End of training
Browse files- all_results.json +10 -10
- eval_results.json +6 -6
- pytorch_model.bin +1 -1
- train_results.json +5 -5
- trainer_state.json +8 -8
all_results.json
CHANGED
@@ -1,14 +1,14 @@
|
|
1 |
{
|
2 |
-
"epoch": 0.
|
3 |
-
"eval_loss":
|
4 |
-
"eval_runtime":
|
5 |
"eval_samples": 301,
|
6 |
-
"eval_samples_per_second":
|
7 |
-
"eval_steps_per_second":
|
8 |
-
"eval_wer": 1.
|
9 |
-
"train_loss": 94.
|
10 |
-
"train_runtime":
|
11 |
"train_samples": 704,
|
12 |
-
"train_samples_per_second":
|
13 |
-
"train_steps_per_second":
|
14 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 0.03,
|
3 |
+
"eval_loss": 156.87892150878906,
|
4 |
+
"eval_runtime": 10.5213,
|
5 |
"eval_samples": 301,
|
6 |
+
"eval_samples_per_second": 28.609,
|
7 |
+
"eval_steps_per_second": 3.612,
|
8 |
+
"eval_wer": 1.3456221198156681,
|
9 |
+
"train_loss": 94.46571044921875,
|
10 |
+
"train_runtime": 5.7606,
|
11 |
"train_samples": 704,
|
12 |
+
"train_samples_per_second": 3.472,
|
13 |
+
"train_steps_per_second": 1.736
|
14 |
}
|
eval_results.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"epoch": 0.
|
3 |
-
"eval_loss":
|
4 |
-
"eval_runtime":
|
5 |
"eval_samples": 301,
|
6 |
-
"eval_samples_per_second":
|
7 |
-
"eval_steps_per_second":
|
8 |
-
"eval_wer": 1.
|
9 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 0.03,
|
3 |
+
"eval_loss": 156.87892150878906,
|
4 |
+
"eval_runtime": 10.5213,
|
5 |
"eval_samples": 301,
|
6 |
+
"eval_samples_per_second": 28.609,
|
7 |
+
"eval_steps_per_second": 3.612,
|
8 |
+
"eval_wer": 1.3456221198156681
|
9 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 143910
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c05ccd9c78fff4448048e975808d4cbfffb9ed1ab3bc22e2e95576f44e950c5d
|
3 |
size 143910
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"epoch": 0.
|
3 |
-
"train_loss": 94.
|
4 |
-
"train_runtime":
|
5 |
"train_samples": 704,
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second":
|
8 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 0.03,
|
3 |
+
"train_loss": 94.46571044921875,
|
4 |
+
"train_runtime": 5.7606,
|
5 |
"train_samples": 704,
|
6 |
+
"train_samples_per_second": 3.472,
|
7 |
+
"train_steps_per_second": 1.736
|
8 |
}
|
trainer_state.json
CHANGED
@@ -1,25 +1,25 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
"global_step": 10,
|
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 |
"step": 10,
|
13 |
-
"total_flos":
|
14 |
-
"train_loss": 94.
|
15 |
-
"train_runtime":
|
16 |
-
"train_samples_per_second":
|
17 |
-
"train_steps_per_second":
|
18 |
}
|
19 |
],
|
20 |
"max_steps": 10,
|
21 |
"num_train_epochs": 1,
|
22 |
-
"total_flos":
|
23 |
"trial_name": null,
|
24 |
"trial_params": null
|
25 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.028409090909090908,
|
5 |
"global_step": 10,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
9 |
"log_history": [
|
10 |
{
|
11 |
+
"epoch": 0.03,
|
12 |
"step": 10,
|
13 |
+
"total_flos": 508182128640.0,
|
14 |
+
"train_loss": 94.46571044921875,
|
15 |
+
"train_runtime": 5.7606,
|
16 |
+
"train_samples_per_second": 3.472,
|
17 |
+
"train_steps_per_second": 1.736
|
18 |
}
|
19 |
],
|
20 |
"max_steps": 10,
|
21 |
"num_train_epochs": 1,
|
22 |
+
"total_flos": 508182128640.0,
|
23 |
"trial_name": null,
|
24 |
"trial_params": null
|
25 |
}
|