Commit
•
6b06c9e
1
Parent(s):
eaf9058
Training in progress, step 5500, 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 577789320
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:127785b687ae550620c07c76161ce4fde314a3f786bb3bdecdd030f4cff25442
|
3 |
size 577789320
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1155772233
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f56a73e3c0f71225db11233195f56bf1f4661b8840ebb310a361c5bbb1b1c79b
|
3 |
size 1155772233
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e814e69ac405112ac0e823a174f61a291238359cb5e185b2802f269183d97fb3
|
3 |
size 14244
|
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 sha256:1f4ebc94f219234dc117648ea36b52869f5ad7c506a78e36de2ec35324b116e9
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "mikhail-panzo/zlm_b128_le5_s8000/checkpoint-
|
4 |
-
"epoch":
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -787,6 +787,84 @@
|
|
787 |
"eval_samples_per_second": 33.136,
|
788 |
"eval_steps_per_second": 4.145,
|
789 |
"step": 5000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
790 |
}
|
791 |
],
|
792 |
"logging_steps": 50,
|
@@ -806,7 +884,7 @@
|
|
806 |
"attributes": {}
|
807 |
}
|
808 |
},
|
809 |
-
"total_flos":
|
810 |
"train_batch_size": 16,
|
811 |
"trial_name": null,
|
812 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.3729405403137207,
|
3 |
+
"best_model_checkpoint": "mikhail-panzo/zlm_b128_le5_s8000/checkpoint-5500",
|
4 |
+
"epoch": 9.214659685863875,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 5500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
787 |
"eval_samples_per_second": 33.136,
|
788 |
"eval_steps_per_second": 4.145,
|
789 |
"step": 5000
|
790 |
+
},
|
791 |
+
{
|
792 |
+
"epoch": 8.460732984293193,
|
793 |
+
"grad_norm": 1.079275369644165,
|
794 |
+
"learning_rate": 4.921666666666666e-06,
|
795 |
+
"loss": 0.4143,
|
796 |
+
"step": 5050
|
797 |
+
},
|
798 |
+
{
|
799 |
+
"epoch": 8.544502617801047,
|
800 |
+
"grad_norm": 1.0949628353118896,
|
801 |
+
"learning_rate": 4.838333333333334e-06,
|
802 |
+
"loss": 0.4123,
|
803 |
+
"step": 5100
|
804 |
+
},
|
805 |
+
{
|
806 |
+
"epoch": 8.6282722513089,
|
807 |
+
"grad_norm": 1.5005624294281006,
|
808 |
+
"learning_rate": 4.755e-06,
|
809 |
+
"loss": 0.4218,
|
810 |
+
"step": 5150
|
811 |
+
},
|
812 |
+
{
|
813 |
+
"epoch": 8.712041884816754,
|
814 |
+
"grad_norm": 5.408727169036865,
|
815 |
+
"learning_rate": 4.671666666666667e-06,
|
816 |
+
"loss": 0.4123,
|
817 |
+
"step": 5200
|
818 |
+
},
|
819 |
+
{
|
820 |
+
"epoch": 8.795811518324607,
|
821 |
+
"grad_norm": 1.0426135063171387,
|
822 |
+
"learning_rate": 4.588333333333333e-06,
|
823 |
+
"loss": 0.4159,
|
824 |
+
"step": 5250
|
825 |
+
},
|
826 |
+
{
|
827 |
+
"epoch": 8.879581151832461,
|
828 |
+
"grad_norm": 2.312485456466675,
|
829 |
+
"learning_rate": 4.505e-06,
|
830 |
+
"loss": 0.4149,
|
831 |
+
"step": 5300
|
832 |
+
},
|
833 |
+
{
|
834 |
+
"epoch": 8.963350785340314,
|
835 |
+
"grad_norm": 1.6531749963760376,
|
836 |
+
"learning_rate": 4.421666666666667e-06,
|
837 |
+
"loss": 0.4147,
|
838 |
+
"step": 5350
|
839 |
+
},
|
840 |
+
{
|
841 |
+
"epoch": 9.047120418848168,
|
842 |
+
"grad_norm": 1.2448443174362183,
|
843 |
+
"learning_rate": 4.338333333333334e-06,
|
844 |
+
"loss": 0.4191,
|
845 |
+
"step": 5400
|
846 |
+
},
|
847 |
+
{
|
848 |
+
"epoch": 9.13089005235602,
|
849 |
+
"grad_norm": 1.1506507396697998,
|
850 |
+
"learning_rate": 4.255e-06,
|
851 |
+
"loss": 0.4094,
|
852 |
+
"step": 5450
|
853 |
+
},
|
854 |
+
{
|
855 |
+
"epoch": 9.214659685863875,
|
856 |
+
"grad_norm": 1.2973967790603638,
|
857 |
+
"learning_rate": 4.171666666666667e-06,
|
858 |
+
"loss": 0.412,
|
859 |
+
"step": 5500
|
860 |
+
},
|
861 |
+
{
|
862 |
+
"epoch": 9.214659685863875,
|
863 |
+
"eval_loss": 0.3729405403137207,
|
864 |
+
"eval_runtime": 258.7159,
|
865 |
+
"eval_samples_per_second": 32.812,
|
866 |
+
"eval_steps_per_second": 4.105,
|
867 |
+
"step": 5500
|
868 |
}
|
869 |
],
|
870 |
"logging_steps": 50,
|
|
|
884 |
"attributes": {}
|
885 |
}
|
886 |
},
|
887 |
+
"total_flos": 9.854783789898643e+16,
|
888 |
"train_batch_size": 16,
|
889 |
"trial_name": null,
|
890 |
"trial_params": null
|