End of training
Browse files- all_results.json +3 -3
- train_results.json +3 -3
- trainer_state.json +8 -8
all_results.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"epoch": 3.0,
|
3 |
"train_loss": 0.0,
|
4 |
-
"train_runtime":
|
5 |
-
"train_samples_per_second":
|
6 |
-
"train_steps_per_second": 2.
|
7 |
}
|
|
|
1 |
{
|
2 |
"epoch": 3.0,
|
3 |
"train_loss": 0.0,
|
4 |
+
"train_runtime": 161.546,
|
5 |
+
"train_samples_per_second": 185.706,
|
6 |
+
"train_steps_per_second": 2.916
|
7 |
}
|
train_results.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"epoch": 3.0,
|
3 |
"train_loss": 0.0,
|
4 |
-
"train_runtime":
|
5 |
-
"train_samples_per_second":
|
6 |
-
"train_steps_per_second": 2.
|
7 |
}
|
|
|
1 |
{
|
2 |
"epoch": 3.0,
|
3 |
"train_loss": 0.0,
|
4 |
+
"train_runtime": 161.546,
|
5 |
+
"train_samples_per_second": 185.706,
|
6 |
+
"train_steps_per_second": 2.916
|
7 |
}
|
trainer_state.json
CHANGED
@@ -2,24 +2,24 @@
|
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
"epoch": 3.0,
|
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": 3.0,
|
12 |
-
"step":
|
13 |
-
"total_flos":
|
14 |
"train_loss": 0.0,
|
15 |
-
"train_runtime":
|
16 |
-
"train_samples_per_second":
|
17 |
-
"train_steps_per_second": 2.
|
18 |
}
|
19 |
],
|
20 |
-
"max_steps":
|
21 |
"num_train_epochs": 3,
|
22 |
-
"total_flos":
|
23 |
"trial_name": null,
|
24 |
"trial_params": null
|
25 |
}
|
|
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
"epoch": 3.0,
|
5 |
+
"global_step": 471,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
9 |
"log_history": [
|
10 |
{
|
11 |
"epoch": 3.0,
|
12 |
+
"step": 471,
|
13 |
+
"total_flos": 4005518400000000.0,
|
14 |
"train_loss": 0.0,
|
15 |
+
"train_runtime": 161.546,
|
16 |
+
"train_samples_per_second": 185.706,
|
17 |
+
"train_steps_per_second": 2.916
|
18 |
}
|
19 |
],
|
20 |
+
"max_steps": 471,
|
21 |
"num_train_epochs": 3,
|
22 |
+
"total_flos": 4005518400000000.0,
|
23 |
"trial_name": null,
|
24 |
"trial_params": null
|
25 |
}
|