Upload failed/desync0/mlp/byte4/results.json with huggingface_hub
Browse files
failed/desync0/mlp/byte4/results.json
CHANGED
|
@@ -8,15 +8,15 @@
|
|
| 8 |
"epochs": 200,
|
| 9 |
"batch_size": 100,
|
| 10 |
"learning_rate": 1e-05,
|
| 11 |
-
"train_time_seconds":
|
| 12 |
-
"final_train_loss": 5.
|
| 13 |
-
"final_train_accuracy": 0.
|
| 14 |
-
"final_val_loss": 5.
|
| 15 |
"final_val_accuracy": 0.004399999976158142,
|
| 16 |
-
"post_train_pre_rank":
|
| 17 |
-
"post_train_final_rank":
|
| 18 |
-
"post_train_min_rank":
|
| 19 |
-
"post_train_max_rank":
|
| 20 |
-
"post_train_rank_at_500":
|
| 21 |
-
"post_train_rank_at_1000":
|
| 22 |
}
|
|
|
|
| 8 |
"epochs": 200,
|
| 9 |
"batch_size": 100,
|
| 10 |
"learning_rate": 1e-05,
|
| 11 |
+
"train_time_seconds": 158.74,
|
| 12 |
+
"final_train_loss": 5.440587043762207,
|
| 13 |
+
"final_train_accuracy": 0.013220000080764294,
|
| 14 |
+
"final_val_loss": 5.586010932922363,
|
| 15 |
"final_val_accuracy": 0.004399999976158142,
|
| 16 |
+
"post_train_pre_rank": 252,
|
| 17 |
+
"post_train_final_rank": 7,
|
| 18 |
+
"post_train_min_rank": 4,
|
| 19 |
+
"post_train_max_rank": 254,
|
| 20 |
+
"post_train_rank_at_500": 48,
|
| 21 |
+
"post_train_rank_at_1000": 10
|
| 22 |
}
|