Training in progress, step 110, 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 59827904
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:351753d46ffc91b1dc947070dd4b639c8388128ee5fe0abea4e2c8d332773b3e
|
3 |
size 59827904
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 30875540
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ffd7e5ecec0c8a3684326bea00fcf95dfb59ebc0b2835bd86344757e5488e83f
|
3 |
size 30875540
|
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 sha256:224a371397cd38e6f33df8d6c03713b6fae877d0326fb5ca5060998390efdc67
|
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 sha256:802e09b6cc63e64e726d0b68ba37b81d6a6fcf54cdf00e4821b3e38426a8a5c4
|
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": 34,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -774,6 +774,41 @@
|
|
774 |
"learning_rate": 0.00011837495178165706,
|
775 |
"loss": 10.1478,
|
776 |
"step": 105
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
777 |
}
|
778 |
],
|
779 |
"logging_steps": 1,
|
@@ -793,7 +828,7 @@
|
|
793 |
"attributes": {}
|
794 |
}
|
795 |
},
|
796 |
-
"total_flos": 2.
|
797 |
"train_batch_size": 3,
|
798 |
"trial_name": null,
|
799 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.05379301913319885,
|
5 |
"eval_steps": 34,
|
6 |
+
"global_step": 110,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
774 |
"learning_rate": 0.00011837495178165706,
|
775 |
"loss": 10.1478,
|
776 |
"step": 105
|
777 |
+
},
|
778 |
+
{
|
779 |
+
"epoch": 0.05183690934653708,
|
780 |
+
"grad_norm": Infinity,
|
781 |
+
"learning_rate": 0.000116555387618413,
|
782 |
+
"loss": 10.6195,
|
783 |
+
"step": 106
|
784 |
+
},
|
785 |
+
{
|
786 |
+
"epoch": 0.05232593679320252,
|
787 |
+
"grad_norm": Infinity,
|
788 |
+
"learning_rate": 0.00011473016980546377,
|
789 |
+
"loss": 9.3004,
|
790 |
+
"step": 107
|
791 |
+
},
|
792 |
+
{
|
793 |
+
"epoch": 0.052814964239867965,
|
794 |
+
"grad_norm": Infinity,
|
795 |
+
"learning_rate": 0.00011289992165302035,
|
796 |
+
"loss": 10.7517,
|
797 |
+
"step": 108
|
798 |
+
},
|
799 |
+
{
|
800 |
+
"epoch": 0.05330399168653341,
|
801 |
+
"grad_norm": Infinity,
|
802 |
+
"learning_rate": 0.00011106526818915008,
|
803 |
+
"loss": 9.5077,
|
804 |
+
"step": 109
|
805 |
+
},
|
806 |
+
{
|
807 |
+
"epoch": 0.05379301913319885,
|
808 |
+
"grad_norm": Infinity,
|
809 |
+
"learning_rate": 0.00010922683594633021,
|
810 |
+
"loss": 8.693,
|
811 |
+
"step": 110
|
812 |
}
|
813 |
],
|
814 |
"logging_steps": 1,
|
|
|
828 |
"attributes": {}
|
829 |
}
|
830 |
},
|
831 |
+
"total_flos": 2.4249276435529728e+17,
|
832 |
"train_batch_size": 3,
|
833 |
"trial_name": null,
|
834 |
"trial_params": null
|