smilemikan
commited on
Commit
•
4a75f3f
1
Parent(s):
85d5d86
Training in progress, step 11500, 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:d42041a41037e15a396adf59b761131c6df3212890520ea4b8a81b5e87859bfb
|
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 sha256:3f6d9b5f6ace7846f66e54325a83eb4bb1b638fe3304783cceae5d11cc4a2c03
|
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 sha256:67afb9ca5ff5dc93d08fbb37308311c5d902249bbda09b3b3f0b514883261a65
|
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:c73ab92407ca5c93876d0a7e59f0176b1954d3d7aa094d297bce73f64e8e4dfa
|
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,
|
@@ -315,13 +315,27 @@
|
|
315 |
"eval_samples_per_second": 208.741,
|
316 |
"eval_steps_per_second": 13.061,
|
317 |
"step": 11000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
318 |
}
|
319 |
],
|
320 |
"logging_steps": 500,
|
321 |
"max_steps": 60000,
|
322 |
"num_train_epochs": 14,
|
323 |
"save_steps": 500,
|
324 |
-
"total_flos": 1.
|
325 |
"trial_name": null,
|
326 |
"trial_params": null
|
327 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.6881217956542969,
|
3 |
+
"best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-11500",
|
4 |
+
"epoch": 2.53359770874642,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 11500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
315 |
"eval_samples_per_second": 208.741,
|
316 |
"eval_steps_per_second": 13.061,
|
317 |
"step": 11000
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 2.53,
|
321 |
+
"learning_rate": 1.6168333333333336e-05,
|
322 |
+
"loss": 1.6977,
|
323 |
+
"step": 11500
|
324 |
+
},
|
325 |
+
{
|
326 |
+
"epoch": 2.53,
|
327 |
+
"eval_loss": 1.6881217956542969,
|
328 |
+
"eval_runtime": 43.1769,
|
329 |
+
"eval_samples_per_second": 210.252,
|
330 |
+
"eval_steps_per_second": 13.155,
|
331 |
+
"step": 11500
|
332 |
}
|
333 |
],
|
334 |
"logging_steps": 500,
|
335 |
"max_steps": 60000,
|
336 |
"num_train_epochs": 14,
|
337 |
"save_steps": 500,
|
338 |
+
"total_flos": 1.1677239982424064e+16,
|
339 |
"trial_name": null,
|
340 |
"trial_params": null
|
341 |
}
|
last-checkpoint/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4664
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a4d31bd653197e606b00aa0de1756222e4b81b7ec3278ac00c924e2ac80413a2
|
3 |
size 4664
|