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 140815952
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:824f09925e06dade0980b7b6f2673ad9313a1860d3955d0f6ec2c24b8d19dac8
|
| 3 |
size 140815952
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 71878612
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0385716b1e421bc04c934b8f7557055a72735142692c3a1dba5e7471da2b24ea
|
| 3 |
size 71878612
|
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 sha256:254216cd1bfa077aac79ddf3aa991dd86be3d924b5693193fb57c269a3229fc5
|
| 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 sha256:98e93359c59ca311edbe89f16d5f0231bbab585603f1b0be35494b54b91a1828
|
| 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 sha256:4653009b10dd48c6a46766f75f0f4c3beaaf299dba0329a995450677bc18ca49
|
| 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 sha256:5415a05b9817c8d92f7f2ef1613eb04335e657362fb7e72f840691f4ab31dc13
|
| 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:dfa835537978680c561926622f8191526b11e7115b2608526fb7b423c2761adb
|
| 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 sha256:1d99df497585478105a47995bca143a42ccb608ae08ea70b6fa51f3ac15d28c3
|
| 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 sha256:975a341ff81520c4a9e0bf9eb1d42a63cc63f204e2529f8679b8c5258e9f3765
|
| 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 sha256:168986a5fc9ca577afbaa24ced94bae1c6aeb7a2e5577615a8f9fb71b2478a65
|
| 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 sha256:4a1d4966bbb3ac4136a17b84f52768cf52a77159d3c183b2a8af35a019ee542b
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 2.
|
| 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": 302.956,
|
| 732 |
"eval_steps_per_second": 9.468,
|
| 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": 2.138585329055786,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-150",
|
| 4 |
+
"epoch": 0.05185825410544512,
|
| 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": 302.956,
|
| 732 |
"eval_steps_per_second": 9.468,
|
| 733 |
"step": 100
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 0.03491789109766638,
|
| 737 |
+
"grad_norm": 0.2299177050590515,
|
| 738 |
+
"learning_rate": 5.4370619800610666e-05,
|
| 739 |
+
"loss": 1.318,
|
| 740 |
+
"step": 101
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 0.03526361279170268,
|
| 744 |
+
"grad_norm": 0.3703376352787018,
|
| 745 |
+
"learning_rate": 5.352877148833434e-05,
|
| 746 |
+
"loss": 1.7293,
|
| 747 |
+
"step": 102
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.03560933448573898,
|
| 751 |
+
"grad_norm": 0.5616604685783386,
|
| 752 |
+
"learning_rate": 5.2686231835182714e-05,
|
| 753 |
+
"loss": 2.084,
|
| 754 |
+
"step": 103
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 0.035955056179775284,
|
| 758 |
+
"grad_norm": 0.6388251781463623,
|
| 759 |
+
"learning_rate": 5.184323118308429e-05,
|
| 760 |
+
"loss": 2.2635,
|
| 761 |
+
"step": 104
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.036300777873811585,
|
| 765 |
+
"grad_norm": 0.859301745891571,
|
| 766 |
+
"learning_rate": 5.1e-05,
|
| 767 |
+
"loss": 2.3282,
|
| 768 |
+
"step": 105
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 0.036646499567847886,
|
| 772 |
+
"grad_norm": 2.1892261505126953,
|
| 773 |
+
"learning_rate": 5.0156768816915715e-05,
|
| 774 |
+
"loss": 2.7334,
|
| 775 |
+
"step": 106
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 0.03699222126188419,
|
| 779 |
+
"grad_norm": 0.24318625032901764,
|
| 780 |
+
"learning_rate": 4.931376816481728e-05,
|
| 781 |
+
"loss": 1.3745,
|
| 782 |
+
"step": 107
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 0.03733794295592048,
|
| 786 |
+
"grad_norm": 0.3018660247325897,
|
| 787 |
+
"learning_rate": 4.8471228511665655e-05,
|
| 788 |
+
"loss": 1.4975,
|
| 789 |
+
"step": 108
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.03768366464995678,
|
| 793 |
+
"grad_norm": 0.42744195461273193,
|
| 794 |
+
"learning_rate": 4.7629380199389334e-05,
|
| 795 |
+
"loss": 2.0573,
|
| 796 |
+
"step": 109
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 0.03802938634399308,
|
| 800 |
+
"grad_norm": 0.5142998099327087,
|
| 801 |
+
"learning_rate": 4.6788453380911054e-05,
|
| 802 |
+
"loss": 2.2087,
|
| 803 |
+
"step": 110
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 0.03837510803802938,
|
| 807 |
+
"grad_norm": 0.7566731572151184,
|
| 808 |
+
"learning_rate": 4.5948677957226404e-05,
|
| 809 |
+
"loss": 2.3133,
|
| 810 |
+
"step": 111
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 0.038720829732065684,
|
| 814 |
+
"grad_norm": 1.5625238418579102,
|
| 815 |
+
"learning_rate": 4.511028351455111e-05,
|
| 816 |
+
"loss": 2.5176,
|
| 817 |
+
"step": 112
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 0.039066551426101985,
|
| 821 |
+
"grad_norm": 0.27059802412986755,
|
| 822 |
+
"learning_rate": 4.427349926155448e-05,
|
| 823 |
+
"loss": 1.447,
|
| 824 |
+
"step": 113
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 0.039412273120138286,
|
| 828 |
+
"grad_norm": 0.2744463086128235,
|
| 829 |
+
"learning_rate": 4.3438553966696056e-05,
|
| 830 |
+
"loss": 1.4258,
|
| 831 |
+
"step": 114
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 0.03975799481417459,
|
| 835 |
+
"grad_norm": 0.373234361410141,
|
| 836 |
+
"learning_rate": 4.260567589568256e-05,
|
| 837 |
+
"loss": 1.9323,
|
| 838 |
+
"step": 115
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 0.04010371650821089,
|
| 842 |
+
"grad_norm": 0.4722805917263031,
|
| 843 |
+
"learning_rate": 4.177509274906241e-05,
|
| 844 |
+
"loss": 2.1376,
|
| 845 |
+
"step": 116
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 0.04044943820224719,
|
| 849 |
+
"grad_norm": 0.6444010734558105,
|
| 850 |
+
"learning_rate": 4.094703159997451e-05,
|
| 851 |
+
"loss": 2.2428,
|
| 852 |
+
"step": 117
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 0.04079515989628349,
|
| 856 |
+
"grad_norm": 1.2310961484909058,
|
| 857 |
+
"learning_rate": 4.012171883206892e-05,
|
| 858 |
+
"loss": 2.5802,
|
| 859 |
+
"step": 118
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 0.04114088159031979,
|
| 863 |
+
"grad_norm": 0.37185004353523254,
|
| 864 |
+
"learning_rate": 3.929938007761567e-05,
|
| 865 |
+
"loss": 1.5409,
|
| 866 |
+
"step": 119
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 0.04148660328435609,
|
| 870 |
+
"grad_norm": 0.2401726394891739,
|
| 871 |
+
"learning_rate": 3.8480240155819247e-05,
|
| 872 |
+
"loss": 1.3984,
|
| 873 |
+
"step": 120
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.04183232497839239,
|
| 877 |
+
"grad_norm": 0.3750150501728058,
|
| 878 |
+
"learning_rate": 3.766452301135519e-05,
|
| 879 |
+
"loss": 1.8374,
|
| 880 |
+
"step": 121
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 0.04217804667242869,
|
| 884 |
+
"grad_norm": 0.4811207354068756,
|
| 885 |
+
"learning_rate": 3.685245165314594e-05,
|
| 886 |
+
"loss": 2.0736,
|
| 887 |
+
"step": 122
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 0.042523768366464994,
|
| 891 |
+
"grad_norm": 0.5793203115463257,
|
| 892 |
+
"learning_rate": 3.60442480933923e-05,
|
| 893 |
+
"loss": 2.2211,
|
| 894 |
+
"step": 123
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 0.042869490060501295,
|
| 898 |
+
"grad_norm": 0.9860462546348572,
|
| 899 |
+
"learning_rate": 3.5240133286877684e-05,
|
| 900 |
+
"loss": 2.3716,
|
| 901 |
+
"step": 124
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 0.043215211754537596,
|
| 905 |
+
"grad_norm": 4.702469825744629,
|
| 906 |
+
"learning_rate": 3.444032707056115e-05,
|
| 907 |
+
"loss": 3.0878,
|
| 908 |
+
"step": 125
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 0.043560933448573896,
|
| 912 |
+
"grad_norm": 0.2194783091545105,
|
| 913 |
+
"learning_rate": 3.36450481034762e-05,
|
| 914 |
+
"loss": 1.426,
|
| 915 |
+
"step": 126
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 0.0439066551426102,
|
| 919 |
+
"grad_norm": 0.3231513202190399,
|
| 920 |
+
"learning_rate": 3.285451380695165e-05,
|
| 921 |
+
"loss": 1.683,
|
| 922 |
+
"step": 127
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 0.0442523768366465,
|
| 926 |
+
"grad_norm": 0.4826495051383972,
|
| 927 |
+
"learning_rate": 3.2068940305170734e-05,
|
| 928 |
+
"loss": 2.0538,
|
| 929 |
+
"step": 128
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 0.0445980985306828,
|
| 933 |
+
"grad_norm": 0.6153631806373596,
|
| 934 |
+
"learning_rate": 3.128854236608495e-05,
|
| 935 |
+
"loss": 2.2823,
|
| 936 |
+
"step": 129
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 0.0449438202247191,
|
| 940 |
+
"grad_norm": 0.8221266269683838,
|
| 941 |
+
"learning_rate": 3.051353334269857e-05,
|
| 942 |
+
"loss": 2.3001,
|
| 943 |
+
"step": 130
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 0.0452895419187554,
|
| 947 |
+
"grad_norm": 2.2605419158935547,
|
| 948 |
+
"learning_rate": 2.9744125114740198e-05,
|
| 949 |
+
"loss": 2.8268,
|
| 950 |
+
"step": 131
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 0.0456352636127917,
|
| 954 |
+
"grad_norm": 0.25618210434913635,
|
| 955 |
+
"learning_rate": 2.898052803073687e-05,
|
| 956 |
+
"loss": 1.4537,
|
| 957 |
+
"step": 132
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 0.045980985306828,
|
| 961 |
+
"grad_norm": 0.3234250545501709,
|
| 962 |
+
"learning_rate": 2.822295085050687e-05,
|
| 963 |
+
"loss": 1.6086,
|
| 964 |
+
"step": 133
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 0.0463267070008643,
|
| 968 |
+
"grad_norm": 0.472940057516098,
|
| 969 |
+
"learning_rate": 2.747160068808693e-05,
|
| 970 |
+
"loss": 2.1081,
|
| 971 |
+
"step": 134
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 0.046672428694900604,
|
| 975 |
+
"grad_norm": 0.5351232290267944,
|
| 976 |
+
"learning_rate": 2.672668295510925e-05,
|
| 977 |
+
"loss": 2.1168,
|
| 978 |
+
"step": 135
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 0.047018150388936905,
|
| 982 |
+
"grad_norm": 0.6955279111862183,
|
| 983 |
+
"learning_rate": 2.5988401304644103e-05,
|
| 984 |
+
"loss": 2.2151,
|
| 985 |
+
"step": 136
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 0.047363872082973206,
|
| 989 |
+
"grad_norm": 1.3634015321731567,
|
| 990 |
+
"learning_rate": 2.5256957575522985e-05,
|
| 991 |
+
"loss": 2.5617,
|
| 992 |
+
"step": 137
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 0.04770959377700951,
|
| 996 |
+
"grad_norm": 0.2829039990901947,
|
| 997 |
+
"learning_rate": 2.453255173715804e-05,
|
| 998 |
+
"loss": 1.3504,
|
| 999 |
+
"step": 138
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.04805531547104581,
|
| 1003 |
+
"grad_norm": 0.2663942277431488,
|
| 1004 |
+
"learning_rate": 2.381538183487233e-05,
|
| 1005 |
+
"loss": 1.4263,
|
| 1006 |
+
"step": 139
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 0.04840103716508211,
|
| 1010 |
+
"grad_norm": 0.3799867331981659,
|
| 1011 |
+
"learning_rate": 2.310564393575624e-05,
|
| 1012 |
+
"loss": 2.0021,
|
| 1013 |
+
"step": 140
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 0.04874675885911841,
|
| 1017 |
+
"grad_norm": 0.4954136908054352,
|
| 1018 |
+
"learning_rate": 2.2403532075064698e-05,
|
| 1019 |
+
"loss": 2.2683,
|
| 1020 |
+
"step": 141
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 0.04909248055315471,
|
| 1024 |
+
"grad_norm": 0.6524636149406433,
|
| 1025 |
+
"learning_rate": 2.1709238203169878e-05,
|
| 1026 |
+
"loss": 2.2982,
|
| 1027 |
+
"step": 142
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 0.04943820224719101,
|
| 1031 |
+
"grad_norm": 1.1989296674728394,
|
| 1032 |
+
"learning_rate": 2.1022952133083876e-05,
|
| 1033 |
+
"loss": 2.5617,
|
| 1034 |
+
"step": 143
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 0.04978392394122731,
|
| 1038 |
+
"grad_norm": 0.36062389612197876,
|
| 1039 |
+
"learning_rate": 2.034486148856572e-05,
|
| 1040 |
+
"loss": 1.3403,
|
| 1041 |
+
"step": 144
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.05012964563526361,
|
| 1045 |
+
"grad_norm": 0.2494451403617859,
|
| 1046 |
+
"learning_rate": 1.967515165282694e-05,
|
| 1047 |
+
"loss": 1.3838,
|
| 1048 |
+
"step": 145
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 0.050475367329299914,
|
| 1052 |
+
"grad_norm": 0.35722383856773376,
|
| 1053 |
+
"learning_rate": 1.9014005717849613e-05,
|
| 1054 |
+
"loss": 1.8768,
|
| 1055 |
+
"step": 146
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 0.050821089023336215,
|
| 1059 |
+
"grad_norm": 0.4523886740207672,
|
| 1060 |
+
"learning_rate": 1.836160443433085e-05,
|
| 1061 |
+
"loss": 2.1016,
|
| 1062 |
+
"step": 147
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 0.051166810717372516,
|
| 1066 |
+
"grad_norm": 0.5969461798667908,
|
| 1067 |
+
"learning_rate": 1.7718126162267396e-05,
|
| 1068 |
+
"loss": 2.223,
|
| 1069 |
+
"step": 148
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 0.051512532411408817,
|
| 1073 |
+
"grad_norm": 0.998309850692749,
|
| 1074 |
+
"learning_rate": 1.7083746822193733e-05,
|
| 1075 |
+
"loss": 2.3714,
|
| 1076 |
+
"step": 149
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 0.05185825410544512,
|
| 1080 |
+
"grad_norm": 3.694688558578491,
|
| 1081 |
+
"learning_rate": 1.6458639847087217e-05,
|
| 1082 |
+
"loss": 2.797,
|
| 1083 |
+
"step": 150
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 0.05185825410544512,
|
| 1087 |
+
"eval_loss": 2.138585329055786,
|
| 1088 |
+
"eval_runtime": 129.102,
|
| 1089 |
+
"eval_samples_per_second": 301.878,
|
| 1090 |
+
"eval_steps_per_second": 9.434,
|
| 1091 |
+
"step": 150
|
| 1092 |
}
|
| 1093 |
],
|
| 1094 |
"logging_steps": 1,
|
|
|
|
| 1117 |
"attributes": {}
|
| 1118 |
}
|
| 1119 |
},
|
| 1120 |
+
"total_flos": 9.515693955350528e+16,
|
| 1121 |
"train_batch_size": 8,
|
| 1122 |
"trial_name": null,
|
| 1123 |
"trial_params": null
|