smilemikan
commited on
Commit
•
21460de
1
Parent(s):
339b34d
Training in progress, step 31500, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5125261
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aec72fc6b91872b2cf2bd64198823e3e160f8af86642633607054f180be06283
|
3 |
size 5125261
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2460465086
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9001eed3be2e0d5ab6e3dab8999d257a9704251775a3235a9a47e0b9c1c391bc
|
3 |
size 2460465086
|
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:d948cd8a11b578b3ccb1af6a3a541fefb268ff26c9228bcbca21e221ffc4623c
|
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:dd49d20cfeda3cb4b70acd2672d5da2d60ccb14ecbaebaf4dadc076196f43288
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 1.387181043624878,
|
3 |
"best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-31000",
|
4 |
-
"epoch": 6.
|
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,
|
@@ -875,13 +875,27 @@
|
|
875 |
"eval_samples_per_second": 204.024,
|
876 |
"eval_steps_per_second": 12.766,
|
877 |
"step": 31000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
878 |
}
|
879 |
],
|
880 |
"logging_steps": 500,
|
881 |
"max_steps": 60000,
|
882 |
"num_train_epochs": 14,
|
883 |
"save_steps": 500,
|
884 |
-
"total_flos": 3.
|
885 |
"trial_name": null,
|
886 |
"trial_params": null
|
887 |
}
|
|
|
1 |
{
|
2 |
"best_metric": 1.387181043624878,
|
3 |
"best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-31000",
|
4 |
+
"epoch": 6.939854593522803,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 31500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
875 |
"eval_samples_per_second": 204.024,
|
876 |
"eval_steps_per_second": 12.766,
|
877 |
"step": 31000
|
878 |
+
},
|
879 |
+
{
|
880 |
+
"epoch": 6.94,
|
881 |
+
"learning_rate": 9.503333333333334e-06,
|
882 |
+
"loss": 1.2396,
|
883 |
+
"step": 31500
|
884 |
+
},
|
885 |
+
{
|
886 |
+
"epoch": 6.94,
|
887 |
+
"eval_loss": 1.3914097547531128,
|
888 |
+
"eval_runtime": 44.936,
|
889 |
+
"eval_samples_per_second": 202.021,
|
890 |
+
"eval_steps_per_second": 12.64,
|
891 |
+
"step": 31500
|
892 |
}
|
893 |
],
|
894 |
"logging_steps": 500,
|
895 |
"max_steps": 60000,
|
896 |
"num_train_epochs": 14,
|
897 |
"save_steps": 500,
|
898 |
+
"total_flos": 3.193435183369421e+16,
|
899 |
"trial_name": null,
|
900 |
"trial_params": null
|
901 |
}
|