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 +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 671149168
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ab56ab7bf4c57a0bb2cc6d6fc81e2ec41344b07f586367a2a945b1bcbeccc971
|
| 3 |
size 671149168
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 341314196
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5dab03a4270595da41cfa4ee22106ecafaf3c759c7dc0ae083b8984c7bc2ede5
|
| 3 |
size 341314196
|
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 sha256:8c76f2525aecfc5057df0bee296c4c17eb80316d619861cfe0c51228d0399ce8
|
| 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 sha256:32fbb9c2b9e148b5f8748e017207e072f9f9a8e5804209ca6645860ea72ee323
|
| 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:a8db7a3503e99295e357a346852133da938b00a4fe8609759d3cf2ec580c3c94
|
| 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 sha256:8106f601df023ef3e4f7b8f6524588a1e507baf19fc4a5e540454ad0acffaf3f
|
| 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:e3d761ec7c2cf2c44083eb8174792393d1d02d8a8540f88a790358d854270f97
|
| 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:bfe284a0b9804c3d4d28855b006fe8548ff9da14080d7d68cb32f4c5bd07a3f0
|
| 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 sha256:9ba3565e65936289111c34a848cbe5078cc4544abb7777b9bb5fc5f4e7c8cd9a
|
| 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 sha256:85b87e1cf92ea10b985e4dedb5d26fdf70606e42545144201cb0401e397f72a5
|
| 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 sha256:7d606eeb1aa97b417de3c30d0a970be83ac979e2c7cc0fa41135c63d459909e5
|
| 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": 144.37,
|
| 732 |
"eval_steps_per_second": 4.517,
|
| 733 |
"step": 100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 734 |
}
|
| 735 |
],
|
| 736 |
"logging_steps": 1,
|
|
@@ -759,7 +1117,7 @@
|
|
| 759 |
"attributes": {}
|
| 760 |
}
|
| 761 |
},
|
| 762 |
-
"total_flos": 1.
|
| 763 |
"train_batch_size": 8,
|
| 764 |
"trial_name": null,
|
| 765 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.5903738141059875,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-150",
|
| 4 |
+
"epoch": 0.21216407355021216,
|
| 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": 144.37,
|
| 732 |
"eval_steps_per_second": 4.517,
|
| 733 |
"step": 100
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 0.14285714285714285,
|
| 737 |
+
"grad_norm": 1.9267340898513794,
|
| 738 |
+
"learning_rate": 5.262631578947368e-05,
|
| 739 |
+
"loss": 2.6755,
|
| 740 |
+
"step": 101
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 0.14427157001414428,
|
| 744 |
+
"grad_norm": 1.8436909914016724,
|
| 745 |
+
"learning_rate": 5.209473684210527e-05,
|
| 746 |
+
"loss": 2.5422,
|
| 747 |
+
"step": 102
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.1456859971711457,
|
| 751 |
+
"grad_norm": 1.7414659261703491,
|
| 752 |
+
"learning_rate": 5.1563157894736844e-05,
|
| 753 |
+
"loss": 2.4531,
|
| 754 |
+
"step": 103
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 0.1471004243281471,
|
| 758 |
+
"grad_norm": 1.595393180847168,
|
| 759 |
+
"learning_rate": 5.1031578947368426e-05,
|
| 760 |
+
"loss": 2.4005,
|
| 761 |
+
"step": 104
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.1485148514851485,
|
| 765 |
+
"grad_norm": 1.85604989528656,
|
| 766 |
+
"learning_rate": 5.05e-05,
|
| 767 |
+
"loss": 2.3848,
|
| 768 |
+
"step": 105
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 0.14992927864214992,
|
| 772 |
+
"grad_norm": 2.049961805343628,
|
| 773 |
+
"learning_rate": 4.9968421052631576e-05,
|
| 774 |
+
"loss": 2.2966,
|
| 775 |
+
"step": 106
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 0.15134370579915135,
|
| 779 |
+
"grad_norm": 1.8361124992370605,
|
| 780 |
+
"learning_rate": 4.943684210526316e-05,
|
| 781 |
+
"loss": 2.5758,
|
| 782 |
+
"step": 107
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 0.15275813295615276,
|
| 786 |
+
"grad_norm": 1.8123300075531006,
|
| 787 |
+
"learning_rate": 4.890526315789474e-05,
|
| 788 |
+
"loss": 2.541,
|
| 789 |
+
"step": 108
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.15417256011315417,
|
| 793 |
+
"grad_norm": 1.7798748016357422,
|
| 794 |
+
"learning_rate": 4.8373684210526316e-05,
|
| 795 |
+
"loss": 2.461,
|
| 796 |
+
"step": 109
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 0.15558698727015557,
|
| 800 |
+
"grad_norm": 1.794299840927124,
|
| 801 |
+
"learning_rate": 4.784210526315789e-05,
|
| 802 |
+
"loss": 2.4377,
|
| 803 |
+
"step": 110
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 0.157001414427157,
|
| 807 |
+
"grad_norm": 1.764225959777832,
|
| 808 |
+
"learning_rate": 4.731052631578947e-05,
|
| 809 |
+
"loss": 2.4051,
|
| 810 |
+
"step": 111
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 0.15841584158415842,
|
| 814 |
+
"grad_norm": 1.998778223991394,
|
| 815 |
+
"learning_rate": 4.6778947368421055e-05,
|
| 816 |
+
"loss": 2.2702,
|
| 817 |
+
"step": 112
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 0.15983026874115983,
|
| 821 |
+
"grad_norm": 1.8289985656738281,
|
| 822 |
+
"learning_rate": 4.624736842105263e-05,
|
| 823 |
+
"loss": 2.4621,
|
| 824 |
+
"step": 113
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 0.16124469589816123,
|
| 828 |
+
"grad_norm": 1.7528291940689087,
|
| 829 |
+
"learning_rate": 4.571578947368421e-05,
|
| 830 |
+
"loss": 2.5883,
|
| 831 |
+
"step": 114
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 0.16265912305516267,
|
| 835 |
+
"grad_norm": 1.732502818107605,
|
| 836 |
+
"learning_rate": 4.518421052631579e-05,
|
| 837 |
+
"loss": 2.4774,
|
| 838 |
+
"step": 115
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 0.16407355021216408,
|
| 842 |
+
"grad_norm": 1.6828466653823853,
|
| 843 |
+
"learning_rate": 4.465263157894737e-05,
|
| 844 |
+
"loss": 2.3899,
|
| 845 |
+
"step": 116
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 0.16548797736916548,
|
| 849 |
+
"grad_norm": 1.5521636009216309,
|
| 850 |
+
"learning_rate": 4.412105263157895e-05,
|
| 851 |
+
"loss": 2.2525,
|
| 852 |
+
"step": 117
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 0.1669024045261669,
|
| 856 |
+
"grad_norm": 1.7095965147018433,
|
| 857 |
+
"learning_rate": 4.358947368421053e-05,
|
| 858 |
+
"loss": 2.2436,
|
| 859 |
+
"step": 118
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 0.16831683168316833,
|
| 863 |
+
"grad_norm": 1.8195699453353882,
|
| 864 |
+
"learning_rate": 4.30578947368421e-05,
|
| 865 |
+
"loss": 2.3708,
|
| 866 |
+
"step": 119
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 0.16973125884016974,
|
| 870 |
+
"grad_norm": 1.6346312761306763,
|
| 871 |
+
"learning_rate": 4.2526315789473685e-05,
|
| 872 |
+
"loss": 2.5518,
|
| 873 |
+
"step": 120
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.17114568599717114,
|
| 877 |
+
"grad_norm": 1.5906932353973389,
|
| 878 |
+
"learning_rate": 4.199473684210527e-05,
|
| 879 |
+
"loss": 2.4394,
|
| 880 |
+
"step": 121
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 0.17256011315417255,
|
| 884 |
+
"grad_norm": 1.6136739253997803,
|
| 885 |
+
"learning_rate": 4.146315789473684e-05,
|
| 886 |
+
"loss": 2.3704,
|
| 887 |
+
"step": 122
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 0.173974540311174,
|
| 891 |
+
"grad_norm": 1.5603336095809937,
|
| 892 |
+
"learning_rate": 4.093157894736842e-05,
|
| 893 |
+
"loss": 2.3416,
|
| 894 |
+
"step": 123
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 0.1753889674681754,
|
| 898 |
+
"grad_norm": 1.7088912725448608,
|
| 899 |
+
"learning_rate": 4.0400000000000006e-05,
|
| 900 |
+
"loss": 2.2935,
|
| 901 |
+
"step": 124
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 0.1768033946251768,
|
| 905 |
+
"grad_norm": 1.952721357345581,
|
| 906 |
+
"learning_rate": 3.986842105263158e-05,
|
| 907 |
+
"loss": 2.1708,
|
| 908 |
+
"step": 125
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 0.1782178217821782,
|
| 912 |
+
"grad_norm": 1.8259592056274414,
|
| 913 |
+
"learning_rate": 3.933684210526316e-05,
|
| 914 |
+
"loss": 2.644,
|
| 915 |
+
"step": 126
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 0.17963224893917965,
|
| 919 |
+
"grad_norm": 1.7780115604400635,
|
| 920 |
+
"learning_rate": 3.880526315789473e-05,
|
| 921 |
+
"loss": 2.4767,
|
| 922 |
+
"step": 127
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 0.18104667609618105,
|
| 926 |
+
"grad_norm": 1.6455316543579102,
|
| 927 |
+
"learning_rate": 3.827368421052632e-05,
|
| 928 |
+
"loss": 2.4048,
|
| 929 |
+
"step": 128
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 0.18246110325318246,
|
| 933 |
+
"grad_norm": 1.5901890993118286,
|
| 934 |
+
"learning_rate": 3.7742105263157896e-05,
|
| 935 |
+
"loss": 2.3776,
|
| 936 |
+
"step": 129
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 0.18387553041018387,
|
| 940 |
+
"grad_norm": 1.6352453231811523,
|
| 941 |
+
"learning_rate": 3.721052631578947e-05,
|
| 942 |
+
"loss": 2.3015,
|
| 943 |
+
"step": 130
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 0.18528995756718528,
|
| 947 |
+
"grad_norm": 1.8599220514297485,
|
| 948 |
+
"learning_rate": 3.6678947368421054e-05,
|
| 949 |
+
"loss": 2.1913,
|
| 950 |
+
"step": 131
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 0.1867043847241867,
|
| 954 |
+
"grad_norm": 1.6458431482315063,
|
| 955 |
+
"learning_rate": 3.6147368421052636e-05,
|
| 956 |
+
"loss": 2.5229,
|
| 957 |
+
"step": 132
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 0.18811881188118812,
|
| 961 |
+
"grad_norm": 1.6390492916107178,
|
| 962 |
+
"learning_rate": 3.561578947368421e-05,
|
| 963 |
+
"loss": 2.4673,
|
| 964 |
+
"step": 133
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 0.18953323903818953,
|
| 968 |
+
"grad_norm": 1.6500605344772339,
|
| 969 |
+
"learning_rate": 3.508421052631579e-05,
|
| 970 |
+
"loss": 2.5057,
|
| 971 |
+
"step": 134
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 0.19094766619519093,
|
| 975 |
+
"grad_norm": 1.5461673736572266,
|
| 976 |
+
"learning_rate": 3.455263157894737e-05,
|
| 977 |
+
"loss": 2.4082,
|
| 978 |
+
"step": 135
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 0.19236209335219237,
|
| 982 |
+
"grad_norm": 1.6012736558914185,
|
| 983 |
+
"learning_rate": 3.402105263157895e-05,
|
| 984 |
+
"loss": 2.3262,
|
| 985 |
+
"step": 136
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 0.19377652050919378,
|
| 989 |
+
"grad_norm": 1.8380329608917236,
|
| 990 |
+
"learning_rate": 3.3489473684210526e-05,
|
| 991 |
+
"loss": 2.2267,
|
| 992 |
+
"step": 137
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 0.19519094766619519,
|
| 996 |
+
"grad_norm": 1.6812222003936768,
|
| 997 |
+
"learning_rate": 3.295789473684211e-05,
|
| 998 |
+
"loss": 2.4013,
|
| 999 |
+
"step": 138
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.1966053748231966,
|
| 1003 |
+
"grad_norm": 1.6972684860229492,
|
| 1004 |
+
"learning_rate": 3.242631578947368e-05,
|
| 1005 |
+
"loss": 2.5284,
|
| 1006 |
+
"step": 139
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 0.19801980198019803,
|
| 1010 |
+
"grad_norm": 1.5738369226455688,
|
| 1011 |
+
"learning_rate": 3.1894736842105265e-05,
|
| 1012 |
+
"loss": 2.4468,
|
| 1013 |
+
"step": 140
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 0.19943422913719944,
|
| 1017 |
+
"grad_norm": 1.5377528667449951,
|
| 1018 |
+
"learning_rate": 3.136315789473685e-05,
|
| 1019 |
+
"loss": 2.4274,
|
| 1020 |
+
"step": 141
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 0.20084865629420084,
|
| 1024 |
+
"grad_norm": 1.4526879787445068,
|
| 1025 |
+
"learning_rate": 3.083157894736842e-05,
|
| 1026 |
+
"loss": 2.278,
|
| 1027 |
+
"step": 142
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 0.20226308345120225,
|
| 1031 |
+
"grad_norm": 1.6539933681488037,
|
| 1032 |
+
"learning_rate": 3.0299999999999998e-05,
|
| 1033 |
+
"loss": 2.2014,
|
| 1034 |
+
"step": 143
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 0.2036775106082037,
|
| 1038 |
+
"grad_norm": 1.7789607048034668,
|
| 1039 |
+
"learning_rate": 2.9768421052631577e-05,
|
| 1040 |
+
"loss": 2.3219,
|
| 1041 |
+
"step": 144
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.2050919377652051,
|
| 1045 |
+
"grad_norm": 1.6558810472488403,
|
| 1046 |
+
"learning_rate": 2.923684210526316e-05,
|
| 1047 |
+
"loss": 2.5565,
|
| 1048 |
+
"step": 145
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 0.2065063649222065,
|
| 1052 |
+
"grad_norm": 1.5841859579086304,
|
| 1053 |
+
"learning_rate": 2.8705263157894737e-05,
|
| 1054 |
+
"loss": 2.4249,
|
| 1055 |
+
"step": 146
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 0.2079207920792079,
|
| 1059 |
+
"grad_norm": 1.541245698928833,
|
| 1060 |
+
"learning_rate": 2.8173684210526313e-05,
|
| 1061 |
+
"loss": 2.3161,
|
| 1062 |
+
"step": 147
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 0.20933521923620935,
|
| 1066 |
+
"grad_norm": 1.540382981300354,
|
| 1067 |
+
"learning_rate": 2.7642105263157898e-05,
|
| 1068 |
+
"loss": 2.2704,
|
| 1069 |
+
"step": 148
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 0.21074964639321075,
|
| 1073 |
+
"grad_norm": 1.6713669300079346,
|
| 1074 |
+
"learning_rate": 2.7110526315789473e-05,
|
| 1075 |
+
"loss": 2.3984,
|
| 1076 |
+
"step": 149
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 0.21216407355021216,
|
| 1080 |
+
"grad_norm": 1.785141110420227,
|
| 1081 |
+
"learning_rate": 2.6578947368421052e-05,
|
| 1082 |
+
"loss": 2.1903,
|
| 1083 |
+
"step": 150
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 0.21216407355021216,
|
| 1087 |
+
"eval_loss": 0.5903738141059875,
|
| 1088 |
+
"eval_runtime": 65.8893,
|
| 1089 |
+
"eval_samples_per_second": 144.561,
|
| 1090 |
+
"eval_steps_per_second": 4.523,
|
| 1091 |
+
"step": 150
|
| 1092 |
}
|
| 1093 |
],
|
| 1094 |
"logging_steps": 1,
|
|
|
|
| 1117 |
"attributes": {}
|
| 1118 |
}
|
| 1119 |
},
|
| 1120 |
+
"total_flos": 1.7171995435204608e+18,
|
| 1121 |
"train_batch_size": 8,
|
| 1122 |
"trial_name": null,
|
| 1123 |
"trial_params": null
|