End of training
Browse files- all_results.json +10 -10
- eval_results.json +6 -6
- runs/Jan28_09-00-35_arjuna/events.out.tfevents.1643356942.arjuna.303241.2 +3 -0
- train_results.json +5 -5
- trainer_state.json +11 -11
all_results.json
CHANGED
@@ -1,14 +1,14 @@
|
|
1 |
{
|
2 |
-
"epoch": 0.
|
3 |
-
"eval_loss":
|
4 |
-
"eval_runtime": 14.
|
5 |
"eval_samples": 301,
|
6 |
-
"eval_samples_per_second": 20.
|
7 |
-
"eval_steps_per_second": 2.
|
8 |
-
"eval_wer": 1.
|
9 |
-
"train_loss":
|
10 |
-
"train_runtime":
|
11 |
"train_samples": 704,
|
12 |
-
"train_samples_per_second": 3.
|
13 |
-
"train_steps_per_second": 1.
|
14 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 0.28,
|
3 |
+
"eval_loss": 135.4674530029297,
|
4 |
+
"eval_runtime": 14.4214,
|
5 |
"eval_samples": 301,
|
6 |
+
"eval_samples_per_second": 20.872,
|
7 |
+
"eval_steps_per_second": 2.635,
|
8 |
+
"eval_wer": 1.0,
|
9 |
+
"train_loss": 79.240166015625,
|
10 |
+
"train_runtime": 50.0456,
|
11 |
"train_samples": 704,
|
12 |
+
"train_samples_per_second": 3.996,
|
13 |
+
"train_steps_per_second": 1.998
|
14 |
}
|
eval_results.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"epoch": 0.
|
3 |
-
"eval_loss":
|
4 |
-
"eval_runtime": 14.
|
5 |
"eval_samples": 301,
|
6 |
-
"eval_samples_per_second": 20.
|
7 |
-
"eval_steps_per_second": 2.
|
8 |
-
"eval_wer": 1.
|
9 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 0.28,
|
3 |
+
"eval_loss": 135.4674530029297,
|
4 |
+
"eval_runtime": 14.4214,
|
5 |
"eval_samples": 301,
|
6 |
+
"eval_samples_per_second": 20.872,
|
7 |
+
"eval_steps_per_second": 2.635,
|
8 |
+
"eval_wer": 1.0
|
9 |
}
|
runs/Jan28_09-00-35_arjuna/events.out.tfevents.1643356942.arjuna.303241.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9305d8984843614ac3e7e32ff352e676707f9a4a777a9a3359c5c0b88caab456
|
3 |
+
size 352
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"epoch": 0.
|
3 |
-
"train_loss":
|
4 |
-
"train_runtime":
|
5 |
"train_samples": 704,
|
6 |
-
"train_samples_per_second": 3.
|
7 |
-
"train_steps_per_second": 1.
|
8 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 0.28,
|
3 |
+
"train_loss": 79.240166015625,
|
4 |
+
"train_runtime": 50.0456,
|
5 |
"train_samples": 704,
|
6 |
+
"train_samples_per_second": 3.996,
|
7 |
+
"train_steps_per_second": 1.998
|
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":
|
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":
|
13 |
-
"total_flos":
|
14 |
-
"train_loss":
|
15 |
-
"train_runtime":
|
16 |
-
"train_samples_per_second": 3.
|
17 |
-
"train_steps_per_second": 1.
|
18 |
}
|
19 |
],
|
20 |
-
"max_steps":
|
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": 0.2840909090909091,
|
5 |
+
"global_step": 100,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
9 |
"log_history": [
|
10 |
{
|
11 |
+
"epoch": 0.28,
|
12 |
+
"step": 100,
|
13 |
+
"total_flos": 3321479416320.0,
|
14 |
+
"train_loss": 79.240166015625,
|
15 |
+
"train_runtime": 50.0456,
|
16 |
+
"train_samples_per_second": 3.996,
|
17 |
+
"train_steps_per_second": 1.998
|
18 |
}
|
19 |
],
|
20 |
+
"max_steps": 100,
|
21 |
"num_train_epochs": 1,
|
22 |
+
"total_flos": 3321479416320.0,
|
23 |
"trial_name": null,
|
24 |
"trial_params": null
|
25 |
}
|