Training in progress, step 250000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +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 +203 -3
- pytorch_model.bin +1 -1
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 202194449
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d3ab9dc056c74cdf5d65dc3a03d7bd30aade58ae1e720539569500f125901ec6
|
3 |
size 202194449
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 102501541
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b912672be50d1a4d1c80a97a69c79548a9895fd6edfdbc5e52d33a97a1f00535
|
3 |
size 102501541
|
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 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:80275ad90d449cfcd19f9c9b9d842c8c524989912548b0b01f19b4b413629488
|
3 |
size 14503
|
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 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:80275ad90d449cfcd19f9c9b9d842c8c524989912548b0b01f19b4b413629488
|
3 |
size 14503
|
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 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:80275ad90d449cfcd19f9c9b9d842c8c524989912548b0b01f19b4b413629488
|
3 |
size 14503
|
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 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:80275ad90d449cfcd19f9c9b9d842c8c524989912548b0b01f19b4b413629488
|
3 |
size 14503
|
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 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:80275ad90d449cfcd19f9c9b9d842c8c524989912548b0b01f19b4b413629488
|
3 |
size 14503
|
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 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:80275ad90d449cfcd19f9c9b9d842c8c524989912548b0b01f19b4b413629488
|
3 |
size 14503
|
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 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:80275ad90d449cfcd19f9c9b9d842c8c524989912548b0b01f19b4b413629488
|
3 |
size 14503
|
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 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:80275ad90d449cfcd19f9c9b9d842c8c524989912548b0b01f19b4b413629488
|
3 |
size 14503
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 623
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:438f3db980ad0547f739432602e1f85cc46b6fbef312b9261fd3b355ceeb97af
|
3 |
size 623
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 6.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -4806,11 +4806,211 @@
|
|
4806 |
"eval_samples_per_second": 777.28,
|
4807 |
"eval_steps_per_second": 12.436,
|
4808 |
"step": 240000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4809 |
}
|
4810 |
],
|
4811 |
"max_steps": 500000,
|
4812 |
"num_train_epochs": 13,
|
4813 |
-
"total_flos": 7.
|
4814 |
"trial_name": null,
|
4815 |
"trial_params": null
|
4816 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 6.37137468780264,
|
5 |
+
"global_step": 250000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
4806 |
"eval_samples_per_second": 777.28,
|
4807 |
"eval_steps_per_second": 12.436,
|
4808 |
"step": 240000
|
4809 |
+
},
|
4810 |
+
{
|
4811 |
+
"epoch": 6.13,
|
4812 |
+
"learning_rate": 0.00017602390554989563,
|
4813 |
+
"loss": 0.2885,
|
4814 |
+
"step": 240500
|
4815 |
+
},
|
4816 |
+
{
|
4817 |
+
"epoch": 6.14,
|
4818 |
+
"learning_rate": 0.0001755493522675115,
|
4819 |
+
"loss": 0.2899,
|
4820 |
+
"step": 241000
|
4821 |
+
},
|
4822 |
+
{
|
4823 |
+
"epoch": 6.14,
|
4824 |
+
"eval_loss": 0.8203925490379333,
|
4825 |
+
"eval_runtime": 1.3437,
|
4826 |
+
"eval_samples_per_second": 744.194,
|
4827 |
+
"eval_steps_per_second": 11.907,
|
4828 |
+
"step": 241000
|
4829 |
+
},
|
4830 |
+
{
|
4831 |
+
"epoch": 6.15,
|
4832 |
+
"learning_rate": 0.00017507457426070317,
|
4833 |
+
"loss": 0.2894,
|
4834 |
+
"step": 241500
|
4835 |
+
},
|
4836 |
+
{
|
4837 |
+
"epoch": 6.17,
|
4838 |
+
"learning_rate": 0.00017459957672156704,
|
4839 |
+
"loss": 0.2894,
|
4840 |
+
"step": 242000
|
4841 |
+
},
|
4842 |
+
{
|
4843 |
+
"epoch": 6.17,
|
4844 |
+
"eval_loss": 0.8142299652099609,
|
4845 |
+
"eval_runtime": 1.2947,
|
4846 |
+
"eval_samples_per_second": 772.387,
|
4847 |
+
"eval_steps_per_second": 12.358,
|
4848 |
+
"step": 242000
|
4849 |
+
},
|
4850 |
+
{
|
4851 |
+
"epoch": 6.18,
|
4852 |
+
"learning_rate": 0.00017412436484459998,
|
4853 |
+
"loss": 0.2896,
|
4854 |
+
"step": 242500
|
4855 |
+
},
|
4856 |
+
{
|
4857 |
+
"epoch": 6.19,
|
4858 |
+
"learning_rate": 0.00017364894382664297,
|
4859 |
+
"loss": 0.2893,
|
4860 |
+
"step": 243000
|
4861 |
+
},
|
4862 |
+
{
|
4863 |
+
"epoch": 6.19,
|
4864 |
+
"eval_loss": 0.8166674971580505,
|
4865 |
+
"eval_runtime": 1.2594,
|
4866 |
+
"eval_samples_per_second": 794.0,
|
4867 |
+
"eval_steps_per_second": 12.704,
|
4868 |
+
"step": 243000
|
4869 |
+
},
|
4870 |
+
{
|
4871 |
+
"epoch": 6.21,
|
4872 |
+
"learning_rate": 0.00017317331886682408,
|
4873 |
+
"loss": 0.2887,
|
4874 |
+
"step": 243500
|
4875 |
+
},
|
4876 |
+
{
|
4877 |
+
"epoch": 6.22,
|
4878 |
+
"learning_rate": 0.0001726974951665017,
|
4879 |
+
"loss": 0.2883,
|
4880 |
+
"step": 244000
|
4881 |
+
},
|
4882 |
+
{
|
4883 |
+
"epoch": 6.22,
|
4884 |
+
"eval_loss": 0.8151687979698181,
|
4885 |
+
"eval_runtime": 1.3439,
|
4886 |
+
"eval_samples_per_second": 744.094,
|
4887 |
+
"eval_steps_per_second": 11.905,
|
4888 |
+
"step": 244000
|
4889 |
+
},
|
4890 |
+
{
|
4891 |
+
"epoch": 6.23,
|
4892 |
+
"learning_rate": 0.0001722214779292076,
|
4893 |
+
"loss": 0.2884,
|
4894 |
+
"step": 244500
|
4895 |
+
},
|
4896 |
+
{
|
4897 |
+
"epoch": 6.24,
|
4898 |
+
"learning_rate": 0.00017174527236058998,
|
4899 |
+
"loss": 0.2882,
|
4900 |
+
"step": 245000
|
4901 |
+
},
|
4902 |
+
{
|
4903 |
+
"epoch": 6.24,
|
4904 |
+
"eval_loss": 0.8129110336303711,
|
4905 |
+
"eval_runtime": 1.2934,
|
4906 |
+
"eval_samples_per_second": 773.156,
|
4907 |
+
"eval_steps_per_second": 12.371,
|
4908 |
+
"step": 245000
|
4909 |
+
},
|
4910 |
+
{
|
4911 |
+
"epoch": 6.26,
|
4912 |
+
"learning_rate": 0.00017126888366835662,
|
4913 |
+
"loss": 0.2879,
|
4914 |
+
"step": 245500
|
4915 |
+
},
|
4916 |
+
{
|
4917 |
+
"epoch": 6.27,
|
4918 |
+
"learning_rate": 0.000170792317062218,
|
4919 |
+
"loss": 0.2883,
|
4920 |
+
"step": 246000
|
4921 |
+
},
|
4922 |
+
{
|
4923 |
+
"epoch": 6.27,
|
4924 |
+
"eval_loss": 0.8146284222602844,
|
4925 |
+
"eval_runtime": 1.2384,
|
4926 |
+
"eval_samples_per_second": 807.487,
|
4927 |
+
"eval_steps_per_second": 12.92,
|
4928 |
+
"step": 246000
|
4929 |
+
},
|
4930 |
+
{
|
4931 |
+
"epoch": 6.28,
|
4932 |
+
"learning_rate": 0.00017031557775383011,
|
4933 |
+
"loss": 0.2883,
|
4934 |
+
"step": 246500
|
4935 |
+
},
|
4936 |
+
{
|
4937 |
+
"epoch": 6.29,
|
4938 |
+
"learning_rate": 0.0001698386709567377,
|
4939 |
+
"loss": 0.2886,
|
4940 |
+
"step": 247000
|
4941 |
+
},
|
4942 |
+
{
|
4943 |
+
"epoch": 6.29,
|
4944 |
+
"eval_loss": 0.8157382607460022,
|
4945 |
+
"eval_runtime": 1.2484,
|
4946 |
+
"eval_samples_per_second": 801.025,
|
4947 |
+
"eval_steps_per_second": 12.816,
|
4948 |
+
"step": 247000
|
4949 |
+
},
|
4950 |
+
{
|
4951 |
+
"epoch": 6.31,
|
4952 |
+
"learning_rate": 0.0001693616018863171,
|
4953 |
+
"loss": 0.2891,
|
4954 |
+
"step": 247500
|
4955 |
+
},
|
4956 |
+
{
|
4957 |
+
"epoch": 6.32,
|
4958 |
+
"learning_rate": 0.00016888437575971913,
|
4959 |
+
"loss": 0.2886,
|
4960 |
+
"step": 248000
|
4961 |
+
},
|
4962 |
+
{
|
4963 |
+
"epoch": 6.32,
|
4964 |
+
"eval_loss": 0.8171519041061401,
|
4965 |
+
"eval_runtime": 1.2819,
|
4966 |
+
"eval_samples_per_second": 780.066,
|
4967 |
+
"eval_steps_per_second": 12.481,
|
4968 |
+
"step": 248000
|
4969 |
+
},
|
4970 |
+
{
|
4971 |
+
"epoch": 6.33,
|
4972 |
+
"learning_rate": 0.00016840699779581238,
|
4973 |
+
"loss": 0.2879,
|
4974 |
+
"step": 248500
|
4975 |
+
},
|
4976 |
+
{
|
4977 |
+
"epoch": 6.35,
|
4978 |
+
"learning_rate": 0.00016792947321512573,
|
4979 |
+
"loss": 0.2885,
|
4980 |
+
"step": 249000
|
4981 |
+
},
|
4982 |
+
{
|
4983 |
+
"epoch": 6.35,
|
4984 |
+
"eval_loss": 0.82103031873703,
|
4985 |
+
"eval_runtime": 1.2758,
|
4986 |
+
"eval_samples_per_second": 783.796,
|
4987 |
+
"eval_steps_per_second": 12.541,
|
4988 |
+
"step": 249000
|
4989 |
+
},
|
4990 |
+
{
|
4991 |
+
"epoch": 6.36,
|
4992 |
+
"learning_rate": 0.00016745180723979144,
|
4993 |
+
"loss": 0.2879,
|
4994 |
+
"step": 249500
|
4995 |
+
},
|
4996 |
+
{
|
4997 |
+
"epoch": 6.37,
|
4998 |
+
"learning_rate": 0.00016697400509348818,
|
4999 |
+
"loss": 0.2886,
|
5000 |
+
"step": 250000
|
5001 |
+
},
|
5002 |
+
{
|
5003 |
+
"epoch": 6.37,
|
5004 |
+
"eval_loss": 0.8212683200836182,
|
5005 |
+
"eval_runtime": 1.2677,
|
5006 |
+
"eval_samples_per_second": 788.807,
|
5007 |
+
"eval_steps_per_second": 12.621,
|
5008 |
+
"step": 250000
|
5009 |
}
|
5010 |
],
|
5011 |
"max_steps": 500000,
|
5012 |
"num_train_epochs": 13,
|
5013 |
+
"total_flos": 7.98709759588423e+21,
|
5014 |
"trial_name": null,
|
5015 |
"trial_params": null
|
5016 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 102501541
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b912672be50d1a4d1c80a97a69c79548a9895fd6edfdbc5e52d33a97a1f00535
|
3 |
size 102501541
|