smilemikan
commited on
Commit
•
0973f73
1
Parent(s):
b7aea87
Training in progress, step 35500, 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:f089ca63a8be28b0b3efc08204d1937c824424cb84f62f2a98d5cad74de540f2
|
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:e070de007c58a4d3419fc03b6d8b8681766ee17017bba7a112f9373f74262005
|
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 sha256:5bb0821d7b1115e7bd56afb45eae715aab192afff0e226a97d34c7c138215a92
|
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:c32a89b05e9441bfcdff8d54b4a37933812368e5f991d0aa3b7462ffb29ad720
|
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,
|
@@ -987,13 +987,27 @@
|
|
987 |
"eval_samples_per_second": 203.892,
|
988 |
"eval_steps_per_second": 12.757,
|
989 |
"step": 35000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
990 |
}
|
991 |
],
|
992 |
"logging_steps": 500,
|
993 |
"max_steps": 60000,
|
994 |
"num_train_epochs": 14,
|
995 |
"save_steps": 500,
|
996 |
-
"total_flos": 3.
|
997 |
"trial_name": null,
|
998 |
"trial_params": null
|
999 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.3616106510162354,
|
3 |
+
"best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-35500",
|
4 |
+
"epoch": 7.8211059704780785,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 35500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
987 |
"eval_samples_per_second": 203.892,
|
988 |
"eval_steps_per_second": 12.757,
|
989 |
"step": 35000
|
990 |
+
},
|
991 |
+
{
|
992 |
+
"epoch": 7.82,
|
993 |
+
"learning_rate": 8.170333333333334e-06,
|
994 |
+
"loss": 1.2194,
|
995 |
+
"step": 35500
|
996 |
+
},
|
997 |
+
{
|
998 |
+
"epoch": 7.82,
|
999 |
+
"eval_loss": 1.3616106510162354,
|
1000 |
+
"eval_runtime": 45.4373,
|
1001 |
+
"eval_samples_per_second": 199.792,
|
1002 |
+
"eval_steps_per_second": 12.501,
|
1003 |
+
"step": 35500
|
1004 |
}
|
1005 |
],
|
1006 |
"logging_steps": 500,
|
1007 |
"max_steps": 60000,
|
1008 |
"num_train_epochs": 14,
|
1009 |
"save_steps": 500,
|
1010 |
+
"total_flos": 3.599083303875379e+16,
|
1011 |
"trial_name": null,
|
1012 |
"trial_params": null
|
1013 |
}
|