mprzibilla
commited on
Commit
•
a17d1a9
1
Parent(s):
39a1eef
Training in progress, step 25800
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 +19 -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 168299
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b9237907e886dac34a7241f9bfde5e114a868b33ffcf1113c9288d38541f3e86
|
3 |
size 168299
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 377643361
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:52421d27124a86e95d2bea008209322bd596fa3a57bb05069fb1c702cd9f501d
|
3 |
size 377643361
|
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 sha256:271c40a36a2accf0371db3e22a1e83ca0fb0d4aae96488226a0e3ac50b60e3c0
|
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:c43f8419cddc82815a5bc5b3fd46727b36ea4841563bd24f29a84030e9e2b62d
|
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 sha256:6a7336bf03ebdfcb2e18e7a35727a7824946970bbec532ee66190e6c0e9c1346
|
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,
|
@@ -54,11 +54,27 @@
|
|
54 |
"eval_steps_per_second": 3.312,
|
55 |
"eval_wer": 1.0,
|
56 |
"step": 19350
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
57 |
}
|
58 |
],
|
59 |
"max_steps": 64500,
|
60 |
"num_train_epochs": 250,
|
61 |
-
"total_flos":
|
62 |
"trial_name": null,
|
63 |
"trial_params": null
|
64 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 100.0,
|
5 |
+
"global_step": 25800,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
54 |
"eval_steps_per_second": 3.312,
|
55 |
"eval_wer": 1.0,
|
56 |
"step": 19350
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 100.0,
|
60 |
+
"learning_rate": 6.318074255405957e-05,
|
61 |
+
"loss": 2.5334,
|
62 |
+
"step": 25800
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 100.0,
|
66 |
+
"eval_cer": 0.8883116883116883,
|
67 |
+
"eval_loss": 2.404860496520996,
|
68 |
+
"eval_runtime": 8.0509,
|
69 |
+
"eval_samples_per_second": 26.084,
|
70 |
+
"eval_steps_per_second": 3.354,
|
71 |
+
"eval_wer": 1.0,
|
72 |
+
"step": 25800
|
73 |
}
|
74 |
],
|
75 |
"max_steps": 64500,
|
76 |
"num_train_epochs": 250,
|
77 |
+
"total_flos": 2.4807253525047214e+19,
|
78 |
"trial_name": null,
|
79 |
"trial_params": null
|
80 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 377643361
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:52421d27124a86e95d2bea008209322bd596fa3a57bb05069fb1c702cd9f501d
|
3 |
size 377643361
|