smilemikan
commited on
Commit
•
86065e0
1
Parent(s):
214f6f5
Training in progress, step 33500, 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:c2c24f5dd3396fd4869b7d0d4f93368f94ba30832d70fbfb1400183269e1417e
|
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 sha256:6899296af8c2023a00274eda1591c4a0d2cab3ac087e4f7517b8dd8f7503b5b4
|
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:ea09739aee88b91fd0a1a6fc63f3458d4db3a62ab804d51b151b4c7545af9133
|
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 sha256:95345dea22b1c3657a1e46c291ee0a1eaf6e182de6780a7952328076902b5364
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 1.
|
3 |
-
"best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-
|
4 |
-
"epoch": 7.
|
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,
|
@@ -931,13 +931,27 @@
|
|
931 |
"eval_samples_per_second": 201.022,
|
932 |
"eval_steps_per_second": 12.578,
|
933 |
"step": 33000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
934 |
}
|
935 |
],
|
936 |
"logging_steps": 500,
|
937 |
"max_steps": 60000,
|
938 |
"num_train_epochs": 14,
|
939 |
"save_steps": 500,
|
940 |
-
"total_flos": 3.
|
941 |
"trial_name": null,
|
942 |
"trial_params": null
|
943 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.3730745315551758,
|
3 |
+
"best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-33500",
|
4 |
+
"epoch": 7.38048028200044,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 33500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
931 |
"eval_samples_per_second": 201.022,
|
932 |
"eval_steps_per_second": 12.578,
|
933 |
"step": 33000
|
934 |
+
},
|
935 |
+
{
|
936 |
+
"epoch": 7.38,
|
937 |
+
"learning_rate": 8.836666666666668e-06,
|
938 |
+
"loss": 1.2292,
|
939 |
+
"step": 33500
|
940 |
+
},
|
941 |
+
{
|
942 |
+
"epoch": 7.38,
|
943 |
+
"eval_loss": 1.3730745315551758,
|
944 |
+
"eval_runtime": 44.6177,
|
945 |
+
"eval_samples_per_second": 203.462,
|
946 |
+
"eval_steps_per_second": 12.73,
|
947 |
+
"step": 33500
|
948 |
}
|
949 |
],
|
950 |
"logging_steps": 500,
|
951 |
"max_steps": 60000,
|
952 |
"num_train_epochs": 14,
|
953 |
"save_steps": 500,
|
954 |
+
"total_flos": 3.3968789000945664e+16,
|
955 |
"trial_name": null,
|
956 |
"trial_params": null
|
957 |
}
|