mprzibilla
commited on
Commit
•
c8536c4
1
Parent(s):
90ca0dd
Training in progress, epoch 5
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- 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 721661957
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:81a7062607cac1bb9981280802bff17d3807ffbc13539f078272ae53aed43bfe
|
3 |
size 721661957
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 377646433
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:22bbfb4b9e264136afcf54d835f86d30b91d15bd58b83912e2178af0cd3f2666
|
3 |
size 377646433
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14639
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b48591106ce6733bfe8aa8039c16e72c98ffafe8d6f13774e6f58b5ba4ac67b4
|
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:bc43511bd8770a13e16b67b47c32146f5dbc07048dc51a654edbe58ef651854b
|
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 sha256:679f5477242e21c0eb1d208391497f1121064c11ae6c0ce137abbbfabb68371e
|
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,
|
@@ -74,11 +74,28 @@
|
|
74 |
"eval_samples_per_second": 24.732,
|
75 |
"eval_steps_per_second": 3.18,
|
76 |
"step": 17080
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
77 |
}
|
78 |
],
|
79 |
"max_steps": 64050,
|
80 |
"num_train_epochs": 15,
|
81 |
-
"total_flos": 1.
|
82 |
"trial_name": null,
|
83 |
"trial_params": null
|
84 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 5.0,
|
5 |
+
"global_step": 21350,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
74 |
"eval_samples_per_second": 24.732,
|
75 |
"eval_steps_per_second": 3.18,
|
76 |
"step": 17080
|
77 |
+
},
|
78 |
+
{
|
79 |
+
"epoch": 5.0,
|
80 |
+
"learning_rate": 7.019787010255062e-05,
|
81 |
+
"loss": 0.3661,
|
82 |
+
"step": 21350
|
83 |
+
},
|
84 |
+
{
|
85 |
+
"epoch": 5.0,
|
86 |
+
"eval_cer": 0.13766233766233765,
|
87 |
+
"eval_loss": 1.2836520671844482,
|
88 |
+
"eval_new_wer": 0.19047619047619047,
|
89 |
+
"eval_old_wer": 0.2619047619047619,
|
90 |
+
"eval_runtime": 8.4952,
|
91 |
+
"eval_samples_per_second": 24.72,
|
92 |
+
"eval_steps_per_second": 3.178,
|
93 |
+
"step": 21350
|
94 |
}
|
95 |
],
|
96 |
"max_steps": 64050,
|
97 |
"num_train_epochs": 15,
|
98 |
+
"total_flos": 1.617800571223677e+19,
|
99 |
"trial_name": null,
|
100 |
"trial_params": null
|
101 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 377646433
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:22bbfb4b9e264136afcf54d835f86d30b91d15bd58b83912e2178af0cd3f2666
|
3 |
size 377646433
|