End of training
Browse files- all_results.json +4 -4
- train_results.json +4 -4
- trainer_state.json +9 -0
all_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 500.0,
|
3 |
-
"train_loss":
|
4 |
-
"train_runtime":
|
5 |
"train_samples": 100,
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second":
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 500.0,
|
3 |
+
"train_loss": 0.0,
|
4 |
+
"train_runtime": 1.3574,
|
5 |
"train_samples": 100,
|
6 |
+
"train_samples_per_second": 36834.222,
|
7 |
+
"train_steps_per_second": 4788.449
|
8 |
}
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 500.0,
|
3 |
-
"train_loss":
|
4 |
-
"train_runtime":
|
5 |
"train_samples": 100,
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second":
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 500.0,
|
3 |
+
"train_loss": 0.0,
|
4 |
+
"train_runtime": 1.3574,
|
5 |
"train_samples": 100,
|
6 |
+
"train_samples_per_second": 36834.222,
|
7 |
+
"train_steps_per_second": 4788.449
|
8 |
}
|
trainer_state.json
CHANGED
@@ -3016,6 +3016,15 @@
|
|
3016 |
"train_runtime": 71445.8185,
|
3017 |
"train_samples_per_second": 0.7,
|
3018 |
"train_steps_per_second": 0.091
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3019 |
}
|
3020 |
],
|
3021 |
"logging_steps": 500,
|
|
|
3016 |
"train_runtime": 71445.8185,
|
3017 |
"train_samples_per_second": 0.7,
|
3018 |
"train_steps_per_second": 0.091
|
3019 |
+
},
|
3020 |
+
{
|
3021 |
+
"epoch": 500.0,
|
3022 |
+
"step": 6500,
|
3023 |
+
"total_flos": 284798065115136.0,
|
3024 |
+
"train_loss": 0.0,
|
3025 |
+
"train_runtime": 1.3574,
|
3026 |
+
"train_samples_per_second": 36834.222,
|
3027 |
+
"train_steps_per_second": 4788.449
|
3028 |
}
|
3029 |
],
|
3030 |
"logging_steps": 500,
|