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:ea7be0a55bf9935123acc11257e95f4b356b1790904d1867a4dd371b322e956b
|
| 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 sha256:897e6d895f22704e6a1c23ce4ca592b880d8558914bb4a5983a7eea76630f862
|
| 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:e1b360d75844050ae534adc8062ee31ea4cab6c9016d088929f88296bf8b48d7
|
| 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:bbe359f4544a10f4aafe547db8545fe2e92f5cd68df9484744aa0f3c9125240a
|
| 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:f4cf8ddd1574625c238fb50fa36db232c26bc83b07ea1affeb132b01c36ffe52
|
| 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 sha256:3cddb1583bcea23396b6d640263dcd7a8001f7859d23185608a686199529db97
|
| 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:a396f7584534e449cb714d0789d3c7fb45c072fa2c3295197dcf1f1809476267
|
| 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 sha256:147b84d5e0e43dbcb1129e5340a16f3713583f6edac056a4582f6de859d57add
|
| 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 sha256:0faaecf51323f12062056272ab23f6e7c289f5dc7518c8da26a157bcc7d7b581
|
| 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 sha256:52bc07b74926283a54473882f6db2090dd7187c28bd2b23e1f2d991d3fb64ac1
|
| 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": 1.
|
| 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": 67.407,
|
| 732 |
"eval_steps_per_second": 2.139,
|
| 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": 0.3432846665382385,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-150",
|
| 4 |
+
"epoch": 1.7319884726224783,
|
| 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": 67.407,
|
| 732 |
"eval_steps_per_second": 2.139,
|
| 733 |
"step": 100
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 1.1671469740634006,
|
| 737 |
+
"grad_norm": 1.1594160795211792,
|
| 738 |
+
"learning_rate": 5.262631578947368e-05,
|
| 739 |
+
"loss": 1.1509,
|
| 740 |
+
"step": 101
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 1.1786743515850144,
|
| 744 |
+
"grad_norm": 1.061645269393921,
|
| 745 |
+
"learning_rate": 5.209473684210527e-05,
|
| 746 |
+
"loss": 1.1868,
|
| 747 |
+
"step": 102
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 1.1902017291066282,
|
| 751 |
+
"grad_norm": 1.021350622177124,
|
| 752 |
+
"learning_rate": 5.1563157894736844e-05,
|
| 753 |
+
"loss": 1.2714,
|
| 754 |
+
"step": 103
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 1.201729106628242,
|
| 758 |
+
"grad_norm": 1.3108984231948853,
|
| 759 |
+
"learning_rate": 5.1031578947368426e-05,
|
| 760 |
+
"loss": 1.5794,
|
| 761 |
+
"step": 104
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 1.2132564841498559,
|
| 765 |
+
"grad_norm": 2.1817190647125244,
|
| 766 |
+
"learning_rate": 5.05e-05,
|
| 767 |
+
"loss": 1.6861,
|
| 768 |
+
"step": 105
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 1.2247838616714697,
|
| 772 |
+
"grad_norm": 2.2876627445220947,
|
| 773 |
+
"learning_rate": 4.9968421052631576e-05,
|
| 774 |
+
"loss": 1.647,
|
| 775 |
+
"step": 106
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 1.2363112391930835,
|
| 779 |
+
"grad_norm": 1.1767092943191528,
|
| 780 |
+
"learning_rate": 4.943684210526316e-05,
|
| 781 |
+
"loss": 1.1436,
|
| 782 |
+
"step": 107
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 1.2478386167146973,
|
| 786 |
+
"grad_norm": 1.122977614402771,
|
| 787 |
+
"learning_rate": 4.890526315789474e-05,
|
| 788 |
+
"loss": 1.2584,
|
| 789 |
+
"step": 108
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 1.2593659942363113,
|
| 793 |
+
"grad_norm": 1.0112011432647705,
|
| 794 |
+
"learning_rate": 4.8373684210526316e-05,
|
| 795 |
+
"loss": 1.2698,
|
| 796 |
+
"step": 109
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 1.270893371757925,
|
| 800 |
+
"grad_norm": 1.2474466562271118,
|
| 801 |
+
"learning_rate": 4.784210526315789e-05,
|
| 802 |
+
"loss": 1.4298,
|
| 803 |
+
"step": 110
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 1.282420749279539,
|
| 807 |
+
"grad_norm": 2.0961225032806396,
|
| 808 |
+
"learning_rate": 4.731052631578947e-05,
|
| 809 |
+
"loss": 1.5249,
|
| 810 |
+
"step": 111
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 1.2939481268011528,
|
| 814 |
+
"grad_norm": 2.892947196960449,
|
| 815 |
+
"learning_rate": 4.6778947368421055e-05,
|
| 816 |
+
"loss": 1.7823,
|
| 817 |
+
"step": 112
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 1.3054755043227666,
|
| 821 |
+
"grad_norm": 1.2904059886932373,
|
| 822 |
+
"learning_rate": 4.624736842105263e-05,
|
| 823 |
+
"loss": 1.0597,
|
| 824 |
+
"step": 113
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 1.3170028818443804,
|
| 828 |
+
"grad_norm": 1.0860971212387085,
|
| 829 |
+
"learning_rate": 4.571578947368421e-05,
|
| 830 |
+
"loss": 1.3479,
|
| 831 |
+
"step": 114
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 1.3285302593659942,
|
| 835 |
+
"grad_norm": 1.0123194456100464,
|
| 836 |
+
"learning_rate": 4.518421052631579e-05,
|
| 837 |
+
"loss": 1.1235,
|
| 838 |
+
"step": 115
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 1.340057636887608,
|
| 842 |
+
"grad_norm": 1.1925913095474243,
|
| 843 |
+
"learning_rate": 4.465263157894737e-05,
|
| 844 |
+
"loss": 1.3878,
|
| 845 |
+
"step": 116
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 1.3515850144092219,
|
| 849 |
+
"grad_norm": 1.8660753965377808,
|
| 850 |
+
"learning_rate": 4.412105263157895e-05,
|
| 851 |
+
"loss": 1.6422,
|
| 852 |
+
"step": 117
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 1.3631123919308357,
|
| 856 |
+
"grad_norm": 2.7606379985809326,
|
| 857 |
+
"learning_rate": 4.358947368421053e-05,
|
| 858 |
+
"loss": 1.6949,
|
| 859 |
+
"step": 118
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 1.3746397694524495,
|
| 863 |
+
"grad_norm": 1.5100210905075073,
|
| 864 |
+
"learning_rate": 4.30578947368421e-05,
|
| 865 |
+
"loss": 1.0997,
|
| 866 |
+
"step": 119
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 1.3861671469740635,
|
| 870 |
+
"grad_norm": 1.165024995803833,
|
| 871 |
+
"learning_rate": 4.2526315789473685e-05,
|
| 872 |
+
"loss": 1.1644,
|
| 873 |
+
"step": 120
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 1.397694524495677,
|
| 877 |
+
"grad_norm": 0.9900702834129333,
|
| 878 |
+
"learning_rate": 4.199473684210527e-05,
|
| 879 |
+
"loss": 1.2457,
|
| 880 |
+
"step": 121
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 1.4092219020172911,
|
| 884 |
+
"grad_norm": 1.1262096166610718,
|
| 885 |
+
"learning_rate": 4.146315789473684e-05,
|
| 886 |
+
"loss": 1.341,
|
| 887 |
+
"step": 122
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 1.420749279538905,
|
| 891 |
+
"grad_norm": 1.4549776315689087,
|
| 892 |
+
"learning_rate": 4.093157894736842e-05,
|
| 893 |
+
"loss": 1.4951,
|
| 894 |
+
"step": 123
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 1.4322766570605188,
|
| 898 |
+
"grad_norm": 2.960393190383911,
|
| 899 |
+
"learning_rate": 4.0400000000000006e-05,
|
| 900 |
+
"loss": 1.9611,
|
| 901 |
+
"step": 124
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 1.4438040345821326,
|
| 905 |
+
"grad_norm": 1.1258149147033691,
|
| 906 |
+
"learning_rate": 3.986842105263158e-05,
|
| 907 |
+
"loss": 1.2408,
|
| 908 |
+
"step": 125
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 1.4553314121037464,
|
| 912 |
+
"grad_norm": 1.0389220714569092,
|
| 913 |
+
"learning_rate": 3.933684210526316e-05,
|
| 914 |
+
"loss": 1.1756,
|
| 915 |
+
"step": 126
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 1.4668587896253602,
|
| 919 |
+
"grad_norm": 1.1349718570709229,
|
| 920 |
+
"learning_rate": 3.880526315789473e-05,
|
| 921 |
+
"loss": 1.2792,
|
| 922 |
+
"step": 127
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 1.478386167146974,
|
| 926 |
+
"grad_norm": 1.1235551834106445,
|
| 927 |
+
"learning_rate": 3.827368421052632e-05,
|
| 928 |
+
"loss": 1.3884,
|
| 929 |
+
"step": 128
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 1.4899135446685878,
|
| 933 |
+
"grad_norm": 1.4590579271316528,
|
| 934 |
+
"learning_rate": 3.7742105263157896e-05,
|
| 935 |
+
"loss": 1.547,
|
| 936 |
+
"step": 129
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 1.5014409221902016,
|
| 940 |
+
"grad_norm": 2.1345937252044678,
|
| 941 |
+
"learning_rate": 3.721052631578947e-05,
|
| 942 |
+
"loss": 1.699,
|
| 943 |
+
"step": 130
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 1.5129682997118157,
|
| 947 |
+
"grad_norm": 2.1057217121124268,
|
| 948 |
+
"learning_rate": 3.6678947368421054e-05,
|
| 949 |
+
"loss": 1.3336,
|
| 950 |
+
"step": 131
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 1.5244956772334293,
|
| 954 |
+
"grad_norm": 1.0975521802902222,
|
| 955 |
+
"learning_rate": 3.6147368421052636e-05,
|
| 956 |
+
"loss": 1.1837,
|
| 957 |
+
"step": 132
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 1.5360230547550433,
|
| 961 |
+
"grad_norm": 1.0290075540542603,
|
| 962 |
+
"learning_rate": 3.561578947368421e-05,
|
| 963 |
+
"loss": 1.0588,
|
| 964 |
+
"step": 133
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 1.547550432276657,
|
| 968 |
+
"grad_norm": 1.109420895576477,
|
| 969 |
+
"learning_rate": 3.508421052631579e-05,
|
| 970 |
+
"loss": 1.2782,
|
| 971 |
+
"step": 134
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 1.559077809798271,
|
| 975 |
+
"grad_norm": 1.3788710832595825,
|
| 976 |
+
"learning_rate": 3.455263157894737e-05,
|
| 977 |
+
"loss": 1.4358,
|
| 978 |
+
"step": 135
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 1.5706051873198847,
|
| 982 |
+
"grad_norm": 1.9282630681991577,
|
| 983 |
+
"learning_rate": 3.402105263157895e-05,
|
| 984 |
+
"loss": 1.5525,
|
| 985 |
+
"step": 136
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 1.5821325648414986,
|
| 989 |
+
"grad_norm": 3.0819172859191895,
|
| 990 |
+
"learning_rate": 3.3489473684210526e-05,
|
| 991 |
+
"loss": 1.6032,
|
| 992 |
+
"step": 137
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 1.5936599423631124,
|
| 996 |
+
"grad_norm": 1.0416362285614014,
|
| 997 |
+
"learning_rate": 3.295789473684211e-05,
|
| 998 |
+
"loss": 1.0864,
|
| 999 |
+
"step": 138
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 1.6051873198847262,
|
| 1003 |
+
"grad_norm": 1.0696144104003906,
|
| 1004 |
+
"learning_rate": 3.242631578947368e-05,
|
| 1005 |
+
"loss": 1.0025,
|
| 1006 |
+
"step": 139
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 1.6167146974063402,
|
| 1010 |
+
"grad_norm": 0.9461542963981628,
|
| 1011 |
+
"learning_rate": 3.1894736842105265e-05,
|
| 1012 |
+
"loss": 0.982,
|
| 1013 |
+
"step": 140
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 1.6282420749279538,
|
| 1017 |
+
"grad_norm": 1.1103463172912598,
|
| 1018 |
+
"learning_rate": 3.136315789473685e-05,
|
| 1019 |
+
"loss": 1.2823,
|
| 1020 |
+
"step": 141
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 1.6397694524495678,
|
| 1024 |
+
"grad_norm": 1.6639349460601807,
|
| 1025 |
+
"learning_rate": 3.083157894736842e-05,
|
| 1026 |
+
"loss": 1.486,
|
| 1027 |
+
"step": 142
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 1.6512968299711814,
|
| 1031 |
+
"grad_norm": 2.9342904090881348,
|
| 1032 |
+
"learning_rate": 3.0299999999999998e-05,
|
| 1033 |
+
"loss": 1.8242,
|
| 1034 |
+
"step": 143
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 1.6628242074927955,
|
| 1038 |
+
"grad_norm": 1.3234608173370361,
|
| 1039 |
+
"learning_rate": 2.9768421052631577e-05,
|
| 1040 |
+
"loss": 1.1624,
|
| 1041 |
+
"step": 144
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 1.674351585014409,
|
| 1045 |
+
"grad_norm": 1.2971738576889038,
|
| 1046 |
+
"learning_rate": 2.923684210526316e-05,
|
| 1047 |
+
"loss": 1.1139,
|
| 1048 |
+
"step": 145
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 1.685878962536023,
|
| 1052 |
+
"grad_norm": 1.0851243734359741,
|
| 1053 |
+
"learning_rate": 2.8705263157894737e-05,
|
| 1054 |
+
"loss": 1.0419,
|
| 1055 |
+
"step": 146
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 1.697406340057637,
|
| 1059 |
+
"grad_norm": 1.0544915199279785,
|
| 1060 |
+
"learning_rate": 2.8173684210526313e-05,
|
| 1061 |
+
"loss": 1.2045,
|
| 1062 |
+
"step": 147
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 1.7089337175792507,
|
| 1066 |
+
"grad_norm": 1.4829477071762085,
|
| 1067 |
+
"learning_rate": 2.7642105263157898e-05,
|
| 1068 |
+
"loss": 1.3821,
|
| 1069 |
+
"step": 148
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 1.7204610951008645,
|
| 1073 |
+
"grad_norm": 2.9280033111572266,
|
| 1074 |
+
"learning_rate": 2.7110526315789473e-05,
|
| 1075 |
+
"loss": 1.8452,
|
| 1076 |
+
"step": 149
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 1.7319884726224783,
|
| 1080 |
+
"grad_norm": 1.1372859477996826,
|
| 1081 |
+
"learning_rate": 2.6578947368421052e-05,
|
| 1082 |
+
"loss": 1.0575,
|
| 1083 |
+
"step": 150
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 1.7319884726224783,
|
| 1087 |
+
"eval_loss": 0.3432846665382385,
|
| 1088 |
+
"eval_runtime": 18.7516,
|
| 1089 |
+
"eval_samples_per_second": 62.181,
|
| 1090 |
+
"eval_steps_per_second": 1.973,
|
| 1091 |
+
"step": 150
|
| 1092 |
}
|
| 1093 |
],
|
| 1094 |
"logging_steps": 1,
|
|
|
|
| 1117 |
"attributes": {}
|
| 1118 |
}
|
| 1119 |
},
|
| 1120 |
+
"total_flos": 2.652357791305433e+18,
|
| 1121 |
"train_batch_size": 8,
|
| 1122 |
"trial_name": null,
|
| 1123 |
"trial_params": null
|