mprzibilla
commited on
Commit
•
66a8126
1
Parent(s):
33578c6
Training in progress, step 45150
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 sha256:6a282c0200e7b8a1c3b5c6930e9dce5dd11d7ac736b9d720d119a96a4e37feba
|
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 sha256:2d65b6875465be54fce3a279579d1be1b01eacd035b3cdc1f6d7372c91c01017
|
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 sha256:146dac9c9637909a97e15ede3b1f1bcab1c72a6e91e02625276a9765be39ad4f
|
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 sha256:55bdb1c6b06f4ff77e1a0ecf5486d4e7ebe7f029f3ba994f73e42a11135cff0a
|
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 sha256:495e200a8d019989c9b27dca17a6724fc07c34bcfc789dff4b01e40c466f4f02
|
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,
|
@@ -102,11 +102,27 @@
|
|
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":
|
110 |
"trial_name": null,
|
111 |
"trial_params": null
|
112 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 175.0,
|
5 |
+
"global_step": 45150,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
102 |
"eval_steps_per_second": 3.364,
|
103 |
"eval_wer": 0.9952380952380953,
|
104 |
"step": 38700
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 175.0,
|
108 |
+
"learning_rate": 3.161158710730314e-05,
|
109 |
+
"loss": 2.3158,
|
110 |
+
"step": 45150
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 175.0,
|
114 |
+
"eval_cer": 0.8363636363636363,
|
115 |
+
"eval_loss": 2.258056402206421,
|
116 |
+
"eval_runtime": 8.0276,
|
117 |
+
"eval_samples_per_second": 26.16,
|
118 |
+
"eval_steps_per_second": 3.363,
|
119 |
+
"eval_wer": 0.9952380952380953,
|
120 |
+
"step": 45150
|
121 |
}
|
122 |
],
|
123 |
"max_steps": 64500,
|
124 |
"num_train_epochs": 250,
|
125 |
+
"total_flos": 4.340159188761437e+19,
|
126 |
"trial_name": null,
|
127 |
"trial_params": null
|
128 |
}
|
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 sha256:2d65b6875465be54fce3a279579d1be1b01eacd035b3cdc1f6d7372c91c01017
|
3 |
size 377643361
|