Upload python KD Optuna tinyBERT checkpoint
Browse files
checkpoints/python/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 57415564
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5bb5c3d87c778c811f0e7da05c17483b86e03eddcfa8104feb4b0e93346a2806
|
| 3 |
size 57415564
|
checkpoints/python/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5969
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:db7e6b236f5185b75afc737584248eb3e43845bf97ee441321a5bcb38644f585
|
| 3 |
size 5969
|
checkpoints/python/trial_config.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
-
"lr":
|
| 3 |
-
"batch_size":
|
| 4 |
-
"epochs":
|
| 5 |
-
"temperature":
|
| 6 |
-
"lambda_hard": 0.
|
| 7 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"lr": 4.390509337305972e-05,
|
| 3 |
+
"batch_size": 16,
|
| 4 |
+
"epochs": 38,
|
| 5 |
+
"temperature": 6.956155158782649,
|
| 6 |
+
"lambda_hard": 0.3375414239502486
|
| 7 |
}
|
checkpoints/python/trial_metrics.json
CHANGED
|
@@ -1,23 +1,23 @@
|
|
| 1 |
{
|
| 2 |
-
"eval_loss":
|
| 3 |
-
"eval_macro_f1": 0.
|
| 4 |
-
"eval_micro_f1": 0.
|
| 5 |
-
"eval_macro_precision": 0.
|
| 6 |
-
"eval_macro_recall": 0.
|
| 7 |
"eval_thresholds": {
|
| 8 |
-
"Usage": 0.
|
| 9 |
-
"Parameters": 0.
|
| 10 |
-
"DevelopmentNotes": 0.
|
| 11 |
-
"Expand": 0.
|
| 12 |
-
"Summary": 0.
|
| 13 |
},
|
| 14 |
-
"eval_f1_Usage": 0.
|
| 15 |
-
"eval_f1_Parameters": 0.
|
| 16 |
-
"eval_f1_DevelopmentNotes": 0.
|
| 17 |
-
"eval_f1_Expand": 0.
|
| 18 |
-
"eval_f1_Summary": 0.
|
| 19 |
-
"eval_runtime": 0.
|
| 20 |
-
"eval_samples_per_second":
|
| 21 |
-
"eval_steps_per_second":
|
| 22 |
-
"epoch":
|
| 23 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"eval_loss": 22.410816192626953,
|
| 3 |
+
"eval_macro_f1": 0.6085962730208606,
|
| 4 |
+
"eval_micro_f1": 0.6426512968299711,
|
| 5 |
+
"eval_macro_precision": 0.569728879948058,
|
| 6 |
+
"eval_macro_recall": 0.668913077841477,
|
| 7 |
"eval_thresholds": {
|
| 8 |
+
"Usage": 0.4,
|
| 9 |
+
"Parameters": 0.4800000000000001,
|
| 10 |
+
"DevelopmentNotes": 0.4,
|
| 11 |
+
"Expand": 0.42000000000000004,
|
| 12 |
+
"Summary": 0.4
|
| 13 |
},
|
| 14 |
+
"eval_f1_Usage": 0.7789473684210526,
|
| 15 |
+
"eval_f1_Parameters": 0.7375,
|
| 16 |
+
"eval_f1_DevelopmentNotes": 0.40476190476190477,
|
| 17 |
+
"eval_f1_Expand": 0.5396825396825397,
|
| 18 |
+
"eval_f1_Summary": 0.582089552238806,
|
| 19 |
+
"eval_runtime": 0.2417,
|
| 20 |
+
"eval_samples_per_second": 1199.64,
|
| 21 |
+
"eval_steps_per_second": 78.597,
|
| 22 |
+
"epoch": 38.0
|
| 23 |
}
|