Commit
•
5dda484
1
Parent(s):
f8cc129
YAY!!
Browse files- all_results.json +13 -0
- eval_results.json +8 -0
- runs/Sep02_13-36-21_e0877e99f71e/events.out.tfevents.1662128357.e0877e99f71e.69.2 +3 -0
- train_results.json +8 -0
- trainer_state.json +1165 -0
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"eval_accuracy": 0.9373007438894793,
|
| 4 |
+
"eval_loss": 0.2868094742298126,
|
| 5 |
+
"eval_runtime": 41.7259,
|
| 6 |
+
"eval_samples_per_second": 22.552,
|
| 7 |
+
"eval_steps_per_second": 2.828,
|
| 8 |
+
"total_flos": 2.6257169541360845e+18,
|
| 9 |
+
"train_loss": 0.509146851408589,
|
| 10 |
+
"train_runtime": 2159.6535,
|
| 11 |
+
"train_samples_per_second": 12.335,
|
| 12 |
+
"train_steps_per_second": 0.771
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"eval_accuracy": 0.9373007438894793,
|
| 4 |
+
"eval_loss": 0.2868094742298126,
|
| 5 |
+
"eval_runtime": 41.7259,
|
| 6 |
+
"eval_samples_per_second": 22.552,
|
| 7 |
+
"eval_steps_per_second": 2.828
|
| 8 |
+
}
|
runs/Sep02_13-36-21_e0877e99f71e/events.out.tfevents.1662128357.e0877e99f71e.69.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d51cfc9711add2e20f8810785d48b74447c5235ddfcf064cb319ea3b28ec7c18
|
| 3 |
+
size 363
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"total_flos": 2.6257169541360845e+18,
|
| 4 |
+
"train_loss": 0.509146851408589,
|
| 5 |
+
"train_runtime": 2159.6535,
|
| 6 |
+
"train_samples_per_second": 12.335,
|
| 7 |
+
"train_steps_per_second": 0.771
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1165 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.2868094742298126,
|
| 3 |
+
"best_model_checkpoint": "DrishtiSharma/finetuned-SwinT-Indian-Food-Classification-v1/checkpoint-1400",
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"global_step": 1665,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.03,
|
| 12 |
+
"learning_rate": 0.0001992792792792793,
|
| 13 |
+
"loss": 8.5776,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.06,
|
| 18 |
+
"learning_rate": 0.00019807807807807807,
|
| 19 |
+
"loss": 4.601,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.09,
|
| 24 |
+
"learning_rate": 0.00019687687687687687,
|
| 25 |
+
"loss": 2.306,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.12,
|
| 30 |
+
"learning_rate": 0.00019567567567567567,
|
| 31 |
+
"loss": 1.784,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.15,
|
| 36 |
+
"learning_rate": 0.00019447447447447448,
|
| 37 |
+
"loss": 1.8375,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.18,
|
| 42 |
+
"learning_rate": 0.0001932732732732733,
|
| 43 |
+
"loss": 1.2307,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.21,
|
| 48 |
+
"learning_rate": 0.00019207207207207208,
|
| 49 |
+
"loss": 1.2008,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.24,
|
| 54 |
+
"learning_rate": 0.00019087087087087088,
|
| 55 |
+
"loss": 1.1303,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.27,
|
| 60 |
+
"learning_rate": 0.00018966966966966968,
|
| 61 |
+
"loss": 0.7806,
|
| 62 |
+
"step": 90
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.3,
|
| 66 |
+
"learning_rate": 0.00018846846846846848,
|
| 67 |
+
"loss": 1.2433,
|
| 68 |
+
"step": 100
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.3,
|
| 72 |
+
"eval_accuracy": 0.8193411264612115,
|
| 73 |
+
"eval_loss": 0.7067487239837646,
|
| 74 |
+
"eval_runtime": 41.0344,
|
| 75 |
+
"eval_samples_per_second": 22.932,
|
| 76 |
+
"eval_steps_per_second": 2.876,
|
| 77 |
+
"step": 100
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 0.33,
|
| 81 |
+
"learning_rate": 0.00018726726726726726,
|
| 82 |
+
"loss": 1.2738,
|
| 83 |
+
"step": 110
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 0.36,
|
| 87 |
+
"learning_rate": 0.00018606606606606606,
|
| 88 |
+
"loss": 0.9205,
|
| 89 |
+
"step": 120
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.39,
|
| 93 |
+
"learning_rate": 0.00018486486486486486,
|
| 94 |
+
"loss": 1.0657,
|
| 95 |
+
"step": 130
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.42,
|
| 99 |
+
"learning_rate": 0.00018366366366366366,
|
| 100 |
+
"loss": 0.7326,
|
| 101 |
+
"step": 140
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.45,
|
| 105 |
+
"learning_rate": 0.0001824624624624625,
|
| 106 |
+
"loss": 0.9267,
|
| 107 |
+
"step": 150
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.48,
|
| 111 |
+
"learning_rate": 0.00018126126126126127,
|
| 112 |
+
"loss": 0.6556,
|
| 113 |
+
"step": 160
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.51,
|
| 117 |
+
"learning_rate": 0.00018006006006006007,
|
| 118 |
+
"loss": 0.9394,
|
| 119 |
+
"step": 170
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 0.54,
|
| 123 |
+
"learning_rate": 0.00017885885885885887,
|
| 124 |
+
"loss": 0.8358,
|
| 125 |
+
"step": 180
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 0.57,
|
| 129 |
+
"learning_rate": 0.00017765765765765767,
|
| 130 |
+
"loss": 0.8192,
|
| 131 |
+
"step": 190
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 0.6,
|
| 135 |
+
"learning_rate": 0.00017645645645645647,
|
| 136 |
+
"loss": 0.6458,
|
| 137 |
+
"step": 200
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.6,
|
| 141 |
+
"eval_accuracy": 0.8788522848034006,
|
| 142 |
+
"eval_loss": 0.4691758453845978,
|
| 143 |
+
"eval_runtime": 40.9715,
|
| 144 |
+
"eval_samples_per_second": 22.967,
|
| 145 |
+
"eval_steps_per_second": 2.88,
|
| 146 |
+
"step": 200
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.63,
|
| 150 |
+
"learning_rate": 0.00017525525525525525,
|
| 151 |
+
"loss": 0.7785,
|
| 152 |
+
"step": 210
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.66,
|
| 156 |
+
"learning_rate": 0.00017405405405405405,
|
| 157 |
+
"loss": 0.7238,
|
| 158 |
+
"step": 220
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.69,
|
| 162 |
+
"learning_rate": 0.00017285285285285285,
|
| 163 |
+
"loss": 0.6252,
|
| 164 |
+
"step": 230
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.72,
|
| 168 |
+
"learning_rate": 0.00017165165165165168,
|
| 169 |
+
"loss": 0.5769,
|
| 170 |
+
"step": 240
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.75,
|
| 174 |
+
"learning_rate": 0.00017045045045045045,
|
| 175 |
+
"loss": 0.7919,
|
| 176 |
+
"step": 250
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.78,
|
| 180 |
+
"learning_rate": 0.00016924924924924926,
|
| 181 |
+
"loss": 0.9191,
|
| 182 |
+
"step": 260
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.81,
|
| 186 |
+
"learning_rate": 0.00016804804804804806,
|
| 187 |
+
"loss": 0.7977,
|
| 188 |
+
"step": 270
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.84,
|
| 192 |
+
"learning_rate": 0.00016684684684684686,
|
| 193 |
+
"loss": 1.0148,
|
| 194 |
+
"step": 280
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.87,
|
| 198 |
+
"learning_rate": 0.00016564564564564566,
|
| 199 |
+
"loss": 0.6755,
|
| 200 |
+
"step": 290
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.9,
|
| 204 |
+
"learning_rate": 0.00016444444444444444,
|
| 205 |
+
"loss": 0.635,
|
| 206 |
+
"step": 300
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.9,
|
| 210 |
+
"eval_accuracy": 0.8682252922422954,
|
| 211 |
+
"eval_loss": 0.48639556765556335,
|
| 212 |
+
"eval_runtime": 40.8306,
|
| 213 |
+
"eval_samples_per_second": 23.046,
|
| 214 |
+
"eval_steps_per_second": 2.89,
|
| 215 |
+
"step": 300
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 0.93,
|
| 219 |
+
"learning_rate": 0.00016324324324324324,
|
| 220 |
+
"loss": 0.6479,
|
| 221 |
+
"step": 310
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 0.96,
|
| 225 |
+
"learning_rate": 0.00016204204204204204,
|
| 226 |
+
"loss": 0.6987,
|
| 227 |
+
"step": 320
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.99,
|
| 231 |
+
"learning_rate": 0.00016084084084084087,
|
| 232 |
+
"loss": 0.6282,
|
| 233 |
+
"step": 330
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.02,
|
| 237 |
+
"learning_rate": 0.00015963963963963964,
|
| 238 |
+
"loss": 0.6216,
|
| 239 |
+
"step": 340
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 1.05,
|
| 243 |
+
"learning_rate": 0.00015843843843843844,
|
| 244 |
+
"loss": 0.539,
|
| 245 |
+
"step": 350
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 1.08,
|
| 249 |
+
"learning_rate": 0.00015723723723723725,
|
| 250 |
+
"loss": 0.2988,
|
| 251 |
+
"step": 360
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 1.11,
|
| 255 |
+
"learning_rate": 0.00015603603603603605,
|
| 256 |
+
"loss": 0.3224,
|
| 257 |
+
"step": 370
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 1.14,
|
| 261 |
+
"learning_rate": 0.00015483483483483485,
|
| 262 |
+
"loss": 0.6158,
|
| 263 |
+
"step": 380
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 1.17,
|
| 267 |
+
"learning_rate": 0.00015363363363363362,
|
| 268 |
+
"loss": 0.484,
|
| 269 |
+
"step": 390
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 1.2,
|
| 273 |
+
"learning_rate": 0.00015243243243243243,
|
| 274 |
+
"loss": 0.6219,
|
| 275 |
+
"step": 400
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 1.2,
|
| 279 |
+
"eval_accuracy": 0.8831030818278427,
|
| 280 |
+
"eval_loss": 0.4240102171897888,
|
| 281 |
+
"eval_runtime": 40.6001,
|
| 282 |
+
"eval_samples_per_second": 23.177,
|
| 283 |
+
"eval_steps_per_second": 2.906,
|
| 284 |
+
"step": 400
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 1.23,
|
| 288 |
+
"learning_rate": 0.00015123123123123123,
|
| 289 |
+
"loss": 0.5453,
|
| 290 |
+
"step": 410
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.26,
|
| 294 |
+
"learning_rate": 0.00015003003003003006,
|
| 295 |
+
"loss": 0.56,
|
| 296 |
+
"step": 420
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 1.29,
|
| 300 |
+
"learning_rate": 0.00014882882882882883,
|
| 301 |
+
"loss": 0.3875,
|
| 302 |
+
"step": 430
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 1.32,
|
| 306 |
+
"learning_rate": 0.00014762762762762763,
|
| 307 |
+
"loss": 0.5187,
|
| 308 |
+
"step": 440
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 1.35,
|
| 312 |
+
"learning_rate": 0.00014642642642642643,
|
| 313 |
+
"loss": 0.5176,
|
| 314 |
+
"step": 450
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 1.38,
|
| 318 |
+
"learning_rate": 0.00014522522522522524,
|
| 319 |
+
"loss": 0.8876,
|
| 320 |
+
"step": 460
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 1.41,
|
| 324 |
+
"learning_rate": 0.00014402402402402404,
|
| 325 |
+
"loss": 0.3874,
|
| 326 |
+
"step": 470
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 1.44,
|
| 330 |
+
"learning_rate": 0.0001428228228228228,
|
| 331 |
+
"loss": 0.7958,
|
| 332 |
+
"step": 480
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.47,
|
| 336 |
+
"learning_rate": 0.00014162162162162161,
|
| 337 |
+
"loss": 0.5271,
|
| 338 |
+
"step": 490
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.5,
|
| 342 |
+
"learning_rate": 0.00014042042042042042,
|
| 343 |
+
"loss": 0.4889,
|
| 344 |
+
"step": 500
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 1.5,
|
| 348 |
+
"eval_accuracy": 0.8947927736450585,
|
| 349 |
+
"eval_loss": 0.3840125799179077,
|
| 350 |
+
"eval_runtime": 41.0356,
|
| 351 |
+
"eval_samples_per_second": 22.931,
|
| 352 |
+
"eval_steps_per_second": 2.876,
|
| 353 |
+
"step": 500
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.53,
|
| 357 |
+
"learning_rate": 0.00013921921921921924,
|
| 358 |
+
"loss": 0.5692,
|
| 359 |
+
"step": 510
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 1.56,
|
| 363 |
+
"learning_rate": 0.00013801801801801802,
|
| 364 |
+
"loss": 0.5541,
|
| 365 |
+
"step": 520
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 1.59,
|
| 369 |
+
"learning_rate": 0.00013681681681681682,
|
| 370 |
+
"loss": 0.6267,
|
| 371 |
+
"step": 530
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 1.62,
|
| 375 |
+
"learning_rate": 0.00013561561561561562,
|
| 376 |
+
"loss": 0.55,
|
| 377 |
+
"step": 540
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 1.65,
|
| 381 |
+
"learning_rate": 0.00013441441441441442,
|
| 382 |
+
"loss": 0.425,
|
| 383 |
+
"step": 550
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 1.68,
|
| 387 |
+
"learning_rate": 0.00013321321321321323,
|
| 388 |
+
"loss": 0.3501,
|
| 389 |
+
"step": 560
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 1.71,
|
| 393 |
+
"learning_rate": 0.000132012012012012,
|
| 394 |
+
"loss": 0.5891,
|
| 395 |
+
"step": 570
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.74,
|
| 399 |
+
"learning_rate": 0.0001308108108108108,
|
| 400 |
+
"loss": 0.5129,
|
| 401 |
+
"step": 580
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 1.77,
|
| 405 |
+
"learning_rate": 0.00012960960960960963,
|
| 406 |
+
"loss": 0.6074,
|
| 407 |
+
"step": 590
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 1.8,
|
| 411 |
+
"learning_rate": 0.00012840840840840843,
|
| 412 |
+
"loss": 0.2963,
|
| 413 |
+
"step": 600
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 1.8,
|
| 417 |
+
"eval_accuracy": 0.895855472901169,
|
| 418 |
+
"eval_loss": 0.42787039279937744,
|
| 419 |
+
"eval_runtime": 40.9188,
|
| 420 |
+
"eval_samples_per_second": 22.997,
|
| 421 |
+
"eval_steps_per_second": 2.884,
|
| 422 |
+
"step": 600
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 1.83,
|
| 426 |
+
"learning_rate": 0.00012720720720720723,
|
| 427 |
+
"loss": 0.3153,
|
| 428 |
+
"step": 610
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 1.86,
|
| 432 |
+
"learning_rate": 0.000126006006006006,
|
| 433 |
+
"loss": 0.4458,
|
| 434 |
+
"step": 620
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 1.89,
|
| 438 |
+
"learning_rate": 0.0001248048048048048,
|
| 439 |
+
"loss": 0.5593,
|
| 440 |
+
"step": 630
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 1.92,
|
| 444 |
+
"learning_rate": 0.0001236036036036036,
|
| 445 |
+
"loss": 0.4581,
|
| 446 |
+
"step": 640
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 1.95,
|
| 450 |
+
"learning_rate": 0.0001224024024024024,
|
| 451 |
+
"loss": 0.4293,
|
| 452 |
+
"step": 650
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 1.98,
|
| 456 |
+
"learning_rate": 0.0001212012012012012,
|
| 457 |
+
"loss": 0.3959,
|
| 458 |
+
"step": 660
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 2.01,
|
| 462 |
+
"learning_rate": 0.00012,
|
| 463 |
+
"loss": 0.6051,
|
| 464 |
+
"step": 670
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 2.04,
|
| 468 |
+
"learning_rate": 0.0001187987987987988,
|
| 469 |
+
"loss": 0.4068,
|
| 470 |
+
"step": 680
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 2.07,
|
| 474 |
+
"learning_rate": 0.0001175975975975976,
|
| 475 |
+
"loss": 0.4732,
|
| 476 |
+
"step": 690
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 2.1,
|
| 480 |
+
"learning_rate": 0.00011639639639639641,
|
| 481 |
+
"loss": 0.4405,
|
| 482 |
+
"step": 700
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 2.1,
|
| 486 |
+
"eval_accuracy": 0.9117959617428267,
|
| 487 |
+
"eval_loss": 0.35077255964279175,
|
| 488 |
+
"eval_runtime": 41.1075,
|
| 489 |
+
"eval_samples_per_second": 22.891,
|
| 490 |
+
"eval_steps_per_second": 2.871,
|
| 491 |
+
"step": 700
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 2.13,
|
| 495 |
+
"learning_rate": 0.0001151951951951952,
|
| 496 |
+
"loss": 0.2055,
|
| 497 |
+
"step": 710
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 2.16,
|
| 501 |
+
"learning_rate": 0.000113993993993994,
|
| 502 |
+
"loss": 0.3782,
|
| 503 |
+
"step": 720
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 2.19,
|
| 507 |
+
"learning_rate": 0.0001127927927927928,
|
| 508 |
+
"loss": 0.2767,
|
| 509 |
+
"step": 730
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 2.22,
|
| 513 |
+
"learning_rate": 0.0001115915915915916,
|
| 514 |
+
"loss": 0.275,
|
| 515 |
+
"step": 740
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 2.25,
|
| 519 |
+
"learning_rate": 0.00011039039039039039,
|
| 520 |
+
"loss": 0.3466,
|
| 521 |
+
"step": 750
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 2.28,
|
| 525 |
+
"learning_rate": 0.00010918918918918919,
|
| 526 |
+
"loss": 0.5017,
|
| 527 |
+
"step": 760
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 2.31,
|
| 531 |
+
"learning_rate": 0.00010798798798798799,
|
| 532 |
+
"loss": 0.3676,
|
| 533 |
+
"step": 770
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 2.34,
|
| 537 |
+
"learning_rate": 0.0001067867867867868,
|
| 538 |
+
"loss": 0.3576,
|
| 539 |
+
"step": 780
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 2.37,
|
| 543 |
+
"learning_rate": 0.0001055855855855856,
|
| 544 |
+
"loss": 0.4545,
|
| 545 |
+
"step": 790
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 2.4,
|
| 549 |
+
"learning_rate": 0.00010438438438438438,
|
| 550 |
+
"loss": 0.3803,
|
| 551 |
+
"step": 800
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 2.4,
|
| 555 |
+
"eval_accuracy": 0.9086078639744952,
|
| 556 |
+
"eval_loss": 0.36589011549949646,
|
| 557 |
+
"eval_runtime": 40.8562,
|
| 558 |
+
"eval_samples_per_second": 23.032,
|
| 559 |
+
"eval_steps_per_second": 2.888,
|
| 560 |
+
"step": 800
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 2.43,
|
| 564 |
+
"learning_rate": 0.00010318318318318319,
|
| 565 |
+
"loss": 0.2818,
|
| 566 |
+
"step": 810
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 2.46,
|
| 570 |
+
"learning_rate": 0.00010198198198198199,
|
| 571 |
+
"loss": 0.4102,
|
| 572 |
+
"step": 820
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 2.49,
|
| 576 |
+
"learning_rate": 0.00010078078078078079,
|
| 577 |
+
"loss": 0.3617,
|
| 578 |
+
"step": 830
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 2.52,
|
| 582 |
+
"learning_rate": 9.957957957957959e-05,
|
| 583 |
+
"loss": 0.4926,
|
| 584 |
+
"step": 840
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 2.55,
|
| 588 |
+
"learning_rate": 9.837837837837839e-05,
|
| 589 |
+
"loss": 0.2893,
|
| 590 |
+
"step": 850
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 2.58,
|
| 594 |
+
"learning_rate": 9.717717717717718e-05,
|
| 595 |
+
"loss": 0.2848,
|
| 596 |
+
"step": 860
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 2.61,
|
| 600 |
+
"learning_rate": 9.597597597597598e-05,
|
| 601 |
+
"loss": 0.292,
|
| 602 |
+
"step": 870
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 2.64,
|
| 606 |
+
"learning_rate": 9.477477477477478e-05,
|
| 607 |
+
"loss": 0.5481,
|
| 608 |
+
"step": 880
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 2.67,
|
| 612 |
+
"learning_rate": 9.357357357357359e-05,
|
| 613 |
+
"loss": 0.2587,
|
| 614 |
+
"step": 890
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 2.7,
|
| 618 |
+
"learning_rate": 9.237237237237237e-05,
|
| 619 |
+
"loss": 0.3499,
|
| 620 |
+
"step": 900
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 2.7,
|
| 624 |
+
"eval_accuracy": 0.9213602550478215,
|
| 625 |
+
"eval_loss": 0.33470773696899414,
|
| 626 |
+
"eval_runtime": 40.8732,
|
| 627 |
+
"eval_samples_per_second": 23.022,
|
| 628 |
+
"eval_steps_per_second": 2.887,
|
| 629 |
+
"step": 900
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 2.73,
|
| 633 |
+
"learning_rate": 9.117117117117118e-05,
|
| 634 |
+
"loss": 0.3355,
|
| 635 |
+
"step": 910
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 2.76,
|
| 639 |
+
"learning_rate": 8.996996996996996e-05,
|
| 640 |
+
"loss": 0.3938,
|
| 641 |
+
"step": 920
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 2.79,
|
| 645 |
+
"learning_rate": 8.876876876876878e-05,
|
| 646 |
+
"loss": 0.3229,
|
| 647 |
+
"step": 930
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 2.82,
|
| 651 |
+
"learning_rate": 8.756756756756758e-05,
|
| 652 |
+
"loss": 0.2761,
|
| 653 |
+
"step": 940
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 2.85,
|
| 657 |
+
"learning_rate": 8.636636636636637e-05,
|
| 658 |
+
"loss": 0.362,
|
| 659 |
+
"step": 950
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 2.88,
|
| 663 |
+
"learning_rate": 8.516516516516517e-05,
|
| 664 |
+
"loss": 0.3807,
|
| 665 |
+
"step": 960
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 2.91,
|
| 669 |
+
"learning_rate": 8.396396396396397e-05,
|
| 670 |
+
"loss": 0.3084,
|
| 671 |
+
"step": 970
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 2.94,
|
| 675 |
+
"learning_rate": 8.276276276276277e-05,
|
| 676 |
+
"loss": 0.664,
|
| 677 |
+
"step": 980
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 2.97,
|
| 681 |
+
"learning_rate": 8.156156156156156e-05,
|
| 682 |
+
"loss": 0.3162,
|
| 683 |
+
"step": 990
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 3.0,
|
| 687 |
+
"learning_rate": 8.036036036036036e-05,
|
| 688 |
+
"loss": 0.3131,
|
| 689 |
+
"step": 1000
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 3.0,
|
| 693 |
+
"eval_accuracy": 0.9277364505844846,
|
| 694 |
+
"eval_loss": 0.290975421667099,
|
| 695 |
+
"eval_runtime": 40.7778,
|
| 696 |
+
"eval_samples_per_second": 23.076,
|
| 697 |
+
"eval_steps_per_second": 2.894,
|
| 698 |
+
"step": 1000
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 3.03,
|
| 702 |
+
"learning_rate": 7.915915915915915e-05,
|
| 703 |
+
"loss": 0.152,
|
| 704 |
+
"step": 1010
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 3.06,
|
| 708 |
+
"learning_rate": 7.795795795795797e-05,
|
| 709 |
+
"loss": 0.3068,
|
| 710 |
+
"step": 1020
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 3.09,
|
| 714 |
+
"learning_rate": 7.675675675675677e-05,
|
| 715 |
+
"loss": 0.1023,
|
| 716 |
+
"step": 1030
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 3.12,
|
| 720 |
+
"learning_rate": 7.555555555555556e-05,
|
| 721 |
+
"loss": 0.4051,
|
| 722 |
+
"step": 1040
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 3.15,
|
| 726 |
+
"learning_rate": 7.435435435435436e-05,
|
| 727 |
+
"loss": 0.2915,
|
| 728 |
+
"step": 1050
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 3.18,
|
| 732 |
+
"learning_rate": 7.315315315315316e-05,
|
| 733 |
+
"loss": 0.1638,
|
| 734 |
+
"step": 1060
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 3.21,
|
| 738 |
+
"learning_rate": 7.195195195195196e-05,
|
| 739 |
+
"loss": 0.1406,
|
| 740 |
+
"step": 1070
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 3.24,
|
| 744 |
+
"learning_rate": 7.075075075075075e-05,
|
| 745 |
+
"loss": 0.1844,
|
| 746 |
+
"step": 1080
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 3.27,
|
| 750 |
+
"learning_rate": 6.954954954954955e-05,
|
| 751 |
+
"loss": 0.4238,
|
| 752 |
+
"step": 1090
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 3.3,
|
| 756 |
+
"learning_rate": 6.834834834834835e-05,
|
| 757 |
+
"loss": 0.3036,
|
| 758 |
+
"step": 1100
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 3.3,
|
| 762 |
+
"eval_accuracy": 0.9107332624867163,
|
| 763 |
+
"eval_loss": 0.3937636613845825,
|
| 764 |
+
"eval_runtime": 40.8699,
|
| 765 |
+
"eval_samples_per_second": 23.024,
|
| 766 |
+
"eval_steps_per_second": 2.887,
|
| 767 |
+
"step": 1100
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 3.33,
|
| 771 |
+
"learning_rate": 6.714714714714715e-05,
|
| 772 |
+
"loss": 0.366,
|
| 773 |
+
"step": 1110
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 3.36,
|
| 777 |
+
"learning_rate": 6.594594594594596e-05,
|
| 778 |
+
"loss": 0.1498,
|
| 779 |
+
"step": 1120
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 3.39,
|
| 783 |
+
"learning_rate": 6.474474474474474e-05,
|
| 784 |
+
"loss": 0.241,
|
| 785 |
+
"step": 1130
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 3.42,
|
| 789 |
+
"learning_rate": 6.354354354354355e-05,
|
| 790 |
+
"loss": 0.3446,
|
| 791 |
+
"step": 1140
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 3.45,
|
| 795 |
+
"learning_rate": 6.234234234234235e-05,
|
| 796 |
+
"loss": 0.1943,
|
| 797 |
+
"step": 1150
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 3.48,
|
| 801 |
+
"learning_rate": 6.114114114114115e-05,
|
| 802 |
+
"loss": 0.2137,
|
| 803 |
+
"step": 1160
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 3.51,
|
| 807 |
+
"learning_rate": 5.993993993993994e-05,
|
| 808 |
+
"loss": 0.1259,
|
| 809 |
+
"step": 1170
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 3.54,
|
| 813 |
+
"learning_rate": 5.873873873873874e-05,
|
| 814 |
+
"loss": 0.1947,
|
| 815 |
+
"step": 1180
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 3.57,
|
| 819 |
+
"learning_rate": 5.753753753753755e-05,
|
| 820 |
+
"loss": 0.138,
|
| 821 |
+
"step": 1190
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 3.6,
|
| 825 |
+
"learning_rate": 5.6336336336336336e-05,
|
| 826 |
+
"loss": 0.2697,
|
| 827 |
+
"step": 1200
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 3.6,
|
| 831 |
+
"eval_accuracy": 0.9171094580233794,
|
| 832 |
+
"eval_loss": 0.35658442974090576,
|
| 833 |
+
"eval_runtime": 40.9373,
|
| 834 |
+
"eval_samples_per_second": 22.986,
|
| 835 |
+
"eval_steps_per_second": 2.882,
|
| 836 |
+
"step": 1200
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 3.63,
|
| 840 |
+
"learning_rate": 5.5135135135135144e-05,
|
| 841 |
+
"loss": 0.1748,
|
| 842 |
+
"step": 1210
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 3.66,
|
| 846 |
+
"learning_rate": 5.393393393393393e-05,
|
| 847 |
+
"loss": 0.1407,
|
| 848 |
+
"step": 1220
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 3.69,
|
| 852 |
+
"learning_rate": 5.2732732732732734e-05,
|
| 853 |
+
"loss": 0.316,
|
| 854 |
+
"step": 1230
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 3.72,
|
| 858 |
+
"learning_rate": 5.153153153153153e-05,
|
| 859 |
+
"loss": 0.1369,
|
| 860 |
+
"step": 1240
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 3.75,
|
| 864 |
+
"learning_rate": 5.033033033033033e-05,
|
| 865 |
+
"loss": 0.2623,
|
| 866 |
+
"step": 1250
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 3.78,
|
| 870 |
+
"learning_rate": 4.912912912912913e-05,
|
| 871 |
+
"loss": 0.0935,
|
| 872 |
+
"step": 1260
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 3.81,
|
| 876 |
+
"learning_rate": 4.792792792792793e-05,
|
| 877 |
+
"loss": 0.2738,
|
| 878 |
+
"step": 1270
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 3.84,
|
| 882 |
+
"learning_rate": 4.672672672672673e-05,
|
| 883 |
+
"loss": 0.35,
|
| 884 |
+
"step": 1280
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 3.87,
|
| 888 |
+
"learning_rate": 4.5525525525525524e-05,
|
| 889 |
+
"loss": 0.1173,
|
| 890 |
+
"step": 1290
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 3.9,
|
| 894 |
+
"learning_rate": 4.432432432432433e-05,
|
| 895 |
+
"loss": 0.1551,
|
| 896 |
+
"step": 1300
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 3.9,
|
| 900 |
+
"eval_accuracy": 0.9341126461211477,
|
| 901 |
+
"eval_loss": 0.3369457423686981,
|
| 902 |
+
"eval_runtime": 41.1834,
|
| 903 |
+
"eval_samples_per_second": 22.849,
|
| 904 |
+
"eval_steps_per_second": 2.865,
|
| 905 |
+
"step": 1300
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 3.93,
|
| 909 |
+
"learning_rate": 4.312312312312313e-05,
|
| 910 |
+
"loss": 0.3394,
|
| 911 |
+
"step": 1310
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 3.96,
|
| 915 |
+
"learning_rate": 4.192192192192192e-05,
|
| 916 |
+
"loss": 0.2533,
|
| 917 |
+
"step": 1320
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 3.99,
|
| 921 |
+
"learning_rate": 4.0720720720720724e-05,
|
| 922 |
+
"loss": 0.1894,
|
| 923 |
+
"step": 1330
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 4.02,
|
| 927 |
+
"learning_rate": 3.951951951951952e-05,
|
| 928 |
+
"loss": 0.1789,
|
| 929 |
+
"step": 1340
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 4.05,
|
| 933 |
+
"learning_rate": 3.831831831831832e-05,
|
| 934 |
+
"loss": 0.0723,
|
| 935 |
+
"step": 1350
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 4.08,
|
| 939 |
+
"learning_rate": 3.7117117117117115e-05,
|
| 940 |
+
"loss": 0.1718,
|
| 941 |
+
"step": 1360
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 4.11,
|
| 945 |
+
"learning_rate": 3.591591591591592e-05,
|
| 946 |
+
"loss": 0.1439,
|
| 947 |
+
"step": 1370
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 4.14,
|
| 951 |
+
"learning_rate": 3.471471471471472e-05,
|
| 952 |
+
"loss": 0.2211,
|
| 953 |
+
"step": 1380
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 4.17,
|
| 957 |
+
"learning_rate": 3.351351351351352e-05,
|
| 958 |
+
"loss": 0.079,
|
| 959 |
+
"step": 1390
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 4.2,
|
| 963 |
+
"learning_rate": 3.2312312312312315e-05,
|
| 964 |
+
"loss": 0.0752,
|
| 965 |
+
"step": 1400
|
| 966 |
+
},
|
| 967 |
+
{
|
| 968 |
+
"epoch": 4.2,
|
| 969 |
+
"eval_accuracy": 0.9373007438894793,
|
| 970 |
+
"eval_loss": 0.2868094742298126,
|
| 971 |
+
"eval_runtime": 41.4456,
|
| 972 |
+
"eval_samples_per_second": 22.704,
|
| 973 |
+
"eval_steps_per_second": 2.847,
|
| 974 |
+
"step": 1400
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 4.23,
|
| 978 |
+
"learning_rate": 3.111111111111111e-05,
|
| 979 |
+
"loss": 0.0999,
|
| 980 |
+
"step": 1410
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 4.26,
|
| 984 |
+
"learning_rate": 2.990990990990991e-05,
|
| 985 |
+
"loss": 0.1528,
|
| 986 |
+
"step": 1420
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 4.29,
|
| 990 |
+
"learning_rate": 2.870870870870871e-05,
|
| 991 |
+
"loss": 0.1456,
|
| 992 |
+
"step": 1430
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 4.32,
|
| 996 |
+
"learning_rate": 2.7507507507507508e-05,
|
| 997 |
+
"loss": 0.1389,
|
| 998 |
+
"step": 1440
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 4.35,
|
| 1002 |
+
"learning_rate": 2.6306306306306306e-05,
|
| 1003 |
+
"loss": 0.0957,
|
| 1004 |
+
"step": 1450
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 4.38,
|
| 1008 |
+
"learning_rate": 2.5105105105105108e-05,
|
| 1009 |
+
"loss": 0.1156,
|
| 1010 |
+
"step": 1460
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 4.41,
|
| 1014 |
+
"learning_rate": 2.3903903903903903e-05,
|
| 1015 |
+
"loss": 0.16,
|
| 1016 |
+
"step": 1470
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 4.44,
|
| 1020 |
+
"learning_rate": 2.2702702702702705e-05,
|
| 1021 |
+
"loss": 0.1485,
|
| 1022 |
+
"step": 1480
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 4.47,
|
| 1026 |
+
"learning_rate": 2.1501501501501503e-05,
|
| 1027 |
+
"loss": 0.1667,
|
| 1028 |
+
"step": 1490
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 4.5,
|
| 1032 |
+
"learning_rate": 2.03003003003003e-05,
|
| 1033 |
+
"loss": 0.132,
|
| 1034 |
+
"step": 1500
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 4.5,
|
| 1038 |
+
"eval_accuracy": 0.9373007438894793,
|
| 1039 |
+
"eval_loss": 0.3023243546485901,
|
| 1040 |
+
"eval_runtime": 41.2414,
|
| 1041 |
+
"eval_samples_per_second": 22.817,
|
| 1042 |
+
"eval_steps_per_second": 2.861,
|
| 1043 |
+
"step": 1500
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 4.53,
|
| 1047 |
+
"learning_rate": 1.90990990990991e-05,
|
| 1048 |
+
"loss": 0.2626,
|
| 1049 |
+
"step": 1510
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 4.56,
|
| 1053 |
+
"learning_rate": 1.78978978978979e-05,
|
| 1054 |
+
"loss": 0.2645,
|
| 1055 |
+
"step": 1520
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 4.59,
|
| 1059 |
+
"learning_rate": 1.66966966966967e-05,
|
| 1060 |
+
"loss": 0.1691,
|
| 1061 |
+
"step": 1530
|
| 1062 |
+
},
|
| 1063 |
+
{
|
| 1064 |
+
"epoch": 4.62,
|
| 1065 |
+
"learning_rate": 1.5495495495495498e-05,
|
| 1066 |
+
"loss": 0.1964,
|
| 1067 |
+
"step": 1540
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 4.65,
|
| 1071 |
+
"learning_rate": 1.4294294294294294e-05,
|
| 1072 |
+
"loss": 0.1062,
|
| 1073 |
+
"step": 1550
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 4.68,
|
| 1077 |
+
"learning_rate": 1.3093093093093094e-05,
|
| 1078 |
+
"loss": 0.1863,
|
| 1079 |
+
"step": 1560
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 4.71,
|
| 1083 |
+
"learning_rate": 1.1891891891891893e-05,
|
| 1084 |
+
"loss": 0.1155,
|
| 1085 |
+
"step": 1570
|
| 1086 |
+
},
|
| 1087 |
+
{
|
| 1088 |
+
"epoch": 4.74,
|
| 1089 |
+
"learning_rate": 1.0690690690690691e-05,
|
| 1090 |
+
"loss": 0.1222,
|
| 1091 |
+
"step": 1580
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 4.77,
|
| 1095 |
+
"learning_rate": 9.489489489489491e-06,
|
| 1096 |
+
"loss": 0.0238,
|
| 1097 |
+
"step": 1590
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 4.8,
|
| 1101 |
+
"learning_rate": 8.288288288288289e-06,
|
| 1102 |
+
"loss": 0.1133,
|
| 1103 |
+
"step": 1600
|
| 1104 |
+
},
|
| 1105 |
+
{
|
| 1106 |
+
"epoch": 4.8,
|
| 1107 |
+
"eval_accuracy": 0.9415515409139213,
|
| 1108 |
+
"eval_loss": 0.29777178168296814,
|
| 1109 |
+
"eval_runtime": 41.1597,
|
| 1110 |
+
"eval_samples_per_second": 22.862,
|
| 1111 |
+
"eval_steps_per_second": 2.867,
|
| 1112 |
+
"step": 1600
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 4.83,
|
| 1116 |
+
"learning_rate": 7.0870870870870866e-06,
|
| 1117 |
+
"loss": 0.1734,
|
| 1118 |
+
"step": 1610
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 4.86,
|
| 1122 |
+
"learning_rate": 5.8858858858858865e-06,
|
| 1123 |
+
"loss": 0.086,
|
| 1124 |
+
"step": 1620
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 4.89,
|
| 1128 |
+
"learning_rate": 4.684684684684685e-06,
|
| 1129 |
+
"loss": 0.0928,
|
| 1130 |
+
"step": 1630
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 4.92,
|
| 1134 |
+
"learning_rate": 3.4834834834834835e-06,
|
| 1135 |
+
"loss": 0.2043,
|
| 1136 |
+
"step": 1640
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 4.95,
|
| 1140 |
+
"learning_rate": 2.2822822822822822e-06,
|
| 1141 |
+
"loss": 0.1768,
|
| 1142 |
+
"step": 1650
|
| 1143 |
+
},
|
| 1144 |
+
{
|
| 1145 |
+
"epoch": 4.98,
|
| 1146 |
+
"learning_rate": 1.0810810810810812e-06,
|
| 1147 |
+
"loss": 0.0674,
|
| 1148 |
+
"step": 1660
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 5.0,
|
| 1152 |
+
"step": 1665,
|
| 1153 |
+
"total_flos": 2.6257169541360845e+18,
|
| 1154 |
+
"train_loss": 0.509146851408589,
|
| 1155 |
+
"train_runtime": 2159.6535,
|
| 1156 |
+
"train_samples_per_second": 12.335,
|
| 1157 |
+
"train_steps_per_second": 0.771
|
| 1158 |
+
}
|
| 1159 |
+
],
|
| 1160 |
+
"max_steps": 1665,
|
| 1161 |
+
"num_train_epochs": 5,
|
| 1162 |
+
"total_flos": 2.6257169541360845e+18,
|
| 1163 |
+
"trial_name": null,
|
| 1164 |
+
"trial_params": null
|
| 1165 |
+
}
|