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 639691872
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ffef11321aeb40c36498a7b0243b13c9ad66a1ed4042e5d2cff5f22aa66c152
|
| 3 |
size 639691872
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 325339796
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:026b4e4a3e304f00ef68b648ee773062cfc432c6ebbdb19dfa9f21385d9c478c
|
| 3 |
size 325339796
|
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 sha256:6fbbf97b3a5982769328e6c17bbd721d4db29f3a90af2964997b842ff0b7c627
|
| 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 sha256:55dae8430b90d80adef1c03a4f3a616fcfecb52c15727db0573d3903a58c7433
|
| 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:e2a53637177b916508a2faa86ffb825e8aec1da6f32f04559dcc4f209969d4ad
|
| 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 sha256:7624a009fbd55b74eabae40d34cae21bdea5444998c9b54d71b3dce9371f4b09
|
| 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:cf945fd2a3d32a022238b4fa2cccd83f027cee749881f4a3cd330deb0fbba67d
|
| 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:b39cc4938391c9cb93ced3ff4ba63e53d75aec591735c4893f30bd34c1bf2cdb
|
| 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:fca866cd199952053cad89fe8ee47fd054f317b68d9a842774a6ed014c7755b5
|
| 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:a6006c96ab3ed3fd9a76884eb4947385722e38fb97c03a068a95364ce3f2f031
|
| 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": 1.
|
| 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": 100.969,
|
| 732 |
"eval_steps_per_second": 3.195,
|
| 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": 1.5667701959609985,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-150",
|
| 4 |
+
"epoch": 0.9404388714733543,
|
| 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": 100.969,
|
| 732 |
"eval_steps_per_second": 3.195,
|
| 733 |
"step": 100
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 0.6332288401253918,
|
| 737 |
+
"grad_norm": 0.12550345063209534,
|
| 738 |
+
"learning_rate": 5.262631578947368e-05,
|
| 739 |
+
"loss": 1.1544,
|
| 740 |
+
"step": 101
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 0.6394984326018809,
|
| 744 |
+
"grad_norm": 0.20995737612247467,
|
| 745 |
+
"learning_rate": 5.209473684210527e-05,
|
| 746 |
+
"loss": 1.5736,
|
| 747 |
+
"step": 102
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.64576802507837,
|
| 751 |
+
"grad_norm": 0.25661516189575195,
|
| 752 |
+
"learning_rate": 5.1563157894736844e-05,
|
| 753 |
+
"loss": 1.6052,
|
| 754 |
+
"step": 103
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 0.6520376175548589,
|
| 758 |
+
"grad_norm": 0.2354477196931839,
|
| 759 |
+
"learning_rate": 5.1031578947368426e-05,
|
| 760 |
+
"loss": 1.6452,
|
| 761 |
+
"step": 104
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.658307210031348,
|
| 765 |
+
"grad_norm": 0.2458198219537735,
|
| 766 |
+
"learning_rate": 5.05e-05,
|
| 767 |
+
"loss": 1.7015,
|
| 768 |
+
"step": 105
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 0.664576802507837,
|
| 772 |
+
"grad_norm": 0.33329248428344727,
|
| 773 |
+
"learning_rate": 4.9968421052631576e-05,
|
| 774 |
+
"loss": 1.5996,
|
| 775 |
+
"step": 106
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 0.670846394984326,
|
| 779 |
+
"grad_norm": 0.1337110549211502,
|
| 780 |
+
"learning_rate": 4.943684210526316e-05,
|
| 781 |
+
"loss": 1.3261,
|
| 782 |
+
"step": 107
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 0.677115987460815,
|
| 786 |
+
"grad_norm": 0.17378275096416473,
|
| 787 |
+
"learning_rate": 4.890526315789474e-05,
|
| 788 |
+
"loss": 1.5064,
|
| 789 |
+
"step": 108
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.6833855799373041,
|
| 793 |
+
"grad_norm": 0.20934435725212097,
|
| 794 |
+
"learning_rate": 4.8373684210526316e-05,
|
| 795 |
+
"loss": 1.6143,
|
| 796 |
+
"step": 109
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 0.6896551724137931,
|
| 800 |
+
"grad_norm": 0.24600297212600708,
|
| 801 |
+
"learning_rate": 4.784210526315789e-05,
|
| 802 |
+
"loss": 1.6473,
|
| 803 |
+
"step": 110
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 0.6959247648902821,
|
| 807 |
+
"grad_norm": 0.2352122813463211,
|
| 808 |
+
"learning_rate": 4.731052631578947e-05,
|
| 809 |
+
"loss": 1.59,
|
| 810 |
+
"step": 111
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 0.7021943573667712,
|
| 814 |
+
"grad_norm": 0.3226903975009918,
|
| 815 |
+
"learning_rate": 4.6778947368421055e-05,
|
| 816 |
+
"loss": 1.5846,
|
| 817 |
+
"step": 112
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 0.7084639498432602,
|
| 821 |
+
"grad_norm": 0.14687702059745789,
|
| 822 |
+
"learning_rate": 4.624736842105263e-05,
|
| 823 |
+
"loss": 1.1129,
|
| 824 |
+
"step": 113
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 0.7147335423197492,
|
| 828 |
+
"grad_norm": 0.15256668627262115,
|
| 829 |
+
"learning_rate": 4.571578947368421e-05,
|
| 830 |
+
"loss": 1.4691,
|
| 831 |
+
"step": 114
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 0.7210031347962382,
|
| 835 |
+
"grad_norm": 0.20408159494400024,
|
| 836 |
+
"learning_rate": 4.518421052631579e-05,
|
| 837 |
+
"loss": 1.6611,
|
| 838 |
+
"step": 115
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 0.7272727272727273,
|
| 842 |
+
"grad_norm": 0.22884103655815125,
|
| 843 |
+
"learning_rate": 4.465263157894737e-05,
|
| 844 |
+
"loss": 1.6256,
|
| 845 |
+
"step": 116
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 0.7335423197492164,
|
| 849 |
+
"grad_norm": 0.23959754407405853,
|
| 850 |
+
"learning_rate": 4.412105263157895e-05,
|
| 851 |
+
"loss": 1.6332,
|
| 852 |
+
"step": 117
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 0.7398119122257053,
|
| 856 |
+
"grad_norm": 0.2993139624595642,
|
| 857 |
+
"learning_rate": 4.358947368421053e-05,
|
| 858 |
+
"loss": 1.6246,
|
| 859 |
+
"step": 118
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 0.7460815047021944,
|
| 863 |
+
"grad_norm": 0.19114616513252258,
|
| 864 |
+
"learning_rate": 4.30578947368421e-05,
|
| 865 |
+
"loss": 1.0553,
|
| 866 |
+
"step": 119
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 0.7523510971786834,
|
| 870 |
+
"grad_norm": 0.1459835320711136,
|
| 871 |
+
"learning_rate": 4.2526315789473685e-05,
|
| 872 |
+
"loss": 1.432,
|
| 873 |
+
"step": 120
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.7586206896551724,
|
| 877 |
+
"grad_norm": 0.19810743629932404,
|
| 878 |
+
"learning_rate": 4.199473684210527e-05,
|
| 879 |
+
"loss": 1.5597,
|
| 880 |
+
"step": 121
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 0.7648902821316614,
|
| 884 |
+
"grad_norm": 0.22155524790287018,
|
| 885 |
+
"learning_rate": 4.146315789473684e-05,
|
| 886 |
+
"loss": 1.5973,
|
| 887 |
+
"step": 122
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 0.7711598746081505,
|
| 891 |
+
"grad_norm": 0.252210795879364,
|
| 892 |
+
"learning_rate": 4.093157894736842e-05,
|
| 893 |
+
"loss": 1.7093,
|
| 894 |
+
"step": 123
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 0.7774294670846394,
|
| 898 |
+
"grad_norm": 0.2699624300003052,
|
| 899 |
+
"learning_rate": 4.0400000000000006e-05,
|
| 900 |
+
"loss": 1.6218,
|
| 901 |
+
"step": 124
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 0.7836990595611285,
|
| 905 |
+
"grad_norm": 0.5296167731285095,
|
| 906 |
+
"learning_rate": 3.986842105263158e-05,
|
| 907 |
+
"loss": 1.6447,
|
| 908 |
+
"step": 125
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 0.7899686520376176,
|
| 912 |
+
"grad_norm": 0.1305689811706543,
|
| 913 |
+
"learning_rate": 3.933684210526316e-05,
|
| 914 |
+
"loss": 1.2415,
|
| 915 |
+
"step": 126
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 0.7962382445141066,
|
| 919 |
+
"grad_norm": 0.19951651990413666,
|
| 920 |
+
"learning_rate": 3.880526315789473e-05,
|
| 921 |
+
"loss": 1.5846,
|
| 922 |
+
"step": 127
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 0.8025078369905956,
|
| 926 |
+
"grad_norm": 0.24844390153884888,
|
| 927 |
+
"learning_rate": 3.827368421052632e-05,
|
| 928 |
+
"loss": 1.5013,
|
| 929 |
+
"step": 128
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 0.8087774294670846,
|
| 933 |
+
"grad_norm": 0.26770254969596863,
|
| 934 |
+
"learning_rate": 3.7742105263157896e-05,
|
| 935 |
+
"loss": 1.6404,
|
| 936 |
+
"step": 129
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 0.8150470219435737,
|
| 940 |
+
"grad_norm": 0.268388956785202,
|
| 941 |
+
"learning_rate": 3.721052631578947e-05,
|
| 942 |
+
"loss": 1.6831,
|
| 943 |
+
"step": 130
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 0.8213166144200627,
|
| 947 |
+
"grad_norm": 0.3877102732658386,
|
| 948 |
+
"learning_rate": 3.6678947368421054e-05,
|
| 949 |
+
"loss": 1.5713,
|
| 950 |
+
"step": 131
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 0.8275862068965517,
|
| 954 |
+
"grad_norm": 0.14182406663894653,
|
| 955 |
+
"learning_rate": 3.6147368421052636e-05,
|
| 956 |
+
"loss": 1.1147,
|
| 957 |
+
"step": 132
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 0.8338557993730408,
|
| 961 |
+
"grad_norm": 0.1862500160932541,
|
| 962 |
+
"learning_rate": 3.561578947368421e-05,
|
| 963 |
+
"loss": 1.4998,
|
| 964 |
+
"step": 133
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 0.8401253918495298,
|
| 968 |
+
"grad_norm": 0.22701646387577057,
|
| 969 |
+
"learning_rate": 3.508421052631579e-05,
|
| 970 |
+
"loss": 1.5137,
|
| 971 |
+
"step": 134
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 0.8463949843260188,
|
| 975 |
+
"grad_norm": 0.2560668885707855,
|
| 976 |
+
"learning_rate": 3.455263157894737e-05,
|
| 977 |
+
"loss": 1.6129,
|
| 978 |
+
"step": 135
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 0.8526645768025078,
|
| 982 |
+
"grad_norm": 0.2551365792751312,
|
| 983 |
+
"learning_rate": 3.402105263157895e-05,
|
| 984 |
+
"loss": 1.6454,
|
| 985 |
+
"step": 136
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 0.8589341692789969,
|
| 989 |
+
"grad_norm": 0.331463485956192,
|
| 990 |
+
"learning_rate": 3.3489473684210526e-05,
|
| 991 |
+
"loss": 1.5863,
|
| 992 |
+
"step": 137
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 0.8652037617554859,
|
| 996 |
+
"grad_norm": 0.17028988897800446,
|
| 997 |
+
"learning_rate": 3.295789473684211e-05,
|
| 998 |
+
"loss": 1.1377,
|
| 999 |
+
"step": 138
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.8714733542319749,
|
| 1003 |
+
"grad_norm": 0.1787910908460617,
|
| 1004 |
+
"learning_rate": 3.242631578947368e-05,
|
| 1005 |
+
"loss": 1.4605,
|
| 1006 |
+
"step": 139
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 0.877742946708464,
|
| 1010 |
+
"grad_norm": 0.21535782516002655,
|
| 1011 |
+
"learning_rate": 3.1894736842105265e-05,
|
| 1012 |
+
"loss": 1.5651,
|
| 1013 |
+
"step": 140
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 0.8840125391849529,
|
| 1017 |
+
"grad_norm": 0.2516005337238312,
|
| 1018 |
+
"learning_rate": 3.136315789473685e-05,
|
| 1019 |
+
"loss": 1.6457,
|
| 1020 |
+
"step": 141
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 0.890282131661442,
|
| 1024 |
+
"grad_norm": 0.26242345571517944,
|
| 1025 |
+
"learning_rate": 3.083157894736842e-05,
|
| 1026 |
+
"loss": 1.6603,
|
| 1027 |
+
"step": 142
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 0.896551724137931,
|
| 1031 |
+
"grad_norm": 0.31754815578460693,
|
| 1032 |
+
"learning_rate": 3.0299999999999998e-05,
|
| 1033 |
+
"loss": 1.6406,
|
| 1034 |
+
"step": 143
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 0.9028213166144201,
|
| 1038 |
+
"grad_norm": 0.19499145448207855,
|
| 1039 |
+
"learning_rate": 2.9768421052631577e-05,
|
| 1040 |
+
"loss": 1.0787,
|
| 1041 |
+
"step": 144
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.9090909090909091,
|
| 1045 |
+
"grad_norm": 0.16461507976055145,
|
| 1046 |
+
"learning_rate": 2.923684210526316e-05,
|
| 1047 |
+
"loss": 1.3539,
|
| 1048 |
+
"step": 145
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 0.9153605015673981,
|
| 1052 |
+
"grad_norm": 0.231450155377388,
|
| 1053 |
+
"learning_rate": 2.8705263157894737e-05,
|
| 1054 |
+
"loss": 1.6046,
|
| 1055 |
+
"step": 146
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 0.9216300940438872,
|
| 1059 |
+
"grad_norm": 0.25709661841392517,
|
| 1060 |
+
"learning_rate": 2.8173684210526313e-05,
|
| 1061 |
+
"loss": 1.5514,
|
| 1062 |
+
"step": 147
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 0.9278996865203761,
|
| 1066 |
+
"grad_norm": 0.26337385177612305,
|
| 1067 |
+
"learning_rate": 2.7642105263157898e-05,
|
| 1068 |
+
"loss": 1.6737,
|
| 1069 |
+
"step": 148
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 0.9341692789968652,
|
| 1073 |
+
"grad_norm": 0.29333168268203735,
|
| 1074 |
+
"learning_rate": 2.7110526315789473e-05,
|
| 1075 |
+
"loss": 1.5403,
|
| 1076 |
+
"step": 149
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 0.9404388714733543,
|
| 1080 |
+
"grad_norm": 0.6478084325790405,
|
| 1081 |
+
"learning_rate": 2.6578947368421052e-05,
|
| 1082 |
+
"loss": 1.7032,
|
| 1083 |
+
"step": 150
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 0.9404388714733543,
|
| 1087 |
+
"eval_loss": 1.5667701959609985,
|
| 1088 |
+
"eval_runtime": 22.4342,
|
| 1089 |
+
"eval_samples_per_second": 95.791,
|
| 1090 |
+
"eval_steps_per_second": 3.031,
|
| 1091 |
+
"step": 150
|
| 1092 |
}
|
| 1093 |
],
|
| 1094 |
"logging_steps": 1,
|
|
|
|
| 1117 |
"attributes": {}
|
| 1118 |
}
|
| 1119 |
},
|
| 1120 |
+
"total_flos": 1.6208921818772275e+18,
|
| 1121 |
"train_batch_size": 8,
|
| 1122 |
"trial_name": null,
|
| 1123 |
"trial_params": null
|