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/rng_state_4.pth +1 -1
- last-checkpoint/rng_state_5.pth +1 -1
- last-checkpoint/rng_state_6.pth +1 -1
- last-checkpoint/rng_state_7.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +362 -4
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 34456
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6e4838fa2c8bb43fc8201d1fb5d3b79356e330dd7d016f30e17495277bee58f9
|
| 3 |
size 34456
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 73222
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a5262e88bd3557a17fa6687be71d9898baee97572a4e4f2054ac7eb2862f226a
|
| 3 |
size 73222
|
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 15984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4739ef310ab20c951c534d2705b5492dee6f6f2c4201d2f19772a6795c9bc0f0
|
| 3 |
size 15984
|
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 15984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:515b01c20d47c4235a61caa45929f2334dd50e09d667c62b3ea73c75730c43ef
|
| 3 |
size 15984
|
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 15984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b4adef96e5ec76c71f47f268873caeee77e3216feab5eca738bb9805d374d739
|
| 3 |
size 15984
|
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 15984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3155846846fa58c87f68d96256f4bc61df6abba308f69477b804614075f5e495
|
| 3 |
size 15984
|
last-checkpoint/rng_state_4.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:28c057076cf2084724735dc32f41dfda26c172f674f9dccde9ac983266354d03
|
| 3 |
size 15984
|
last-checkpoint/rng_state_5.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4a009d96aafa20eefe57b2fe7a1860ec304b152a12480df82f2454c641964e95
|
| 3 |
size 15984
|
last-checkpoint/rng_state_6.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5e32fe7dfd7bc3da0fb5496daadb63ed69841ce068b5ed17509d922bf461bb74
|
| 3 |
size 15984
|
last-checkpoint/rng_state_7.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0a8628e0674db96292ef8de772b7c476428c09427022ddce2a3875d28de96525
|
| 3 |
size 15984
|
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:e618c561766e531a3b508498a52b6a60ed26e61c8d989456e9bc321d17c91c51
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 11.5,
|
| 3 |
"best_model_checkpoint": "miner_id_24/checkpoint-50",
|
| 4 |
-
"epoch":
|
| 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": 1485.776,
|
| 732 |
"eval_steps_per_second": 47.51,
|
| 733 |
"step": 100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 734 |
}
|
| 735 |
],
|
| 736 |
"logging_steps": 1,
|
|
@@ -745,7 +1103,7 @@
|
|
| 745 |
"early_stopping_threshold": 0.0
|
| 746 |
},
|
| 747 |
"attributes": {
|
| 748 |
-
"early_stopping_patience_counter":
|
| 749 |
}
|
| 750 |
},
|
| 751 |
"TrainerControl": {
|
|
@@ -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": 11.5,
|
| 3 |
"best_model_checkpoint": "miner_id_24/checkpoint-50",
|
| 4 |
+
"epoch": 2.9411764705882355,
|
| 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": 1485.776,
|
| 732 |
"eval_steps_per_second": 47.51,
|
| 733 |
"step": 100
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 1.9803921568627452,
|
| 737 |
+
"grad_norm": 0.0004091408336535096,
|
| 738 |
+
"learning_rate": 3.672727272727273e-05,
|
| 739 |
+
"loss": 46.0,
|
| 740 |
+
"step": 101
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 2.0,
|
| 744 |
+
"grad_norm": 0.00023171439534053206,
|
| 745 |
+
"learning_rate": 3.602097902097902e-05,
|
| 746 |
+
"loss": 46.0,
|
| 747 |
+
"step": 102
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 2.019607843137255,
|
| 751 |
+
"grad_norm": 0.00039071572246029973,
|
| 752 |
+
"learning_rate": 3.531468531468531e-05,
|
| 753 |
+
"loss": 46.0,
|
| 754 |
+
"step": 103
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 2.0392156862745097,
|
| 758 |
+
"grad_norm": 0.00026147387688979506,
|
| 759 |
+
"learning_rate": 3.460839160839161e-05,
|
| 760 |
+
"loss": 46.0,
|
| 761 |
+
"step": 104
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 2.0588235294117645,
|
| 765 |
+
"grad_norm": 0.0003073408151976764,
|
| 766 |
+
"learning_rate": 3.39020979020979e-05,
|
| 767 |
+
"loss": 46.0,
|
| 768 |
+
"step": 105
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 2.0784313725490198,
|
| 772 |
+
"grad_norm": 0.00033114402322098613,
|
| 773 |
+
"learning_rate": 3.319580419580419e-05,
|
| 774 |
+
"loss": 46.0,
|
| 775 |
+
"step": 106
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 2.0980392156862746,
|
| 779 |
+
"grad_norm": 0.00034095364389941096,
|
| 780 |
+
"learning_rate": 3.2489510489510486e-05,
|
| 781 |
+
"loss": 46.0,
|
| 782 |
+
"step": 107
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 2.1176470588235294,
|
| 786 |
+
"grad_norm": 0.0003768288588616997,
|
| 787 |
+
"learning_rate": 3.178321678321678e-05,
|
| 788 |
+
"loss": 46.0,
|
| 789 |
+
"step": 108
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 2.1372549019607843,
|
| 793 |
+
"grad_norm": 0.00041196009260602295,
|
| 794 |
+
"learning_rate": 3.107692307692308e-05,
|
| 795 |
+
"loss": 46.0,
|
| 796 |
+
"step": 109
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 2.156862745098039,
|
| 800 |
+
"grad_norm": 0.0002800294605549425,
|
| 801 |
+
"learning_rate": 3.037062937062937e-05,
|
| 802 |
+
"loss": 46.0,
|
| 803 |
+
"step": 110
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 2.176470588235294,
|
| 807 |
+
"grad_norm": 0.000317448255373165,
|
| 808 |
+
"learning_rate": 2.9664335664335664e-05,
|
| 809 |
+
"loss": 46.0,
|
| 810 |
+
"step": 111
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 2.196078431372549,
|
| 814 |
+
"grad_norm": 0.0003218978818040341,
|
| 815 |
+
"learning_rate": 2.895804195804196e-05,
|
| 816 |
+
"loss": 46.0,
|
| 817 |
+
"step": 112
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 2.215686274509804,
|
| 821 |
+
"grad_norm": 0.00034446208155713975,
|
| 822 |
+
"learning_rate": 2.8251748251748255e-05,
|
| 823 |
+
"loss": 46.0,
|
| 824 |
+
"step": 113
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 2.235294117647059,
|
| 828 |
+
"grad_norm": 0.0004481629002839327,
|
| 829 |
+
"learning_rate": 2.7545454545454544e-05,
|
| 830 |
+
"loss": 46.0,
|
| 831 |
+
"step": 114
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 2.2549019607843137,
|
| 835 |
+
"grad_norm": 0.000561642344109714,
|
| 836 |
+
"learning_rate": 2.683916083916084e-05,
|
| 837 |
+
"loss": 46.0,
|
| 838 |
+
"step": 115
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 2.2745098039215685,
|
| 842 |
+
"grad_norm": 0.0004017452010884881,
|
| 843 |
+
"learning_rate": 2.6132867132867135e-05,
|
| 844 |
+
"loss": 46.0,
|
| 845 |
+
"step": 116
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 2.2941176470588234,
|
| 849 |
+
"grad_norm": 0.0003688019060064107,
|
| 850 |
+
"learning_rate": 2.542657342657343e-05,
|
| 851 |
+
"loss": 46.0,
|
| 852 |
+
"step": 117
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 2.313725490196078,
|
| 856 |
+
"grad_norm": 0.0004349400696810335,
|
| 857 |
+
"learning_rate": 2.4720279720279722e-05,
|
| 858 |
+
"loss": 46.0,
|
| 859 |
+
"step": 118
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 2.3333333333333335,
|
| 863 |
+
"grad_norm": 0.00039143659523688257,
|
| 864 |
+
"learning_rate": 2.4013986013986014e-05,
|
| 865 |
+
"loss": 46.0,
|
| 866 |
+
"step": 119
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 2.3529411764705883,
|
| 870 |
+
"grad_norm": 0.0004510066064540297,
|
| 871 |
+
"learning_rate": 2.330769230769231e-05,
|
| 872 |
+
"loss": 46.0,
|
| 873 |
+
"step": 120
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 2.372549019607843,
|
| 877 |
+
"grad_norm": 0.0004265211464371532,
|
| 878 |
+
"learning_rate": 2.26013986013986e-05,
|
| 879 |
+
"loss": 46.0,
|
| 880 |
+
"step": 121
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 2.392156862745098,
|
| 884 |
+
"grad_norm": 0.00033641376649029553,
|
| 885 |
+
"learning_rate": 2.1895104895104893e-05,
|
| 886 |
+
"loss": 46.0,
|
| 887 |
+
"step": 122
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 2.411764705882353,
|
| 891 |
+
"grad_norm": 0.00030129088554531336,
|
| 892 |
+
"learning_rate": 2.118881118881119e-05,
|
| 893 |
+
"loss": 46.0,
|
| 894 |
+
"step": 123
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 2.431372549019608,
|
| 898 |
+
"grad_norm": 0.0003684493131004274,
|
| 899 |
+
"learning_rate": 2.048251748251748e-05,
|
| 900 |
+
"loss": 46.0,
|
| 901 |
+
"step": 124
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 2.450980392156863,
|
| 905 |
+
"grad_norm": 0.00033330111182294786,
|
| 906 |
+
"learning_rate": 1.9776223776223776e-05,
|
| 907 |
+
"loss": 46.0,
|
| 908 |
+
"step": 125
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 2.4705882352941178,
|
| 912 |
+
"grad_norm": 0.0004395820142235607,
|
| 913 |
+
"learning_rate": 1.9069930069930068e-05,
|
| 914 |
+
"loss": 46.0,
|
| 915 |
+
"step": 126
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 2.4901960784313726,
|
| 919 |
+
"grad_norm": 0.00040403471211902797,
|
| 920 |
+
"learning_rate": 1.8363636363636364e-05,
|
| 921 |
+
"loss": 46.0,
|
| 922 |
+
"step": 127
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 2.5098039215686274,
|
| 926 |
+
"grad_norm": 0.00036949978675693274,
|
| 927 |
+
"learning_rate": 1.7657342657342656e-05,
|
| 928 |
+
"loss": 46.0,
|
| 929 |
+
"step": 128
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 2.5294117647058822,
|
| 933 |
+
"grad_norm": 0.0002842578978743404,
|
| 934 |
+
"learning_rate": 1.695104895104895e-05,
|
| 935 |
+
"loss": 46.0,
|
| 936 |
+
"step": 129
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 2.549019607843137,
|
| 940 |
+
"grad_norm": 0.00042267926619388163,
|
| 941 |
+
"learning_rate": 1.6244755244755243e-05,
|
| 942 |
+
"loss": 46.0,
|
| 943 |
+
"step": 130
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 2.568627450980392,
|
| 947 |
+
"grad_norm": 0.0003992296988144517,
|
| 948 |
+
"learning_rate": 1.553846153846154e-05,
|
| 949 |
+
"loss": 46.0,
|
| 950 |
+
"step": 131
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 2.588235294117647,
|
| 954 |
+
"grad_norm": 0.0004117234202567488,
|
| 955 |
+
"learning_rate": 1.4832167832167832e-05,
|
| 956 |
+
"loss": 46.0,
|
| 957 |
+
"step": 132
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 2.607843137254902,
|
| 961 |
+
"grad_norm": 0.00047374825226143,
|
| 962 |
+
"learning_rate": 1.4125874125874128e-05,
|
| 963 |
+
"loss": 46.0,
|
| 964 |
+
"step": 133
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 2.627450980392157,
|
| 968 |
+
"grad_norm": 0.0004487686383072287,
|
| 969 |
+
"learning_rate": 1.341958041958042e-05,
|
| 970 |
+
"loss": 46.0,
|
| 971 |
+
"step": 134
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 2.6470588235294117,
|
| 975 |
+
"grad_norm": 0.000370257708709687,
|
| 976 |
+
"learning_rate": 1.2713286713286715e-05,
|
| 977 |
+
"loss": 46.0,
|
| 978 |
+
"step": 135
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 2.6666666666666665,
|
| 982 |
+
"grad_norm": 0.00045377013157121837,
|
| 983 |
+
"learning_rate": 1.2006993006993007e-05,
|
| 984 |
+
"loss": 46.0,
|
| 985 |
+
"step": 136
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 2.686274509803922,
|
| 989 |
+
"grad_norm": 0.00031919433968141675,
|
| 990 |
+
"learning_rate": 1.13006993006993e-05,
|
| 991 |
+
"loss": 46.0,
|
| 992 |
+
"step": 137
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 2.7058823529411766,
|
| 996 |
+
"grad_norm": 0.0004188633756712079,
|
| 997 |
+
"learning_rate": 1.0594405594405594e-05,
|
| 998 |
+
"loss": 46.0,
|
| 999 |
+
"step": 138
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 2.7254901960784315,
|
| 1003 |
+
"grad_norm": 0.0004712211084552109,
|
| 1004 |
+
"learning_rate": 9.888111888111888e-06,
|
| 1005 |
+
"loss": 46.0,
|
| 1006 |
+
"step": 139
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 2.7450980392156863,
|
| 1010 |
+
"grad_norm": 0.00039058204856701195,
|
| 1011 |
+
"learning_rate": 9.181818181818182e-06,
|
| 1012 |
+
"loss": 46.0,
|
| 1013 |
+
"step": 140
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 2.764705882352941,
|
| 1017 |
+
"grad_norm": 0.0003306346479803324,
|
| 1018 |
+
"learning_rate": 8.475524475524476e-06,
|
| 1019 |
+
"loss": 46.0,
|
| 1020 |
+
"step": 141
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 2.784313725490196,
|
| 1024 |
+
"grad_norm": 0.000356231932528317,
|
| 1025 |
+
"learning_rate": 7.76923076923077e-06,
|
| 1026 |
+
"loss": 46.0,
|
| 1027 |
+
"step": 142
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 2.803921568627451,
|
| 1031 |
+
"grad_norm": 0.0004590142925735563,
|
| 1032 |
+
"learning_rate": 7.062937062937064e-06,
|
| 1033 |
+
"loss": 46.0,
|
| 1034 |
+
"step": 143
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 2.8235294117647056,
|
| 1038 |
+
"grad_norm": 0.0003684695693664253,
|
| 1039 |
+
"learning_rate": 6.3566433566433575e-06,
|
| 1040 |
+
"loss": 46.0,
|
| 1041 |
+
"step": 144
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 2.843137254901961,
|
| 1045 |
+
"grad_norm": 0.0005272235721349716,
|
| 1046 |
+
"learning_rate": 5.65034965034965e-06,
|
| 1047 |
+
"loss": 46.0,
|
| 1048 |
+
"step": 145
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 2.8627450980392157,
|
| 1052 |
+
"grad_norm": 0.0006201413343660533,
|
| 1053 |
+
"learning_rate": 4.944055944055944e-06,
|
| 1054 |
+
"loss": 46.0,
|
| 1055 |
+
"step": 146
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 2.8823529411764706,
|
| 1059 |
+
"grad_norm": 0.0004487824044190347,
|
| 1060 |
+
"learning_rate": 4.237762237762238e-06,
|
| 1061 |
+
"loss": 46.0,
|
| 1062 |
+
"step": 147
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 2.9019607843137254,
|
| 1066 |
+
"grad_norm": 0.00032599197584204376,
|
| 1067 |
+
"learning_rate": 3.531468531468532e-06,
|
| 1068 |
+
"loss": 46.0,
|
| 1069 |
+
"step": 148
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 2.9215686274509802,
|
| 1073 |
+
"grad_norm": 0.00035970291355624795,
|
| 1074 |
+
"learning_rate": 2.825174825174825e-06,
|
| 1075 |
+
"loss": 46.0,
|
| 1076 |
+
"step": 149
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 2.9411764705882355,
|
| 1080 |
+
"grad_norm": 0.0003452469245530665,
|
| 1081 |
+
"learning_rate": 2.118881118881119e-06,
|
| 1082 |
+
"loss": 46.0,
|
| 1083 |
+
"step": 150
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 2.9411764705882355,
|
| 1087 |
+
"eval_loss": 11.5,
|
| 1088 |
+
"eval_runtime": 1.0845,
|
| 1089 |
+
"eval_samples_per_second": 634.42,
|
| 1090 |
+
"eval_steps_per_second": 20.287,
|
| 1091 |
+
"step": 150
|
| 1092 |
}
|
| 1093 |
],
|
| 1094 |
"logging_steps": 1,
|
|
|
|
| 1103 |
"early_stopping_threshold": 0.0
|
| 1104 |
},
|
| 1105 |
"attributes": {
|
| 1106 |
+
"early_stopping_patience_counter": 2
|
| 1107 |
}
|
| 1108 |
},
|
| 1109 |
"TrainerControl": {
|
|
|
|
| 1117 |
"attributes": {}
|
| 1118 |
}
|
| 1119 |
},
|
| 1120 |
+
"total_flos": 192950776627200.0,
|
| 1121 |
"train_batch_size": 8,
|
| 1122 |
"trial_name": null,
|
| 1123 |
"trial_params": null
|