
|
| 752 |
+
"learning_rate": 5.165316846586541e-05,
|
| 753 |
+
"loss": 0.5201,
|
| 754 |
+
"step": 103
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 0.035491852231038304,
|
| 758 |
+
"grad_norm": 0.27417340874671936,
|
| 759 |
+
"learning_rate": 5.0826697238317935e-05,
|
| 760 |
+
"loss": 0.4761,
|
| 761 |
+
"step": 104
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.03583312004095214,
|
| 765 |
+
"grad_norm": 0.2158539742231369,
|
| 766 |
+
"learning_rate": 5e-05,
|
| 767 |
+
"loss": 0.3365,
|
| 768 |
+
"step": 105
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 0.03617438785086597,
|
| 772 |
+
"grad_norm": 0.2179335206747055,
|
| 773 |
+
"learning_rate": 4.917330276168208e-05,
|
| 774 |
+
"loss": 0.3098,
|
| 775 |
+
"step": 106
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 0.0365156556607798,
|
| 779 |
+
"grad_norm": 0.2259940207004547,
|
| 780 |
+
"learning_rate": 4.834683153413459e-05,
|
| 781 |
+
"loss": 0.2926,
|
| 782 |
+
"step": 107
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 0.03685692347069363,
|
| 786 |
+
"grad_norm": 0.2270604819059372,
|
| 787 |
+
"learning_rate": 4.7520812266338885e-05,
|
| 788 |
+
"loss": 0.323,
|
| 789 |
+
"step": 108
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.03719819128060746,
|
| 793 |
+
"grad_norm": 0.22030046582221985,
|
| 794 |
+
"learning_rate": 4.669547078371504e-05,
|
| 795 |
+
"loss": 0.2834,
|
| 796 |
+
"step": 109
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 0.03753945909052129,
|
| 800 |
+
"grad_norm": 0.24005058407783508,
|
| 801 |
+
"learning_rate": 4.5871032726383386e-05,
|
| 802 |
+
"loss": 0.307,
|
| 803 |
+
"step": 110
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 0.03788072690043512,
|
| 807 |
+
"grad_norm": 0.27254408597946167,
|
| 808 |
+
"learning_rate": 4.504772348747687e-05,
|
| 809 |
+
"loss": 0.3485,
|
| 810 |
+
"step": 111
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 0.03822199471034895,
|
| 814 |
+
"grad_norm": 0.24621416628360748,
|
| 815 |
+
"learning_rate": 4.4225768151520694e-05,
|
| 816 |
+
"loss": 0.3179,
|
| 817 |
+
"step": 112
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 0.03856326252026278,
|
| 821 |
+
"grad_norm": 0.20467038452625275,
|
| 822 |
+
"learning_rate": 4.3405391432896555e-05,
|
| 823 |
+
"loss": 0.429,
|
| 824 |
+
"step": 113
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 0.03890453033017661,
|
| 828 |
+
"grad_norm": 0.24165219068527222,
|
| 829 |
+
"learning_rate": 4.2586817614407895e-05,
|
| 830 |
+
"loss": 0.4942,
|
| 831 |
+
"step": 114
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 0.03924579814009044,
|
| 835 |
+
"grad_norm": 0.2582136392593384,
|
| 836 |
+
"learning_rate": 4.17702704859633e-05,
|
| 837 |
+
"loss": 0.5515,
|
| 838 |
+
"step": 115
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 0.03958706595000427,
|
| 842 |
+
"grad_norm": 0.27229195833206177,
|
| 843 |
+
"learning_rate": 4.095597328339452e-05,
|
| 844 |
+
"loss": 0.5142,
|
| 845 |
+
"step": 116
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 0.0399283337599181,
|
| 849 |
+
"grad_norm": 0.21786056458950043,
|
| 850 |
+
"learning_rate": 4.0144148627425993e-05,
|
| 851 |
+
"loss": 0.3657,
|
| 852 |
+
"step": 117
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 0.04026960156983193,
|
| 856 |
+
"grad_norm": 0.23516137897968292,
|
| 857 |
+
"learning_rate": 3.933501846281267e-05,
|
| 858 |
+
"loss": 0.342,
|
| 859 |
+
"step": 118
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 0.040610869379745757,
|
| 863 |
+
"grad_norm": 0.20134663581848145,
|
| 864 |
+
"learning_rate": 3.852880399766243e-05,
|
| 865 |
+
"loss": 0.3004,
|
| 866 |
+
"step": 119
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 0.040952137189659586,
|
| 870 |
+
"grad_norm": 0.2039736956357956,
|
| 871 |
+
"learning_rate": 3.772572564296005e-05,
|
| 872 |
+
"loss": 0.2787,
|
| 873 |
+
"step": 120
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.041293404999573416,
|
| 877 |
+
"grad_norm": 0.22337153553962708,
|
| 878 |
+
"learning_rate": 3.6926002952309016e-05,
|
| 879 |
+
"loss": 0.3031,
|
| 880 |
+
"step": 121
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 0.041634672809487246,
|
| 884 |
+
"grad_norm": 0.21707502007484436,
|
| 885 |
+
"learning_rate": 3.612985456190778e-05,
|
| 886 |
+
"loss": 0.2959,
|
| 887 |
+
"step": 122
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 0.041975940619401075,
|
| 891 |
+
"grad_norm": 0.23799727857112885,
|
| 892 |
+
"learning_rate": 3.533749813077677e-05,
|
| 893 |
+
"loss": 0.3139,
|
| 894 |
+
"step": 123
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 0.042317208429314905,
|
| 898 |
+
"grad_norm": 0.2188572734594345,
|
| 899 |
+
"learning_rate": 3.4549150281252636e-05,
|
| 900 |
+
"loss": 0.2982,
|
| 901 |
+
"step": 124
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 0.042658476239228735,
|
| 905 |
+
"grad_norm": 0.26045840978622437,
|
| 906 |
+
"learning_rate": 3.3765026539765834e-05,
|
| 907 |
+
"loss": 0.3144,
|
| 908 |
+
"step": 125
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 0.042999744049142564,
|
| 912 |
+
"grad_norm": 0.1674930453300476,
|
| 913 |
+
"learning_rate": 3.298534127791785e-05,
|
| 914 |
+
"loss": 0.4554,
|
| 915 |
+
"step": 126
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 0.043341011859056394,
|
| 919 |
+
"grad_norm": 0.20759105682373047,
|
| 920 |
+
"learning_rate": 3.221030765387417e-05,
|
| 921 |
+
"loss": 0.5329,
|
| 922 |
+
"step": 127
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 0.043682279668970224,
|
| 926 |
+
"grad_norm": 0.23097668588161469,
|
| 927 |
+
"learning_rate": 3.144013755408895e-05,
|
| 928 |
+
"loss": 0.5192,
|
| 929 |
+
"step": 128
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 0.044023547478884054,
|
| 933 |
+
"grad_norm": 0.2753804922103882,
|
| 934 |
+
"learning_rate": 3.0675041535377405e-05,
|
| 935 |
+
"loss": 0.4202,
|
| 936 |
+
"step": 129
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 0.04436481528879788,
|
| 940 |
+
"grad_norm": 0.2095237821340561,
|
| 941 |
+
"learning_rate": 2.991522876735154e-05,
|
| 942 |
+
"loss": 0.2953,
|
| 943 |
+
"step": 130
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 0.04470608309871171,
|
| 947 |
+
"grad_norm": 0.2132461667060852,
|
| 948 |
+
"learning_rate": 2.916090697523549e-05,
|
| 949 |
+
"loss": 0.3091,
|
| 950 |
+
"step": 131
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 0.04504735090862554,
|
| 954 |
+
"grad_norm": 0.21441613137722015,
|
| 955 |
+
"learning_rate": 2.8412282383075363e-05,
|
| 956 |
+
"loss": 0.2988,
|
| 957 |
+
"step": 132
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 0.04538861871853937,
|
| 961 |
+
"grad_norm": 0.22250419855117798,
|
| 962 |
+
"learning_rate": 2.766955965735968e-05,
|
| 963 |
+
"loss": 0.3046,
|
| 964 |
+
"step": 133
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 0.0457298865284532,
|
| 968 |
+
"grad_norm": 0.2193128615617752,
|
| 969 |
+
"learning_rate": 2.693294185106562e-05,
|
| 970 |
+
"loss": 0.2892,
|
| 971 |
+
"step": 134
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 0.04607115433836703,
|
| 975 |
+
"grad_norm": 0.19122985005378723,
|
| 976 |
+
"learning_rate": 2.6202630348146324e-05,
|
| 977 |
+
"loss": 0.2641,
|
| 978 |
+
"step": 135
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 0.04641242214828086,
|
| 982 |
+
"grad_norm": 0.2623761296272278,
|
| 983 |
+
"learning_rate": 2.547882480847461e-05,
|
| 984 |
+
"loss": 0.3437,
|
| 985 |
+
"step": 136
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 0.04675368995819469,
|
| 989 |
+
"grad_norm": 0.2327306568622589,
|
| 990 |
+
"learning_rate": 2.476172311325783e-05,
|
| 991 |
+
"loss": 0.2995,
|
| 992 |
+
"step": 137
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 0.04709495776810852,
|
| 996 |
+
"grad_norm": 0.18870247900485992,
|
| 997 |
+
"learning_rate": 2.405152131093926e-05,
|
| 998 |
+
"loss": 0.4046,
|
| 999 |
+
"step": 138
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.04743622557802235,
|
| 1003 |
+
"grad_norm": 0.22929644584655762,
|
| 1004 |
+
"learning_rate": 2.3348413563600325e-05,
|
| 1005 |
+
"loss": 0.4661,
|
| 1006 |
+
"step": 139
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 0.04777749338793618,
|
| 1010 |
+
"grad_norm": 0.2513699531555176,
|
| 1011 |
+
"learning_rate": 2.2652592093878666e-05,
|
| 1012 |
+
"loss": 0.579,
|
| 1013 |
+
"step": 140
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 0.04811876119785001,
|
| 1017 |
+
"grad_norm": 0.24072954058647156,
|
| 1018 |
+
"learning_rate": 2.196424713241637e-05,
|
| 1019 |
+
"loss": 0.5762,
|
| 1020 |
+
"step": 141
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 0.04846002900776384,
|
| 1024 |
+
"grad_norm": 0.2634357511997223,
|
| 1025 |
+
"learning_rate": 2.128356686585282e-05,
|
| 1026 |
+
"loss": 0.3994,
|
| 1027 |
+
"step": 142
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 0.04880129681767767,
|
| 1031 |
+
"grad_norm": 0.22981932759284973,
|
| 1032 |
+
"learning_rate": 2.061073738537635e-05,
|
| 1033 |
+
"loss": 0.2735,
|
| 1034 |
+
"step": 143
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 0.0491425646275915,
|
| 1038 |
+
"grad_norm": 0.22643893957138062,
|
| 1039 |
+
"learning_rate": 1.9945942635848748e-05,
|
| 1040 |
+
"loss": 0.2708,
|
| 1041 |
+
"step": 144
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.04948383243750533,
|
| 1045 |
+
"grad_norm": 0.23719343543052673,
|
| 1046 |
+
"learning_rate": 1.928936436551661e-05,
|
| 1047 |
+
"loss": 0.3119,
|
| 1048 |
+
"step": 145
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 0.049825100247419166,
|
| 1052 |
+
"grad_norm": 0.22354793548583984,
|
| 1053 |
+
"learning_rate": 1.8641182076323148e-05,
|
| 1054 |
+
"loss": 0.2881,
|
| 1055 |
+
"step": 146
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 0.050166368057332995,
|
| 1059 |
+
"grad_norm": 0.23652666807174683,
|
| 1060 |
+
"learning_rate": 1.800157297483417e-05,
|
| 1061 |
+
"loss": 0.3083,
|
| 1062 |
+
"step": 147
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 0.050507635867246825,
|
| 1066 |
+
"grad_norm": 0.22466449439525604,
|
| 1067 |
+
"learning_rate": 1.7370711923791567e-05,
|
| 1068 |
+
"loss": 0.313,
|
| 1069 |
+
"step": 148
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 0.050848903677160655,
|
| 1073 |
+
"grad_norm": 0.22616927325725555,
|
| 1074 |
+
"learning_rate": 1.6748771394307585e-05,
|
| 1075 |
+
"loss": 0.3104,
|
| 1076 |
+
"step": 149
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 0.051190171487074485,
|
| 1080 |
+
"grad_norm": 0.253631591796875,
|
| 1081 |
+
"learning_rate": 1.6135921418712956e-05,
|
| 1082 |
+
"loss": 0.3248,
|
| 1083 |
+
"step": 150
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 0.051190171487074485,
|
| 1087 |
+
"eval_loss": 0.36475056409835815,
|
| 1088 |
+
"eval_runtime": 234.7864,
|
| 1089 |
+
"eval_samples_per_second": 84.076,
|
| 1090 |
+
"eval_steps_per_second": 5.256,
|
| 1091 |
+
"step": 150
|
| 1092 |
}
|
| 1093 |
],
|
| 1094 |
"logging_steps": 1,
|
|
|
|
| 1117 |
"attributes": {}
|
| 1118 |
}
|
| 1119 |
},
|
| 1120 |
+
"total_flos": 1.0893434161830298e+18,
|
| 1121 |
"train_batch_size": 8,
|
| 1122 |
"trial_name": null,
|
| 1123 |
"trial_params": null
|