smilemikan
commited on
Commit
•
9a74e36
1
Parent(s):
5c1f322
Training in progress, step 10500, 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 sha256:118c2e22c16d42dbd2776fbb076e8546e5cb7cd6bf229b723c77ab38e0385425
|
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 sha256:25857705789979a95a8fff123eea7f489a0c89dcb1912dbf0abc14149ccec348
|
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 sha256:198c5817caf91e9f61134f521f55807668fe5b1347f183b2642fbb8d27142fb1
|
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 sha256:96b92a7a072ef7600585449bd01b526e3c8816ab7a9ab3013b79d123647e6be5
|
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": 2.
|
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,
|
@@ -287,13 +287,27 @@
|
|
287 |
"eval_samples_per_second": 208.055,
|
288 |
"eval_steps_per_second": 13.018,
|
289 |
"step": 10000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
290 |
}
|
291 |
],
|
292 |
"logging_steps": 500,
|
293 |
"max_steps": 60000,
|
294 |
"num_train_epochs": 14,
|
295 |
"save_steps": 500,
|
296 |
-
"total_flos": 1.
|
297 |
"trial_name": null,
|
298 |
"trial_params": null
|
299 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.7204526662826538,
|
3 |
+
"best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-10500",
|
4 |
+
"epoch": 2.313284864507601,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 10500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
287 |
"eval_samples_per_second": 208.055,
|
288 |
"eval_steps_per_second": 13.018,
|
289 |
"step": 10000
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 2.31,
|
293 |
+
"learning_rate": 1.6501333333333334e-05,
|
294 |
+
"loss": 1.7434,
|
295 |
+
"step": 10500
|
296 |
+
},
|
297 |
+
{
|
298 |
+
"epoch": 2.31,
|
299 |
+
"eval_loss": 1.7204526662826538,
|
300 |
+
"eval_runtime": 44.0612,
|
301 |
+
"eval_samples_per_second": 206.032,
|
302 |
+
"eval_steps_per_second": 12.891,
|
303 |
+
"step": 10500
|
304 |
}
|
305 |
],
|
306 |
"logging_steps": 500,
|
307 |
"max_steps": 60000,
|
308 |
"num_train_epochs": 14,
|
309 |
"save_steps": 500,
|
310 |
+
"total_flos": 1.0653113752879104e+16,
|
311 |
"trial_name": null,
|
312 |
"trial_params": null
|
313 |
}
|