End of training
Browse files
all_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 59.01,
|
3 |
+
"eval_accuracy": 0.8148148148148148,
|
4 |
+
"eval_loss": 0.5676685571670532,
|
5 |
+
"eval_runtime": 292.9189,
|
6 |
+
"eval_samples_per_second": 0.737,
|
7 |
+
"eval_steps_per_second": 0.092
|
8 |
+
}
|
runs/Jan01_13-03-48_DESKTOP-M04OTBM/events.out.tfevents.1704154807.DESKTOP-M04OTBM.12612.5
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:babd1a4a4d2ffd066a74e9a0816674c95d25c7fc7833f80414711bfb8fe4b8f1
|
3 |
+
size 734
|
test_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 59.01,
|
3 |
+
"eval_accuracy": 0.8148148148148148,
|
4 |
+
"eval_loss": 0.5676685571670532,
|
5 |
+
"eval_runtime": 292.9189,
|
6 |
+
"eval_samples_per_second": 0.737,
|
7 |
+
"eval_steps_per_second": 0.092
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,2692 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.8387096774193549,
|
3 |
+
"best_model_checkpoint": "videomae-base-finetuned-ucf101-subset-finetuned-subset\\checkpoint-2655",
|
4 |
+
"epoch": 59.00826210826211,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 3510,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0,
|
13 |
+
"learning_rate": 1.4245014245014246e-06,
|
14 |
+
"loss": 1.5791,
|
15 |
+
"step": 10
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.01,
|
19 |
+
"learning_rate": 2.8490028490028492e-06,
|
20 |
+
"loss": 1.6248,
|
21 |
+
"step": 20
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.01,
|
25 |
+
"learning_rate": 4.273504273504274e-06,
|
26 |
+
"loss": 1.6509,
|
27 |
+
"step": 30
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.01,
|
31 |
+
"learning_rate": 5.6980056980056985e-06,
|
32 |
+
"loss": 1.6033,
|
33 |
+
"step": 40
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.01,
|
37 |
+
"learning_rate": 7.122507122507123e-06,
|
38 |
+
"loss": 1.58,
|
39 |
+
"step": 50
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.02,
|
43 |
+
"eval_accuracy": 0.37327188940092165,
|
44 |
+
"eval_loss": 1.5475504398345947,
|
45 |
+
"eval_runtime": 280.9942,
|
46 |
+
"eval_samples_per_second": 0.772,
|
47 |
+
"eval_steps_per_second": 0.1,
|
48 |
+
"step": 59
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 1.0,
|
52 |
+
"learning_rate": 8.547008547008548e-06,
|
53 |
+
"loss": 1.5857,
|
54 |
+
"step": 60
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 1.0,
|
58 |
+
"learning_rate": 9.971509971509972e-06,
|
59 |
+
"loss": 1.5372,
|
60 |
+
"step": 70
|
61 |
+
},
|
62 |
+
{
|
63 |
+
"epoch": 1.01,
|
64 |
+
"learning_rate": 1.1396011396011397e-05,
|
65 |
+
"loss": 1.4931,
|
66 |
+
"step": 80
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 1.01,
|
70 |
+
"learning_rate": 1.282051282051282e-05,
|
71 |
+
"loss": 1.6021,
|
72 |
+
"step": 90
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 1.01,
|
76 |
+
"learning_rate": 1.4245014245014246e-05,
|
77 |
+
"loss": 1.5149,
|
78 |
+
"step": 100
|
79 |
+
},
|
80 |
+
{
|
81 |
+
"epoch": 1.01,
|
82 |
+
"learning_rate": 1.566951566951567e-05,
|
83 |
+
"loss": 1.3617,
|
84 |
+
"step": 110
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 1.02,
|
88 |
+
"eval_accuracy": 0.4976958525345622,
|
89 |
+
"eval_loss": 1.2123247385025024,
|
90 |
+
"eval_runtime": 282.6781,
|
91 |
+
"eval_samples_per_second": 0.768,
|
92 |
+
"eval_steps_per_second": 0.099,
|
93 |
+
"step": 118
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 2.0,
|
97 |
+
"learning_rate": 1.7094017094017095e-05,
|
98 |
+
"loss": 1.345,
|
99 |
+
"step": 120
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 2.0,
|
103 |
+
"learning_rate": 1.8518518518518518e-05,
|
104 |
+
"loss": 1.4019,
|
105 |
+
"step": 130
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 2.01,
|
109 |
+
"learning_rate": 1.9943019943019945e-05,
|
110 |
+
"loss": 1.2799,
|
111 |
+
"step": 140
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 2.01,
|
115 |
+
"learning_rate": 2.1367521367521368e-05,
|
116 |
+
"loss": 1.2003,
|
117 |
+
"step": 150
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 2.01,
|
121 |
+
"learning_rate": 2.2792022792022794e-05,
|
122 |
+
"loss": 1.1992,
|
123 |
+
"step": 160
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 2.01,
|
127 |
+
"learning_rate": 2.4216524216524217e-05,
|
128 |
+
"loss": 1.1668,
|
129 |
+
"step": 170
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 2.02,
|
133 |
+
"eval_accuracy": 0.3824884792626728,
|
134 |
+
"eval_loss": 1.3331272602081299,
|
135 |
+
"eval_runtime": 283.1967,
|
136 |
+
"eval_samples_per_second": 0.766,
|
137 |
+
"eval_steps_per_second": 0.099,
|
138 |
+
"step": 177
|
139 |
+
},
|
140 |
+
{
|
141 |
+
"epoch": 3.0,
|
142 |
+
"learning_rate": 2.564102564102564e-05,
|
143 |
+
"loss": 1.5354,
|
144 |
+
"step": 180
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 3.0,
|
148 |
+
"learning_rate": 2.706552706552707e-05,
|
149 |
+
"loss": 1.2036,
|
150 |
+
"step": 190
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 3.01,
|
154 |
+
"learning_rate": 2.8490028490028492e-05,
|
155 |
+
"loss": 1.252,
|
156 |
+
"step": 200
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 3.01,
|
160 |
+
"learning_rate": 2.9914529914529915e-05,
|
161 |
+
"loss": 1.1877,
|
162 |
+
"step": 210
|
163 |
+
},
|
164 |
+
{
|
165 |
+
"epoch": 3.01,
|
166 |
+
"learning_rate": 3.133903133903134e-05,
|
167 |
+
"loss": 1.3834,
|
168 |
+
"step": 220
|
169 |
+
},
|
170 |
+
{
|
171 |
+
"epoch": 3.02,
|
172 |
+
"learning_rate": 3.2763532763532764e-05,
|
173 |
+
"loss": 1.1751,
|
174 |
+
"step": 230
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 3.02,
|
178 |
+
"eval_accuracy": 0.3686635944700461,
|
179 |
+
"eval_loss": 1.2529356479644775,
|
180 |
+
"eval_runtime": 303.7124,
|
181 |
+
"eval_samples_per_second": 0.714,
|
182 |
+
"eval_steps_per_second": 0.092,
|
183 |
+
"step": 236
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 4.0,
|
187 |
+
"learning_rate": 3.418803418803419e-05,
|
188 |
+
"loss": 1.1436,
|
189 |
+
"step": 240
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 4.0,
|
193 |
+
"learning_rate": 3.561253561253561e-05,
|
194 |
+
"loss": 1.2635,
|
195 |
+
"step": 250
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 4.01,
|
199 |
+
"learning_rate": 3.7037037037037037e-05,
|
200 |
+
"loss": 1.2653,
|
201 |
+
"step": 260
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 4.01,
|
205 |
+
"learning_rate": 3.846153846153846e-05,
|
206 |
+
"loss": 1.2505,
|
207 |
+
"step": 270
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 4.01,
|
211 |
+
"learning_rate": 3.988603988603989e-05,
|
212 |
+
"loss": 1.1114,
|
213 |
+
"step": 280
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 4.02,
|
217 |
+
"learning_rate": 4.131054131054131e-05,
|
218 |
+
"loss": 0.9961,
|
219 |
+
"step": 290
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 4.02,
|
223 |
+
"eval_accuracy": 0.6451612903225806,
|
224 |
+
"eval_loss": 1.0007940530776978,
|
225 |
+
"eval_runtime": 291.2333,
|
226 |
+
"eval_samples_per_second": 0.745,
|
227 |
+
"eval_steps_per_second": 0.096,
|
228 |
+
"step": 295
|
229 |
+
},
|
230 |
+
{
|
231 |
+
"epoch": 5.0,
|
232 |
+
"learning_rate": 4.2735042735042735e-05,
|
233 |
+
"loss": 1.1199,
|
234 |
+
"step": 300
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 5.0,
|
238 |
+
"learning_rate": 4.415954415954416e-05,
|
239 |
+
"loss": 1.0766,
|
240 |
+
"step": 310
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 5.01,
|
244 |
+
"learning_rate": 4.558404558404559e-05,
|
245 |
+
"loss": 1.1833,
|
246 |
+
"step": 320
|
247 |
+
},
|
248 |
+
{
|
249 |
+
"epoch": 5.01,
|
250 |
+
"learning_rate": 4.700854700854701e-05,
|
251 |
+
"loss": 1.2997,
|
252 |
+
"step": 330
|
253 |
+
},
|
254 |
+
{
|
255 |
+
"epoch": 5.01,
|
256 |
+
"learning_rate": 4.8433048433048433e-05,
|
257 |
+
"loss": 1.1507,
|
258 |
+
"step": 340
|
259 |
+
},
|
260 |
+
{
|
261 |
+
"epoch": 5.02,
|
262 |
+
"learning_rate": 4.985754985754986e-05,
|
263 |
+
"loss": 1.0562,
|
264 |
+
"step": 350
|
265 |
+
},
|
266 |
+
{
|
267 |
+
"epoch": 5.02,
|
268 |
+
"eval_accuracy": 0.5391705069124424,
|
269 |
+
"eval_loss": 1.0534659624099731,
|
270 |
+
"eval_runtime": 288.9126,
|
271 |
+
"eval_samples_per_second": 0.751,
|
272 |
+
"eval_steps_per_second": 0.097,
|
273 |
+
"step": 354
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"epoch": 6.0,
|
277 |
+
"learning_rate": 4.985754985754986e-05,
|
278 |
+
"loss": 1.1336,
|
279 |
+
"step": 360
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 6.0,
|
283 |
+
"learning_rate": 4.9699271921494144e-05,
|
284 |
+
"loss": 1.192,
|
285 |
+
"step": 370
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"epoch": 6.01,
|
289 |
+
"learning_rate": 4.9540993985438435e-05,
|
290 |
+
"loss": 1.1785,
|
291 |
+
"step": 380
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 6.01,
|
295 |
+
"learning_rate": 4.938271604938271e-05,
|
296 |
+
"loss": 1.2818,
|
297 |
+
"step": 390
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 6.01,
|
301 |
+
"learning_rate": 4.9224438113327004e-05,
|
302 |
+
"loss": 1.179,
|
303 |
+
"step": 400
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 6.02,
|
307 |
+
"learning_rate": 4.906616017727129e-05,
|
308 |
+
"loss": 1.0189,
|
309 |
+
"step": 410
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 6.02,
|
313 |
+
"eval_accuracy": 0.6866359447004609,
|
314 |
+
"eval_loss": 0.9321132302284241,
|
315 |
+
"eval_runtime": 300.2588,
|
316 |
+
"eval_samples_per_second": 0.723,
|
317 |
+
"eval_steps_per_second": 0.093,
|
318 |
+
"step": 413
|
319 |
+
},
|
320 |
+
{
|
321 |
+
"epoch": 7.0,
|
322 |
+
"learning_rate": 4.890788224121557e-05,
|
323 |
+
"loss": 1.178,
|
324 |
+
"step": 420
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 7.0,
|
328 |
+
"learning_rate": 4.8749604305159865e-05,
|
329 |
+
"loss": 1.0559,
|
330 |
+
"step": 430
|
331 |
+
},
|
332 |
+
{
|
333 |
+
"epoch": 7.01,
|
334 |
+
"learning_rate": 4.859132636910415e-05,
|
335 |
+
"loss": 1.3566,
|
336 |
+
"step": 440
|
337 |
+
},
|
338 |
+
{
|
339 |
+
"epoch": 7.01,
|
340 |
+
"learning_rate": 4.8433048433048433e-05,
|
341 |
+
"loss": 1.2278,
|
342 |
+
"step": 450
|
343 |
+
},
|
344 |
+
{
|
345 |
+
"epoch": 7.01,
|
346 |
+
"learning_rate": 4.8274770496992725e-05,
|
347 |
+
"loss": 1.1068,
|
348 |
+
"step": 460
|
349 |
+
},
|
350 |
+
{
|
351 |
+
"epoch": 7.02,
|
352 |
+
"learning_rate": 4.811649256093701e-05,
|
353 |
+
"loss": 0.8553,
|
354 |
+
"step": 470
|
355 |
+
},
|
356 |
+
{
|
357 |
+
"epoch": 7.02,
|
358 |
+
"eval_accuracy": 0.5852534562211982,
|
359 |
+
"eval_loss": 0.895534098148346,
|
360 |
+
"eval_runtime": 301.0743,
|
361 |
+
"eval_samples_per_second": 0.721,
|
362 |
+
"eval_steps_per_second": 0.093,
|
363 |
+
"step": 472
|
364 |
+
},
|
365 |
+
{
|
366 |
+
"epoch": 8.0,
|
367 |
+
"learning_rate": 4.7958214624881294e-05,
|
368 |
+
"loss": 0.8541,
|
369 |
+
"step": 480
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 8.01,
|
373 |
+
"learning_rate": 4.779993668882558e-05,
|
374 |
+
"loss": 1.1329,
|
375 |
+
"step": 490
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 8.01,
|
379 |
+
"learning_rate": 4.764165875276987e-05,
|
380 |
+
"loss": 1.1688,
|
381 |
+
"step": 500
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 8.01,
|
385 |
+
"learning_rate": 4.7483380816714154e-05,
|
386 |
+
"loss": 0.8642,
|
387 |
+
"step": 510
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 8.01,
|
391 |
+
"learning_rate": 4.732510288065844e-05,
|
392 |
+
"loss": 0.9557,
|
393 |
+
"step": 520
|
394 |
+
},
|
395 |
+
{
|
396 |
+
"epoch": 8.02,
|
397 |
+
"learning_rate": 4.716682494460272e-05,
|
398 |
+
"loss": 0.8961,
|
399 |
+
"step": 530
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 8.02,
|
403 |
+
"eval_accuracy": 0.7419354838709677,
|
404 |
+
"eval_loss": 0.7889271974563599,
|
405 |
+
"eval_runtime": 301.0199,
|
406 |
+
"eval_samples_per_second": 0.721,
|
407 |
+
"eval_steps_per_second": 0.093,
|
408 |
+
"step": 531
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 9.0,
|
412 |
+
"learning_rate": 4.700854700854701e-05,
|
413 |
+
"loss": 1.1113,
|
414 |
+
"step": 540
|
415 |
+
},
|
416 |
+
{
|
417 |
+
"epoch": 9.01,
|
418 |
+
"learning_rate": 4.68502690724913e-05,
|
419 |
+
"loss": 1.0851,
|
420 |
+
"step": 550
|
421 |
+
},
|
422 |
+
{
|
423 |
+
"epoch": 9.01,
|
424 |
+
"learning_rate": 4.669199113643558e-05,
|
425 |
+
"loss": 1.0467,
|
426 |
+
"step": 560
|
427 |
+
},
|
428 |
+
{
|
429 |
+
"epoch": 9.01,
|
430 |
+
"learning_rate": 4.653371320037987e-05,
|
431 |
+
"loss": 0.8215,
|
432 |
+
"step": 570
|
433 |
+
},
|
434 |
+
{
|
435 |
+
"epoch": 9.01,
|
436 |
+
"learning_rate": 4.637543526432416e-05,
|
437 |
+
"loss": 0.9789,
|
438 |
+
"step": 580
|
439 |
+
},
|
440 |
+
{
|
441 |
+
"epoch": 9.02,
|
442 |
+
"learning_rate": 4.621715732826844e-05,
|
443 |
+
"loss": 1.1626,
|
444 |
+
"step": 590
|
445 |
+
},
|
446 |
+
{
|
447 |
+
"epoch": 9.02,
|
448 |
+
"eval_accuracy": 0.6175115207373272,
|
449 |
+
"eval_loss": 0.95318603515625,
|
450 |
+
"eval_runtime": 305.3217,
|
451 |
+
"eval_samples_per_second": 0.711,
|
452 |
+
"eval_steps_per_second": 0.092,
|
453 |
+
"step": 590
|
454 |
+
},
|
455 |
+
{
|
456 |
+
"epoch": 10.0,
|
457 |
+
"learning_rate": 4.605887939221273e-05,
|
458 |
+
"loss": 0.8144,
|
459 |
+
"step": 600
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 10.01,
|
463 |
+
"learning_rate": 4.590060145615702e-05,
|
464 |
+
"loss": 0.7724,
|
465 |
+
"step": 610
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 10.01,
|
469 |
+
"learning_rate": 4.5742323520101296e-05,
|
470 |
+
"loss": 1.088,
|
471 |
+
"step": 620
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 10.01,
|
475 |
+
"learning_rate": 4.558404558404559e-05,
|
476 |
+
"loss": 1.074,
|
477 |
+
"step": 630
|
478 |
+
},
|
479 |
+
{
|
480 |
+
"epoch": 10.01,
|
481 |
+
"learning_rate": 4.542576764798987e-05,
|
482 |
+
"loss": 0.7951,
|
483 |
+
"step": 640
|
484 |
+
},
|
485 |
+
{
|
486 |
+
"epoch": 10.02,
|
487 |
+
"eval_accuracy": 0.5529953917050692,
|
488 |
+
"eval_loss": 1.1165187358856201,
|
489 |
+
"eval_runtime": 303.3614,
|
490 |
+
"eval_samples_per_second": 0.715,
|
491 |
+
"eval_steps_per_second": 0.092,
|
492 |
+
"step": 649
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 11.0,
|
496 |
+
"learning_rate": 4.5267489711934157e-05,
|
497 |
+
"loss": 0.8376,
|
498 |
+
"step": 650
|
499 |
+
},
|
500 |
+
{
|
501 |
+
"epoch": 11.0,
|
502 |
+
"learning_rate": 4.510921177587845e-05,
|
503 |
+
"loss": 0.9325,
|
504 |
+
"step": 660
|
505 |
+
},
|
506 |
+
{
|
507 |
+
"epoch": 11.01,
|
508 |
+
"learning_rate": 4.4950933839822725e-05,
|
509 |
+
"loss": 0.8498,
|
510 |
+
"step": 670
|
511 |
+
},
|
512 |
+
{
|
513 |
+
"epoch": 11.01,
|
514 |
+
"learning_rate": 4.479265590376702e-05,
|
515 |
+
"loss": 0.7743,
|
516 |
+
"step": 680
|
517 |
+
},
|
518 |
+
{
|
519 |
+
"epoch": 11.01,
|
520 |
+
"learning_rate": 4.463437796771131e-05,
|
521 |
+
"loss": 1.0063,
|
522 |
+
"step": 690
|
523 |
+
},
|
524 |
+
{
|
525 |
+
"epoch": 11.01,
|
526 |
+
"learning_rate": 4.4476100031655586e-05,
|
527 |
+
"loss": 0.9042,
|
528 |
+
"step": 700
|
529 |
+
},
|
530 |
+
{
|
531 |
+
"epoch": 11.02,
|
532 |
+
"eval_accuracy": 0.7649769585253456,
|
533 |
+
"eval_loss": 0.7012106776237488,
|
534 |
+
"eval_runtime": 307.8679,
|
535 |
+
"eval_samples_per_second": 0.705,
|
536 |
+
"eval_steps_per_second": 0.091,
|
537 |
+
"step": 708
|
538 |
+
},
|
539 |
+
{
|
540 |
+
"epoch": 12.0,
|
541 |
+
"learning_rate": 4.431782209559988e-05,
|
542 |
+
"loss": 0.8243,
|
543 |
+
"step": 710
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 12.0,
|
547 |
+
"learning_rate": 4.415954415954416e-05,
|
548 |
+
"loss": 0.7756,
|
549 |
+
"step": 720
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 12.01,
|
553 |
+
"learning_rate": 4.4001266223488446e-05,
|
554 |
+
"loss": 0.9731,
|
555 |
+
"step": 730
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 12.01,
|
559 |
+
"learning_rate": 4.384298828743274e-05,
|
560 |
+
"loss": 0.8979,
|
561 |
+
"step": 740
|
562 |
+
},
|
563 |
+
{
|
564 |
+
"epoch": 12.01,
|
565 |
+
"learning_rate": 4.368471035137702e-05,
|
566 |
+
"loss": 0.9586,
|
567 |
+
"step": 750
|
568 |
+
},
|
569 |
+
{
|
570 |
+
"epoch": 12.01,
|
571 |
+
"learning_rate": 4.3526432415321306e-05,
|
572 |
+
"loss": 0.8642,
|
573 |
+
"step": 760
|
574 |
+
},
|
575 |
+
{
|
576 |
+
"epoch": 12.02,
|
577 |
+
"eval_accuracy": 0.6774193548387096,
|
578 |
+
"eval_loss": 0.7588521838188171,
|
579 |
+
"eval_runtime": 303.2535,
|
580 |
+
"eval_samples_per_second": 0.716,
|
581 |
+
"eval_steps_per_second": 0.092,
|
582 |
+
"step": 767
|
583 |
+
},
|
584 |
+
{
|
585 |
+
"epoch": 13.0,
|
586 |
+
"learning_rate": 4.336815447926559e-05,
|
587 |
+
"loss": 0.7979,
|
588 |
+
"step": 770
|
589 |
+
},
|
590 |
+
{
|
591 |
+
"epoch": 13.0,
|
592 |
+
"learning_rate": 4.3209876543209875e-05,
|
593 |
+
"loss": 0.8616,
|
594 |
+
"step": 780
|
595 |
+
},
|
596 |
+
{
|
597 |
+
"epoch": 13.01,
|
598 |
+
"learning_rate": 4.3051598607154166e-05,
|
599 |
+
"loss": 0.6542,
|
600 |
+
"step": 790
|
601 |
+
},
|
602 |
+
{
|
603 |
+
"epoch": 13.01,
|
604 |
+
"learning_rate": 4.289332067109845e-05,
|
605 |
+
"loss": 0.732,
|
606 |
+
"step": 800
|
607 |
+
},
|
608 |
+
{
|
609 |
+
"epoch": 13.01,
|
610 |
+
"learning_rate": 4.2735042735042735e-05,
|
611 |
+
"loss": 0.806,
|
612 |
+
"step": 810
|
613 |
+
},
|
614 |
+
{
|
615 |
+
"epoch": 13.02,
|
616 |
+
"learning_rate": 4.2576764798987026e-05,
|
617 |
+
"loss": 0.8017,
|
618 |
+
"step": 820
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 13.02,
|
622 |
+
"eval_accuracy": 0.695852534562212,
|
623 |
+
"eval_loss": 0.7485441565513611,
|
624 |
+
"eval_runtime": 294.6482,
|
625 |
+
"eval_samples_per_second": 0.736,
|
626 |
+
"eval_steps_per_second": 0.095,
|
627 |
+
"step": 826
|
628 |
+
},
|
629 |
+
{
|
630 |
+
"epoch": 14.0,
|
631 |
+
"learning_rate": 4.241848686293131e-05,
|
632 |
+
"loss": 0.7243,
|
633 |
+
"step": 830
|
634 |
+
},
|
635 |
+
{
|
636 |
+
"epoch": 14.0,
|
637 |
+
"learning_rate": 4.2260208926875595e-05,
|
638 |
+
"loss": 0.7128,
|
639 |
+
"step": 840
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 14.01,
|
643 |
+
"learning_rate": 4.210193099081988e-05,
|
644 |
+
"loss": 0.876,
|
645 |
+
"step": 850
|
646 |
+
},
|
647 |
+
{
|
648 |
+
"epoch": 14.01,
|
649 |
+
"learning_rate": 4.194365305476417e-05,
|
650 |
+
"loss": 0.7118,
|
651 |
+
"step": 860
|
652 |
+
},
|
653 |
+
{
|
654 |
+
"epoch": 14.01,
|
655 |
+
"learning_rate": 4.1785375118708455e-05,
|
656 |
+
"loss": 0.7758,
|
657 |
+
"step": 870
|
658 |
+
},
|
659 |
+
{
|
660 |
+
"epoch": 14.02,
|
661 |
+
"learning_rate": 4.162709718265274e-05,
|
662 |
+
"loss": 0.7523,
|
663 |
+
"step": 880
|
664 |
+
},
|
665 |
+
{
|
666 |
+
"epoch": 14.02,
|
667 |
+
"eval_accuracy": 0.783410138248848,
|
668 |
+
"eval_loss": 0.5616857409477234,
|
669 |
+
"eval_runtime": 286.0674,
|
670 |
+
"eval_samples_per_second": 0.759,
|
671 |
+
"eval_steps_per_second": 0.098,
|
672 |
+
"step": 885
|
673 |
+
},
|
674 |
+
{
|
675 |
+
"epoch": 15.0,
|
676 |
+
"learning_rate": 4.1468819246597024e-05,
|
677 |
+
"loss": 0.5866,
|
678 |
+
"step": 890
|
679 |
+
},
|
680 |
+
{
|
681 |
+
"epoch": 15.0,
|
682 |
+
"learning_rate": 4.131054131054131e-05,
|
683 |
+
"loss": 0.7429,
|
684 |
+
"step": 900
|
685 |
+
},
|
686 |
+
{
|
687 |
+
"epoch": 15.01,
|
688 |
+
"learning_rate": 4.11522633744856e-05,
|
689 |
+
"loss": 0.8891,
|
690 |
+
"step": 910
|
691 |
+
},
|
692 |
+
{
|
693 |
+
"epoch": 15.01,
|
694 |
+
"learning_rate": 4.0993985438429884e-05,
|
695 |
+
"loss": 0.8778,
|
696 |
+
"step": 920
|
697 |
+
},
|
698 |
+
{
|
699 |
+
"epoch": 15.01,
|
700 |
+
"learning_rate": 4.083570750237417e-05,
|
701 |
+
"loss": 0.673,
|
702 |
+
"step": 930
|
703 |
+
},
|
704 |
+
{
|
705 |
+
"epoch": 15.02,
|
706 |
+
"learning_rate": 4.067742956631846e-05,
|
707 |
+
"loss": 0.7223,
|
708 |
+
"step": 940
|
709 |
+
},
|
710 |
+
{
|
711 |
+
"epoch": 15.02,
|
712 |
+
"eval_accuracy": 0.6129032258064516,
|
713 |
+
"eval_loss": 1.0343618392944336,
|
714 |
+
"eval_runtime": 282.8856,
|
715 |
+
"eval_samples_per_second": 0.767,
|
716 |
+
"eval_steps_per_second": 0.099,
|
717 |
+
"step": 944
|
718 |
+
},
|
719 |
+
{
|
720 |
+
"epoch": 16.0,
|
721 |
+
"learning_rate": 4.0519151630262745e-05,
|
722 |
+
"loss": 0.8074,
|
723 |
+
"step": 950
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 16.0,
|
727 |
+
"learning_rate": 4.036087369420703e-05,
|
728 |
+
"loss": 0.6108,
|
729 |
+
"step": 960
|
730 |
+
},
|
731 |
+
{
|
732 |
+
"epoch": 16.01,
|
733 |
+
"learning_rate": 4.020259575815132e-05,
|
734 |
+
"loss": 0.9762,
|
735 |
+
"step": 970
|
736 |
+
},
|
737 |
+
{
|
738 |
+
"epoch": 16.01,
|
739 |
+
"learning_rate": 4.00443178220956e-05,
|
740 |
+
"loss": 0.7148,
|
741 |
+
"step": 980
|
742 |
+
},
|
743 |
+
{
|
744 |
+
"epoch": 16.01,
|
745 |
+
"learning_rate": 3.988603988603989e-05,
|
746 |
+
"loss": 0.8286,
|
747 |
+
"step": 990
|
748 |
+
},
|
749 |
+
{
|
750 |
+
"epoch": 16.02,
|
751 |
+
"learning_rate": 3.9727761949984174e-05,
|
752 |
+
"loss": 0.6164,
|
753 |
+
"step": 1000
|
754 |
+
},
|
755 |
+
{
|
756 |
+
"epoch": 16.02,
|
757 |
+
"eval_accuracy": 0.7419354838709677,
|
758 |
+
"eval_loss": 0.727464497089386,
|
759 |
+
"eval_runtime": 330.7312,
|
760 |
+
"eval_samples_per_second": 0.656,
|
761 |
+
"eval_steps_per_second": 0.085,
|
762 |
+
"step": 1003
|
763 |
+
},
|
764 |
+
{
|
765 |
+
"epoch": 17.0,
|
766 |
+
"learning_rate": 3.956948401392846e-05,
|
767 |
+
"loss": 0.7374,
|
768 |
+
"step": 1010
|
769 |
+
},
|
770 |
+
{
|
771 |
+
"epoch": 17.0,
|
772 |
+
"learning_rate": 3.941120607787275e-05,
|
773 |
+
"loss": 0.8524,
|
774 |
+
"step": 1020
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"epoch": 17.01,
|
778 |
+
"learning_rate": 3.925292814181703e-05,
|
779 |
+
"loss": 0.8531,
|
780 |
+
"step": 1030
|
781 |
+
},
|
782 |
+
{
|
783 |
+
"epoch": 17.01,
|
784 |
+
"learning_rate": 3.909465020576132e-05,
|
785 |
+
"loss": 0.6948,
|
786 |
+
"step": 1040
|
787 |
+
},
|
788 |
+
{
|
789 |
+
"epoch": 17.01,
|
790 |
+
"learning_rate": 3.893637226970561e-05,
|
791 |
+
"loss": 0.6618,
|
792 |
+
"step": 1050
|
793 |
+
},
|
794 |
+
{
|
795 |
+
"epoch": 17.02,
|
796 |
+
"learning_rate": 3.877809433364989e-05,
|
797 |
+
"loss": 0.6892,
|
798 |
+
"step": 1060
|
799 |
+
},
|
800 |
+
{
|
801 |
+
"epoch": 17.02,
|
802 |
+
"eval_accuracy": 0.7788018433179723,
|
803 |
+
"eval_loss": 0.616241991519928,
|
804 |
+
"eval_runtime": 331.0915,
|
805 |
+
"eval_samples_per_second": 0.655,
|
806 |
+
"eval_steps_per_second": 0.085,
|
807 |
+
"step": 1062
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 18.0,
|
811 |
+
"learning_rate": 3.861981639759418e-05,
|
812 |
+
"loss": 0.7827,
|
813 |
+
"step": 1070
|
814 |
+
},
|
815 |
+
{
|
816 |
+
"epoch": 18.01,
|
817 |
+
"learning_rate": 3.846153846153846e-05,
|
818 |
+
"loss": 0.6962,
|
819 |
+
"step": 1080
|
820 |
+
},
|
821 |
+
{
|
822 |
+
"epoch": 18.01,
|
823 |
+
"learning_rate": 3.830326052548275e-05,
|
824 |
+
"loss": 0.7623,
|
825 |
+
"step": 1090
|
826 |
+
},
|
827 |
+
{
|
828 |
+
"epoch": 18.01,
|
829 |
+
"learning_rate": 3.814498258942704e-05,
|
830 |
+
"loss": 0.6629,
|
831 |
+
"step": 1100
|
832 |
+
},
|
833 |
+
{
|
834 |
+
"epoch": 18.01,
|
835 |
+
"learning_rate": 3.798670465337132e-05,
|
836 |
+
"loss": 0.8101,
|
837 |
+
"step": 1110
|
838 |
+
},
|
839 |
+
{
|
840 |
+
"epoch": 18.02,
|
841 |
+
"learning_rate": 3.782842671731561e-05,
|
842 |
+
"loss": 0.7865,
|
843 |
+
"step": 1120
|
844 |
+
},
|
845 |
+
{
|
846 |
+
"epoch": 18.02,
|
847 |
+
"eval_accuracy": 0.6589861751152074,
|
848 |
+
"eval_loss": 0.7966123819351196,
|
849 |
+
"eval_runtime": 336.073,
|
850 |
+
"eval_samples_per_second": 0.646,
|
851 |
+
"eval_steps_per_second": 0.083,
|
852 |
+
"step": 1121
|
853 |
+
},
|
854 |
+
{
|
855 |
+
"epoch": 19.0,
|
856 |
+
"learning_rate": 3.767014878125989e-05,
|
857 |
+
"loss": 0.5888,
|
858 |
+
"step": 1130
|
859 |
+
},
|
860 |
+
{
|
861 |
+
"epoch": 19.01,
|
862 |
+
"learning_rate": 3.7511870845204176e-05,
|
863 |
+
"loss": 0.8017,
|
864 |
+
"step": 1140
|
865 |
+
},
|
866 |
+
{
|
867 |
+
"epoch": 19.01,
|
868 |
+
"learning_rate": 3.735359290914847e-05,
|
869 |
+
"loss": 0.6144,
|
870 |
+
"step": 1150
|
871 |
+
},
|
872 |
+
{
|
873 |
+
"epoch": 19.01,
|
874 |
+
"learning_rate": 3.719531497309275e-05,
|
875 |
+
"loss": 0.715,
|
876 |
+
"step": 1160
|
877 |
+
},
|
878 |
+
{
|
879 |
+
"epoch": 19.01,
|
880 |
+
"learning_rate": 3.7037037037037037e-05,
|
881 |
+
"loss": 0.6533,
|
882 |
+
"step": 1170
|
883 |
+
},
|
884 |
+
{
|
885 |
+
"epoch": 19.02,
|
886 |
+
"learning_rate": 3.687875910098133e-05,
|
887 |
+
"loss": 0.6387,
|
888 |
+
"step": 1180
|
889 |
+
},
|
890 |
+
{
|
891 |
+
"epoch": 19.02,
|
892 |
+
"eval_accuracy": 0.6774193548387096,
|
893 |
+
"eval_loss": 0.7435915470123291,
|
894 |
+
"eval_runtime": 310.5543,
|
895 |
+
"eval_samples_per_second": 0.699,
|
896 |
+
"eval_steps_per_second": 0.09,
|
897 |
+
"step": 1180
|
898 |
+
},
|
899 |
+
{
|
900 |
+
"epoch": 20.0,
|
901 |
+
"learning_rate": 3.672048116492561e-05,
|
902 |
+
"loss": 0.6266,
|
903 |
+
"step": 1190
|
904 |
+
},
|
905 |
+
{
|
906 |
+
"epoch": 20.01,
|
907 |
+
"learning_rate": 3.65622032288699e-05,
|
908 |
+
"loss": 0.519,
|
909 |
+
"step": 1200
|
910 |
+
},
|
911 |
+
{
|
912 |
+
"epoch": 20.01,
|
913 |
+
"learning_rate": 3.640392529281418e-05,
|
914 |
+
"loss": 0.5029,
|
915 |
+
"step": 1210
|
916 |
+
},
|
917 |
+
{
|
918 |
+
"epoch": 20.01,
|
919 |
+
"learning_rate": 3.624564735675847e-05,
|
920 |
+
"loss": 1.0188,
|
921 |
+
"step": 1220
|
922 |
+
},
|
923 |
+
{
|
924 |
+
"epoch": 20.01,
|
925 |
+
"learning_rate": 3.608736942070276e-05,
|
926 |
+
"loss": 0.6181,
|
927 |
+
"step": 1230
|
928 |
+
},
|
929 |
+
{
|
930 |
+
"epoch": 20.02,
|
931 |
+
"eval_accuracy": 0.7373271889400922,
|
932 |
+
"eval_loss": 0.7136892676353455,
|
933 |
+
"eval_runtime": 305.6632,
|
934 |
+
"eval_samples_per_second": 0.71,
|
935 |
+
"eval_steps_per_second": 0.092,
|
936 |
+
"step": 1239
|
937 |
+
},
|
938 |
+
{
|
939 |
+
"epoch": 21.0,
|
940 |
+
"learning_rate": 3.592909148464704e-05,
|
941 |
+
"loss": 0.8196,
|
942 |
+
"step": 1240
|
943 |
+
},
|
944 |
+
{
|
945 |
+
"epoch": 21.0,
|
946 |
+
"learning_rate": 3.5770813548591326e-05,
|
947 |
+
"loss": 0.7009,
|
948 |
+
"step": 1250
|
949 |
+
},
|
950 |
+
{
|
951 |
+
"epoch": 21.01,
|
952 |
+
"learning_rate": 3.561253561253561e-05,
|
953 |
+
"loss": 0.7675,
|
954 |
+
"step": 1260
|
955 |
+
},
|
956 |
+
{
|
957 |
+
"epoch": 21.01,
|
958 |
+
"learning_rate": 3.54542576764799e-05,
|
959 |
+
"loss": 0.6991,
|
960 |
+
"step": 1270
|
961 |
+
},
|
962 |
+
{
|
963 |
+
"epoch": 21.01,
|
964 |
+
"learning_rate": 3.5295979740424186e-05,
|
965 |
+
"loss": 0.5857,
|
966 |
+
"step": 1280
|
967 |
+
},
|
968 |
+
{
|
969 |
+
"epoch": 21.01,
|
970 |
+
"learning_rate": 3.513770180436847e-05,
|
971 |
+
"loss": 0.6085,
|
972 |
+
"step": 1290
|
973 |
+
},
|
974 |
+
{
|
975 |
+
"epoch": 21.02,
|
976 |
+
"eval_accuracy": 0.6682027649769585,
|
977 |
+
"eval_loss": 0.9580748081207275,
|
978 |
+
"eval_runtime": 300.6045,
|
979 |
+
"eval_samples_per_second": 0.722,
|
980 |
+
"eval_steps_per_second": 0.093,
|
981 |
+
"step": 1298
|
982 |
+
},
|
983 |
+
{
|
984 |
+
"epoch": 22.0,
|
985 |
+
"learning_rate": 3.497942386831276e-05,
|
986 |
+
"loss": 0.738,
|
987 |
+
"step": 1300
|
988 |
+
},
|
989 |
+
{
|
990 |
+
"epoch": 22.0,
|
991 |
+
"learning_rate": 3.4821145932257046e-05,
|
992 |
+
"loss": 0.6597,
|
993 |
+
"step": 1310
|
994 |
+
},
|
995 |
+
{
|
996 |
+
"epoch": 22.01,
|
997 |
+
"learning_rate": 3.466286799620133e-05,
|
998 |
+
"loss": 0.7283,
|
999 |
+
"step": 1320
|
1000 |
+
},
|
1001 |
+
{
|
1002 |
+
"epoch": 22.01,
|
1003 |
+
"learning_rate": 3.450459006014562e-05,
|
1004 |
+
"loss": 0.8223,
|
1005 |
+
"step": 1330
|
1006 |
+
},
|
1007 |
+
{
|
1008 |
+
"epoch": 22.01,
|
1009 |
+
"learning_rate": 3.43463121240899e-05,
|
1010 |
+
"loss": 0.5629,
|
1011 |
+
"step": 1340
|
1012 |
+
},
|
1013 |
+
{
|
1014 |
+
"epoch": 22.01,
|
1015 |
+
"learning_rate": 3.418803418803419e-05,
|
1016 |
+
"loss": 0.7109,
|
1017 |
+
"step": 1350
|
1018 |
+
},
|
1019 |
+
{
|
1020 |
+
"epoch": 22.02,
|
1021 |
+
"eval_accuracy": 0.7096774193548387,
|
1022 |
+
"eval_loss": 0.7746023535728455,
|
1023 |
+
"eval_runtime": 300.4789,
|
1024 |
+
"eval_samples_per_second": 0.722,
|
1025 |
+
"eval_steps_per_second": 0.093,
|
1026 |
+
"step": 1357
|
1027 |
+
},
|
1028 |
+
{
|
1029 |
+
"epoch": 23.0,
|
1030 |
+
"learning_rate": 3.4029756251978475e-05,
|
1031 |
+
"loss": 0.8563,
|
1032 |
+
"step": 1360
|
1033 |
+
},
|
1034 |
+
{
|
1035 |
+
"epoch": 23.0,
|
1036 |
+
"learning_rate": 3.387147831592276e-05,
|
1037 |
+
"loss": 0.6669,
|
1038 |
+
"step": 1370
|
1039 |
+
},
|
1040 |
+
{
|
1041 |
+
"epoch": 23.01,
|
1042 |
+
"learning_rate": 3.371320037986705e-05,
|
1043 |
+
"loss": 0.786,
|
1044 |
+
"step": 1380
|
1045 |
+
},
|
1046 |
+
{
|
1047 |
+
"epoch": 23.01,
|
1048 |
+
"learning_rate": 3.355492244381133e-05,
|
1049 |
+
"loss": 0.5724,
|
1050 |
+
"step": 1390
|
1051 |
+
},
|
1052 |
+
{
|
1053 |
+
"epoch": 23.01,
|
1054 |
+
"learning_rate": 3.339664450775562e-05,
|
1055 |
+
"loss": 0.928,
|
1056 |
+
"step": 1400
|
1057 |
+
},
|
1058 |
+
{
|
1059 |
+
"epoch": 23.02,
|
1060 |
+
"learning_rate": 3.323836657169991e-05,
|
1061 |
+
"loss": 0.7686,
|
1062 |
+
"step": 1410
|
1063 |
+
},
|
1064 |
+
{
|
1065 |
+
"epoch": 23.02,
|
1066 |
+
"eval_accuracy": 0.7096774193548387,
|
1067 |
+
"eval_loss": 0.7969343066215515,
|
1068 |
+
"eval_runtime": 303.3779,
|
1069 |
+
"eval_samples_per_second": 0.715,
|
1070 |
+
"eval_steps_per_second": 0.092,
|
1071 |
+
"step": 1416
|
1072 |
+
},
|
1073 |
+
{
|
1074 |
+
"epoch": 24.0,
|
1075 |
+
"learning_rate": 3.308008863564419e-05,
|
1076 |
+
"loss": 0.5478,
|
1077 |
+
"step": 1420
|
1078 |
+
},
|
1079 |
+
{
|
1080 |
+
"epoch": 24.0,
|
1081 |
+
"learning_rate": 3.292181069958848e-05,
|
1082 |
+
"loss": 0.7107,
|
1083 |
+
"step": 1430
|
1084 |
+
},
|
1085 |
+
{
|
1086 |
+
"epoch": 24.01,
|
1087 |
+
"learning_rate": 3.2763532763532764e-05,
|
1088 |
+
"loss": 0.5742,
|
1089 |
+
"step": 1440
|
1090 |
+
},
|
1091 |
+
{
|
1092 |
+
"epoch": 24.01,
|
1093 |
+
"learning_rate": 3.260525482747705e-05,
|
1094 |
+
"loss": 0.5811,
|
1095 |
+
"step": 1450
|
1096 |
+
},
|
1097 |
+
{
|
1098 |
+
"epoch": 24.01,
|
1099 |
+
"learning_rate": 3.244697689142134e-05,
|
1100 |
+
"loss": 0.676,
|
1101 |
+
"step": 1460
|
1102 |
+
},
|
1103 |
+
{
|
1104 |
+
"epoch": 24.02,
|
1105 |
+
"learning_rate": 3.2288698955365625e-05,
|
1106 |
+
"loss": 0.5995,
|
1107 |
+
"step": 1470
|
1108 |
+
},
|
1109 |
+
{
|
1110 |
+
"epoch": 24.02,
|
1111 |
+
"eval_accuracy": 0.6129032258064516,
|
1112 |
+
"eval_loss": 1.0075043439865112,
|
1113 |
+
"eval_runtime": 295.2487,
|
1114 |
+
"eval_samples_per_second": 0.735,
|
1115 |
+
"eval_steps_per_second": 0.095,
|
1116 |
+
"step": 1475
|
1117 |
+
},
|
1118 |
+
{
|
1119 |
+
"epoch": 25.0,
|
1120 |
+
"learning_rate": 3.213042101930991e-05,
|
1121 |
+
"loss": 0.6382,
|
1122 |
+
"step": 1480
|
1123 |
+
},
|
1124 |
+
{
|
1125 |
+
"epoch": 25.0,
|
1126 |
+
"learning_rate": 3.1972143083254193e-05,
|
1127 |
+
"loss": 0.5384,
|
1128 |
+
"step": 1490
|
1129 |
+
},
|
1130 |
+
{
|
1131 |
+
"epoch": 25.01,
|
1132 |
+
"learning_rate": 3.181386514719848e-05,
|
1133 |
+
"loss": 0.7876,
|
1134 |
+
"step": 1500
|
1135 |
+
},
|
1136 |
+
{
|
1137 |
+
"epoch": 25.01,
|
1138 |
+
"learning_rate": 3.165558721114277e-05,
|
1139 |
+
"loss": 0.6693,
|
1140 |
+
"step": 1510
|
1141 |
+
},
|
1142 |
+
{
|
1143 |
+
"epoch": 25.01,
|
1144 |
+
"learning_rate": 3.1497309275087054e-05,
|
1145 |
+
"loss": 0.5688,
|
1146 |
+
"step": 1520
|
1147 |
+
},
|
1148 |
+
{
|
1149 |
+
"epoch": 25.02,
|
1150 |
+
"learning_rate": 3.133903133903134e-05,
|
1151 |
+
"loss": 0.5854,
|
1152 |
+
"step": 1530
|
1153 |
+
},
|
1154 |
+
{
|
1155 |
+
"epoch": 25.02,
|
1156 |
+
"eval_accuracy": 0.7419354838709677,
|
1157 |
+
"eval_loss": 0.7388768196105957,
|
1158 |
+
"eval_runtime": 335.3249,
|
1159 |
+
"eval_samples_per_second": 0.647,
|
1160 |
+
"eval_steps_per_second": 0.084,
|
1161 |
+
"step": 1534
|
1162 |
+
},
|
1163 |
+
{
|
1164 |
+
"epoch": 26.0,
|
1165 |
+
"learning_rate": 3.118075340297563e-05,
|
1166 |
+
"loss": 0.4072,
|
1167 |
+
"step": 1540
|
1168 |
+
},
|
1169 |
+
{
|
1170 |
+
"epoch": 26.0,
|
1171 |
+
"learning_rate": 3.1022475466919914e-05,
|
1172 |
+
"loss": 0.6526,
|
1173 |
+
"step": 1550
|
1174 |
+
},
|
1175 |
+
{
|
1176 |
+
"epoch": 26.01,
|
1177 |
+
"learning_rate": 3.08641975308642e-05,
|
1178 |
+
"loss": 0.6973,
|
1179 |
+
"step": 1560
|
1180 |
+
},
|
1181 |
+
{
|
1182 |
+
"epoch": 26.01,
|
1183 |
+
"learning_rate": 3.070591959480848e-05,
|
1184 |
+
"loss": 0.8606,
|
1185 |
+
"step": 1570
|
1186 |
+
},
|
1187 |
+
{
|
1188 |
+
"epoch": 26.01,
|
1189 |
+
"learning_rate": 3.0547641658752774e-05,
|
1190 |
+
"loss": 0.6417,
|
1191 |
+
"step": 1580
|
1192 |
+
},
|
1193 |
+
{
|
1194 |
+
"epoch": 26.02,
|
1195 |
+
"learning_rate": 3.0389363722697055e-05,
|
1196 |
+
"loss": 0.575,
|
1197 |
+
"step": 1590
|
1198 |
+
},
|
1199 |
+
{
|
1200 |
+
"epoch": 26.02,
|
1201 |
+
"eval_accuracy": 0.7142857142857143,
|
1202 |
+
"eval_loss": 0.7198013067245483,
|
1203 |
+
"eval_runtime": 323.3382,
|
1204 |
+
"eval_samples_per_second": 0.671,
|
1205 |
+
"eval_steps_per_second": 0.087,
|
1206 |
+
"step": 1593
|
1207 |
+
},
|
1208 |
+
{
|
1209 |
+
"epoch": 27.0,
|
1210 |
+
"learning_rate": 3.0231085786641343e-05,
|
1211 |
+
"loss": 0.5309,
|
1212 |
+
"step": 1600
|
1213 |
+
},
|
1214 |
+
{
|
1215 |
+
"epoch": 27.0,
|
1216 |
+
"learning_rate": 3.0072807850585634e-05,
|
1217 |
+
"loss": 0.6287,
|
1218 |
+
"step": 1610
|
1219 |
+
},
|
1220 |
+
{
|
1221 |
+
"epoch": 27.01,
|
1222 |
+
"learning_rate": 2.9914529914529915e-05,
|
1223 |
+
"loss": 0.7234,
|
1224 |
+
"step": 1620
|
1225 |
+
},
|
1226 |
+
{
|
1227 |
+
"epoch": 27.01,
|
1228 |
+
"learning_rate": 2.9756251978474203e-05,
|
1229 |
+
"loss": 0.6081,
|
1230 |
+
"step": 1630
|
1231 |
+
},
|
1232 |
+
{
|
1233 |
+
"epoch": 27.01,
|
1234 |
+
"learning_rate": 2.9597974042418487e-05,
|
1235 |
+
"loss": 0.7265,
|
1236 |
+
"step": 1640
|
1237 |
+
},
|
1238 |
+
{
|
1239 |
+
"epoch": 27.02,
|
1240 |
+
"learning_rate": 2.9439696106362775e-05,
|
1241 |
+
"loss": 0.7478,
|
1242 |
+
"step": 1650
|
1243 |
+
},
|
1244 |
+
{
|
1245 |
+
"epoch": 27.02,
|
1246 |
+
"eval_accuracy": 0.7741935483870968,
|
1247 |
+
"eval_loss": 0.6097679734230042,
|
1248 |
+
"eval_runtime": 329.3249,
|
1249 |
+
"eval_samples_per_second": 0.659,
|
1250 |
+
"eval_steps_per_second": 0.085,
|
1251 |
+
"step": 1652
|
1252 |
+
},
|
1253 |
+
{
|
1254 |
+
"epoch": 28.0,
|
1255 |
+
"learning_rate": 2.9281418170307063e-05,
|
1256 |
+
"loss": 0.5044,
|
1257 |
+
"step": 1660
|
1258 |
+
},
|
1259 |
+
{
|
1260 |
+
"epoch": 28.01,
|
1261 |
+
"learning_rate": 2.9123140234251344e-05,
|
1262 |
+
"loss": 0.5792,
|
1263 |
+
"step": 1670
|
1264 |
+
},
|
1265 |
+
{
|
1266 |
+
"epoch": 28.01,
|
1267 |
+
"learning_rate": 2.8964862298195632e-05,
|
1268 |
+
"loss": 0.5314,
|
1269 |
+
"step": 1680
|
1270 |
+
},
|
1271 |
+
{
|
1272 |
+
"epoch": 28.01,
|
1273 |
+
"learning_rate": 2.880658436213992e-05,
|
1274 |
+
"loss": 0.4202,
|
1275 |
+
"step": 1690
|
1276 |
+
},
|
1277 |
+
{
|
1278 |
+
"epoch": 28.01,
|
1279 |
+
"learning_rate": 2.8648306426084204e-05,
|
1280 |
+
"loss": 0.4768,
|
1281 |
+
"step": 1700
|
1282 |
+
},
|
1283 |
+
{
|
1284 |
+
"epoch": 28.02,
|
1285 |
+
"learning_rate": 2.8490028490028492e-05,
|
1286 |
+
"loss": 0.7204,
|
1287 |
+
"step": 1710
|
1288 |
+
},
|
1289 |
+
{
|
1290 |
+
"epoch": 28.02,
|
1291 |
+
"eval_accuracy": 0.7972350230414746,
|
1292 |
+
"eval_loss": 0.6458683013916016,
|
1293 |
+
"eval_runtime": 340.899,
|
1294 |
+
"eval_samples_per_second": 0.637,
|
1295 |
+
"eval_steps_per_second": 0.082,
|
1296 |
+
"step": 1711
|
1297 |
+
},
|
1298 |
+
{
|
1299 |
+
"epoch": 29.0,
|
1300 |
+
"learning_rate": 2.833175055397278e-05,
|
1301 |
+
"loss": 0.5258,
|
1302 |
+
"step": 1720
|
1303 |
+
},
|
1304 |
+
{
|
1305 |
+
"epoch": 29.01,
|
1306 |
+
"learning_rate": 2.817347261791706e-05,
|
1307 |
+
"loss": 0.7548,
|
1308 |
+
"step": 1730
|
1309 |
+
},
|
1310 |
+
{
|
1311 |
+
"epoch": 29.01,
|
1312 |
+
"learning_rate": 2.8015194681861352e-05,
|
1313 |
+
"loss": 0.6974,
|
1314 |
+
"step": 1740
|
1315 |
+
},
|
1316 |
+
{
|
1317 |
+
"epoch": 29.01,
|
1318 |
+
"learning_rate": 2.7856916745805633e-05,
|
1319 |
+
"loss": 0.5245,
|
1320 |
+
"step": 1750
|
1321 |
+
},
|
1322 |
+
{
|
1323 |
+
"epoch": 29.01,
|
1324 |
+
"learning_rate": 2.769863880974992e-05,
|
1325 |
+
"loss": 0.6382,
|
1326 |
+
"step": 1760
|
1327 |
+
},
|
1328 |
+
{
|
1329 |
+
"epoch": 29.02,
|
1330 |
+
"learning_rate": 2.754036087369421e-05,
|
1331 |
+
"loss": 0.4325,
|
1332 |
+
"step": 1770
|
1333 |
+
},
|
1334 |
+
{
|
1335 |
+
"epoch": 29.02,
|
1336 |
+
"eval_accuracy": 0.7511520737327189,
|
1337 |
+
"eval_loss": 0.726778507232666,
|
1338 |
+
"eval_runtime": 317.8406,
|
1339 |
+
"eval_samples_per_second": 0.683,
|
1340 |
+
"eval_steps_per_second": 0.088,
|
1341 |
+
"step": 1770
|
1342 |
+
},
|
1343 |
+
{
|
1344 |
+
"epoch": 30.0,
|
1345 |
+
"learning_rate": 2.7382082937638494e-05,
|
1346 |
+
"loss": 0.4622,
|
1347 |
+
"step": 1780
|
1348 |
+
},
|
1349 |
+
{
|
1350 |
+
"epoch": 30.01,
|
1351 |
+
"learning_rate": 2.722380500158278e-05,
|
1352 |
+
"loss": 0.6414,
|
1353 |
+
"step": 1790
|
1354 |
+
},
|
1355 |
+
{
|
1356 |
+
"epoch": 30.01,
|
1357 |
+
"learning_rate": 2.706552706552707e-05,
|
1358 |
+
"loss": 0.72,
|
1359 |
+
"step": 1800
|
1360 |
+
},
|
1361 |
+
{
|
1362 |
+
"epoch": 30.01,
|
1363 |
+
"learning_rate": 2.690724912947135e-05,
|
1364 |
+
"loss": 0.5362,
|
1365 |
+
"step": 1810
|
1366 |
+
},
|
1367 |
+
{
|
1368 |
+
"epoch": 30.01,
|
1369 |
+
"learning_rate": 2.6748971193415638e-05,
|
1370 |
+
"loss": 0.593,
|
1371 |
+
"step": 1820
|
1372 |
+
},
|
1373 |
+
{
|
1374 |
+
"epoch": 30.02,
|
1375 |
+
"eval_accuracy": 0.7880184331797235,
|
1376 |
+
"eval_loss": 0.5901350975036621,
|
1377 |
+
"eval_runtime": 316.6009,
|
1378 |
+
"eval_samples_per_second": 0.685,
|
1379 |
+
"eval_steps_per_second": 0.088,
|
1380 |
+
"step": 1829
|
1381 |
+
},
|
1382 |
+
{
|
1383 |
+
"epoch": 31.0,
|
1384 |
+
"learning_rate": 2.6590693257359926e-05,
|
1385 |
+
"loss": 0.4719,
|
1386 |
+
"step": 1830
|
1387 |
+
},
|
1388 |
+
{
|
1389 |
+
"epoch": 31.0,
|
1390 |
+
"learning_rate": 2.643241532130421e-05,
|
1391 |
+
"loss": 0.461,
|
1392 |
+
"step": 1840
|
1393 |
+
},
|
1394 |
+
{
|
1395 |
+
"epoch": 31.01,
|
1396 |
+
"learning_rate": 2.62741373852485e-05,
|
1397 |
+
"loss": 0.4394,
|
1398 |
+
"step": 1850
|
1399 |
+
},
|
1400 |
+
{
|
1401 |
+
"epoch": 31.01,
|
1402 |
+
"learning_rate": 2.611585944919278e-05,
|
1403 |
+
"loss": 0.7129,
|
1404 |
+
"step": 1860
|
1405 |
+
},
|
1406 |
+
{
|
1407 |
+
"epoch": 31.01,
|
1408 |
+
"learning_rate": 2.595758151313707e-05,
|
1409 |
+
"loss": 0.6618,
|
1410 |
+
"step": 1870
|
1411 |
+
},
|
1412 |
+
{
|
1413 |
+
"epoch": 31.01,
|
1414 |
+
"learning_rate": 2.579930357708136e-05,
|
1415 |
+
"loss": 0.6432,
|
1416 |
+
"step": 1880
|
1417 |
+
},
|
1418 |
+
{
|
1419 |
+
"epoch": 31.02,
|
1420 |
+
"eval_accuracy": 0.7880184331797235,
|
1421 |
+
"eval_loss": 0.5924447774887085,
|
1422 |
+
"eval_runtime": 310.8109,
|
1423 |
+
"eval_samples_per_second": 0.698,
|
1424 |
+
"eval_steps_per_second": 0.09,
|
1425 |
+
"step": 1888
|
1426 |
+
},
|
1427 |
+
{
|
1428 |
+
"epoch": 32.0,
|
1429 |
+
"learning_rate": 2.564102564102564e-05,
|
1430 |
+
"loss": 0.4229,
|
1431 |
+
"step": 1890
|
1432 |
+
},
|
1433 |
+
{
|
1434 |
+
"epoch": 32.0,
|
1435 |
+
"learning_rate": 2.5482747704969927e-05,
|
1436 |
+
"loss": 0.7339,
|
1437 |
+
"step": 1900
|
1438 |
+
},
|
1439 |
+
{
|
1440 |
+
"epoch": 32.01,
|
1441 |
+
"learning_rate": 2.5324469768914215e-05,
|
1442 |
+
"loss": 0.6894,
|
1443 |
+
"step": 1910
|
1444 |
+
},
|
1445 |
+
{
|
1446 |
+
"epoch": 32.01,
|
1447 |
+
"learning_rate": 2.51661918328585e-05,
|
1448 |
+
"loss": 0.5088,
|
1449 |
+
"step": 1920
|
1450 |
+
},
|
1451 |
+
{
|
1452 |
+
"epoch": 32.01,
|
1453 |
+
"learning_rate": 2.5007913896802788e-05,
|
1454 |
+
"loss": 0.4812,
|
1455 |
+
"step": 1930
|
1456 |
+
},
|
1457 |
+
{
|
1458 |
+
"epoch": 32.01,
|
1459 |
+
"learning_rate": 2.4849635960747072e-05,
|
1460 |
+
"loss": 0.4821,
|
1461 |
+
"step": 1940
|
1462 |
+
},
|
1463 |
+
{
|
1464 |
+
"epoch": 32.02,
|
1465 |
+
"eval_accuracy": 0.815668202764977,
|
1466 |
+
"eval_loss": 0.5730257630348206,
|
1467 |
+
"eval_runtime": 290.7811,
|
1468 |
+
"eval_samples_per_second": 0.746,
|
1469 |
+
"eval_steps_per_second": 0.096,
|
1470 |
+
"step": 1947
|
1471 |
+
},
|
1472 |
+
{
|
1473 |
+
"epoch": 33.0,
|
1474 |
+
"learning_rate": 2.4691358024691357e-05,
|
1475 |
+
"loss": 0.4808,
|
1476 |
+
"step": 1950
|
1477 |
+
},
|
1478 |
+
{
|
1479 |
+
"epoch": 33.0,
|
1480 |
+
"learning_rate": 2.4533080088635644e-05,
|
1481 |
+
"loss": 0.4051,
|
1482 |
+
"step": 1960
|
1483 |
+
},
|
1484 |
+
{
|
1485 |
+
"epoch": 33.01,
|
1486 |
+
"learning_rate": 2.4374802152579932e-05,
|
1487 |
+
"loss": 0.559,
|
1488 |
+
"step": 1970
|
1489 |
+
},
|
1490 |
+
{
|
1491 |
+
"epoch": 33.01,
|
1492 |
+
"learning_rate": 2.4216524216524217e-05,
|
1493 |
+
"loss": 0.4306,
|
1494 |
+
"step": 1980
|
1495 |
+
},
|
1496 |
+
{
|
1497 |
+
"epoch": 33.01,
|
1498 |
+
"learning_rate": 2.4058246280468505e-05,
|
1499 |
+
"loss": 0.7199,
|
1500 |
+
"step": 1990
|
1501 |
+
},
|
1502 |
+
{
|
1503 |
+
"epoch": 33.02,
|
1504 |
+
"learning_rate": 2.389996834441279e-05,
|
1505 |
+
"loss": 0.9189,
|
1506 |
+
"step": 2000
|
1507 |
+
},
|
1508 |
+
{
|
1509 |
+
"epoch": 33.02,
|
1510 |
+
"eval_accuracy": 0.783410138248848,
|
1511 |
+
"eval_loss": 0.6241814494132996,
|
1512 |
+
"eval_runtime": 285.8334,
|
1513 |
+
"eval_samples_per_second": 0.759,
|
1514 |
+
"eval_steps_per_second": 0.098,
|
1515 |
+
"step": 2006
|
1516 |
+
},
|
1517 |
+
{
|
1518 |
+
"epoch": 34.0,
|
1519 |
+
"learning_rate": 2.3741690408357077e-05,
|
1520 |
+
"loss": 0.5293,
|
1521 |
+
"step": 2010
|
1522 |
+
},
|
1523 |
+
{
|
1524 |
+
"epoch": 34.0,
|
1525 |
+
"learning_rate": 2.358341247230136e-05,
|
1526 |
+
"loss": 0.5029,
|
1527 |
+
"step": 2020
|
1528 |
+
},
|
1529 |
+
{
|
1530 |
+
"epoch": 34.01,
|
1531 |
+
"learning_rate": 2.342513453624565e-05,
|
1532 |
+
"loss": 0.7058,
|
1533 |
+
"step": 2030
|
1534 |
+
},
|
1535 |
+
{
|
1536 |
+
"epoch": 34.01,
|
1537 |
+
"learning_rate": 2.3266856600189934e-05,
|
1538 |
+
"loss": 0.4917,
|
1539 |
+
"step": 2040
|
1540 |
+
},
|
1541 |
+
{
|
1542 |
+
"epoch": 34.01,
|
1543 |
+
"learning_rate": 2.310857866413422e-05,
|
1544 |
+
"loss": 0.6182,
|
1545 |
+
"step": 2050
|
1546 |
+
},
|
1547 |
+
{
|
1548 |
+
"epoch": 34.02,
|
1549 |
+
"learning_rate": 2.295030072807851e-05,
|
1550 |
+
"loss": 0.6179,
|
1551 |
+
"step": 2060
|
1552 |
+
},
|
1553 |
+
{
|
1554 |
+
"epoch": 34.02,
|
1555 |
+
"eval_accuracy": 0.8018433179723502,
|
1556 |
+
"eval_loss": 0.584676206111908,
|
1557 |
+
"eval_runtime": 329.7075,
|
1558 |
+
"eval_samples_per_second": 0.658,
|
1559 |
+
"eval_steps_per_second": 0.085,
|
1560 |
+
"step": 2065
|
1561 |
+
},
|
1562 |
+
{
|
1563 |
+
"epoch": 35.0,
|
1564 |
+
"learning_rate": 2.2792022792022794e-05,
|
1565 |
+
"loss": 0.4189,
|
1566 |
+
"step": 2070
|
1567 |
+
},
|
1568 |
+
{
|
1569 |
+
"epoch": 35.0,
|
1570 |
+
"learning_rate": 2.2633744855967078e-05,
|
1571 |
+
"loss": 0.3077,
|
1572 |
+
"step": 2080
|
1573 |
+
},
|
1574 |
+
{
|
1575 |
+
"epoch": 35.01,
|
1576 |
+
"learning_rate": 2.2475466919911363e-05,
|
1577 |
+
"loss": 0.4646,
|
1578 |
+
"step": 2090
|
1579 |
+
},
|
1580 |
+
{
|
1581 |
+
"epoch": 35.01,
|
1582 |
+
"learning_rate": 2.2317188983855654e-05,
|
1583 |
+
"loss": 0.4642,
|
1584 |
+
"step": 2100
|
1585 |
+
},
|
1586 |
+
{
|
1587 |
+
"epoch": 35.01,
|
1588 |
+
"learning_rate": 2.215891104779994e-05,
|
1589 |
+
"loss": 0.658,
|
1590 |
+
"step": 2110
|
1591 |
+
},
|
1592 |
+
{
|
1593 |
+
"epoch": 35.02,
|
1594 |
+
"learning_rate": 2.2000633111744223e-05,
|
1595 |
+
"loss": 0.5767,
|
1596 |
+
"step": 2120
|
1597 |
+
},
|
1598 |
+
{
|
1599 |
+
"epoch": 35.02,
|
1600 |
+
"eval_accuracy": 0.8248847926267281,
|
1601 |
+
"eval_loss": 0.59653639793396,
|
1602 |
+
"eval_runtime": 363.307,
|
1603 |
+
"eval_samples_per_second": 0.597,
|
1604 |
+
"eval_steps_per_second": 0.077,
|
1605 |
+
"step": 2124
|
1606 |
+
},
|
1607 |
+
{
|
1608 |
+
"epoch": 36.0,
|
1609 |
+
"learning_rate": 2.184235517568851e-05,
|
1610 |
+
"loss": 0.5256,
|
1611 |
+
"step": 2130
|
1612 |
+
},
|
1613 |
+
{
|
1614 |
+
"epoch": 36.0,
|
1615 |
+
"learning_rate": 2.1684077239632795e-05,
|
1616 |
+
"loss": 0.7286,
|
1617 |
+
"step": 2140
|
1618 |
+
},
|
1619 |
+
{
|
1620 |
+
"epoch": 36.01,
|
1621 |
+
"learning_rate": 2.1525799303577083e-05,
|
1622 |
+
"loss": 0.5342,
|
1623 |
+
"step": 2150
|
1624 |
+
},
|
1625 |
+
{
|
1626 |
+
"epoch": 36.01,
|
1627 |
+
"learning_rate": 2.1367521367521368e-05,
|
1628 |
+
"loss": 0.5483,
|
1629 |
+
"step": 2160
|
1630 |
+
},
|
1631 |
+
{
|
1632 |
+
"epoch": 36.01,
|
1633 |
+
"learning_rate": 2.1209243431465655e-05,
|
1634 |
+
"loss": 0.4426,
|
1635 |
+
"step": 2170
|
1636 |
+
},
|
1637 |
+
{
|
1638 |
+
"epoch": 36.02,
|
1639 |
+
"learning_rate": 2.105096549540994e-05,
|
1640 |
+
"loss": 0.5298,
|
1641 |
+
"step": 2180
|
1642 |
+
},
|
1643 |
+
{
|
1644 |
+
"epoch": 36.02,
|
1645 |
+
"eval_accuracy": 0.7235023041474654,
|
1646 |
+
"eval_loss": 0.7917733788490295,
|
1647 |
+
"eval_runtime": 318.2413,
|
1648 |
+
"eval_samples_per_second": 0.682,
|
1649 |
+
"eval_steps_per_second": 0.088,
|
1650 |
+
"step": 2183
|
1651 |
+
},
|
1652 |
+
{
|
1653 |
+
"epoch": 37.0,
|
1654 |
+
"learning_rate": 2.0892687559354228e-05,
|
1655 |
+
"loss": 0.4776,
|
1656 |
+
"step": 2190
|
1657 |
+
},
|
1658 |
+
{
|
1659 |
+
"epoch": 37.0,
|
1660 |
+
"learning_rate": 2.0734409623298512e-05,
|
1661 |
+
"loss": 0.4896,
|
1662 |
+
"step": 2200
|
1663 |
+
},
|
1664 |
+
{
|
1665 |
+
"epoch": 37.01,
|
1666 |
+
"learning_rate": 2.05761316872428e-05,
|
1667 |
+
"loss": 0.4383,
|
1668 |
+
"step": 2210
|
1669 |
+
},
|
1670 |
+
{
|
1671 |
+
"epoch": 37.01,
|
1672 |
+
"learning_rate": 2.0417853751187084e-05,
|
1673 |
+
"loss": 0.5552,
|
1674 |
+
"step": 2220
|
1675 |
+
},
|
1676 |
+
{
|
1677 |
+
"epoch": 37.01,
|
1678 |
+
"learning_rate": 2.0259575815131372e-05,
|
1679 |
+
"loss": 0.3671,
|
1680 |
+
"step": 2230
|
1681 |
+
},
|
1682 |
+
{
|
1683 |
+
"epoch": 37.02,
|
1684 |
+
"learning_rate": 2.010129787907566e-05,
|
1685 |
+
"loss": 0.5651,
|
1686 |
+
"step": 2240
|
1687 |
+
},
|
1688 |
+
{
|
1689 |
+
"epoch": 37.02,
|
1690 |
+
"eval_accuracy": 0.7327188940092166,
|
1691 |
+
"eval_loss": 0.8338220119476318,
|
1692 |
+
"eval_runtime": 318.76,
|
1693 |
+
"eval_samples_per_second": 0.681,
|
1694 |
+
"eval_steps_per_second": 0.088,
|
1695 |
+
"step": 2242
|
1696 |
+
},
|
1697 |
+
{
|
1698 |
+
"epoch": 38.0,
|
1699 |
+
"learning_rate": 1.9943019943019945e-05,
|
1700 |
+
"loss": 0.5144,
|
1701 |
+
"step": 2250
|
1702 |
+
},
|
1703 |
+
{
|
1704 |
+
"epoch": 38.01,
|
1705 |
+
"learning_rate": 1.978474200696423e-05,
|
1706 |
+
"loss": 0.3722,
|
1707 |
+
"step": 2260
|
1708 |
+
},
|
1709 |
+
{
|
1710 |
+
"epoch": 38.01,
|
1711 |
+
"learning_rate": 1.9626464070908514e-05,
|
1712 |
+
"loss": 0.5191,
|
1713 |
+
"step": 2270
|
1714 |
+
},
|
1715 |
+
{
|
1716 |
+
"epoch": 38.01,
|
1717 |
+
"learning_rate": 1.9468186134852805e-05,
|
1718 |
+
"loss": 0.5935,
|
1719 |
+
"step": 2280
|
1720 |
+
},
|
1721 |
+
{
|
1722 |
+
"epoch": 38.01,
|
1723 |
+
"learning_rate": 1.930990819879709e-05,
|
1724 |
+
"loss": 0.5033,
|
1725 |
+
"step": 2290
|
1726 |
+
},
|
1727 |
+
{
|
1728 |
+
"epoch": 38.02,
|
1729 |
+
"learning_rate": 1.9151630262741374e-05,
|
1730 |
+
"loss": 0.9236,
|
1731 |
+
"step": 2300
|
1732 |
+
},
|
1733 |
+
{
|
1734 |
+
"epoch": 38.02,
|
1735 |
+
"eval_accuracy": 0.7142857142857143,
|
1736 |
+
"eval_loss": 0.8370778560638428,
|
1737 |
+
"eval_runtime": 304.2351,
|
1738 |
+
"eval_samples_per_second": 0.713,
|
1739 |
+
"eval_steps_per_second": 0.092,
|
1740 |
+
"step": 2301
|
1741 |
+
},
|
1742 |
+
{
|
1743 |
+
"epoch": 39.0,
|
1744 |
+
"learning_rate": 1.899335232668566e-05,
|
1745 |
+
"loss": 0.3032,
|
1746 |
+
"step": 2310
|
1747 |
+
},
|
1748 |
+
{
|
1749 |
+
"epoch": 39.01,
|
1750 |
+
"learning_rate": 1.8835074390629946e-05,
|
1751 |
+
"loss": 0.6756,
|
1752 |
+
"step": 2320
|
1753 |
+
},
|
1754 |
+
{
|
1755 |
+
"epoch": 39.01,
|
1756 |
+
"learning_rate": 1.8676796454574234e-05,
|
1757 |
+
"loss": 0.3696,
|
1758 |
+
"step": 2330
|
1759 |
+
},
|
1760 |
+
{
|
1761 |
+
"epoch": 39.01,
|
1762 |
+
"learning_rate": 1.8518518518518518e-05,
|
1763 |
+
"loss": 0.5895,
|
1764 |
+
"step": 2340
|
1765 |
+
},
|
1766 |
+
{
|
1767 |
+
"epoch": 39.01,
|
1768 |
+
"learning_rate": 1.8360240582462806e-05,
|
1769 |
+
"loss": 0.6435,
|
1770 |
+
"step": 2350
|
1771 |
+
},
|
1772 |
+
{
|
1773 |
+
"epoch": 39.02,
|
1774 |
+
"learning_rate": 1.820196264640709e-05,
|
1775 |
+
"loss": 0.4854,
|
1776 |
+
"step": 2360
|
1777 |
+
},
|
1778 |
+
{
|
1779 |
+
"epoch": 39.02,
|
1780 |
+
"eval_accuracy": 0.7695852534562212,
|
1781 |
+
"eval_loss": 0.7114577889442444,
|
1782 |
+
"eval_runtime": 292.8077,
|
1783 |
+
"eval_samples_per_second": 0.741,
|
1784 |
+
"eval_steps_per_second": 0.096,
|
1785 |
+
"step": 2360
|
1786 |
+
},
|
1787 |
+
{
|
1788 |
+
"epoch": 40.0,
|
1789 |
+
"learning_rate": 1.804368471035138e-05,
|
1790 |
+
"loss": 0.534,
|
1791 |
+
"step": 2370
|
1792 |
+
},
|
1793 |
+
{
|
1794 |
+
"epoch": 40.01,
|
1795 |
+
"learning_rate": 1.7885406774295663e-05,
|
1796 |
+
"loss": 0.5408,
|
1797 |
+
"step": 2380
|
1798 |
+
},
|
1799 |
+
{
|
1800 |
+
"epoch": 40.01,
|
1801 |
+
"learning_rate": 1.772712883823995e-05,
|
1802 |
+
"loss": 0.5112,
|
1803 |
+
"step": 2390
|
1804 |
+
},
|
1805 |
+
{
|
1806 |
+
"epoch": 40.01,
|
1807 |
+
"learning_rate": 1.7568850902184235e-05,
|
1808 |
+
"loss": 0.4957,
|
1809 |
+
"step": 2400
|
1810 |
+
},
|
1811 |
+
{
|
1812 |
+
"epoch": 40.01,
|
1813 |
+
"learning_rate": 1.7410572966128523e-05,
|
1814 |
+
"loss": 0.4837,
|
1815 |
+
"step": 2410
|
1816 |
+
},
|
1817 |
+
{
|
1818 |
+
"epoch": 40.02,
|
1819 |
+
"eval_accuracy": 0.7695852534562212,
|
1820 |
+
"eval_loss": 0.6325687170028687,
|
1821 |
+
"eval_runtime": 288.9229,
|
1822 |
+
"eval_samples_per_second": 0.751,
|
1823 |
+
"eval_steps_per_second": 0.097,
|
1824 |
+
"step": 2419
|
1825 |
+
},
|
1826 |
+
{
|
1827 |
+
"epoch": 41.0,
|
1828 |
+
"learning_rate": 1.725229503007281e-05,
|
1829 |
+
"loss": 0.6155,
|
1830 |
+
"step": 2420
|
1831 |
+
},
|
1832 |
+
{
|
1833 |
+
"epoch": 41.0,
|
1834 |
+
"learning_rate": 1.7094017094017095e-05,
|
1835 |
+
"loss": 0.4444,
|
1836 |
+
"step": 2430
|
1837 |
+
},
|
1838 |
+
{
|
1839 |
+
"epoch": 41.01,
|
1840 |
+
"learning_rate": 1.693573915796138e-05,
|
1841 |
+
"loss": 0.5507,
|
1842 |
+
"step": 2440
|
1843 |
+
},
|
1844 |
+
{
|
1845 |
+
"epoch": 41.01,
|
1846 |
+
"learning_rate": 1.6777461221905664e-05,
|
1847 |
+
"loss": 0.5443,
|
1848 |
+
"step": 2450
|
1849 |
+
},
|
1850 |
+
{
|
1851 |
+
"epoch": 41.01,
|
1852 |
+
"learning_rate": 1.6619183285849956e-05,
|
1853 |
+
"loss": 0.5536,
|
1854 |
+
"step": 2460
|
1855 |
+
},
|
1856 |
+
{
|
1857 |
+
"epoch": 41.01,
|
1858 |
+
"learning_rate": 1.646090534979424e-05,
|
1859 |
+
"loss": 0.4142,
|
1860 |
+
"step": 2470
|
1861 |
+
},
|
1862 |
+
{
|
1863 |
+
"epoch": 41.02,
|
1864 |
+
"eval_accuracy": 0.8202764976958525,
|
1865 |
+
"eval_loss": 0.6266201138496399,
|
1866 |
+
"eval_runtime": 291.4173,
|
1867 |
+
"eval_samples_per_second": 0.745,
|
1868 |
+
"eval_steps_per_second": 0.096,
|
1869 |
+
"step": 2478
|
1870 |
+
},
|
1871 |
+
{
|
1872 |
+
"epoch": 42.0,
|
1873 |
+
"learning_rate": 1.6302627413738524e-05,
|
1874 |
+
"loss": 0.7275,
|
1875 |
+
"step": 2480
|
1876 |
+
},
|
1877 |
+
{
|
1878 |
+
"epoch": 42.0,
|
1879 |
+
"learning_rate": 1.6144349477682812e-05,
|
1880 |
+
"loss": 0.425,
|
1881 |
+
"step": 2490
|
1882 |
+
},
|
1883 |
+
{
|
1884 |
+
"epoch": 42.01,
|
1885 |
+
"learning_rate": 1.5986071541627097e-05,
|
1886 |
+
"loss": 0.445,
|
1887 |
+
"step": 2500
|
1888 |
+
},
|
1889 |
+
{
|
1890 |
+
"epoch": 42.01,
|
1891 |
+
"learning_rate": 1.5827793605571385e-05,
|
1892 |
+
"loss": 0.5725,
|
1893 |
+
"step": 2510
|
1894 |
+
},
|
1895 |
+
{
|
1896 |
+
"epoch": 42.01,
|
1897 |
+
"learning_rate": 1.566951566951567e-05,
|
1898 |
+
"loss": 0.619,
|
1899 |
+
"step": 2520
|
1900 |
+
},
|
1901 |
+
{
|
1902 |
+
"epoch": 42.01,
|
1903 |
+
"learning_rate": 1.5511237733459957e-05,
|
1904 |
+
"loss": 0.3309,
|
1905 |
+
"step": 2530
|
1906 |
+
},
|
1907 |
+
{
|
1908 |
+
"epoch": 42.02,
|
1909 |
+
"eval_accuracy": 0.8110599078341014,
|
1910 |
+
"eval_loss": 0.5805542469024658,
|
1911 |
+
"eval_runtime": 347.0673,
|
1912 |
+
"eval_samples_per_second": 0.625,
|
1913 |
+
"eval_steps_per_second": 0.081,
|
1914 |
+
"step": 2537
|
1915 |
+
},
|
1916 |
+
{
|
1917 |
+
"epoch": 43.0,
|
1918 |
+
"learning_rate": 1.535295979740424e-05,
|
1919 |
+
"loss": 0.5073,
|
1920 |
+
"step": 2540
|
1921 |
+
},
|
1922 |
+
{
|
1923 |
+
"epoch": 43.0,
|
1924 |
+
"learning_rate": 1.5194681861348528e-05,
|
1925 |
+
"loss": 0.5336,
|
1926 |
+
"step": 2550
|
1927 |
+
},
|
1928 |
+
{
|
1929 |
+
"epoch": 43.01,
|
1930 |
+
"learning_rate": 1.5036403925292817e-05,
|
1931 |
+
"loss": 0.4556,
|
1932 |
+
"step": 2560
|
1933 |
+
},
|
1934 |
+
{
|
1935 |
+
"epoch": 43.01,
|
1936 |
+
"learning_rate": 1.4878125989237102e-05,
|
1937 |
+
"loss": 0.5441,
|
1938 |
+
"step": 2570
|
1939 |
+
},
|
1940 |
+
{
|
1941 |
+
"epoch": 43.01,
|
1942 |
+
"learning_rate": 1.4719848053181388e-05,
|
1943 |
+
"loss": 0.4513,
|
1944 |
+
"step": 2580
|
1945 |
+
},
|
1946 |
+
{
|
1947 |
+
"epoch": 43.02,
|
1948 |
+
"learning_rate": 1.4561570117125672e-05,
|
1949 |
+
"loss": 0.3939,
|
1950 |
+
"step": 2590
|
1951 |
+
},
|
1952 |
+
{
|
1953 |
+
"epoch": 43.02,
|
1954 |
+
"eval_accuracy": 0.8248847926267281,
|
1955 |
+
"eval_loss": 0.5745505690574646,
|
1956 |
+
"eval_runtime": 351.9313,
|
1957 |
+
"eval_samples_per_second": 0.617,
|
1958 |
+
"eval_steps_per_second": 0.08,
|
1959 |
+
"step": 2596
|
1960 |
+
},
|
1961 |
+
{
|
1962 |
+
"epoch": 44.0,
|
1963 |
+
"learning_rate": 1.440329218106996e-05,
|
1964 |
+
"loss": 0.4569,
|
1965 |
+
"step": 2600
|
1966 |
+
},
|
1967 |
+
{
|
1968 |
+
"epoch": 44.0,
|
1969 |
+
"learning_rate": 1.4245014245014246e-05,
|
1970 |
+
"loss": 0.3418,
|
1971 |
+
"step": 2610
|
1972 |
+
},
|
1973 |
+
{
|
1974 |
+
"epoch": 44.01,
|
1975 |
+
"learning_rate": 1.408673630895853e-05,
|
1976 |
+
"loss": 0.5716,
|
1977 |
+
"step": 2620
|
1978 |
+
},
|
1979 |
+
{
|
1980 |
+
"epoch": 44.01,
|
1981 |
+
"learning_rate": 1.3928458372902817e-05,
|
1982 |
+
"loss": 0.4198,
|
1983 |
+
"step": 2630
|
1984 |
+
},
|
1985 |
+
{
|
1986 |
+
"epoch": 44.01,
|
1987 |
+
"learning_rate": 1.3770180436847105e-05,
|
1988 |
+
"loss": 0.5132,
|
1989 |
+
"step": 2640
|
1990 |
+
},
|
1991 |
+
{
|
1992 |
+
"epoch": 44.02,
|
1993 |
+
"learning_rate": 1.361190250079139e-05,
|
1994 |
+
"loss": 0.4993,
|
1995 |
+
"step": 2650
|
1996 |
+
},
|
1997 |
+
{
|
1998 |
+
"epoch": 44.02,
|
1999 |
+
"eval_accuracy": 0.8387096774193549,
|
2000 |
+
"eval_loss": 0.6113536357879639,
|
2001 |
+
"eval_runtime": 312.9643,
|
2002 |
+
"eval_samples_per_second": 0.693,
|
2003 |
+
"eval_steps_per_second": 0.089,
|
2004 |
+
"step": 2655
|
2005 |
+
},
|
2006 |
+
{
|
2007 |
+
"epoch": 45.0,
|
2008 |
+
"learning_rate": 1.3453624564735675e-05,
|
2009 |
+
"loss": 0.4347,
|
2010 |
+
"step": 2660
|
2011 |
+
},
|
2012 |
+
{
|
2013 |
+
"epoch": 45.0,
|
2014 |
+
"learning_rate": 1.3295346628679963e-05,
|
2015 |
+
"loss": 0.6201,
|
2016 |
+
"step": 2670
|
2017 |
+
},
|
2018 |
+
{
|
2019 |
+
"epoch": 45.01,
|
2020 |
+
"learning_rate": 1.313706869262425e-05,
|
2021 |
+
"loss": 0.4937,
|
2022 |
+
"step": 2680
|
2023 |
+
},
|
2024 |
+
{
|
2025 |
+
"epoch": 45.01,
|
2026 |
+
"learning_rate": 1.2978790756568535e-05,
|
2027 |
+
"loss": 0.4629,
|
2028 |
+
"step": 2690
|
2029 |
+
},
|
2030 |
+
{
|
2031 |
+
"epoch": 45.01,
|
2032 |
+
"learning_rate": 1.282051282051282e-05,
|
2033 |
+
"loss": 0.6889,
|
2034 |
+
"step": 2700
|
2035 |
+
},
|
2036 |
+
{
|
2037 |
+
"epoch": 45.02,
|
2038 |
+
"learning_rate": 1.2662234884457108e-05,
|
2039 |
+
"loss": 0.3785,
|
2040 |
+
"step": 2710
|
2041 |
+
},
|
2042 |
+
{
|
2043 |
+
"epoch": 45.02,
|
2044 |
+
"eval_accuracy": 0.8018433179723502,
|
2045 |
+
"eval_loss": 0.6317055821418762,
|
2046 |
+
"eval_runtime": 311.0444,
|
2047 |
+
"eval_samples_per_second": 0.698,
|
2048 |
+
"eval_steps_per_second": 0.09,
|
2049 |
+
"step": 2714
|
2050 |
+
},
|
2051 |
+
{
|
2052 |
+
"epoch": 46.0,
|
2053 |
+
"learning_rate": 1.2503956948401394e-05,
|
2054 |
+
"loss": 0.3386,
|
2055 |
+
"step": 2720
|
2056 |
+
},
|
2057 |
+
{
|
2058 |
+
"epoch": 46.0,
|
2059 |
+
"learning_rate": 1.2345679012345678e-05,
|
2060 |
+
"loss": 0.5517,
|
2061 |
+
"step": 2730
|
2062 |
+
},
|
2063 |
+
{
|
2064 |
+
"epoch": 46.01,
|
2065 |
+
"learning_rate": 1.2187401076289966e-05,
|
2066 |
+
"loss": 0.3834,
|
2067 |
+
"step": 2740
|
2068 |
+
},
|
2069 |
+
{
|
2070 |
+
"epoch": 46.01,
|
2071 |
+
"learning_rate": 1.2029123140234252e-05,
|
2072 |
+
"loss": 0.4447,
|
2073 |
+
"step": 2750
|
2074 |
+
},
|
2075 |
+
{
|
2076 |
+
"epoch": 46.01,
|
2077 |
+
"learning_rate": 1.1870845204178538e-05,
|
2078 |
+
"loss": 0.3444,
|
2079 |
+
"step": 2760
|
2080 |
+
},
|
2081 |
+
{
|
2082 |
+
"epoch": 46.02,
|
2083 |
+
"learning_rate": 1.1712567268122825e-05,
|
2084 |
+
"loss": 0.5224,
|
2085 |
+
"step": 2770
|
2086 |
+
},
|
2087 |
+
{
|
2088 |
+
"epoch": 46.02,
|
2089 |
+
"eval_accuracy": 0.7972350230414746,
|
2090 |
+
"eval_loss": 0.666746199131012,
|
2091 |
+
"eval_runtime": 298.4433,
|
2092 |
+
"eval_samples_per_second": 0.727,
|
2093 |
+
"eval_steps_per_second": 0.094,
|
2094 |
+
"step": 2773
|
2095 |
+
},
|
2096 |
+
{
|
2097 |
+
"epoch": 47.0,
|
2098 |
+
"learning_rate": 1.155428933206711e-05,
|
2099 |
+
"loss": 0.4419,
|
2100 |
+
"step": 2780
|
2101 |
+
},
|
2102 |
+
{
|
2103 |
+
"epoch": 47.0,
|
2104 |
+
"learning_rate": 1.1396011396011397e-05,
|
2105 |
+
"loss": 0.3244,
|
2106 |
+
"step": 2790
|
2107 |
+
},
|
2108 |
+
{
|
2109 |
+
"epoch": 47.01,
|
2110 |
+
"learning_rate": 1.1237733459955681e-05,
|
2111 |
+
"loss": 0.5273,
|
2112 |
+
"step": 2800
|
2113 |
+
},
|
2114 |
+
{
|
2115 |
+
"epoch": 47.01,
|
2116 |
+
"learning_rate": 1.107945552389997e-05,
|
2117 |
+
"loss": 0.3442,
|
2118 |
+
"step": 2810
|
2119 |
+
},
|
2120 |
+
{
|
2121 |
+
"epoch": 47.01,
|
2122 |
+
"learning_rate": 1.0921177587844255e-05,
|
2123 |
+
"loss": 0.4701,
|
2124 |
+
"step": 2820
|
2125 |
+
},
|
2126 |
+
{
|
2127 |
+
"epoch": 47.02,
|
2128 |
+
"learning_rate": 1.0762899651788542e-05,
|
2129 |
+
"loss": 0.5705,
|
2130 |
+
"step": 2830
|
2131 |
+
},
|
2132 |
+
{
|
2133 |
+
"epoch": 47.02,
|
2134 |
+
"eval_accuracy": 0.7926267281105991,
|
2135 |
+
"eval_loss": 0.6382005214691162,
|
2136 |
+
"eval_runtime": 298.8237,
|
2137 |
+
"eval_samples_per_second": 0.726,
|
2138 |
+
"eval_steps_per_second": 0.094,
|
2139 |
+
"step": 2832
|
2140 |
+
},
|
2141 |
+
{
|
2142 |
+
"epoch": 48.0,
|
2143 |
+
"learning_rate": 1.0604621715732828e-05,
|
2144 |
+
"loss": 0.5681,
|
2145 |
+
"step": 2840
|
2146 |
+
},
|
2147 |
+
{
|
2148 |
+
"epoch": 48.01,
|
2149 |
+
"learning_rate": 1.0446343779677114e-05,
|
2150 |
+
"loss": 0.4655,
|
2151 |
+
"step": 2850
|
2152 |
+
},
|
2153 |
+
{
|
2154 |
+
"epoch": 48.01,
|
2155 |
+
"learning_rate": 1.02880658436214e-05,
|
2156 |
+
"loss": 0.5486,
|
2157 |
+
"step": 2860
|
2158 |
+
},
|
2159 |
+
{
|
2160 |
+
"epoch": 48.01,
|
2161 |
+
"learning_rate": 1.0129787907565686e-05,
|
2162 |
+
"loss": 0.4268,
|
2163 |
+
"step": 2870
|
2164 |
+
},
|
2165 |
+
{
|
2166 |
+
"epoch": 48.01,
|
2167 |
+
"learning_rate": 9.971509971509972e-06,
|
2168 |
+
"loss": 0.5592,
|
2169 |
+
"step": 2880
|
2170 |
+
},
|
2171 |
+
{
|
2172 |
+
"epoch": 48.02,
|
2173 |
+
"learning_rate": 9.813232035454257e-06,
|
2174 |
+
"loss": 0.3342,
|
2175 |
+
"step": 2890
|
2176 |
+
},
|
2177 |
+
{
|
2178 |
+
"epoch": 48.02,
|
2179 |
+
"eval_accuracy": 0.815668202764977,
|
2180 |
+
"eval_loss": 0.5592498779296875,
|
2181 |
+
"eval_runtime": 307.6803,
|
2182 |
+
"eval_samples_per_second": 0.705,
|
2183 |
+
"eval_steps_per_second": 0.091,
|
2184 |
+
"step": 2891
|
2185 |
+
},
|
2186 |
+
{
|
2187 |
+
"epoch": 49.0,
|
2188 |
+
"learning_rate": 9.654954099398545e-06,
|
2189 |
+
"loss": 0.4835,
|
2190 |
+
"step": 2900
|
2191 |
+
},
|
2192 |
+
{
|
2193 |
+
"epoch": 49.01,
|
2194 |
+
"learning_rate": 9.49667616334283e-06,
|
2195 |
+
"loss": 0.3971,
|
2196 |
+
"step": 2910
|
2197 |
+
},
|
2198 |
+
{
|
2199 |
+
"epoch": 49.01,
|
2200 |
+
"learning_rate": 9.338398227287117e-06,
|
2201 |
+
"loss": 0.4908,
|
2202 |
+
"step": 2920
|
2203 |
+
},
|
2204 |
+
{
|
2205 |
+
"epoch": 49.01,
|
2206 |
+
"learning_rate": 9.180120291231403e-06,
|
2207 |
+
"loss": 0.4665,
|
2208 |
+
"step": 2930
|
2209 |
+
},
|
2210 |
+
{
|
2211 |
+
"epoch": 49.01,
|
2212 |
+
"learning_rate": 9.02184235517569e-06,
|
2213 |
+
"loss": 0.4262,
|
2214 |
+
"step": 2940
|
2215 |
+
},
|
2216 |
+
{
|
2217 |
+
"epoch": 49.02,
|
2218 |
+
"learning_rate": 8.863564419119975e-06,
|
2219 |
+
"loss": 0.5044,
|
2220 |
+
"step": 2950
|
2221 |
+
},
|
2222 |
+
{
|
2223 |
+
"epoch": 49.02,
|
2224 |
+
"eval_accuracy": 0.7926267281105991,
|
2225 |
+
"eval_loss": 0.574846625328064,
|
2226 |
+
"eval_runtime": 296.7758,
|
2227 |
+
"eval_samples_per_second": 0.731,
|
2228 |
+
"eval_steps_per_second": 0.094,
|
2229 |
+
"step": 2950
|
2230 |
+
},
|
2231 |
+
{
|
2232 |
+
"epoch": 50.0,
|
2233 |
+
"learning_rate": 8.705286483064262e-06,
|
2234 |
+
"loss": 0.5795,
|
2235 |
+
"step": 2960
|
2236 |
+
},
|
2237 |
+
{
|
2238 |
+
"epoch": 50.01,
|
2239 |
+
"learning_rate": 8.547008547008548e-06,
|
2240 |
+
"loss": 0.6522,
|
2241 |
+
"step": 2970
|
2242 |
+
},
|
2243 |
+
{
|
2244 |
+
"epoch": 50.01,
|
2245 |
+
"learning_rate": 8.388730610952832e-06,
|
2246 |
+
"loss": 0.4391,
|
2247 |
+
"step": 2980
|
2248 |
+
},
|
2249 |
+
{
|
2250 |
+
"epoch": 50.01,
|
2251 |
+
"learning_rate": 8.23045267489712e-06,
|
2252 |
+
"loss": 0.3763,
|
2253 |
+
"step": 2990
|
2254 |
+
},
|
2255 |
+
{
|
2256 |
+
"epoch": 50.01,
|
2257 |
+
"learning_rate": 8.072174738841406e-06,
|
2258 |
+
"loss": 0.3838,
|
2259 |
+
"step": 3000
|
2260 |
+
},
|
2261 |
+
{
|
2262 |
+
"epoch": 50.02,
|
2263 |
+
"eval_accuracy": 0.7788018433179723,
|
2264 |
+
"eval_loss": 0.6050373315811157,
|
2265 |
+
"eval_runtime": 338.1899,
|
2266 |
+
"eval_samples_per_second": 0.642,
|
2267 |
+
"eval_steps_per_second": 0.083,
|
2268 |
+
"step": 3009
|
2269 |
+
},
|
2270 |
+
{
|
2271 |
+
"epoch": 51.0,
|
2272 |
+
"learning_rate": 7.913896802785692e-06,
|
2273 |
+
"loss": 0.3898,
|
2274 |
+
"step": 3010
|
2275 |
+
},
|
2276 |
+
{
|
2277 |
+
"epoch": 51.0,
|
2278 |
+
"learning_rate": 7.755618866729978e-06,
|
2279 |
+
"loss": 0.4642,
|
2280 |
+
"step": 3020
|
2281 |
+
},
|
2282 |
+
{
|
2283 |
+
"epoch": 51.01,
|
2284 |
+
"learning_rate": 7.597340930674264e-06,
|
2285 |
+
"loss": 0.4582,
|
2286 |
+
"step": 3030
|
2287 |
+
},
|
2288 |
+
{
|
2289 |
+
"epoch": 51.01,
|
2290 |
+
"learning_rate": 7.439062994618551e-06,
|
2291 |
+
"loss": 0.4935,
|
2292 |
+
"step": 3040
|
2293 |
+
},
|
2294 |
+
{
|
2295 |
+
"epoch": 51.01,
|
2296 |
+
"learning_rate": 7.280785058562836e-06,
|
2297 |
+
"loss": 0.3878,
|
2298 |
+
"step": 3050
|
2299 |
+
},
|
2300 |
+
{
|
2301 |
+
"epoch": 51.01,
|
2302 |
+
"learning_rate": 7.122507122507123e-06,
|
2303 |
+
"loss": 0.5099,
|
2304 |
+
"step": 3060
|
2305 |
+
},
|
2306 |
+
{
|
2307 |
+
"epoch": 51.02,
|
2308 |
+
"eval_accuracy": 0.7603686635944701,
|
2309 |
+
"eval_loss": 0.6556740999221802,
|
2310 |
+
"eval_runtime": 332.6773,
|
2311 |
+
"eval_samples_per_second": 0.652,
|
2312 |
+
"eval_steps_per_second": 0.084,
|
2313 |
+
"step": 3068
|
2314 |
+
},
|
2315 |
+
{
|
2316 |
+
"epoch": 52.0,
|
2317 |
+
"learning_rate": 6.964229186451408e-06,
|
2318 |
+
"loss": 0.4264,
|
2319 |
+
"step": 3070
|
2320 |
+
},
|
2321 |
+
{
|
2322 |
+
"epoch": 52.0,
|
2323 |
+
"learning_rate": 6.805951250395695e-06,
|
2324 |
+
"loss": 0.378,
|
2325 |
+
"step": 3080
|
2326 |
+
},
|
2327 |
+
{
|
2328 |
+
"epoch": 52.01,
|
2329 |
+
"learning_rate": 6.6476733143399815e-06,
|
2330 |
+
"loss": 0.4568,
|
2331 |
+
"step": 3090
|
2332 |
+
},
|
2333 |
+
{
|
2334 |
+
"epoch": 52.01,
|
2335 |
+
"learning_rate": 6.489395378284268e-06,
|
2336 |
+
"loss": 0.4432,
|
2337 |
+
"step": 3100
|
2338 |
+
},
|
2339 |
+
{
|
2340 |
+
"epoch": 52.01,
|
2341 |
+
"learning_rate": 6.331117442228554e-06,
|
2342 |
+
"loss": 0.523,
|
2343 |
+
"step": 3110
|
2344 |
+
},
|
2345 |
+
{
|
2346 |
+
"epoch": 52.01,
|
2347 |
+
"learning_rate": 6.172839506172839e-06,
|
2348 |
+
"loss": 0.4335,
|
2349 |
+
"step": 3120
|
2350 |
+
},
|
2351 |
+
{
|
2352 |
+
"epoch": 52.02,
|
2353 |
+
"eval_accuracy": 0.7511520737327189,
|
2354 |
+
"eval_loss": 0.7118790149688721,
|
2355 |
+
"eval_runtime": 337.6952,
|
2356 |
+
"eval_samples_per_second": 0.643,
|
2357 |
+
"eval_steps_per_second": 0.083,
|
2358 |
+
"step": 3127
|
2359 |
+
},
|
2360 |
+
{
|
2361 |
+
"epoch": 53.0,
|
2362 |
+
"learning_rate": 6.014561570117126e-06,
|
2363 |
+
"loss": 0.3422,
|
2364 |
+
"step": 3130
|
2365 |
+
},
|
2366 |
+
{
|
2367 |
+
"epoch": 53.0,
|
2368 |
+
"learning_rate": 5.856283634061412e-06,
|
2369 |
+
"loss": 0.3893,
|
2370 |
+
"step": 3140
|
2371 |
+
},
|
2372 |
+
{
|
2373 |
+
"epoch": 53.01,
|
2374 |
+
"learning_rate": 5.6980056980056985e-06,
|
2375 |
+
"loss": 0.407,
|
2376 |
+
"step": 3150
|
2377 |
+
},
|
2378 |
+
{
|
2379 |
+
"epoch": 53.01,
|
2380 |
+
"learning_rate": 5.539727761949985e-06,
|
2381 |
+
"loss": 0.561,
|
2382 |
+
"step": 3160
|
2383 |
+
},
|
2384 |
+
{
|
2385 |
+
"epoch": 53.01,
|
2386 |
+
"learning_rate": 5.381449825894271e-06,
|
2387 |
+
"loss": 0.2949,
|
2388 |
+
"step": 3170
|
2389 |
+
},
|
2390 |
+
{
|
2391 |
+
"epoch": 53.02,
|
2392 |
+
"learning_rate": 5.223171889838557e-06,
|
2393 |
+
"loss": 0.4122,
|
2394 |
+
"step": 3180
|
2395 |
+
},
|
2396 |
+
{
|
2397 |
+
"epoch": 53.02,
|
2398 |
+
"eval_accuracy": 0.7788018433179723,
|
2399 |
+
"eval_loss": 0.6562320590019226,
|
2400 |
+
"eval_runtime": 360.9203,
|
2401 |
+
"eval_samples_per_second": 0.601,
|
2402 |
+
"eval_steps_per_second": 0.078,
|
2403 |
+
"step": 3186
|
2404 |
+
},
|
2405 |
+
{
|
2406 |
+
"epoch": 54.0,
|
2407 |
+
"learning_rate": 5.064893953782843e-06,
|
2408 |
+
"loss": 0.291,
|
2409 |
+
"step": 3190
|
2410 |
+
},
|
2411 |
+
{
|
2412 |
+
"epoch": 54.0,
|
2413 |
+
"learning_rate": 4.906616017727128e-06,
|
2414 |
+
"loss": 0.3532,
|
2415 |
+
"step": 3200
|
2416 |
+
},
|
2417 |
+
{
|
2418 |
+
"epoch": 54.01,
|
2419 |
+
"learning_rate": 4.748338081671415e-06,
|
2420 |
+
"loss": 0.3911,
|
2421 |
+
"step": 3210
|
2422 |
+
},
|
2423 |
+
{
|
2424 |
+
"epoch": 54.01,
|
2425 |
+
"learning_rate": 4.5900601456157015e-06,
|
2426 |
+
"loss": 0.5269,
|
2427 |
+
"step": 3220
|
2428 |
+
},
|
2429 |
+
{
|
2430 |
+
"epoch": 54.01,
|
2431 |
+
"learning_rate": 4.431782209559988e-06,
|
2432 |
+
"loss": 0.3041,
|
2433 |
+
"step": 3230
|
2434 |
+
},
|
2435 |
+
{
|
2436 |
+
"epoch": 54.02,
|
2437 |
+
"learning_rate": 4.273504273504274e-06,
|
2438 |
+
"loss": 0.4431,
|
2439 |
+
"step": 3240
|
2440 |
+
},
|
2441 |
+
{
|
2442 |
+
"epoch": 54.02,
|
2443 |
+
"eval_accuracy": 0.7649769585253456,
|
2444 |
+
"eval_loss": 0.6700997948646545,
|
2445 |
+
"eval_runtime": 319.5418,
|
2446 |
+
"eval_samples_per_second": 0.679,
|
2447 |
+
"eval_steps_per_second": 0.088,
|
2448 |
+
"step": 3245
|
2449 |
+
},
|
2450 |
+
{
|
2451 |
+
"epoch": 55.0,
|
2452 |
+
"learning_rate": 4.11522633744856e-06,
|
2453 |
+
"loss": 0.5306,
|
2454 |
+
"step": 3250
|
2455 |
+
},
|
2456 |
+
{
|
2457 |
+
"epoch": 55.0,
|
2458 |
+
"learning_rate": 3.956948401392846e-06,
|
2459 |
+
"loss": 0.5086,
|
2460 |
+
"step": 3260
|
2461 |
+
},
|
2462 |
+
{
|
2463 |
+
"epoch": 55.01,
|
2464 |
+
"learning_rate": 3.798670465337132e-06,
|
2465 |
+
"loss": 0.3345,
|
2466 |
+
"step": 3270
|
2467 |
+
},
|
2468 |
+
{
|
2469 |
+
"epoch": 55.01,
|
2470 |
+
"learning_rate": 3.640392529281418e-06,
|
2471 |
+
"loss": 0.3607,
|
2472 |
+
"step": 3280
|
2473 |
+
},
|
2474 |
+
{
|
2475 |
+
"epoch": 55.01,
|
2476 |
+
"learning_rate": 3.482114593225704e-06,
|
2477 |
+
"loss": 0.4845,
|
2478 |
+
"step": 3290
|
2479 |
+
},
|
2480 |
+
{
|
2481 |
+
"epoch": 55.02,
|
2482 |
+
"learning_rate": 3.3238366571699908e-06,
|
2483 |
+
"loss": 0.4536,
|
2484 |
+
"step": 3300
|
2485 |
+
},
|
2486 |
+
{
|
2487 |
+
"epoch": 55.02,
|
2488 |
+
"eval_accuracy": 0.7695852534562212,
|
2489 |
+
"eval_loss": 0.6659231781959534,
|
2490 |
+
"eval_runtime": 312.5964,
|
2491 |
+
"eval_samples_per_second": 0.694,
|
2492 |
+
"eval_steps_per_second": 0.09,
|
2493 |
+
"step": 3304
|
2494 |
+
},
|
2495 |
+
{
|
2496 |
+
"epoch": 56.0,
|
2497 |
+
"learning_rate": 3.165558721114277e-06,
|
2498 |
+
"loss": 0.3168,
|
2499 |
+
"step": 3310
|
2500 |
+
},
|
2501 |
+
{
|
2502 |
+
"epoch": 56.0,
|
2503 |
+
"learning_rate": 3.007280785058563e-06,
|
2504 |
+
"loss": 0.459,
|
2505 |
+
"step": 3320
|
2506 |
+
},
|
2507 |
+
{
|
2508 |
+
"epoch": 56.01,
|
2509 |
+
"learning_rate": 2.8490028490028492e-06,
|
2510 |
+
"loss": 0.4485,
|
2511 |
+
"step": 3330
|
2512 |
+
},
|
2513 |
+
{
|
2514 |
+
"epoch": 56.01,
|
2515 |
+
"learning_rate": 2.6907249129471354e-06,
|
2516 |
+
"loss": 0.4044,
|
2517 |
+
"step": 3340
|
2518 |
+
},
|
2519 |
+
{
|
2520 |
+
"epoch": 56.01,
|
2521 |
+
"learning_rate": 2.5324469768914215e-06,
|
2522 |
+
"loss": 0.4181,
|
2523 |
+
"step": 3350
|
2524 |
+
},
|
2525 |
+
{
|
2526 |
+
"epoch": 56.02,
|
2527 |
+
"learning_rate": 2.3741690408357077e-06,
|
2528 |
+
"loss": 0.3867,
|
2529 |
+
"step": 3360
|
2530 |
+
},
|
2531 |
+
{
|
2532 |
+
"epoch": 56.02,
|
2533 |
+
"eval_accuracy": 0.7788018433179723,
|
2534 |
+
"eval_loss": 0.6631873846054077,
|
2535 |
+
"eval_runtime": 302.7333,
|
2536 |
+
"eval_samples_per_second": 0.717,
|
2537 |
+
"eval_steps_per_second": 0.092,
|
2538 |
+
"step": 3363
|
2539 |
+
},
|
2540 |
+
{
|
2541 |
+
"epoch": 57.0,
|
2542 |
+
"learning_rate": 2.215891104779994e-06,
|
2543 |
+
"loss": 0.4615,
|
2544 |
+
"step": 3370
|
2545 |
+
},
|
2546 |
+
{
|
2547 |
+
"epoch": 57.0,
|
2548 |
+
"learning_rate": 2.05761316872428e-06,
|
2549 |
+
"loss": 0.459,
|
2550 |
+
"step": 3380
|
2551 |
+
},
|
2552 |
+
{
|
2553 |
+
"epoch": 57.01,
|
2554 |
+
"learning_rate": 1.899335232668566e-06,
|
2555 |
+
"loss": 0.2905,
|
2556 |
+
"step": 3390
|
2557 |
+
},
|
2558 |
+
{
|
2559 |
+
"epoch": 57.01,
|
2560 |
+
"learning_rate": 1.741057296612852e-06,
|
2561 |
+
"loss": 0.3776,
|
2562 |
+
"step": 3400
|
2563 |
+
},
|
2564 |
+
{
|
2565 |
+
"epoch": 57.01,
|
2566 |
+
"learning_rate": 1.5827793605571385e-06,
|
2567 |
+
"loss": 0.4584,
|
2568 |
+
"step": 3410
|
2569 |
+
},
|
2570 |
+
{
|
2571 |
+
"epoch": 57.02,
|
2572 |
+
"learning_rate": 1.4245014245014246e-06,
|
2573 |
+
"loss": 0.3878,
|
2574 |
+
"step": 3420
|
2575 |
+
},
|
2576 |
+
{
|
2577 |
+
"epoch": 57.02,
|
2578 |
+
"eval_accuracy": 0.7741935483870968,
|
2579 |
+
"eval_loss": 0.6911003589630127,
|
2580 |
+
"eval_runtime": 288.2901,
|
2581 |
+
"eval_samples_per_second": 0.753,
|
2582 |
+
"eval_steps_per_second": 0.097,
|
2583 |
+
"step": 3422
|
2584 |
+
},
|
2585 |
+
{
|
2586 |
+
"epoch": 58.0,
|
2587 |
+
"learning_rate": 1.2662234884457108e-06,
|
2588 |
+
"loss": 0.3642,
|
2589 |
+
"step": 3430
|
2590 |
+
},
|
2591 |
+
{
|
2592 |
+
"epoch": 58.01,
|
2593 |
+
"learning_rate": 1.107945552389997e-06,
|
2594 |
+
"loss": 0.5532,
|
2595 |
+
"step": 3440
|
2596 |
+
},
|
2597 |
+
{
|
2598 |
+
"epoch": 58.01,
|
2599 |
+
"learning_rate": 9.49667616334283e-07,
|
2600 |
+
"loss": 0.3968,
|
2601 |
+
"step": 3450
|
2602 |
+
},
|
2603 |
+
{
|
2604 |
+
"epoch": 58.01,
|
2605 |
+
"learning_rate": 7.913896802785692e-07,
|
2606 |
+
"loss": 0.4202,
|
2607 |
+
"step": 3460
|
2608 |
+
},
|
2609 |
+
{
|
2610 |
+
"epoch": 58.01,
|
2611 |
+
"learning_rate": 6.331117442228554e-07,
|
2612 |
+
"loss": 0.5291,
|
2613 |
+
"step": 3470
|
2614 |
+
},
|
2615 |
+
{
|
2616 |
+
"epoch": 58.02,
|
2617 |
+
"learning_rate": 4.748338081671415e-07,
|
2618 |
+
"loss": 0.3853,
|
2619 |
+
"step": 3480
|
2620 |
+
},
|
2621 |
+
{
|
2622 |
+
"epoch": 58.02,
|
2623 |
+
"eval_accuracy": 0.7788018433179723,
|
2624 |
+
"eval_loss": 0.6931061148643494,
|
2625 |
+
"eval_runtime": 338.901,
|
2626 |
+
"eval_samples_per_second": 0.64,
|
2627 |
+
"eval_steps_per_second": 0.083,
|
2628 |
+
"step": 3481
|
2629 |
+
},
|
2630 |
+
{
|
2631 |
+
"epoch": 59.0,
|
2632 |
+
"learning_rate": 3.165558721114277e-07,
|
2633 |
+
"loss": 0.4615,
|
2634 |
+
"step": 3490
|
2635 |
+
},
|
2636 |
+
{
|
2637 |
+
"epoch": 59.01,
|
2638 |
+
"learning_rate": 1.5827793605571385e-07,
|
2639 |
+
"loss": 0.4759,
|
2640 |
+
"step": 3500
|
2641 |
+
},
|
2642 |
+
{
|
2643 |
+
"epoch": 59.01,
|
2644 |
+
"learning_rate": 0.0,
|
2645 |
+
"loss": 0.3268,
|
2646 |
+
"step": 3510
|
2647 |
+
},
|
2648 |
+
{
|
2649 |
+
"epoch": 59.01,
|
2650 |
+
"eval_accuracy": 0.7788018433179723,
|
2651 |
+
"eval_loss": 0.6913787126541138,
|
2652 |
+
"eval_runtime": 307.5387,
|
2653 |
+
"eval_samples_per_second": 0.706,
|
2654 |
+
"eval_steps_per_second": 0.091,
|
2655 |
+
"step": 3510
|
2656 |
+
},
|
2657 |
+
{
|
2658 |
+
"epoch": 59.01,
|
2659 |
+
"step": 3510,
|
2660 |
+
"total_flos": 3.476987046291161e+19,
|
2661 |
+
"train_loss": 0.68851605188473,
|
2662 |
+
"train_runtime": 67730.7107,
|
2663 |
+
"train_samples_per_second": 0.415,
|
2664 |
+
"train_steps_per_second": 0.052
|
2665 |
+
},
|
2666 |
+
{
|
2667 |
+
"epoch": 59.01,
|
2668 |
+
"eval_accuracy": 0.8148148148148148,
|
2669 |
+
"eval_loss": 0.567668616771698,
|
2670 |
+
"eval_runtime": 331.762,
|
2671 |
+
"eval_samples_per_second": 0.651,
|
2672 |
+
"eval_steps_per_second": 0.081,
|
2673 |
+
"step": 3510
|
2674 |
+
},
|
2675 |
+
{
|
2676 |
+
"epoch": 59.01,
|
2677 |
+
"eval_accuracy": 0.8148148148148148,
|
2678 |
+
"eval_loss": 0.5676685571670532,
|
2679 |
+
"eval_runtime": 292.9189,
|
2680 |
+
"eval_samples_per_second": 0.737,
|
2681 |
+
"eval_steps_per_second": 0.092,
|
2682 |
+
"step": 3510
|
2683 |
+
}
|
2684 |
+
],
|
2685 |
+
"logging_steps": 10,
|
2686 |
+
"max_steps": 3510,
|
2687 |
+
"num_train_epochs": 9223372036854775807,
|
2688 |
+
"save_steps": 500,
|
2689 |
+
"total_flos": 3.476987046291161e+19,
|
2690 |
+
"trial_name": null,
|
2691 |
+
"trial_params": null
|
2692 |
+
}
|