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 sha256:0b438c3d1349a199aea5123049ed9f422bd9a34801af6269ad08d0f7d67e0ae8
|
| 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 sha256:0200c0e95015c9a47f86d1b179a6db6de3c6e5e21fb699730fb17d7213df8823
|
| 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 15920
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bb2e3f45655858362a8daa01ec1a1702dfb87fa4cbbdefa95524bde033691cf5
|
| 3 |
size 15920
|
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 sha256:37eb3ebbbc7bcfb8c889413570bd4faab1d89175179cb5e9bc5a09d6eb4e1cf9
|
| 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 sha256:10aed89d32bf03c8e8d4c25f75a024987cbcade97716d6bfa9f96cbdf2f45806
|
| 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 sha256:5459262d6e510975a089da27218419fd06424870b68672c6b0c04d59019dbe7c
|
| 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 sha256:129ac206589e670ebf155c369e486370e47b23f5f7fc368544720c64fc6399b7
|
| 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:a98d5e4158e5a9630aae82a9d4c88f3e9b4c4065a2e91fc09060e1f886b87c51
|
| 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 sha256:1bbfba84c4edff6234d9cf37d2bfad839e16e1ecdd824671b3fd43f87ca89354
|
| 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 sha256:87ec47a0979e35d953eaf69727f83d4c1015010d277951eee0d223973a58dcae
|
| 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": 121.737,
|
| 732 |
"eval_steps_per_second": 3.818,
|
| 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": 0.5818656086921692,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-150",
|
| 4 |
+
"epoch": 0.487408610885459,
|
| 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": 121.737,
|
| 732 |
"eval_steps_per_second": 3.818,
|
| 733 |
"step": 100
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 0.3281884646628757,
|
| 737 |
+
"grad_norm": 0.0793076679110527,
|
| 738 |
+
"learning_rate": 5.262631578947368e-05,
|
| 739 |
+
"loss": 0.4153,
|
| 740 |
+
"step": 101
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 0.3314378554021121,
|
| 744 |
+
"grad_norm": 0.10799999535083771,
|
| 745 |
+
"learning_rate": 5.209473684210527e-05,
|
| 746 |
+
"loss": 0.5407,
|
| 747 |
+
"step": 102
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.3346872461413485,
|
| 751 |
+
"grad_norm": 0.12578538060188293,
|
| 752 |
+
"learning_rate": 5.1563157894736844e-05,
|
| 753 |
+
"loss": 0.5839,
|
| 754 |
+
"step": 103
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 0.3379366368805849,
|
| 758 |
+
"grad_norm": 0.1581355482339859,
|
| 759 |
+
"learning_rate": 5.1031578947368426e-05,
|
| 760 |
+
"loss": 0.6407,
|
| 761 |
+
"step": 104
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.3411860276198213,
|
| 765 |
+
"grad_norm": 0.1918567270040512,
|
| 766 |
+
"learning_rate": 5.05e-05,
|
| 767 |
+
"loss": 0.651,
|
| 768 |
+
"step": 105
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 0.34443541835905767,
|
| 772 |
+
"grad_norm": 0.28396371006965637,
|
| 773 |
+
"learning_rate": 4.9968421052631576e-05,
|
| 774 |
+
"loss": 0.6952,
|
| 775 |
+
"step": 106
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 0.3476848090982941,
|
| 779 |
+
"grad_norm": 0.0913185104727745,
|
| 780 |
+
"learning_rate": 4.943684210526316e-05,
|
| 781 |
+
"loss": 0.4104,
|
| 782 |
+
"step": 107
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 0.35093419983753044,
|
| 786 |
+
"grad_norm": 0.09755459427833557,
|
| 787 |
+
"learning_rate": 4.890526315789474e-05,
|
| 788 |
+
"loss": 0.5118,
|
| 789 |
+
"step": 108
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.35418359057676685,
|
| 793 |
+
"grad_norm": 0.11383837461471558,
|
| 794 |
+
"learning_rate": 4.8373684210526316e-05,
|
| 795 |
+
"loss": 0.5756,
|
| 796 |
+
"step": 109
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 0.35743298131600326,
|
| 800 |
+
"grad_norm": 0.13957881927490234,
|
| 801 |
+
"learning_rate": 4.784210526315789e-05,
|
| 802 |
+
"loss": 0.6268,
|
| 803 |
+
"step": 110
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 0.3606823720552396,
|
| 807 |
+
"grad_norm": 0.16021229326725006,
|
| 808 |
+
"learning_rate": 4.731052631578947e-05,
|
| 809 |
+
"loss": 0.6517,
|
| 810 |
+
"step": 111
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 0.36393176279447603,
|
| 814 |
+
"grad_norm": 0.22842200100421906,
|
| 815 |
+
"learning_rate": 4.6778947368421055e-05,
|
| 816 |
+
"loss": 0.6824,
|
| 817 |
+
"step": 112
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 0.36718115353371245,
|
| 821 |
+
"grad_norm": 0.09870794415473938,
|
| 822 |
+
"learning_rate": 4.624736842105263e-05,
|
| 823 |
+
"loss": 0.3942,
|
| 824 |
+
"step": 113
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 0.3704305442729488,
|
| 828 |
+
"grad_norm": 0.09231571108102798,
|
| 829 |
+
"learning_rate": 4.571578947368421e-05,
|
| 830 |
+
"loss": 0.4683,
|
| 831 |
+
"step": 114
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 0.3736799350121852,
|
| 835 |
+
"grad_norm": 0.10994287580251694,
|
| 836 |
+
"learning_rate": 4.518421052631579e-05,
|
| 837 |
+
"loss": 0.555,
|
| 838 |
+
"step": 115
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 0.37692932575142163,
|
| 842 |
+
"grad_norm": 0.13546720147132874,
|
| 843 |
+
"learning_rate": 4.465263157894737e-05,
|
| 844 |
+
"loss": 0.632,
|
| 845 |
+
"step": 116
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 0.380178716490658,
|
| 849 |
+
"grad_norm": 0.15742133557796478,
|
| 850 |
+
"learning_rate": 4.412105263157895e-05,
|
| 851 |
+
"loss": 0.6484,
|
| 852 |
+
"step": 117
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 0.3834281072298944,
|
| 856 |
+
"grad_norm": 0.21697165071964264,
|
| 857 |
+
"learning_rate": 4.358947368421053e-05,
|
| 858 |
+
"loss": 0.66,
|
| 859 |
+
"step": 118
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 0.3866774979691308,
|
| 863 |
+
"grad_norm": 0.13058695197105408,
|
| 864 |
+
"learning_rate": 4.30578947368421e-05,
|
| 865 |
+
"loss": 0.4018,
|
| 866 |
+
"step": 119
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 0.38992688870836717,
|
| 870 |
+
"grad_norm": 0.09321828931570053,
|
| 871 |
+
"learning_rate": 4.2526315789473685e-05,
|
| 872 |
+
"loss": 0.4504,
|
| 873 |
+
"step": 120
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.3931762794476036,
|
| 877 |
+
"grad_norm": 0.11127794533967972,
|
| 878 |
+
"learning_rate": 4.199473684210527e-05,
|
| 879 |
+
"loss": 0.5384,
|
| 880 |
+
"step": 121
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 0.39642567018683994,
|
| 884 |
+
"grad_norm": 0.13234351575374603,
|
| 885 |
+
"learning_rate": 4.146315789473684e-05,
|
| 886 |
+
"loss": 0.5954,
|
| 887 |
+
"step": 122
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 0.39967506092607635,
|
| 891 |
+
"grad_norm": 0.15013480186462402,
|
| 892 |
+
"learning_rate": 4.093157894736842e-05,
|
| 893 |
+
"loss": 0.6251,
|
| 894 |
+
"step": 123
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 0.40292445166531277,
|
| 898 |
+
"grad_norm": 0.18615896999835968,
|
| 899 |
+
"learning_rate": 4.0400000000000006e-05,
|
| 900 |
+
"loss": 0.6394,
|
| 901 |
+
"step": 124
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 0.4061738424045491,
|
| 905 |
+
"grad_norm": 0.3680824935436249,
|
| 906 |
+
"learning_rate": 3.986842105263158e-05,
|
| 907 |
+
"loss": 0.6591,
|
| 908 |
+
"step": 125
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 0.40942323314378554,
|
| 912 |
+
"grad_norm": 0.08504093438386917,
|
| 913 |
+
"learning_rate": 3.933684210526316e-05,
|
| 914 |
+
"loss": 0.4255,
|
| 915 |
+
"step": 126
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 0.41267262388302195,
|
| 919 |
+
"grad_norm": 0.10568774491548538,
|
| 920 |
+
"learning_rate": 3.880526315789473e-05,
|
| 921 |
+
"loss": 0.5556,
|
| 922 |
+
"step": 127
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 0.4159220146222583,
|
| 926 |
+
"grad_norm": 0.12182536721229553,
|
| 927 |
+
"learning_rate": 3.827368421052632e-05,
|
| 928 |
+
"loss": 0.5852,
|
| 929 |
+
"step": 128
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 0.4191714053614947,
|
| 933 |
+
"grad_norm": 0.1525968313217163,
|
| 934 |
+
"learning_rate": 3.7742105263157896e-05,
|
| 935 |
+
"loss": 0.6436,
|
| 936 |
+
"step": 129
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 0.42242079610073113,
|
| 940 |
+
"grad_norm": 0.1934550702571869,
|
| 941 |
+
"learning_rate": 3.721052631578947e-05,
|
| 942 |
+
"loss": 0.6896,
|
| 943 |
+
"step": 130
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 0.4256701868399675,
|
| 947 |
+
"grad_norm": 0.28480178117752075,
|
| 948 |
+
"learning_rate": 3.6678947368421054e-05,
|
| 949 |
+
"loss": 0.6857,
|
| 950 |
+
"step": 131
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 0.4289195775792039,
|
| 954 |
+
"grad_norm": 0.09007880091667175,
|
| 955 |
+
"learning_rate": 3.6147368421052636e-05,
|
| 956 |
+
"loss": 0.3843,
|
| 957 |
+
"step": 132
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 0.4321689683184403,
|
| 961 |
+
"grad_norm": 0.09930918365716934,
|
| 962 |
+
"learning_rate": 3.561578947368421e-05,
|
| 963 |
+
"loss": 0.5109,
|
| 964 |
+
"step": 133
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 0.4354183590576767,
|
| 968 |
+
"grad_norm": 0.118385449051857,
|
| 969 |
+
"learning_rate": 3.508421052631579e-05,
|
| 970 |
+
"loss": 0.5836,
|
| 971 |
+
"step": 134
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 0.4386677497969131,
|
| 975 |
+
"grad_norm": 0.139013409614563,
|
| 976 |
+
"learning_rate": 3.455263157894737e-05,
|
| 977 |
+
"loss": 0.6216,
|
| 978 |
+
"step": 135
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 0.44191714053614944,
|
| 982 |
+
"grad_norm": 0.16059033572673798,
|
| 983 |
+
"learning_rate": 3.402105263157895e-05,
|
| 984 |
+
"loss": 0.6354,
|
| 985 |
+
"step": 136
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 0.44516653127538586,
|
| 989 |
+
"grad_norm": 0.24489456415176392,
|
| 990 |
+
"learning_rate": 3.3489473684210526e-05,
|
| 991 |
+
"loss": 0.6692,
|
| 992 |
+
"step": 137
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 0.44841592201462227,
|
| 996 |
+
"grad_norm": 0.10024583339691162,
|
| 997 |
+
"learning_rate": 3.295789473684211e-05,
|
| 998 |
+
"loss": 0.3742,
|
| 999 |
+
"step": 138
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.4516653127538586,
|
| 1003 |
+
"grad_norm": 0.09301915764808655,
|
| 1004 |
+
"learning_rate": 3.242631578947368e-05,
|
| 1005 |
+
"loss": 0.4654,
|
| 1006 |
+
"step": 139
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 0.45491470349309504,
|
| 1010 |
+
"grad_norm": 0.11495403945446014,
|
| 1011 |
+
"learning_rate": 3.1894736842105265e-05,
|
| 1012 |
+
"loss": 0.5628,
|
| 1013 |
+
"step": 140
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 0.45816409423233145,
|
| 1017 |
+
"grad_norm": 0.13312485814094543,
|
| 1018 |
+
"learning_rate": 3.136315789473685e-05,
|
| 1019 |
+
"loss": 0.5899,
|
| 1020 |
+
"step": 141
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 0.4614134849715678,
|
| 1024 |
+
"grad_norm": 0.1566401571035385,
|
| 1025 |
+
"learning_rate": 3.083157894736842e-05,
|
| 1026 |
+
"loss": 0.6362,
|
| 1027 |
+
"step": 142
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 0.4646628757108042,
|
| 1031 |
+
"grad_norm": 0.20983877778053284,
|
| 1032 |
+
"learning_rate": 3.0299999999999998e-05,
|
| 1033 |
+
"loss": 0.6727,
|
| 1034 |
+
"step": 143
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 0.46791226645004064,
|
| 1038 |
+
"grad_norm": 0.13690727949142456,
|
| 1039 |
+
"learning_rate": 2.9768421052631577e-05,
|
| 1040 |
+
"loss": 0.4128,
|
| 1041 |
+
"step": 144
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.471161657189277,
|
| 1045 |
+
"grad_norm": 0.0922754630446434,
|
| 1046 |
+
"learning_rate": 2.923684210526316e-05,
|
| 1047 |
+
"loss": 0.4803,
|
| 1048 |
+
"step": 145
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 0.4744110479285134,
|
| 1052 |
+
"grad_norm": 0.10565061867237091,
|
| 1053 |
+
"learning_rate": 2.8705263157894737e-05,
|
| 1054 |
+
"loss": 0.547,
|
| 1055 |
+
"step": 146
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 0.4776604386677498,
|
| 1059 |
+
"grad_norm": 0.13177412748336792,
|
| 1060 |
+
"learning_rate": 2.8173684210526313e-05,
|
| 1061 |
+
"loss": 0.6094,
|
| 1062 |
+
"step": 147
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 0.4809098294069862,
|
| 1066 |
+
"grad_norm": 0.14827612042427063,
|
| 1067 |
+
"learning_rate": 2.7642105263157898e-05,
|
| 1068 |
+
"loss": 0.6221,
|
| 1069 |
+
"step": 148
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 0.4841592201462226,
|
| 1073 |
+
"grad_norm": 0.19302710890769958,
|
| 1074 |
+
"learning_rate": 2.7110526315789473e-05,
|
| 1075 |
+
"loss": 0.6625,
|
| 1076 |
+
"step": 149
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 0.487408610885459,
|
| 1080 |
+
"grad_norm": 0.37328875064849854,
|
| 1081 |
+
"learning_rate": 2.6578947368421052e-05,
|
| 1082 |
+
"loss": 0.6865,
|
| 1083 |
+
"step": 150
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 0.487408610885459,
|
| 1087 |
+
"eval_loss": 0.5818656086921692,
|
| 1088 |
+
"eval_runtime": 34.0476,
|
| 1089 |
+
"eval_samples_per_second": 121.741,
|
| 1090 |
+
"eval_steps_per_second": 3.818,
|
| 1091 |
+
"step": 150
|
| 1092 |
}
|
| 1093 |
],
|
| 1094 |
"logging_steps": 1,
|
|
|
|
| 1117 |
"attributes": {}
|
| 1118 |
}
|
| 1119 |
},
|
| 1120 |
+
"total_flos": 1.867916955323728e+18,
|
| 1121 |
"train_batch_size": 8,
|
| 1122 |
"trial_name": null,
|
| 1123 |
"trial_params": null
|