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 1521616
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e177a55a4f8968030141b68018bb00b657e902abe021c6295443a76822d37319
|
| 3 |
size 1521616
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3108666
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a9d55e8407570a07e057e59aa40756a92f640ad3c3b2cadc7b3ccb8aebdf144a
|
| 3 |
size 3108666
|
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 sha256:1f122f27ff41d75d8242038bdb7dcc56b03a3ee0fef27e0813a0e5bd33facded
|
| 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 sha256:1a7ca8e55af6b4feda97946cf69d286f368ca3c1d50f3951c0dcbfa4faae95ae
|
| 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 sha256:8207164e65c023390018e471df1c8a2d6b63497b02538e7c9479a46941ee2ec7
|
| 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:faf9d6db6d338497d7f96bb6781178aab234997fa413b22da388194e8a349725
|
| 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 sha256:028a9b4a00b26e663bf1479c01a19ca4776fdbabc2a9b3b6ed73cd614df36408
|
| 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":
|
| 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": 258.808,
|
| 748 |
"eval_steps_per_second": 67.29,
|
| 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": 1.972500205039978,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-150",
|
| 4 |
+
"epoch": 2.771667146559171,
|
| 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": 258.808,
|
| 748 |
"eval_steps_per_second": 67.29,
|
| 749 |
"step": 100
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 1.8649582493521453,
|
| 753 |
+
"grad_norm": 0.6175363659858704,
|
| 754 |
+
"learning_rate": 6.377906449072578e-05,
|
| 755 |
+
"loss": 1.937,
|
| 756 |
+
"step": 101
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 1.883386121508782,
|
| 760 |
+
"grad_norm": 0.5189071297645569,
|
| 761 |
+
"learning_rate": 6.311147670162576e-05,
|
| 762 |
+
"loss": 2.0043,
|
| 763 |
+
"step": 102
|
| 764 |
+
},
|
| 765 |
+
{
|
| 766 |
+
"epoch": 1.901813993665419,
|
| 767 |
+
"grad_norm": 0.7783696055412292,
|
| 768 |
+
"learning_rate": 6.244203851625526e-05,
|
| 769 |
+
"loss": 1.9778,
|
| 770 |
+
"step": 103
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 1.9202418658220557,
|
| 774 |
+
"grad_norm": 1.224826693534851,
|
| 775 |
+
"learning_rate": 6.177090264736525e-05,
|
| 776 |
+
"loss": 2.0057,
|
| 777 |
+
"step": 104
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 1.9386697379786928,
|
| 781 |
+
"grad_norm": 2.2593610286712646,
|
| 782 |
+
"learning_rate": 6.109822219498354e-05,
|
| 783 |
+
"loss": 1.9667,
|
| 784 |
+
"step": 105
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 1.9570976101353297,
|
| 788 |
+
"grad_norm": 1.2801239490509033,
|
| 789 |
+
"learning_rate": 6.042415061148954e-05,
|
| 790 |
+
"loss": 1.9922,
|
| 791 |
+
"step": 106
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 1.9755254822919666,
|
| 795 |
+
"grad_norm": 0.8543593883514404,
|
| 796 |
+
"learning_rate": 5.9748841666608565e-05,
|
| 797 |
+
"loss": 1.9925,
|
| 798 |
+
"step": 107
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 1.9939533544486037,
|
| 802 |
+
"grad_norm": 0.5854929685592651,
|
| 803 |
+
"learning_rate": 5.907244941233371e-05,
|
| 804 |
+
"loss": 1.9671,
|
| 805 |
+
"step": 108
|
| 806 |
+
},
|
| 807 |
+
{
|
| 808 |
+
"epoch": 2.016124388137057,
|
| 809 |
+
"grad_norm": 2.585685968399048,
|
| 810 |
+
"learning_rate": 5.8395128147783474e-05,
|
| 811 |
+
"loss": 4.0407,
|
| 812 |
+
"step": 109
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 2.0345522602936943,
|
| 816 |
+
"grad_norm": 1.6653348207473755,
|
| 817 |
+
"learning_rate": 5.771703238400288e-05,
|
| 818 |
+
"loss": 2.0671,
|
| 819 |
+
"step": 110
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 2.052980132450331,
|
| 823 |
+
"grad_norm": 0.6874579191207886,
|
| 824 |
+
"learning_rate": 5.703831680871631e-05,
|
| 825 |
+
"loss": 1.9964,
|
| 826 |
+
"step": 111
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 2.071408004606968,
|
| 830 |
+
"grad_norm": 0.906933605670929,
|
| 831 |
+
"learning_rate": 5.635913625104e-05,
|
| 832 |
+
"loss": 1.9681,
|
| 833 |
+
"step": 112
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 2.089835876763605,
|
| 837 |
+
"grad_norm": 0.7688360214233398,
|
| 838 |
+
"learning_rate": 5.567964564616237e-05,
|
| 839 |
+
"loss": 2.0265,
|
| 840 |
+
"step": 113
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 2.108263748920242,
|
| 844 |
+
"grad_norm": 1.0667365789413452,
|
| 845 |
+
"learning_rate": 5.500000000000001e-05,
|
| 846 |
+
"loss": 1.9802,
|
| 847 |
+
"step": 114
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 2.126691621076879,
|
| 851 |
+
"grad_norm": 1.1549663543701172,
|
| 852 |
+
"learning_rate": 5.432035435383764e-05,
|
| 853 |
+
"loss": 2.0294,
|
| 854 |
+
"step": 115
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 2.1451194932335156,
|
| 858 |
+
"grad_norm": 0.9386123418807983,
|
| 859 |
+
"learning_rate": 5.364086374896001e-05,
|
| 860 |
+
"loss": 1.9267,
|
| 861 |
+
"step": 116
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 2.1635473653901527,
|
| 865 |
+
"grad_norm": 0.7642337679862976,
|
| 866 |
+
"learning_rate": 5.296168319128372e-05,
|
| 867 |
+
"loss": 1.9907,
|
| 868 |
+
"step": 117
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 2.1819752375467893,
|
| 872 |
+
"grad_norm": 0.5543763041496277,
|
| 873 |
+
"learning_rate": 5.2282967615997125e-05,
|
| 874 |
+
"loss": 1.9707,
|
| 875 |
+
"step": 118
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 2.2004031097034265,
|
| 879 |
+
"grad_norm": 0.7983617186546326,
|
| 880 |
+
"learning_rate": 5.160487185221653e-05,
|
| 881 |
+
"loss": 1.9696,
|
| 882 |
+
"step": 119
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 2.218830981860063,
|
| 886 |
+
"grad_norm": 0.3363061845302582,
|
| 887 |
+
"learning_rate": 5.092755058766631e-05,
|
| 888 |
+
"loss": 1.9536,
|
| 889 |
+
"step": 120
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 2.2372588540167,
|
| 893 |
+
"grad_norm": 0.9921276569366455,
|
| 894 |
+
"learning_rate": 5.025115833339146e-05,
|
| 895 |
+
"loss": 2.0054,
|
| 896 |
+
"step": 121
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 2.2556867261733373,
|
| 900 |
+
"grad_norm": 1.2545318603515625,
|
| 901 |
+
"learning_rate": 4.9575849388510473e-05,
|
| 902 |
+
"loss": 1.9755,
|
| 903 |
+
"step": 122
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 2.274114598329974,
|
| 907 |
+
"grad_norm": 1.0431549549102783,
|
| 908 |
+
"learning_rate": 4.890177780501648e-05,
|
| 909 |
+
"loss": 2.047,
|
| 910 |
+
"step": 123
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 2.292542470486611,
|
| 914 |
+
"grad_norm": 0.9374226331710815,
|
| 915 |
+
"learning_rate": 4.8229097352634765e-05,
|
| 916 |
+
"loss": 1.9859,
|
| 917 |
+
"step": 124
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 2.3109703426432477,
|
| 921 |
+
"grad_norm": 1.3169200420379639,
|
| 922 |
+
"learning_rate": 4.755796148374475e-05,
|
| 923 |
+
"loss": 1.957,
|
| 924 |
+
"step": 125
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 2.3109703426432477,
|
| 928 |
+
"eval_loss": 1.9774408340454102,
|
| 929 |
+
"eval_runtime": 0.1937,
|
| 930 |
+
"eval_samples_per_second": 258.081,
|
| 931 |
+
"eval_steps_per_second": 67.101,
|
| 932 |
+
"step": 125
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 2.329398214799885,
|
| 936 |
+
"grad_norm": 0.6126213669776917,
|
| 937 |
+
"learning_rate": 4.688852329837424e-05,
|
| 938 |
+
"loss": 1.9839,
|
| 939 |
+
"step": 126
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 2.3478260869565215,
|
| 943 |
+
"grad_norm": 1.152384638786316,
|
| 944 |
+
"learning_rate": 4.6220935509274235e-05,
|
| 945 |
+
"loss": 1.9543,
|
| 946 |
+
"step": 127
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 2.3662539591131586,
|
| 950 |
+
"grad_norm": 0.6893303394317627,
|
| 951 |
+
"learning_rate": 4.5555350407081863e-05,
|
| 952 |
+
"loss": 1.9423,
|
| 953 |
+
"step": 128
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 2.3846818312697957,
|
| 957 |
+
"grad_norm": 0.8432124853134155,
|
| 958 |
+
"learning_rate": 4.489191982557984e-05,
|
| 959 |
+
"loss": 2.0398,
|
| 960 |
+
"step": 129
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 2.4031097034264324,
|
| 964 |
+
"grad_norm": 0.5620063543319702,
|
| 965 |
+
"learning_rate": 4.423079510705992e-05,
|
| 966 |
+
"loss": 1.9957,
|
| 967 |
+
"step": 130
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 2.4215375755830695,
|
| 971 |
+
"grad_norm": 1.0304889678955078,
|
| 972 |
+
"learning_rate": 4.357212706779864e-05,
|
| 973 |
+
"loss": 2.0187,
|
| 974 |
+
"step": 131
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 2.439965447739706,
|
| 978 |
+
"grad_norm": 0.32691672444343567,
|
| 979 |
+
"learning_rate": 4.291606596365304e-05,
|
| 980 |
+
"loss": 1.952,
|
| 981 |
+
"step": 132
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 2.4583933198963432,
|
| 985 |
+
"grad_norm": 0.4635773301124573,
|
| 986 |
+
"learning_rate": 4.226276145578408e-05,
|
| 987 |
+
"loss": 1.9837,
|
| 988 |
+
"step": 133
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 2.47682119205298,
|
| 992 |
+
"grad_norm": 1.219428300857544,
|
| 993 |
+
"learning_rate": 4.161236257651587e-05,
|
| 994 |
+
"loss": 1.9887,
|
| 995 |
+
"step": 134
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 2.495249064209617,
|
| 999 |
+
"grad_norm": 0.8382700681686401,
|
| 1000 |
+
"learning_rate": 4.09650176953383e-05,
|
| 1001 |
+
"loss": 1.9683,
|
| 1002 |
+
"step": 135
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 2.513676936366254,
|
| 1006 |
+
"grad_norm": 0.7893387675285339,
|
| 1007 |
+
"learning_rate": 4.032087448506089e-05,
|
| 1008 |
+
"loss": 1.9834,
|
| 1009 |
+
"step": 136
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 2.5321048085228908,
|
| 1013 |
+
"grad_norm": 0.38780632615089417,
|
| 1014 |
+
"learning_rate": 3.968007988812552e-05,
|
| 1015 |
+
"loss": 1.9808,
|
| 1016 |
+
"step": 137
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 2.550532680679528,
|
| 1020 |
+
"grad_norm": 0.579411506652832,
|
| 1021 |
+
"learning_rate": 3.904278008308589e-05,
|
| 1022 |
+
"loss": 1.9948,
|
| 1023 |
+
"step": 138
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 2.5689605528361645,
|
| 1027 |
+
"grad_norm": 0.5201661586761475,
|
| 1028 |
+
"learning_rate": 3.840912045126106e-05,
|
| 1029 |
+
"loss": 2.0085,
|
| 1030 |
+
"step": 139
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"epoch": 2.5873884249928016,
|
| 1034 |
+
"grad_norm": 0.2307479977607727,
|
| 1035 |
+
"learning_rate": 3.777924554357096e-05,
|
| 1036 |
+
"loss": 1.9852,
|
| 1037 |
+
"step": 140
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 2.6058162971494383,
|
| 1041 |
+
"grad_norm": 0.4744541645050049,
|
| 1042 |
+
"learning_rate": 3.715329904756143e-05,
|
| 1043 |
+
"loss": 1.9508,
|
| 1044 |
+
"step": 141
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 2.6242441693060754,
|
| 1048 |
+
"grad_norm": 0.33469077944755554,
|
| 1049 |
+
"learning_rate": 3.653142375462596e-05,
|
| 1050 |
+
"loss": 1.9608,
|
| 1051 |
+
"step": 142
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"epoch": 2.6426720414627125,
|
| 1055 |
+
"grad_norm": 0.2714967429637909,
|
| 1056 |
+
"learning_rate": 3.591376152743211e-05,
|
| 1057 |
+
"loss": 1.9771,
|
| 1058 |
+
"step": 143
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 2.661099913619349,
|
| 1062 |
+
"grad_norm": 0.6618818044662476,
|
| 1063 |
+
"learning_rate": 3.530045326755967e-05,
|
| 1064 |
+
"loss": 1.9385,
|
| 1065 |
+
"step": 144
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 2.6795277857759863,
|
| 1069 |
+
"grad_norm": 0.7056910991668701,
|
| 1070 |
+
"learning_rate": 3.46916388833581e-05,
|
| 1071 |
+
"loss": 1.9505,
|
| 1072 |
+
"step": 145
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 2.697955657932623,
|
| 1076 |
+
"grad_norm": 0.5343828201293945,
|
| 1077 |
+
"learning_rate": 3.408745725803042e-05,
|
| 1078 |
+
"loss": 2.0025,
|
| 1079 |
+
"step": 146
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 2.71638353008926,
|
| 1083 |
+
"grad_norm": 1.5520598888397217,
|
| 1084 |
+
"learning_rate": 3.348804621795122e-05,
|
| 1085 |
+
"loss": 1.9265,
|
| 1086 |
+
"step": 147
|
| 1087 |
+
},
|
| 1088 |
+
{
|
| 1089 |
+
"epoch": 2.7348114022458967,
|
| 1090 |
+
"grad_norm": 0.4644526243209839,
|
| 1091 |
+
"learning_rate": 3.2893542501225534e-05,
|
| 1092 |
+
"loss": 2.0005,
|
| 1093 |
+
"step": 148
|
| 1094 |
+
},
|
| 1095 |
+
{
|
| 1096 |
+
"epoch": 2.753239274402534,
|
| 1097 |
+
"grad_norm": 0.3085757791996002,
|
| 1098 |
+
"learning_rate": 3.2304081726495974e-05,
|
| 1099 |
+
"loss": 1.9679,
|
| 1100 |
+
"step": 149
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 2.771667146559171,
|
| 1104 |
+
"grad_norm": 1.0300484895706177,
|
| 1105 |
+
"learning_rate": 3.1719798362005444e-05,
|
| 1106 |
+
"loss": 1.9888,
|
| 1107 |
+
"step": 150
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 2.771667146559171,
|
| 1111 |
+
"eval_loss": 1.972500205039978,
|
| 1112 |
+
"eval_runtime": 0.1941,
|
| 1113 |
+
"eval_samples_per_second": 257.57,
|
| 1114 |
+
"eval_steps_per_second": 66.968,
|
| 1115 |
+
"step": 150
|
| 1116 |
}
|
| 1117 |
],
|
| 1118 |
"logging_steps": 1,
|
|
|
|
| 1141 |
"attributes": {}
|
| 1142 |
}
|
| 1143 |
},
|
| 1144 |
+
"total_flos": 1392626572984320.0,
|
| 1145 |
"train_batch_size": 1,
|
| 1146 |
"trial_name": null,
|
| 1147 |
"trial_params": null
|