Training in progress, step 64000, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 469337272
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4f1052fc44f17677882e9c85aa46ba7cf0ce95d12039334b20adedd2169a62e5
|
| 3 |
size 469337272
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 938825803
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3fc31a21e830e5240ed3d4e54481bf756f6f044cd5580281c9cff0c9b8736b9e
|
| 3 |
size 938825803
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:907db0cce0a5bafbb1926a59c3e73634f18337e15182c3dda71e7ef66bbb3df1
|
| 3 |
size 14645
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1845127fa7eca8c5b502f7e5468e1855ba6951691315fb77854957ecb9da8539
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 0.
|
| 6 |
"eval_steps": 1000,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -4688,6 +4688,318 @@
|
|
| 4688 |
"eval_samples_per_second": 77.714,
|
| 4689 |
"eval_steps_per_second": 19.429,
|
| 4690 |
"step": 60000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4691 |
}
|
| 4692 |
],
|
| 4693 |
"logging_steps": 100,
|
|
@@ -4707,7 +5019,7 @@
|
|
| 4707 |
"attributes": {}
|
| 4708 |
}
|
| 4709 |
},
|
| 4710 |
-
"total_flos": 1.
|
| 4711 |
"train_batch_size": 22,
|
| 4712 |
"trial_name": null,
|
| 4713 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.2545454545454545,
|
| 6 |
"eval_steps": 1000,
|
| 7 |
+
"global_step": 64000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4688 |
"eval_samples_per_second": 77.714,
|
| 4689 |
"eval_steps_per_second": 19.429,
|
| 4690 |
"step": 60000
|
| 4691 |
+
},
|
| 4692 |
+
{
|
| 4693 |
+
"epoch": 0.2190909090909091,
|
| 4694 |
+
"grad_norm": 0.16105052828788757,
|
| 4695 |
+
"learning_rate": 0.0004284064105413123,
|
| 4696 |
+
"loss": 2.6820413208007814,
|
| 4697 |
+
"step": 60100
|
| 4698 |
+
},
|
| 4699 |
+
{
|
| 4700 |
+
"epoch": 0.22,
|
| 4701 |
+
"grad_norm": 0.17260073125362396,
|
| 4702 |
+
"learning_rate": 0.00042699149336866053,
|
| 4703 |
+
"loss": 2.705378112792969,
|
| 4704 |
+
"step": 60200
|
| 4705 |
+
},
|
| 4706 |
+
{
|
| 4707 |
+
"epoch": 0.22090909090909092,
|
| 4708 |
+
"grad_norm": 0.1929374486207962,
|
| 4709 |
+
"learning_rate": 0.0004255771733313727,
|
| 4710 |
+
"loss": 2.6583901977539064,
|
| 4711 |
+
"step": 60300
|
| 4712 |
+
},
|
| 4713 |
+
{
|
| 4714 |
+
"epoch": 0.22181818181818183,
|
| 4715 |
+
"grad_norm": 0.15301187336444855,
|
| 4716 |
+
"learning_rate": 0.00042416346199714895,
|
| 4717 |
+
"loss": 2.6433419799804687,
|
| 4718 |
+
"step": 60400
|
| 4719 |
+
},
|
| 4720 |
+
{
|
| 4721 |
+
"epoch": 0.22272727272727272,
|
| 4722 |
+
"grad_norm": 0.16559265553951263,
|
| 4723 |
+
"learning_rate": 0.0004227503709287107,
|
| 4724 |
+
"loss": 2.6537457275390626,
|
| 4725 |
+
"step": 60500
|
| 4726 |
+
},
|
| 4727 |
+
{
|
| 4728 |
+
"epoch": 0.22363636363636363,
|
| 4729 |
+
"grad_norm": 0.16312868893146515,
|
| 4730 |
+
"learning_rate": 0.0004213379116837065,
|
| 4731 |
+
"loss": 2.642680969238281,
|
| 4732 |
+
"step": 60600
|
| 4733 |
+
},
|
| 4734 |
+
{
|
| 4735 |
+
"epoch": 0.22454545454545455,
|
| 4736 |
+
"grad_norm": 0.1596183180809021,
|
| 4737 |
+
"learning_rate": 0.00041992609581461714,
|
| 4738 |
+
"loss": 2.6479568481445312,
|
| 4739 |
+
"step": 60700
|
| 4740 |
+
},
|
| 4741 |
+
{
|
| 4742 |
+
"epoch": 0.22545454545454546,
|
| 4743 |
+
"grad_norm": 0.1691562980413437,
|
| 4744 |
+
"learning_rate": 0.00041851493486866093,
|
| 4745 |
+
"loss": 2.668114013671875,
|
| 4746 |
+
"step": 60800
|
| 4747 |
+
},
|
| 4748 |
+
{
|
| 4749 |
+
"epoch": 0.22636363636363635,
|
| 4750 |
+
"grad_norm": 0.17783690989017487,
|
| 4751 |
+
"learning_rate": 0.00041710444038770006,
|
| 4752 |
+
"loss": 2.6744537353515625,
|
| 4753 |
+
"step": 60900
|
| 4754 |
+
},
|
| 4755 |
+
{
|
| 4756 |
+
"epoch": 0.22727272727272727,
|
| 4757 |
+
"grad_norm": 0.14821407198905945,
|
| 4758 |
+
"learning_rate": 0.00041569462390814507,
|
| 4759 |
+
"loss": 2.6778204345703127,
|
| 4760 |
+
"step": 61000
|
| 4761 |
+
},
|
| 4762 |
+
{
|
| 4763 |
+
"epoch": 0.22727272727272727,
|
| 4764 |
+
"eval_loss": 3.0541512966156006,
|
| 4765 |
+
"eval_runtime": 7.4401,
|
| 4766 |
+
"eval_samples_per_second": 77.419,
|
| 4767 |
+
"eval_steps_per_second": 19.355,
|
| 4768 |
+
"step": 61000
|
| 4769 |
+
},
|
| 4770 |
+
{
|
| 4771 |
+
"epoch": 0.22818181818181818,
|
| 4772 |
+
"grad_norm": 0.15560130774974823,
|
| 4773 |
+
"learning_rate": 0.00041428549696086213,
|
| 4774 |
+
"loss": 2.6814599609375,
|
| 4775 |
+
"step": 61100
|
| 4776 |
+
},
|
| 4777 |
+
{
|
| 4778 |
+
"epoch": 0.2290909090909091,
|
| 4779 |
+
"grad_norm": 0.16080529987812042,
|
| 4780 |
+
"learning_rate": 0.0004128770710710768,
|
| 4781 |
+
"loss": 2.6637908935546877,
|
| 4782 |
+
"step": 61200
|
| 4783 |
+
},
|
| 4784 |
+
{
|
| 4785 |
+
"epoch": 0.23,
|
| 4786 |
+
"grad_norm": 0.15518587827682495,
|
| 4787 |
+
"learning_rate": 0.0004114693577582812,
|
| 4788 |
+
"loss": 2.6588839721679687,
|
| 4789 |
+
"step": 61300
|
| 4790 |
+
},
|
| 4791 |
+
{
|
| 4792 |
+
"epoch": 0.2309090909090909,
|
| 4793 |
+
"grad_norm": 0.16887351870536804,
|
| 4794 |
+
"learning_rate": 0.000410062368536139,
|
| 4795 |
+
"loss": 2.674110107421875,
|
| 4796 |
+
"step": 61400
|
| 4797 |
+
},
|
| 4798 |
+
{
|
| 4799 |
+
"epoch": 0.2318181818181818,
|
| 4800 |
+
"grad_norm": 0.1643567532300949,
|
| 4801 |
+
"learning_rate": 0.0004086561149123919,
|
| 4802 |
+
"loss": 2.6627960205078125,
|
| 4803 |
+
"step": 61500
|
| 4804 |
+
},
|
| 4805 |
+
{
|
| 4806 |
+
"epoch": 0.23272727272727273,
|
| 4807 |
+
"grad_norm": 0.17247343063354492,
|
| 4808 |
+
"learning_rate": 0.0004072506083887647,
|
| 4809 |
+
"loss": 2.680544738769531,
|
| 4810 |
+
"step": 61600
|
| 4811 |
+
},
|
| 4812 |
+
{
|
| 4813 |
+
"epoch": 0.23363636363636364,
|
| 4814 |
+
"grad_norm": 0.17303307354450226,
|
| 4815 |
+
"learning_rate": 0.0004058458604608721,
|
| 4816 |
+
"loss": 2.6711715698242187,
|
| 4817 |
+
"step": 61700
|
| 4818 |
+
},
|
| 4819 |
+
{
|
| 4820 |
+
"epoch": 0.23454545454545456,
|
| 4821 |
+
"grad_norm": 0.15602687001228333,
|
| 4822 |
+
"learning_rate": 0.0004044418826181241,
|
| 4823 |
+
"loss": 2.6567123413085936,
|
| 4824 |
+
"step": 61800
|
| 4825 |
+
},
|
| 4826 |
+
{
|
| 4827 |
+
"epoch": 0.23545454545454544,
|
| 4828 |
+
"grad_norm": 0.17260140180587769,
|
| 4829 |
+
"learning_rate": 0.0004030386863436319,
|
| 4830 |
+
"loss": 2.6413006591796875,
|
| 4831 |
+
"step": 61900
|
| 4832 |
+
},
|
| 4833 |
+
{
|
| 4834 |
+
"epoch": 0.23636363636363636,
|
| 4835 |
+
"grad_norm": 0.15273793041706085,
|
| 4836 |
+
"learning_rate": 0.000401636283114115,
|
| 4837 |
+
"loss": 2.6535302734375,
|
| 4838 |
+
"step": 62000
|
| 4839 |
+
},
|
| 4840 |
+
{
|
| 4841 |
+
"epoch": 0.23636363636363636,
|
| 4842 |
+
"eval_loss": 3.0504443645477295,
|
| 4843 |
+
"eval_runtime": 7.4706,
|
| 4844 |
+
"eval_samples_per_second": 77.102,
|
| 4845 |
+
"eval_steps_per_second": 19.276,
|
| 4846 |
+
"step": 62000
|
| 4847 |
+
},
|
| 4848 |
+
{
|
| 4849 |
+
"epoch": 0.23727272727272727,
|
| 4850 |
+
"grad_norm": 0.1516442894935608,
|
| 4851 |
+
"learning_rate": 0.0004002346843998058,
|
| 4852 |
+
"loss": 2.65826416015625,
|
| 4853 |
+
"step": 62100
|
| 4854 |
+
},
|
| 4855 |
+
{
|
| 4856 |
+
"epoch": 0.2381818181818182,
|
| 4857 |
+
"grad_norm": 0.16887111961841583,
|
| 4858 |
+
"learning_rate": 0.0003988339016643571,
|
| 4859 |
+
"loss": 2.65544189453125,
|
| 4860 |
+
"step": 62200
|
| 4861 |
+
},
|
| 4862 |
+
{
|
| 4863 |
+
"epoch": 0.2390909090909091,
|
| 4864 |
+
"grad_norm": 0.17878231406211853,
|
| 4865 |
+
"learning_rate": 0.00039743394636474735,
|
| 4866 |
+
"loss": 2.6390304565429688,
|
| 4867 |
+
"step": 62300
|
| 4868 |
+
},
|
| 4869 |
+
{
|
| 4870 |
+
"epoch": 0.24,
|
| 4871 |
+
"grad_norm": 0.14858455955982208,
|
| 4872 |
+
"learning_rate": 0.00039603482995118793,
|
| 4873 |
+
"loss": 2.6456539916992186,
|
| 4874 |
+
"step": 62400
|
| 4875 |
+
},
|
| 4876 |
+
{
|
| 4877 |
+
"epoch": 0.2409090909090909,
|
| 4878 |
+
"grad_norm": 0.16330905258655548,
|
| 4879 |
+
"learning_rate": 0.0003946365638670289,
|
| 4880 |
+
"loss": 2.6405880737304686,
|
| 4881 |
+
"step": 62500
|
| 4882 |
+
},
|
| 4883 |
+
{
|
| 4884 |
+
"epoch": 0.24181818181818182,
|
| 4885 |
+
"grad_norm": 0.17122872173786163,
|
| 4886 |
+
"learning_rate": 0.00039323915954866506,
|
| 4887 |
+
"loss": 2.6345315551757813,
|
| 4888 |
+
"step": 62600
|
| 4889 |
+
},
|
| 4890 |
+
{
|
| 4891 |
+
"epoch": 0.24272727272727274,
|
| 4892 |
+
"grad_norm": 0.15139397978782654,
|
| 4893 |
+
"learning_rate": 0.00039184262842544346,
|
| 4894 |
+
"loss": 2.617703857421875,
|
| 4895 |
+
"step": 62700
|
| 4896 |
+
},
|
| 4897 |
+
{
|
| 4898 |
+
"epoch": 0.24363636363636362,
|
| 4899 |
+
"grad_norm": 0.14694419503211975,
|
| 4900 |
+
"learning_rate": 0.0003904469819195686,
|
| 4901 |
+
"loss": 2.6260647583007812,
|
| 4902 |
+
"step": 62800
|
| 4903 |
+
},
|
| 4904 |
+
{
|
| 4905 |
+
"epoch": 0.24454545454545454,
|
| 4906 |
+
"grad_norm": 0.1512179970741272,
|
| 4907 |
+
"learning_rate": 0.00038905223144601044,
|
| 4908 |
+
"loss": 2.6326007080078124,
|
| 4909 |
+
"step": 62900
|
| 4910 |
+
},
|
| 4911 |
+
{
|
| 4912 |
+
"epoch": 0.24545454545454545,
|
| 4913 |
+
"grad_norm": 0.1644383668899536,
|
| 4914 |
+
"learning_rate": 0.00038765838841240964,
|
| 4915 |
+
"loss": 2.655694885253906,
|
| 4916 |
+
"step": 63000
|
| 4917 |
+
},
|
| 4918 |
+
{
|
| 4919 |
+
"epoch": 0.24545454545454545,
|
| 4920 |
+
"eval_loss": 3.050816774368286,
|
| 4921 |
+
"eval_runtime": 7.4114,
|
| 4922 |
+
"eval_samples_per_second": 77.718,
|
| 4923 |
+
"eval_steps_per_second": 19.43,
|
| 4924 |
+
"step": 63000
|
| 4925 |
+
},
|
| 4926 |
+
{
|
| 4927 |
+
"epoch": 0.24636363636363637,
|
| 4928 |
+
"grad_norm": 0.16079971194267273,
|
| 4929 |
+
"learning_rate": 0.00038626546421898547,
|
| 4930 |
+
"loss": 2.6361544799804686,
|
| 4931 |
+
"step": 63100
|
| 4932 |
+
},
|
| 4933 |
+
{
|
| 4934 |
+
"epoch": 0.24727272727272728,
|
| 4935 |
+
"grad_norm": 0.16880013048648834,
|
| 4936 |
+
"learning_rate": 0.0003848734702584417,
|
| 4937 |
+
"loss": 2.6428652954101564,
|
| 4938 |
+
"step": 63200
|
| 4939 |
+
},
|
| 4940 |
+
{
|
| 4941 |
+
"epoch": 0.24818181818181817,
|
| 4942 |
+
"grad_norm": 0.15799115598201752,
|
| 4943 |
+
"learning_rate": 0.00038348241791587377,
|
| 4944 |
+
"loss": 2.63120361328125,
|
| 4945 |
+
"step": 63300
|
| 4946 |
+
},
|
| 4947 |
+
{
|
| 4948 |
+
"epoch": 0.24909090909090909,
|
| 4949 |
+
"grad_norm": 0.1738392412662506,
|
| 4950 |
+
"learning_rate": 0.00038209231856867594,
|
| 4951 |
+
"loss": 2.6429544067382813,
|
| 4952 |
+
"step": 63400
|
| 4953 |
+
},
|
| 4954 |
+
{
|
| 4955 |
+
"epoch": 0.25,
|
| 4956 |
+
"grad_norm": 0.16007262468338013,
|
| 4957 |
+
"learning_rate": 0.0003807031835864474,
|
| 4958 |
+
"loss": 2.6346502685546875,
|
| 4959 |
+
"step": 63500
|
| 4960 |
+
},
|
| 4961 |
+
{
|
| 4962 |
+
"epoch": 0.2509090909090909,
|
| 4963 |
+
"grad_norm": 0.16581037640571594,
|
| 4964 |
+
"learning_rate": 0.0003793150243309002,
|
| 4965 |
+
"loss": 2.625074462890625,
|
| 4966 |
+
"step": 63600
|
| 4967 |
+
},
|
| 4968 |
+
{
|
| 4969 |
+
"epoch": 0.25181818181818183,
|
| 4970 |
+
"grad_norm": 0.14953260123729706,
|
| 4971 |
+
"learning_rate": 0.00037792785215576605,
|
| 4972 |
+
"loss": 2.6320794677734374,
|
| 4973 |
+
"step": 63700
|
| 4974 |
+
},
|
| 4975 |
+
{
|
| 4976 |
+
"epoch": 0.25272727272727274,
|
| 4977 |
+
"grad_norm": 0.15426383912563324,
|
| 4978 |
+
"learning_rate": 0.0003765416784067028,
|
| 4979 |
+
"loss": 2.6317816162109375,
|
| 4980 |
+
"step": 63800
|
| 4981 |
+
},
|
| 4982 |
+
{
|
| 4983 |
+
"epoch": 0.25363636363636366,
|
| 4984 |
+
"grad_norm": 0.1912180483341217,
|
| 4985 |
+
"learning_rate": 0.0003751565144212027,
|
| 4986 |
+
"loss": 2.63588623046875,
|
| 4987 |
+
"step": 63900
|
| 4988 |
+
},
|
| 4989 |
+
{
|
| 4990 |
+
"epoch": 0.2545454545454545,
|
| 4991 |
+
"grad_norm": 0.1402943879365921,
|
| 4992 |
+
"learning_rate": 0.0003737723715284992,
|
| 4993 |
+
"loss": 2.644476013183594,
|
| 4994 |
+
"step": 64000
|
| 4995 |
+
},
|
| 4996 |
+
{
|
| 4997 |
+
"epoch": 0.2545454545454545,
|
| 4998 |
+
"eval_loss": 3.0472707748413086,
|
| 4999 |
+
"eval_runtime": 7.4723,
|
| 5000 |
+
"eval_samples_per_second": 77.085,
|
| 5001 |
+
"eval_steps_per_second": 19.271,
|
| 5002 |
+
"step": 64000
|
| 5003 |
}
|
| 5004 |
],
|
| 5005 |
"logging_steps": 100,
|
|
|
|
| 5019 |
"attributes": {}
|
| 5020 |
}
|
| 5021 |
},
|
| 5022 |
+
"total_flos": 1.594533183750144e+18,
|
| 5023 |
"train_batch_size": 22,
|
| 5024 |
"trial_name": null,
|
| 5025 |
"trial_params": null
|