Commit
·
46a62f2
1
Parent(s):
9ffa664
Training in progress, step 135, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 125248064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:71205dacc20f51f05a9bcfa2f1ab3ad7f1f0a30833e33969ab8c639a27d26769
|
3 |
size 125248064
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 63350356
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bc8dd3433a97375eb4aeddc3bfaae20ea72add67bf7c3ccae14919e2234955ee
|
3 |
size 63350356
|
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:a0ea44b215605d2b833a5ba8cb7e5ee930255d3027cf7a1afb9eb3718de5d569
|
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 sha256:08db62840dbcab25b1cc963eabefaf10f3c247ffc35b4858d5e35cab6ca752cd
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 1000,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -787,13 +787,43 @@
|
|
787 |
"learning_rate": 2.72108843537415e-05,
|
788 |
"loss": 2.031,
|
789 |
"step": 130
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
790 |
}
|
791 |
],
|
792 |
"logging_steps": 1,
|
793 |
"max_steps": 150,
|
794 |
"num_train_epochs": 1,
|
795 |
"save_steps": 5,
|
796 |
-
"total_flos": 1.
|
797 |
"trial_name": null,
|
798 |
"trial_params": null
|
799 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.054,
|
5 |
"eval_steps": 1000,
|
6 |
+
"global_step": 135,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
787 |
"learning_rate": 2.72108843537415e-05,
|
788 |
"loss": 2.031,
|
789 |
"step": 130
|
790 |
+
},
|
791 |
+
{
|
792 |
+
"epoch": 0.05,
|
793 |
+
"learning_rate": 2.5850340136054425e-05,
|
794 |
+
"loss": 1.726,
|
795 |
+
"step": 131
|
796 |
+
},
|
797 |
+
{
|
798 |
+
"epoch": 0.05,
|
799 |
+
"learning_rate": 2.448979591836735e-05,
|
800 |
+
"loss": 1.0537,
|
801 |
+
"step": 132
|
802 |
+
},
|
803 |
+
{
|
804 |
+
"epoch": 0.05,
|
805 |
+
"learning_rate": 2.3129251700680275e-05,
|
806 |
+
"loss": 1.2133,
|
807 |
+
"step": 133
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 0.05,
|
811 |
+
"learning_rate": 2.17687074829932e-05,
|
812 |
+
"loss": 1.4264,
|
813 |
+
"step": 134
|
814 |
+
},
|
815 |
+
{
|
816 |
+
"epoch": 0.05,
|
817 |
+
"learning_rate": 2.0408163265306123e-05,
|
818 |
+
"loss": 1.8015,
|
819 |
+
"step": 135
|
820 |
}
|
821 |
],
|
822 |
"logging_steps": 1,
|
823 |
"max_steps": 150,
|
824 |
"num_train_epochs": 1,
|
825 |
"save_steps": 5,
|
826 |
+
"total_flos": 1.664593632436224e+16,
|
827 |
"trial_name": null,
|
828 |
"trial_params": null
|
829 |
}
|