mprzibilla
commited on
Commit
•
50eab8c
1
Parent(s):
24aa983
Training in progress, epoch 15
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +2 -2
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +20 -3
- pytorch_model.bin +1 -1
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 721668101
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a374d4c547392a0fc8dbbff94afd0e61e2ff46e6f589137cfd9a8e41077ce945
|
3 |
size 721668101
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 377649505
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f86c22efcd7cd2f11cfbb7e85aa783d8626765cf22c97efd88a3c7cb2f3318e4
|
3 |
size 377649505
|
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 sha256:265110a6df7b4bef4c792a272907f2049d348ea5fda819bcfb26a038fbcc209b
|
3 |
+
size 14639
|
last-checkpoint/scaler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 557
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1b194beddb4052686b902e84aeeee728c9ce3d45c919e63d0ab6e09b2c4ad3d3
|
3 |
size 557
|
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:bc5d77f0d6adf3609725da55fcb8fd333ce42813b683213ddf75d159f19cc884
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -244,11 +244,28 @@
|
|
244 |
"eval_samples_per_second": 26.635,
|
245 |
"eval_steps_per_second": 3.424,
|
246 |
"step": 18746
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
247 |
}
|
248 |
],
|
249 |
"max_steps": 20085,
|
250 |
"num_train_epochs": 15,
|
251 |
-
"total_flos": 1.
|
252 |
"trial_name": null,
|
253 |
"trial_params": null
|
254 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 15.0,
|
5 |
+
"global_step": 20085,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
244 |
"eval_samples_per_second": 26.635,
|
245 |
"eval_steps_per_second": 3.424,
|
246 |
"step": 18746
|
247 |
+
},
|
248 |
+
{
|
249 |
+
"epoch": 15.0,
|
250 |
+
"learning_rate": 5.764897017975998e-08,
|
251 |
+
"loss": 0.0255,
|
252 |
+
"step": 20085
|
253 |
+
},
|
254 |
+
{
|
255 |
+
"epoch": 15.0,
|
256 |
+
"eval_cer": 0.12987012987012986,
|
257 |
+
"eval_loss": 1.6889647245407104,
|
258 |
+
"eval_new_wer": 0.13333333333333333,
|
259 |
+
"eval_old_wer": 0.24285714285714285,
|
260 |
+
"eval_runtime": 7.9672,
|
261 |
+
"eval_samples_per_second": 26.358,
|
262 |
+
"eval_steps_per_second": 3.389,
|
263 |
+
"step": 20085
|
264 |
}
|
265 |
],
|
266 |
"max_steps": 20085,
|
267 |
"num_train_epochs": 15,
|
268 |
+
"total_flos": 1.5248746564040909e+19,
|
269 |
"trial_name": null,
|
270 |
"trial_params": null
|
271 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 377649505
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f86c22efcd7cd2f11cfbb7e85aa783d8626765cf22c97efd88a3c7cb2f3318e4
|
3 |
size 377649505
|