Upload 9 files
Browse files- optimizer.pt +1 -1
- pytorch_model.bin +1 -1
- rng_state.pth +1 -1
- scaler.pt +1 -1
- scheduler.pt +1 -1
- trainer_state.json +22 -16
- training_args.bin +1 -1
optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2490593669
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5a91c5aa11afa2604bf7bb0b90cbc68113580e2884d0ff8c8208194e01a56e57
|
3 |
size 2490593669
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1262168365
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:37bb631b7d49f97e816b6c3d9a747efe7351267ce10a2720c1b38d070eb83ef0
|
3 |
size 1262168365
|
rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1b1cef899f8b0d08c683c5ba411f1722de0bf50bd37d6023cd9ce9341114ce6e
|
3 |
size 14575
|
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 sha256:27aa20a390729e58f6745ce2ad2e4708be7725c1059fb8166449e11f78ca8fd2
|
3 |
size 557
|
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:d58333f13a4be9481a370b83e2e31581cd1cb3067525fafd785239d29764fbc8
|
3 |
size 627
|
trainer_state.json
CHANGED
@@ -1,31 +1,37 @@
|
|
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,
|
9 |
"log_history": [
|
10 |
{
|
11 |
-
"epoch": 0.
|
12 |
-
"learning_rate": 5e-
|
13 |
-
"loss": 0.
|
14 |
-
"step":
|
15 |
},
|
16 |
{
|
17 |
-
"epoch":
|
18 |
-
"
|
19 |
-
"
|
20 |
-
"
|
21 |
-
|
22 |
-
|
23 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
24 |
}
|
25 |
],
|
26 |
-
"max_steps":
|
27 |
-
"num_train_epochs":
|
28 |
-
"total_flos":
|
29 |
"trial_name": null,
|
30 |
"trial_params": null
|
31 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.8640595903165735,
|
5 |
+
"global_step": 250,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
9 |
"log_history": [
|
10 |
{
|
11 |
+
"epoch": 0.74,
|
12 |
+
"learning_rate": 5e-05,
|
13 |
+
"loss": 0.0641,
|
14 |
+
"step": 100
|
15 |
},
|
16 |
{
|
17 |
+
"epoch": 1.49,
|
18 |
+
"learning_rate": 4.999626837823718e-05,
|
19 |
+
"loss": 0.041,
|
20 |
+
"step": 200
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 1.86,
|
24 |
+
"eval_loss": 0.1974974274635315,
|
25 |
+
"eval_runtime": 282.4584,
|
26 |
+
"eval_samples_per_second": 13.57,
|
27 |
+
"eval_steps_per_second": 1.699,
|
28 |
+
"eval_wer": 0.18217074305806918,
|
29 |
+
"step": 250
|
30 |
}
|
31 |
],
|
32 |
+
"max_steps": 1340000,
|
33 |
+
"num_train_epochs": 10000,
|
34 |
+
"total_flos": 5.767164029691619e+18,
|
35 |
"trial_name": null,
|
36 |
"trial_params": null
|
37 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3323
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9846a1507d4ada50dd723a0e61aec8d644c8d60edcf9028dab07630b9a2c14bd
|
3 |
size 3323
|