mprzibilla
commited on
Commit
•
33578c6
1
Parent(s):
014e03f
Training in progress, step 38700
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:ab7425f6f20a7e700795a502bde029c251a95fca2aea4432b7393baa13c654e9
|
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 sha256:5f4965a601e3ab51ee0d7f8e7247b30f9ce7dc0c1c09760f0388e9a221dd04cf
|
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 sha256:177e387800ca8cd2666fa4801257038fdf7622da72486457a4106aa98f35648d
|
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 sha256:772e1c2f94d336bf774f1e725393354a53abaa80b5474cd301f1e914f8300325
|
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:b570477637a779a81744c28011e555936fb69b232ffad60a4d749f8dae2e00c3
|
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,
|
@@ -86,11 +86,27 @@
|
|
86 |
"eval_steps_per_second": 3.359,
|
87 |
"eval_wer": 0.9952380952380953,
|
88 |
"step": 32250
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
89 |
}
|
90 |
],
|
91 |
"max_steps": 64500,
|
92 |
"num_train_epochs": 250,
|
93 |
-
"total_flos": 3.
|
94 |
"trial_name": null,
|
95 |
"trial_params": null
|
96 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 150.0,
|
5 |
+
"global_step": 38700,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
86 |
"eval_steps_per_second": 3.359,
|
87 |
"eval_wer": 0.9952380952380953,
|
88 |
"step": 32250
|
89 |
+
},
|
90 |
+
{
|
91 |
+
"epoch": 150.0,
|
92 |
+
"learning_rate": 4.213463892288862e-05,
|
93 |
+
"loss": 2.3529,
|
94 |
+
"step": 38700
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"epoch": 150.0,
|
98 |
+
"eval_cer": 0.8545454545454545,
|
99 |
+
"eval_loss": 2.290559768676758,
|
100 |
+
"eval_runtime": 8.0265,
|
101 |
+
"eval_samples_per_second": 26.163,
|
102 |
+
"eval_steps_per_second": 3.364,
|
103 |
+
"eval_wer": 0.9952380952380953,
|
104 |
+
"step": 38700
|
105 |
}
|
106 |
],
|
107 |
"max_steps": 64500,
|
108 |
"num_train_epochs": 250,
|
109 |
+
"total_flos": 3.720106427628256e+19,
|
110 |
"trial_name": null,
|
111 |
"trial_params": null
|
112 |
}
|
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 sha256:5f4965a601e3ab51ee0d7f8e7247b30f9ce7dc0c1c09760f0388e9a221dd04cf
|
3 |
size 377643361
|