yonathanstwn
commited on
Commit
•
099aa0c
1
Parent(s):
779feae
Training in progress, epoch 24
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 577701381
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:856e4e057c2796812eff6bbd3d1934c04ce80163c67c29e951d0975bc2b1f618
|
3 |
size 577701381
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 289081861
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2506a6f22cfd7ab11cfa58484b255206a5c452a7e99929155c6112a90b91f7c
|
3 |
size 289081861
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e76e1ba239304f13ddaad86e92a668d41885109e8b8b5960a1a0f87a36dcac8f
|
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 sha256:6730863fb1e1fe1fffd81b37a3fd16f0d1494fadd52c8e1ef3f7147078a6110f
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": 1.6302595138549805,
|
3 |
"best_model_checkpoint": "models/opus-mt-id-en-opus100/checkpoint-31250",
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -351,11 +351,26 @@
|
|
351 |
"eval_samples_per_second": 58.475,
|
352 |
"eval_steps_per_second": 1.842,
|
353 |
"step": 718750
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
354 |
}
|
355 |
],
|
356 |
"max_steps": 781250,
|
357 |
"num_train_epochs": 25,
|
358 |
-
"total_flos": 2.
|
359 |
"trial_name": null,
|
360 |
"trial_params": null
|
361 |
}
|
|
|
1 |
{
|
2 |
"best_metric": 1.6302595138549805,
|
3 |
"best_model_checkpoint": "models/opus-mt-id-en-opus100/checkpoint-31250",
|
4 |
+
"epoch": 24.0,
|
5 |
+
"global_step": 750000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
351 |
"eval_samples_per_second": 58.475,
|
352 |
"eval_steps_per_second": 1.842,
|
353 |
"step": 718750
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 24.0,
|
357 |
+
"learning_rate": 4.020585397233837e-06,
|
358 |
+
"loss": 0.4681,
|
359 |
+
"step": 750000
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 24.0,
|
363 |
+
"eval_bleu": 32.1197,
|
364 |
+
"eval_loss": 2.084930419921875,
|
365 |
+
"eval_runtime": 34.0638,
|
366 |
+
"eval_samples_per_second": 58.713,
|
367 |
+
"eval_steps_per_second": 1.849,
|
368 |
+
"step": 750000
|
369 |
}
|
370 |
],
|
371 |
"max_steps": 781250,
|
372 |
"num_train_epochs": 25,
|
373 |
+
"total_flos": 2.456349166880686e+17,
|
374 |
"trial_name": null,
|
375 |
"trial_params": null
|
376 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 289081861
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2506a6f22cfd7ab11cfa58484b255206a5c452a7e99929155c6112a90b91f7c
|
3 |
size 289081861
|