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 sha256:0b0d11a0c9563fc9b309894a3ea72052d18d47c5d2c7383d7f135a6f7e75bbf6
|
| 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:ccc19d3760e42bf952fe3f4416369525889e94276e27e85715f534215e6d1fbc
|
| 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 sha256:80ad0144eca33b04b3d4f2b29d4af62fc22d673739ee2272250b1b21f6f349c2
|
| 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:f5f01b3d4386ea634ed6767aa1edfa6779ba81e1725f3e3e0c0b9a9f92776b83
|
| 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 sha256:3a5bb99b77e13ee757e01e8e860bc41eebc1421459e9c89d0a23b81def884f78
|
| 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 sha256:2e625baf0c17e4ad56e8b11a83cbda177c07e59a3d18f926b7eb718549b22f65
|
| 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 sha256:3a56f9e526fbefceff44eaa8fd41d4c73340d4c2a80ffbd5f860cb7089f42cc1
|
| 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": 1.
|
| 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": 179.386,
|
| 748 |
"eval_steps_per_second": 46.64,
|
| 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": 1.9268525838851929,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-150",
|
| 4 |
+
"epoch": 1.955193482688391,
|
| 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": 179.386,
|
| 748 |
"eval_steps_per_second": 46.64,
|
| 749 |
"step": 100
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 1.3164969450101833,
|
| 753 |
+
"grad_norm": 0.7522782683372498,
|
| 754 |
+
"learning_rate": 0.00010497425081003482,
|
| 755 |
+
"loss": 2.1272,
|
| 756 |
+
"step": 101
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 1.329531568228106,
|
| 760 |
+
"grad_norm": 0.7502726316452026,
|
| 761 |
+
"learning_rate": 0.0001024550352588187,
|
| 762 |
+
"loss": 2.2586,
|
| 763 |
+
"step": 102
|
| 764 |
+
},
|
| 765 |
+
{
|
| 766 |
+
"epoch": 1.3425661914460285,
|
| 767 |
+
"grad_norm": 0.4233168661594391,
|
| 768 |
+
"learning_rate": 9.996325399626841e-05,
|
| 769 |
+
"loss": 1.871,
|
| 770 |
+
"step": 103
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 1.355600814663951,
|
| 774 |
+
"grad_norm": 0.5849415063858032,
|
| 775 |
+
"learning_rate": 9.750000000000003e-05,
|
| 776 |
+
"loss": 1.9998,
|
| 777 |
+
"step": 104
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 1.3686354378818737,
|
| 781 |
+
"grad_norm": 0.5961419343948364,
|
| 782 |
+
"learning_rate": 9.506635373462745e-05,
|
| 783 |
+
"loss": 2.0286,
|
| 784 |
+
"step": 105
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 1.3816700610997963,
|
| 788 |
+
"grad_norm": 0.5850256085395813,
|
| 789 |
+
"learning_rate": 9.266338267783541e-05,
|
| 790 |
+
"loss": 1.9748,
|
| 791 |
+
"step": 106
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 1.3947046843177189,
|
| 795 |
+
"grad_norm": 0.5355044007301331,
|
| 796 |
+
"learning_rate": 9.029214085214857e-05,
|
| 797 |
+
"loss": 1.9777,
|
| 798 |
+
"step": 107
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 1.4077393075356415,
|
| 802 |
+
"grad_norm": 0.40355584025382996,
|
| 803 |
+
"learning_rate": 8.795366836260173e-05,
|
| 804 |
+
"loss": 1.9819,
|
| 805 |
+
"step": 108
|
| 806 |
+
},
|
| 807 |
+
{
|
| 808 |
+
"epoch": 1.420773930753564,
|
| 809 |
+
"grad_norm": 0.30112820863723755,
|
| 810 |
+
"learning_rate": 8.564899094051614e-05,
|
| 811 |
+
"loss": 1.9478,
|
| 812 |
+
"step": 109
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 1.4338085539714869,
|
| 816 |
+
"grad_norm": 0.286545068025589,
|
| 817 |
+
"learning_rate": 8.33791194935794e-05,
|
| 818 |
+
"loss": 1.9474,
|
| 819 |
+
"step": 110
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 1.4468431771894092,
|
| 823 |
+
"grad_norm": 0.3926275372505188,
|
| 824 |
+
"learning_rate": 8.11450496624281e-05,
|
| 825 |
+
"loss": 1.9474,
|
| 826 |
+
"step": 111
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 1.459877800407332,
|
| 830 |
+
"grad_norm": 0.5009521245956421,
|
| 831 |
+
"learning_rate": 7.894776138392688e-05,
|
| 832 |
+
"loss": 2.0219,
|
| 833 |
+
"step": 112
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 1.4729124236252547,
|
| 837 |
+
"grad_norm": 0.6338520646095276,
|
| 838 |
+
"learning_rate": 7.678821846133576e-05,
|
| 839 |
+
"loss": 2.0353,
|
| 840 |
+
"step": 113
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 1.4859470468431772,
|
| 844 |
+
"grad_norm": 0.7013182044029236,
|
| 845 |
+
"learning_rate": 7.466736814155418e-05,
|
| 846 |
+
"loss": 1.62,
|
| 847 |
+
"step": 114
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 1.4989816700610998,
|
| 851 |
+
"grad_norm": 0.40693536400794983,
|
| 852 |
+
"learning_rate": 7.258614069962701e-05,
|
| 853 |
+
"loss": 2.5179,
|
| 854 |
+
"step": 115
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 1.5120162932790224,
|
| 858 |
+
"grad_norm": 0.31738847494125366,
|
| 859 |
+
"learning_rate": 7.054544903069565e-05,
|
| 860 |
+
"loss": 1.9209,
|
| 861 |
+
"step": 116
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 1.525050916496945,
|
| 865 |
+
"grad_norm": 0.3408113718032837,
|
| 866 |
+
"learning_rate": 6.854618824957157e-05,
|
| 867 |
+
"loss": 1.9408,
|
| 868 |
+
"step": 117
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 1.5380855397148676,
|
| 872 |
+
"grad_norm": 0.30903321504592896,
|
| 873 |
+
"learning_rate": 6.658923529810946e-05,
|
| 874 |
+
"loss": 1.9548,
|
| 875 |
+
"step": 118
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 1.5511201629327902,
|
| 879 |
+
"grad_norm": 0.30865398049354553,
|
| 880 |
+
"learning_rate": 6.467544856055175e-05,
|
| 881 |
+
"loss": 1.9355,
|
| 882 |
+
"step": 119
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 1.5641547861507128,
|
| 886 |
+
"grad_norm": 0.2949885427951813,
|
| 887 |
+
"learning_rate": 6.28056674870129e-05,
|
| 888 |
+
"loss": 1.9534,
|
| 889 |
+
"step": 120
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 1.5771894093686354,
|
| 893 |
+
"grad_norm": 0.28894004225730896,
|
| 894 |
+
"learning_rate": 6.098071222526847e-05,
|
| 895 |
+
"loss": 1.9511,
|
| 896 |
+
"step": 121
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 1.590224032586558,
|
| 900 |
+
"grad_norm": 0.2710161507129669,
|
| 901 |
+
"learning_rate": 5.9201383261011636e-05,
|
| 902 |
+
"loss": 1.9424,
|
| 903 |
+
"step": 122
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 1.6032586558044808,
|
| 907 |
+
"grad_norm": 0.30530881881713867,
|
| 908 |
+
"learning_rate": 5.7468461066733505e-05,
|
| 909 |
+
"loss": 1.9794,
|
| 910 |
+
"step": 123
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 1.6162932790224032,
|
| 914 |
+
"grad_norm": 0.3637678027153015,
|
| 915 |
+
"learning_rate": 5.578270575938211e-05,
|
| 916 |
+
"loss": 1.9562,
|
| 917 |
+
"step": 124
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 1.629327902240326,
|
| 921 |
+
"grad_norm": 0.4117651581764221,
|
| 922 |
+
"learning_rate": 5.4144856766949957e-05,
|
| 923 |
+
"loss": 1.9505,
|
| 924 |
+
"step": 125
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 1.629327902240326,
|
| 928 |
+
"eval_loss": 1.9424113035202026,
|
| 929 |
+
"eval_runtime": 0.2795,
|
| 930 |
+
"eval_samples_per_second": 178.903,
|
| 931 |
+
"eval_steps_per_second": 46.515,
|
| 932 |
+
"step": 125
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 1.6423625254582483,
|
| 936 |
+
"grad_norm": 0.5891804695129395,
|
| 937 |
+
"learning_rate": 5.255563250413657e-05,
|
| 938 |
+
"loss": 2.0759,
|
| 939 |
+
"step": 126
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 1.6553971486761712,
|
| 943 |
+
"grad_norm": 0.6447423696517944,
|
| 944 |
+
"learning_rate": 5.1015730057227994e-05,
|
| 945 |
+
"loss": 2.2958,
|
| 946 |
+
"step": 127
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 1.6684317718940935,
|
| 950 |
+
"grad_norm": 0.3930685818195343,
|
| 951 |
+
"learning_rate": 4.952582487833161e-05,
|
| 952 |
+
"loss": 1.817,
|
| 953 |
+
"step": 128
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 1.6814663951120163,
|
| 957 |
+
"grad_norm": 0.43411514163017273,
|
| 958 |
+
"learning_rate": 4.808657048910077e-05,
|
| 959 |
+
"loss": 1.9874,
|
| 960 |
+
"step": 129
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 1.694501018329939,
|
| 964 |
+
"grad_norm": 0.4237060546875,
|
| 965 |
+
"learning_rate": 4.669859819407844e-05,
|
| 966 |
+
"loss": 1.9388,
|
| 967 |
+
"step": 130
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 1.7075356415478615,
|
| 971 |
+
"grad_norm": 0.3899717926979065,
|
| 972 |
+
"learning_rate": 4.536251680378601e-05,
|
| 973 |
+
"loss": 1.9506,
|
| 974 |
+
"step": 131
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 1.7205702647657841,
|
| 978 |
+
"grad_norm": 0.3600156009197235,
|
| 979 |
+
"learning_rate": 4.407891236767926e-05,
|
| 980 |
+
"loss": 1.9307,
|
| 981 |
+
"step": 132
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 1.7336048879837067,
|
| 985 |
+
"grad_norm": 0.29930025339126587,
|
| 986 |
+
"learning_rate": 4.2848347917087386e-05,
|
| 987 |
+
"loss": 1.9395,
|
| 988 |
+
"step": 133
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 1.7466395112016293,
|
| 992 |
+
"grad_norm": 0.28485575318336487,
|
| 993 |
+
"learning_rate": 4.167136321824887e-05,
|
| 994 |
+
"loss": 1.9331,
|
| 995 |
+
"step": 134
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 1.759674134419552,
|
| 999 |
+
"grad_norm": 0.28593364357948303,
|
| 1000 |
+
"learning_rate": 4.054847453555244e-05,
|
| 1001 |
+
"loss": 1.9109,
|
| 1002 |
+
"step": 135
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 1.7727087576374747,
|
| 1006 |
+
"grad_norm": 0.33563509583473206,
|
| 1007 |
+
"learning_rate": 3.948017440508607e-05,
|
| 1008 |
+
"loss": 1.94,
|
| 1009 |
+
"step": 136
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 1.785743380855397,
|
| 1013 |
+
"grad_norm": 0.41171127557754517,
|
| 1014 |
+
"learning_rate": 3.846693141859465e-05,
|
| 1015 |
+
"loss": 1.9329,
|
| 1016 |
+
"step": 137
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 1.79877800407332,
|
| 1020 |
+
"grad_norm": 0.5771033763885498,
|
| 1021 |
+
"learning_rate": 3.7509190017940066e-05,
|
| 1022 |
+
"loss": 2.0034,
|
| 1023 |
+
"step": 138
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 1.8118126272912423,
|
| 1027 |
+
"grad_norm": 0.566257655620575,
|
| 1028 |
+
"learning_rate": 3.660737030015427e-05,
|
| 1029 |
+
"loss": 1.5604,
|
| 1030 |
+
"step": 139
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"epoch": 1.824847250509165,
|
| 1034 |
+
"grad_norm": 0.44189655780792236,
|
| 1035 |
+
"learning_rate": 3.576186783317092e-05,
|
| 1036 |
+
"loss": 2.4998,
|
| 1037 |
+
"step": 140
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 1.8378818737270874,
|
| 1041 |
+
"grad_norm": 0.3839716911315918,
|
| 1042 |
+
"learning_rate": 3.4973053482316156e-05,
|
| 1043 |
+
"loss": 1.9946,
|
| 1044 |
+
"step": 141
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 1.8509164969450103,
|
| 1048 |
+
"grad_norm": 0.3798718750476837,
|
| 1049 |
+
"learning_rate": 3.4241273247634805e-05,
|
| 1050 |
+
"loss": 1.9378,
|
| 1051 |
+
"step": 142
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"epoch": 1.8639511201629326,
|
| 1055 |
+
"grad_norm": 0.33077380061149597,
|
| 1056 |
+
"learning_rate": 3.356684811212336e-05,
|
| 1057 |
+
"loss": 1.9503,
|
| 1058 |
+
"step": 143
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 1.8769857433808554,
|
| 1062 |
+
"grad_norm": 0.3309776186943054,
|
| 1063 |
+
"learning_rate": 3.2950073900936234e-05,
|
| 1064 |
+
"loss": 1.9187,
|
| 1065 |
+
"step": 144
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 1.890020366598778,
|
| 1069 |
+
"grad_norm": 0.2614622116088867,
|
| 1070 |
+
"learning_rate": 3.2391221151627036e-05,
|
| 1071 |
+
"loss": 1.9367,
|
| 1072 |
+
"step": 145
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 1.9030549898167006,
|
| 1076 |
+
"grad_norm": 0.27304932475090027,
|
| 1077 |
+
"learning_rate": 3.1890534995481836e-05,
|
| 1078 |
+
"loss": 1.9302,
|
| 1079 |
+
"step": 146
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 1.9160896130346232,
|
| 1083 |
+
"grad_norm": 0.26790907979011536,
|
| 1084 |
+
"learning_rate": 3.144823504999658e-05,
|
| 1085 |
+
"loss": 1.9228,
|
| 1086 |
+
"step": 147
|
| 1087 |
+
},
|
| 1088 |
+
{
|
| 1089 |
+
"epoch": 1.9291242362525458,
|
| 1090 |
+
"grad_norm": 0.3259439468383789,
|
| 1091 |
+
"learning_rate": 3.10645153225455e-05,
|
| 1092 |
+
"loss": 1.9133,
|
| 1093 |
+
"step": 148
|
| 1094 |
+
},
|
| 1095 |
+
{
|
| 1096 |
+
"epoch": 1.9421588594704684,
|
| 1097 |
+
"grad_norm": 0.40042850375175476,
|
| 1098 |
+
"learning_rate": 3.0739544125283105e-05,
|
| 1099 |
+
"loss": 1.9946,
|
| 1100 |
+
"step": 149
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 1.955193482688391,
|
| 1104 |
+
"grad_norm": 0.49017587304115295,
|
| 1105 |
+
"learning_rate": 3.047346400131691e-05,
|
| 1106 |
+
"loss": 1.9776,
|
| 1107 |
+
"step": 150
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 1.955193482688391,
|
| 1111 |
+
"eval_loss": 1.9268525838851929,
|
| 1112 |
+
"eval_runtime": 0.2825,
|
| 1113 |
+
"eval_samples_per_second": 176.994,
|
| 1114 |
+
"eval_steps_per_second": 46.019,
|
| 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
|