mprzibilla
commited on
Commit
•
39a1eef
1
Parent(s):
8a52de7
Training in progress, step 19350
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 sha256:566f97faa13e78969b8a2cfbb6031a33414cf8a10669c8e82027ec1d49a66f5b
|
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:d9d4ff37307ed9106891785166662989d83845de6509dc8371114f483d7e622c
|
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 sha256:1016b430b290557621459e70bf9820167548c2be65b6b430a0f1a32eff5d81cb
|
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 sha256:20d02d738fc2a16f378fb88a1ec287c7b07fdab31e3b1a0a574d7f3ca005de8c
|
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 sha256:9a4159041c25f1427151eb10e096ed5f474792ac744e48c48459cfcf9c3cb735
|
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,
|
@@ -38,11 +38,27 @@
|
|
38 |
"eval_steps_per_second": 3.382,
|
39 |
"eval_wer": 1.0,
|
40 |
"step": 12900
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
41 |
}
|
42 |
],
|
43 |
"max_steps": 64500,
|
44 |
"num_train_epochs": 250,
|
45 |
-
"total_flos": 1.
|
46 |
"trial_name": null,
|
47 |
"trial_params": null
|
48 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 75.0,
|
5 |
+
"global_step": 19350,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
38 |
"eval_steps_per_second": 3.382,
|
39 |
"eval_wer": 1.0,
|
40 |
"step": 12900
|
41 |
+
},
|
42 |
+
{
|
43 |
+
"epoch": 75.0,
|
44 |
+
"learning_rate": 7.370216238270095e-05,
|
45 |
+
"loss": 2.8102,
|
46 |
+
"step": 19350
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"epoch": 75.0,
|
50 |
+
"eval_cer": 0.9298701298701298,
|
51 |
+
"eval_loss": 2.55711030960083,
|
52 |
+
"eval_runtime": 8.1516,
|
53 |
+
"eval_samples_per_second": 25.762,
|
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": 1.859384111433596e+19,
|
62 |
"trial_name": null,
|
63 |
"trial_params": null
|
64 |
}
|
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:d9d4ff37307ed9106891785166662989d83845de6509dc8371114f483d7e622c
|
3 |
size 377643361
|