Training in progress, step 61000, 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 891644712
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dfbbbdf5e0f7e1e75984b8a87f3e00820c6720f8b58391005c381702a07c4655
|
3 |
size 891644712
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1783444357
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ec27daf70b494d2ff8c64e8643c93445ac61cf57d9539ca709da5a21408ca147
|
3 |
size 1783444357
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bb6e27605cfbdbbe56fb86eafa8a4f9c8afa89179aa209cea4a2aad4a0e0629b
|
3 |
size 14575
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1cbd243928a750e8ab80bcce9d0d6e45db7cd8c8e143e8c4373b48e856fd52e7
|
3 |
size 627
|
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": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -840,6 +840,27 @@
|
|
840 |
"learning_rate": 4.048352e-05,
|
841 |
"loss": 0.3275,
|
842 |
"step": 59500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
843 |
}
|
844 |
],
|
845 |
"logging_steps": 500,
|
@@ -859,7 +880,7 @@
|
|
859 |
"attributes": {}
|
860 |
}
|
861 |
},
|
862 |
-
"total_flos": 2.
|
863 |
"train_batch_size": 64,
|
864 |
"trial_name": null,
|
865 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.3904,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 61000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
840 |
"learning_rate": 4.048352e-05,
|
841 |
"loss": 0.3275,
|
842 |
"step": 59500
|
843 |
+
},
|
844 |
+
{
|
845 |
+
"epoch": 0.384,
|
846 |
+
"grad_norm": 0.6306772232055664,
|
847 |
+
"learning_rate": 4.040352e-05,
|
848 |
+
"loss": 0.3308,
|
849 |
+
"step": 60000
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 0.3872,
|
853 |
+
"grad_norm": 0.6059302687644958,
|
854 |
+
"learning_rate": 4.032352e-05,
|
855 |
+
"loss": 0.3266,
|
856 |
+
"step": 60500
|
857 |
+
},
|
858 |
+
{
|
859 |
+
"epoch": 0.3904,
|
860 |
+
"grad_norm": 0.6875105500221252,
|
861 |
+
"learning_rate": 4.024352e-05,
|
862 |
+
"loss": 0.3265,
|
863 |
+
"step": 61000
|
864 |
}
|
865 |
],
|
866 |
"logging_steps": 500,
|
|
|
880 |
"attributes": {}
|
881 |
}
|
882 |
},
|
883 |
+
"total_flos": 2.9717145059328e+17,
|
884 |
"train_batch_size": 64,
|
885 |
"trial_name": null,
|
886 |
"trial_params": null
|