🍻 cheers
Browse files- all_results.json +10 -10
- test_results.json +8 -0
- train_results.json +5 -5
- trainer_state.json +0 -0
all_results.json
CHANGED
|
@@ -1,13 +1,13 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 2.0,
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime":
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second":
|
| 8 |
-
"total_flos":
|
| 9 |
-
"train_loss": 0.
|
| 10 |
-
"train_runtime":
|
| 11 |
-
"train_samples_per_second":
|
| 12 |
-
"train_steps_per_second": 1.
|
| 13 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 2.0,
|
| 3 |
+
"eval_accuracy": 0.991131153701616,
|
| 4 |
+
"eval_loss": 0.021174494177103043,
|
| 5 |
+
"eval_runtime": 243.8019,
|
| 6 |
+
"eval_samples_per_second": 54.573,
|
| 7 |
+
"eval_steps_per_second": 6.825,
|
| 8 |
+
"total_flos": 7.422802701202538e+18,
|
| 9 |
+
"train_loss": 0.06747758854398318,
|
| 10 |
+
"train_runtime": 4227.9196,
|
| 11 |
+
"train_samples_per_second": 22.656,
|
| 12 |
+
"train_steps_per_second": 1.416
|
| 13 |
}
|
test_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"eval_accuracy": 0.991131153701616,
|
| 4 |
+
"eval_loss": 0.021174494177103043,
|
| 5 |
+
"eval_runtime": 243.8019,
|
| 6 |
+
"eval_samples_per_second": 54.573,
|
| 7 |
+
"eval_steps_per_second": 6.825
|
| 8 |
+
}
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 2.0,
|
| 3 |
-
"total_flos":
|
| 4 |
-
"train_loss": 0.
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 1.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 2.0,
|
| 3 |
+
"total_flos": 7.422802701202538e+18,
|
| 4 |
+
"train_loss": 0.06747758854398318,
|
| 5 |
+
"train_runtime": 4227.9196,
|
| 6 |
+
"train_samples_per_second": 22.656,
|
| 7 |
+
"train_steps_per_second": 1.416
|
| 8 |
}
|
trainer_state.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|