smilemikan
commited on
Commit
•
2c8ec49
1
Parent(s):
e3b5ed0
Training in progress, step 37500, 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 sha256:1fc89a64d1ceca5ddf4ecd58e538857ab8e4788d8326fe55e22a797e9fe9fcfb
|
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 sha256:5b5741c1a726cf0b8a568122dd53243946d8eab9e85a32aeb1932527e9c6a156
|
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:a40ed8f46e7af8c713e8a2d3baff2a529e74555fdc4f15e47aa0eb5ae14260ab
|
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 sha256:16997df99f028947206813663490936f805cb39b71dcde5dbb0806b9ec0bb53a
|
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": 8.
|
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,
|
@@ -1043,13 +1043,27 @@
|
|
1043 |
"eval_samples_per_second": 203.295,
|
1044 |
"eval_steps_per_second": 12.72,
|
1045 |
"step": 37000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1046 |
}
|
1047 |
],
|
1048 |
"logging_steps": 500,
|
1049 |
"max_steps": 60000,
|
1050 |
"num_train_epochs": 14,
|
1051 |
"save_steps": 500,
|
1052 |
-
"total_flos": 3.
|
1053 |
"trial_name": null,
|
1054 |
"trial_params": null
|
1055 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.35381281375885,
|
3 |
+
"best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-37500",
|
4 |
+
"epoch": 8.261731658955718,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 37500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
1043 |
"eval_samples_per_second": 203.295,
|
1044 |
"eval_steps_per_second": 12.72,
|
1045 |
"step": 37000
|
1046 |
+
},
|
1047 |
+
{
|
1048 |
+
"epoch": 8.26,
|
1049 |
+
"learning_rate": 7.504333333333334e-06,
|
1050 |
+
"loss": 1.1652,
|
1051 |
+
"step": 37500
|
1052 |
+
},
|
1053 |
+
{
|
1054 |
+
"epoch": 8.26,
|
1055 |
+
"eval_loss": 1.35381281375885,
|
1056 |
+
"eval_runtime": 45.0638,
|
1057 |
+
"eval_samples_per_second": 201.448,
|
1058 |
+
"eval_steps_per_second": 12.604,
|
1059 |
+
"step": 37500
|
1060 |
}
|
1061 |
],
|
1062 |
"logging_steps": 500,
|
1063 |
"max_steps": 60000,
|
1064 |
"num_train_epochs": 14,
|
1065 |
"save_steps": 500,
|
1066 |
+
"total_flos": 3.799716556819661e+16,
|
1067 |
"trial_name": null,
|
1068 |
"trial_params": null
|
1069 |
}
|