Commit
·
04ad936
1
Parent(s):
93ba36f
YAY!!
Browse files- all_results.json +13 -0
- eval_results.json +8 -0
- runs/Sep02_14-55-27_e0877e99f71e/events.out.tfevents.1662132947.e0877e99f71e.69.5 +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": 0.9458023379383634,
|
| 4 |
+
"eval_loss": 0.22263780236244202,
|
| 5 |
+
"eval_runtime": 40.2749,
|
| 6 |
+
"eval_samples_per_second": 23.364,
|
| 7 |
+
"eval_steps_per_second": 2.93,
|
| 8 |
+
"total_flos": 2.0875695162281165e+18,
|
| 9 |
+
"train_loss": 0.38661149321375665,
|
| 10 |
+
"train_runtime": 2052.9844,
|
| 11 |
+
"train_samples_per_second": 12.976,
|
| 12 |
+
"train_steps_per_second": 0.811
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"eval_accuracy": 0.9458023379383634,
|
| 4 |
+
"eval_loss": 0.22263780236244202,
|
| 5 |
+
"eval_runtime": 40.2749,
|
| 6 |
+
"eval_samples_per_second": 23.364,
|
| 7 |
+
"eval_steps_per_second": 2.93
|
| 8 |
+
}
|
runs/Sep02_14-55-27_e0877e99f71e/events.out.tfevents.1662132947.e0877e99f71e.69.5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:22073e55355d396d6c7dcf09398f4f4e350a2acc7303c6c3800ca2c9171af8f0
|
| 3 |
+
size 363
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"total_flos": 2.0875695162281165e+18,
|
| 4 |
+
"train_loss": 0.38661149321375665,
|
| 5 |
+
"train_runtime": 2052.9844,
|
| 6 |
+
"train_samples_per_second": 12.976,
|
| 7 |
+
"train_steps_per_second": 0.811
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1165 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.22263780236244202,
|
| 3 |
+
"best_model_checkpoint": "DrishtiSharma/finetuned-SwinT-Indian-Food-Classification-v2/checkpoint-1500",
|
| 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": 0.00019903903903903904,
|
| 13 |
+
"loss": 2.4985,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.06,
|
| 18 |
+
"learning_rate": 0.00019783783783783784,
|
| 19 |
+
"loss": 1.4444,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.09,
|
| 24 |
+
"learning_rate": 0.00019663663663663664,
|
| 25 |
+
"loss": 1.0698,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.12,
|
| 30 |
+
"learning_rate": 0.00019543543543543545,
|
| 31 |
+
"loss": 1.0817,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.15,
|
| 36 |
+
"learning_rate": 0.00019423423423423425,
|
| 37 |
+
"loss": 0.8105,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.18,
|
| 42 |
+
"learning_rate": 0.00019303303303303305,
|
| 43 |
+
"loss": 0.8324,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.21,
|
| 48 |
+
"learning_rate": 0.00019183183183183185,
|
| 49 |
+
"loss": 0.8106,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.24,
|
| 54 |
+
"learning_rate": 0.00019063063063063065,
|
| 55 |
+
"loss": 0.6581,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.27,
|
| 60 |
+
"learning_rate": 0.00018942942942942943,
|
| 61 |
+
"loss": 0.6992,
|
| 62 |
+
"step": 90
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.3,
|
| 66 |
+
"learning_rate": 0.00018822822822822823,
|
| 67 |
+
"loss": 0.9351,
|
| 68 |
+
"step": 100
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.3,
|
| 72 |
+
"eval_accuracy": 0.8363443145589798,
|
| 73 |
+
"eval_loss": 0.6016978025436401,
|
| 74 |
+
"eval_runtime": 39.9065,
|
| 75 |
+
"eval_samples_per_second": 23.58,
|
| 76 |
+
"eval_steps_per_second": 2.957,
|
| 77 |
+
"step": 100
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 0.33,
|
| 81 |
+
"learning_rate": 0.00018702702702702703,
|
| 82 |
+
"loss": 0.9577,
|
| 83 |
+
"step": 110
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 0.36,
|
| 87 |
+
"learning_rate": 0.00018582582582582583,
|
| 88 |
+
"loss": 0.789,
|
| 89 |
+
"step": 120
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.39,
|
| 93 |
+
"learning_rate": 0.00018462462462462463,
|
| 94 |
+
"loss": 1.0007,
|
| 95 |
+
"step": 130
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.42,
|
| 99 |
+
"learning_rate": 0.00018342342342342343,
|
| 100 |
+
"loss": 0.6186,
|
| 101 |
+
"step": 140
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.45,
|
| 105 |
+
"learning_rate": 0.00018222222222222224,
|
| 106 |
+
"loss": 0.5886,
|
| 107 |
+
"step": 150
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.48,
|
| 111 |
+
"learning_rate": 0.00018114114114114115,
|
| 112 |
+
"loss": 0.6685,
|
| 113 |
+
"step": 160
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.51,
|
| 117 |
+
"learning_rate": 0.00017993993993993993,
|
| 118 |
+
"loss": 0.886,
|
| 119 |
+
"step": 170
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 0.54,
|
| 123 |
+
"learning_rate": 0.00017873873873873876,
|
| 124 |
+
"loss": 0.7398,
|
| 125 |
+
"step": 180
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 0.57,
|
| 129 |
+
"learning_rate": 0.00017753753753753756,
|
| 130 |
+
"loss": 0.6541,
|
| 131 |
+
"step": 190
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 0.6,
|
| 135 |
+
"learning_rate": 0.00017633633633633636,
|
| 136 |
+
"loss": 0.5667,
|
| 137 |
+
"step": 200
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.6,
|
| 141 |
+
"eval_accuracy": 0.8767268862911796,
|
| 142 |
+
"eval_loss": 0.43840092420578003,
|
| 143 |
+
"eval_runtime": 39.8194,
|
| 144 |
+
"eval_samples_per_second": 23.632,
|
| 145 |
+
"eval_steps_per_second": 2.963,
|
| 146 |
+
"step": 200
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.63,
|
| 150 |
+
"learning_rate": 0.00017513513513513516,
|
| 151 |
+
"loss": 0.5596,
|
| 152 |
+
"step": 210
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.66,
|
| 156 |
+
"learning_rate": 0.00017393393393393394,
|
| 157 |
+
"loss": 0.5697,
|
| 158 |
+
"step": 220
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.69,
|
| 162 |
+
"learning_rate": 0.00017273273273273274,
|
| 163 |
+
"loss": 0.6168,
|
| 164 |
+
"step": 230
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.72,
|
| 168 |
+
"learning_rate": 0.00017153153153153154,
|
| 169 |
+
"loss": 0.6351,
|
| 170 |
+
"step": 240
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.75,
|
| 174 |
+
"learning_rate": 0.00017033033033033034,
|
| 175 |
+
"loss": 0.578,
|
| 176 |
+
"step": 250
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.78,
|
| 180 |
+
"learning_rate": 0.00016912912912912911,
|
| 181 |
+
"loss": 0.8882,
|
| 182 |
+
"step": 260
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.81,
|
| 186 |
+
"learning_rate": 0.00016792792792792794,
|
| 187 |
+
"loss": 0.6284,
|
| 188 |
+
"step": 270
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.84,
|
| 192 |
+
"learning_rate": 0.00016672672672672675,
|
| 193 |
+
"loss": 0.8874,
|
| 194 |
+
"step": 280
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.87,
|
| 198 |
+
"learning_rate": 0.00016552552552552555,
|
| 199 |
+
"loss": 0.7083,
|
| 200 |
+
"step": 290
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.9,
|
| 204 |
+
"learning_rate": 0.00016432432432432435,
|
| 205 |
+
"loss": 0.5548,
|
| 206 |
+
"step": 300
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.9,
|
| 210 |
+
"eval_accuracy": 0.8767268862911796,
|
| 211 |
+
"eval_loss": 0.42152631282806396,
|
| 212 |
+
"eval_runtime": 40.3274,
|
| 213 |
+
"eval_samples_per_second": 23.334,
|
| 214 |
+
"eval_steps_per_second": 2.926,
|
| 215 |
+
"step": 300
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 0.93,
|
| 219 |
+
"learning_rate": 0.00016312312312312312,
|
| 220 |
+
"loss": 0.6819,
|
| 221 |
+
"step": 310
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 0.96,
|
| 225 |
+
"learning_rate": 0.00016192192192192192,
|
| 226 |
+
"loss": 0.4283,
|
| 227 |
+
"step": 320
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.99,
|
| 231 |
+
"learning_rate": 0.00016072072072072073,
|
| 232 |
+
"loss": 0.4916,
|
| 233 |
+
"step": 330
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.02,
|
| 237 |
+
"learning_rate": 0.00015951951951951953,
|
| 238 |
+
"loss": 0.5186,
|
| 239 |
+
"step": 340
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 1.05,
|
| 243 |
+
"learning_rate": 0.0001583183183183183,
|
| 244 |
+
"loss": 0.6319,
|
| 245 |
+
"step": 350
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 1.08,
|
| 249 |
+
"learning_rate": 0.00015711711711711713,
|
| 250 |
+
"loss": 0.3755,
|
| 251 |
+
"step": 360
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 1.11,
|
| 255 |
+
"learning_rate": 0.00015591591591591593,
|
| 256 |
+
"loss": 0.3293,
|
| 257 |
+
"step": 370
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 1.14,
|
| 261 |
+
"learning_rate": 0.00015471471471471474,
|
| 262 |
+
"loss": 0.4974,
|
| 263 |
+
"step": 380
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 1.17,
|
| 267 |
+
"learning_rate": 0.00015351351351351354,
|
| 268 |
+
"loss": 0.6046,
|
| 269 |
+
"step": 390
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 1.2,
|
| 273 |
+
"learning_rate": 0.0001523123123123123,
|
| 274 |
+
"loss": 0.5516,
|
| 275 |
+
"step": 400
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 1.2,
|
| 279 |
+
"eval_accuracy": 0.873538788522848,
|
| 280 |
+
"eval_loss": 0.42902085185050964,
|
| 281 |
+
"eval_runtime": 40.2528,
|
| 282 |
+
"eval_samples_per_second": 23.377,
|
| 283 |
+
"eval_steps_per_second": 2.931,
|
| 284 |
+
"step": 400
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 1.23,
|
| 288 |
+
"learning_rate": 0.0001511111111111111,
|
| 289 |
+
"loss": 0.5308,
|
| 290 |
+
"step": 410
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.26,
|
| 294 |
+
"learning_rate": 0.00014990990990990991,
|
| 295 |
+
"loss": 0.4627,
|
| 296 |
+
"step": 420
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 1.29,
|
| 300 |
+
"learning_rate": 0.00014870870870870872,
|
| 301 |
+
"loss": 0.4123,
|
| 302 |
+
"step": 430
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 1.32,
|
| 306 |
+
"learning_rate": 0.00014750750750750752,
|
| 307 |
+
"loss": 0.5095,
|
| 308 |
+
"step": 440
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 1.35,
|
| 312 |
+
"learning_rate": 0.00014630630630630632,
|
| 313 |
+
"loss": 0.5262,
|
| 314 |
+
"step": 450
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 1.38,
|
| 318 |
+
"learning_rate": 0.00014510510510510512,
|
| 319 |
+
"loss": 0.6747,
|
| 320 |
+
"step": 460
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 1.41,
|
| 324 |
+
"learning_rate": 0.00014390390390390392,
|
| 325 |
+
"loss": 0.3073,
|
| 326 |
+
"step": 470
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 1.44,
|
| 330 |
+
"learning_rate": 0.00014270270270270272,
|
| 331 |
+
"loss": 0.5508,
|
| 332 |
+
"step": 480
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.47,
|
| 336 |
+
"learning_rate": 0.0001415015015015015,
|
| 337 |
+
"loss": 0.5183,
|
| 338 |
+
"step": 490
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.5,
|
| 342 |
+
"learning_rate": 0.0001403003003003003,
|
| 343 |
+
"loss": 0.3782,
|
| 344 |
+
"step": 500
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 1.5,
|
| 348 |
+
"eval_accuracy": 0.89798087141339,
|
| 349 |
+
"eval_loss": 0.35022875666618347,
|
| 350 |
+
"eval_runtime": 39.8292,
|
| 351 |
+
"eval_samples_per_second": 23.626,
|
| 352 |
+
"eval_steps_per_second": 2.963,
|
| 353 |
+
"step": 500
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.53,
|
| 357 |
+
"learning_rate": 0.0001390990990990991,
|
| 358 |
+
"loss": 0.4911,
|
| 359 |
+
"step": 510
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 1.56,
|
| 363 |
+
"learning_rate": 0.0001378978978978979,
|
| 364 |
+
"loss": 0.544,
|
| 365 |
+
"step": 520
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 1.59,
|
| 369 |
+
"learning_rate": 0.0001366966966966967,
|
| 370 |
+
"loss": 0.5958,
|
| 371 |
+
"step": 530
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 1.62,
|
| 375 |
+
"learning_rate": 0.0001354954954954955,
|
| 376 |
+
"loss": 0.4798,
|
| 377 |
+
"step": 540
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 1.65,
|
| 381 |
+
"learning_rate": 0.0001342942942942943,
|
| 382 |
+
"loss": 0.3317,
|
| 383 |
+
"step": 550
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 1.68,
|
| 387 |
+
"learning_rate": 0.0001330930930930931,
|
| 388 |
+
"loss": 0.3693,
|
| 389 |
+
"step": 560
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 1.71,
|
| 393 |
+
"learning_rate": 0.0001318918918918919,
|
| 394 |
+
"loss": 0.3432,
|
| 395 |
+
"step": 570
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.74,
|
| 399 |
+
"learning_rate": 0.0001306906906906907,
|
| 400 |
+
"loss": 0.4374,
|
| 401 |
+
"step": 580
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 1.77,
|
| 405 |
+
"learning_rate": 0.0001294894894894895,
|
| 406 |
+
"loss": 0.5319,
|
| 407 |
+
"step": 590
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 1.8,
|
| 411 |
+
"learning_rate": 0.0001282882882882883,
|
| 412 |
+
"loss": 0.3115,
|
| 413 |
+
"step": 600
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 1.8,
|
| 417 |
+
"eval_accuracy": 0.8937300743889479,
|
| 418 |
+
"eval_loss": 0.3780476152896881,
|
| 419 |
+
"eval_runtime": 39.7563,
|
| 420 |
+
"eval_samples_per_second": 23.669,
|
| 421 |
+
"eval_steps_per_second": 2.968,
|
| 422 |
+
"step": 600
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 1.83,
|
| 426 |
+
"learning_rate": 0.0001270870870870871,
|
| 427 |
+
"loss": 0.3055,
|
| 428 |
+
"step": 610
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 1.86,
|
| 432 |
+
"learning_rate": 0.0001258858858858859,
|
| 433 |
+
"loss": 0.361,
|
| 434 |
+
"step": 620
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 1.89,
|
| 438 |
+
"learning_rate": 0.0001246846846846847,
|
| 439 |
+
"loss": 0.5006,
|
| 440 |
+
"step": 630
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 1.92,
|
| 444 |
+
"learning_rate": 0.0001234834834834835,
|
| 445 |
+
"loss": 0.4293,
|
| 446 |
+
"step": 640
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 1.95,
|
| 450 |
+
"learning_rate": 0.0001222822822822823,
|
| 451 |
+
"loss": 0.3787,
|
| 452 |
+
"step": 650
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 1.98,
|
| 456 |
+
"learning_rate": 0.00012108108108108109,
|
| 457 |
+
"loss": 0.4617,
|
| 458 |
+
"step": 660
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 2.01,
|
| 462 |
+
"learning_rate": 0.00011987987987987988,
|
| 463 |
+
"loss": 0.4291,
|
| 464 |
+
"step": 670
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 2.04,
|
| 468 |
+
"learning_rate": 0.00011867867867867868,
|
| 469 |
+
"loss": 0.4525,
|
| 470 |
+
"step": 680
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 2.07,
|
| 474 |
+
"learning_rate": 0.00011747747747747748,
|
| 475 |
+
"loss": 0.419,
|
| 476 |
+
"step": 690
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 2.1,
|
| 480 |
+
"learning_rate": 0.00011627627627627628,
|
| 481 |
+
"loss": 0.4229,
|
| 482 |
+
"step": 700
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 2.1,
|
| 486 |
+
"eval_accuracy": 0.8905419766206164,
|
| 487 |
+
"eval_loss": 0.35450688004493713,
|
| 488 |
+
"eval_runtime": 39.4995,
|
| 489 |
+
"eval_samples_per_second": 23.823,
|
| 490 |
+
"eval_steps_per_second": 2.987,
|
| 491 |
+
"step": 700
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 2.13,
|
| 495 |
+
"learning_rate": 0.0001150750750750751,
|
| 496 |
+
"loss": 0.117,
|
| 497 |
+
"step": 710
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 2.16,
|
| 501 |
+
"learning_rate": 0.00011387387387387387,
|
| 502 |
+
"loss": 0.3166,
|
| 503 |
+
"step": 720
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 2.19,
|
| 507 |
+
"learning_rate": 0.00011267267267267267,
|
| 508 |
+
"loss": 0.3709,
|
| 509 |
+
"step": 730
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 2.22,
|
| 513 |
+
"learning_rate": 0.00011147147147147147,
|
| 514 |
+
"loss": 0.2417,
|
| 515 |
+
"step": 740
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 2.25,
|
| 519 |
+
"learning_rate": 0.00011027027027027029,
|
| 520 |
+
"loss": 0.4182,
|
| 521 |
+
"step": 750
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 2.28,
|
| 525 |
+
"learning_rate": 0.00010906906906906909,
|
| 526 |
+
"loss": 0.3219,
|
| 527 |
+
"step": 760
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 2.31,
|
| 531 |
+
"learning_rate": 0.00010786786786786786,
|
| 532 |
+
"loss": 0.3879,
|
| 533 |
+
"step": 770
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 2.34,
|
| 537 |
+
"learning_rate": 0.00010666666666666667,
|
| 538 |
+
"loss": 0.3304,
|
| 539 |
+
"step": 780
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 2.37,
|
| 543 |
+
"learning_rate": 0.00010546546546546547,
|
| 544 |
+
"loss": 0.4358,
|
| 545 |
+
"step": 790
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 2.4,
|
| 549 |
+
"learning_rate": 0.00010426426426426428,
|
| 550 |
+
"loss": 0.3832,
|
| 551 |
+
"step": 800
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 2.4,
|
| 555 |
+
"eval_accuracy": 0.9086078639744952,
|
| 556 |
+
"eval_loss": 0.3445776104927063,
|
| 557 |
+
"eval_runtime": 40.5544,
|
| 558 |
+
"eval_samples_per_second": 23.203,
|
| 559 |
+
"eval_steps_per_second": 2.91,
|
| 560 |
+
"step": 800
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 2.43,
|
| 564 |
+
"learning_rate": 0.00010306306306306306,
|
| 565 |
+
"loss": 0.2202,
|
| 566 |
+
"step": 810
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 2.46,
|
| 570 |
+
"learning_rate": 0.00010186186186186186,
|
| 571 |
+
"loss": 0.2851,
|
| 572 |
+
"step": 820
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 2.49,
|
| 576 |
+
"learning_rate": 0.00010066066066066066,
|
| 577 |
+
"loss": 0.2624,
|
| 578 |
+
"step": 830
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 2.52,
|
| 582 |
+
"learning_rate": 9.945945945945948e-05,
|
| 583 |
+
"loss": 0.3048,
|
| 584 |
+
"step": 840
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 2.55,
|
| 588 |
+
"learning_rate": 9.825825825825826e-05,
|
| 589 |
+
"loss": 0.2088,
|
| 590 |
+
"step": 850
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 2.58,
|
| 594 |
+
"learning_rate": 9.705705705705707e-05,
|
| 595 |
+
"loss": 0.3517,
|
| 596 |
+
"step": 860
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 2.61,
|
| 600 |
+
"learning_rate": 9.585585585585585e-05,
|
| 601 |
+
"loss": 0.4147,
|
| 602 |
+
"step": 870
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 2.64,
|
| 606 |
+
"learning_rate": 9.465465465465466e-05,
|
| 607 |
+
"loss": 0.3886,
|
| 608 |
+
"step": 880
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 2.67,
|
| 612 |
+
"learning_rate": 9.345345345345346e-05,
|
| 613 |
+
"loss": 0.2345,
|
| 614 |
+
"step": 890
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 2.7,
|
| 618 |
+
"learning_rate": 9.225225225225226e-05,
|
| 619 |
+
"loss": 0.2745,
|
| 620 |
+
"step": 900
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 2.7,
|
| 624 |
+
"eval_accuracy": 0.9149840595111584,
|
| 625 |
+
"eval_loss": 0.32985183596611023,
|
| 626 |
+
"eval_runtime": 40.5661,
|
| 627 |
+
"eval_samples_per_second": 23.197,
|
| 628 |
+
"eval_steps_per_second": 2.909,
|
| 629 |
+
"step": 900
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 2.73,
|
| 633 |
+
"learning_rate": 9.105105105105105e-05,
|
| 634 |
+
"loss": 0.2712,
|
| 635 |
+
"step": 910
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 2.76,
|
| 639 |
+
"learning_rate": 8.984984984984985e-05,
|
| 640 |
+
"loss": 0.389,
|
| 641 |
+
"step": 920
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 2.79,
|
| 645 |
+
"learning_rate": 8.864864864864866e-05,
|
| 646 |
+
"loss": 0.4054,
|
| 647 |
+
"step": 930
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 2.82,
|
| 651 |
+
"learning_rate": 8.744744744744745e-05,
|
| 652 |
+
"loss": 0.3054,
|
| 653 |
+
"step": 940
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 2.85,
|
| 657 |
+
"learning_rate": 8.624624624624625e-05,
|
| 658 |
+
"loss": 0.2941,
|
| 659 |
+
"step": 950
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 2.88,
|
| 663 |
+
"learning_rate": 8.504504504504504e-05,
|
| 664 |
+
"loss": 0.2896,
|
| 665 |
+
"step": 960
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 2.91,
|
| 669 |
+
"learning_rate": 8.384384384384384e-05,
|
| 670 |
+
"loss": 0.2729,
|
| 671 |
+
"step": 970
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 2.94,
|
| 675 |
+
"learning_rate": 8.264264264264265e-05,
|
| 676 |
+
"loss": 0.5281,
|
| 677 |
+
"step": 980
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 2.97,
|
| 681 |
+
"learning_rate": 8.144144144144145e-05,
|
| 682 |
+
"loss": 0.2477,
|
| 683 |
+
"step": 990
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 3.0,
|
| 687 |
+
"learning_rate": 8.024024024024024e-05,
|
| 688 |
+
"loss": 0.2063,
|
| 689 |
+
"step": 1000
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 3.0,
|
| 693 |
+
"eval_accuracy": 0.9277364505844846,
|
| 694 |
+
"eval_loss": 0.2592255771160126,
|
| 695 |
+
"eval_runtime": 40.3202,
|
| 696 |
+
"eval_samples_per_second": 23.338,
|
| 697 |
+
"eval_steps_per_second": 2.927,
|
| 698 |
+
"step": 1000
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 3.03,
|
| 702 |
+
"learning_rate": 7.903903903903904e-05,
|
| 703 |
+
"loss": 0.1643,
|
| 704 |
+
"step": 1010
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 3.06,
|
| 708 |
+
"learning_rate": 7.783783783783785e-05,
|
| 709 |
+
"loss": 0.322,
|
| 710 |
+
"step": 1020
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 3.09,
|
| 714 |
+
"learning_rate": 7.663663663663664e-05,
|
| 715 |
+
"loss": 0.1657,
|
| 716 |
+
"step": 1030
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 3.12,
|
| 720 |
+
"learning_rate": 7.543543543543544e-05,
|
| 721 |
+
"loss": 0.2675,
|
| 722 |
+
"step": 1040
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 3.15,
|
| 726 |
+
"learning_rate": 7.423423423423423e-05,
|
| 727 |
+
"loss": 0.2194,
|
| 728 |
+
"step": 1050
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 3.18,
|
| 732 |
+
"learning_rate": 7.303303303303303e-05,
|
| 733 |
+
"loss": 0.1154,
|
| 734 |
+
"step": 1060
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 3.21,
|
| 738 |
+
"learning_rate": 7.183183183183183e-05,
|
| 739 |
+
"loss": 0.1816,
|
| 740 |
+
"step": 1070
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 3.24,
|
| 744 |
+
"learning_rate": 7.063063063063064e-05,
|
| 745 |
+
"loss": 0.1359,
|
| 746 |
+
"step": 1080
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 3.27,
|
| 750 |
+
"learning_rate": 6.942942942942944e-05,
|
| 751 |
+
"loss": 0.3088,
|
| 752 |
+
"step": 1090
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 3.3,
|
| 756 |
+
"learning_rate": 6.822822822822822e-05,
|
| 757 |
+
"loss": 0.2077,
|
| 758 |
+
"step": 1100
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 3.3,
|
| 762 |
+
"eval_accuracy": 0.9149840595111584,
|
| 763 |
+
"eval_loss": 0.37718382477760315,
|
| 764 |
+
"eval_runtime": 40.237,
|
| 765 |
+
"eval_samples_per_second": 23.386,
|
| 766 |
+
"eval_steps_per_second": 2.933,
|
| 767 |
+
"step": 1100
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 3.33,
|
| 771 |
+
"learning_rate": 6.702702702702704e-05,
|
| 772 |
+
"loss": 0.316,
|
| 773 |
+
"step": 1110
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 3.36,
|
| 777 |
+
"learning_rate": 6.582582582582583e-05,
|
| 778 |
+
"loss": 0.1016,
|
| 779 |
+
"step": 1120
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 3.39,
|
| 783 |
+
"learning_rate": 6.462462462462463e-05,
|
| 784 |
+
"loss": 0.1508,
|
| 785 |
+
"step": 1130
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 3.42,
|
| 789 |
+
"learning_rate": 6.342342342342342e-05,
|
| 790 |
+
"loss": 0.2685,
|
| 791 |
+
"step": 1140
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 3.45,
|
| 795 |
+
"learning_rate": 6.222222222222222e-05,
|
| 796 |
+
"loss": 0.2662,
|
| 797 |
+
"step": 1150
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 3.48,
|
| 801 |
+
"learning_rate": 6.102102102102102e-05,
|
| 802 |
+
"loss": 0.2772,
|
| 803 |
+
"step": 1160
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 3.51,
|
| 807 |
+
"learning_rate": 5.981981981981982e-05,
|
| 808 |
+
"loss": 0.1013,
|
| 809 |
+
"step": 1170
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 3.54,
|
| 813 |
+
"learning_rate": 5.8618618618618625e-05,
|
| 814 |
+
"loss": 0.1762,
|
| 815 |
+
"step": 1180
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 3.57,
|
| 819 |
+
"learning_rate": 5.741741741741742e-05,
|
| 820 |
+
"loss": 0.1514,
|
| 821 |
+
"step": 1190
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 3.6,
|
| 825 |
+
"learning_rate": 5.621621621621622e-05,
|
| 826 |
+
"loss": 0.2041,
|
| 827 |
+
"step": 1200
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 3.6,
|
| 831 |
+
"eval_accuracy": 0.9213602550478215,
|
| 832 |
+
"eval_loss": 0.2855222523212433,
|
| 833 |
+
"eval_runtime": 39.5438,
|
| 834 |
+
"eval_samples_per_second": 23.796,
|
| 835 |
+
"eval_steps_per_second": 2.984,
|
| 836 |
+
"step": 1200
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 3.63,
|
| 840 |
+
"learning_rate": 5.5015015015015016e-05,
|
| 841 |
+
"loss": 0.1939,
|
| 842 |
+
"step": 1210
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 3.66,
|
| 846 |
+
"learning_rate": 5.381381381381382e-05,
|
| 847 |
+
"loss": 0.0919,
|
| 848 |
+
"step": 1220
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 3.69,
|
| 852 |
+
"learning_rate": 5.261261261261261e-05,
|
| 853 |
+
"loss": 0.2731,
|
| 854 |
+
"step": 1230
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 3.72,
|
| 858 |
+
"learning_rate": 5.1411411411411414e-05,
|
| 859 |
+
"loss": 0.1865,
|
| 860 |
+
"step": 1240
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 3.75,
|
| 864 |
+
"learning_rate": 5.0210210210210216e-05,
|
| 865 |
+
"loss": 0.238,
|
| 866 |
+
"step": 1250
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 3.78,
|
| 870 |
+
"learning_rate": 4.900900900900901e-05,
|
| 871 |
+
"loss": 0.0804,
|
| 872 |
+
"step": 1260
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 3.81,
|
| 876 |
+
"learning_rate": 4.7807807807807806e-05,
|
| 877 |
+
"loss": 0.3592,
|
| 878 |
+
"step": 1270
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 3.84,
|
| 882 |
+
"learning_rate": 4.660660660660661e-05,
|
| 883 |
+
"loss": 0.323,
|
| 884 |
+
"step": 1280
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 3.87,
|
| 888 |
+
"learning_rate": 4.540540540540541e-05,
|
| 889 |
+
"loss": 0.1983,
|
| 890 |
+
"step": 1290
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 3.9,
|
| 894 |
+
"learning_rate": 4.420420420420421e-05,
|
| 895 |
+
"loss": 0.2541,
|
| 896 |
+
"step": 1300
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 3.9,
|
| 900 |
+
"eval_accuracy": 0.9330499468650372,
|
| 901 |
+
"eval_loss": 0.25022733211517334,
|
| 902 |
+
"eval_runtime": 39.5082,
|
| 903 |
+
"eval_samples_per_second": 23.818,
|
| 904 |
+
"eval_steps_per_second": 2.987,
|
| 905 |
+
"step": 1300
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 3.93,
|
| 909 |
+
"learning_rate": 4.3003003003003006e-05,
|
| 910 |
+
"loss": 0.3586,
|
| 911 |
+
"step": 1310
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 3.96,
|
| 915 |
+
"learning_rate": 4.180180180180181e-05,
|
| 916 |
+
"loss": 0.2121,
|
| 917 |
+
"step": 1320
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 3.99,
|
| 921 |
+
"learning_rate": 4.06006006006006e-05,
|
| 922 |
+
"loss": 0.1308,
|
| 923 |
+
"step": 1330
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 4.02,
|
| 927 |
+
"learning_rate": 3.93993993993994e-05,
|
| 928 |
+
"loss": 0.2163,
|
| 929 |
+
"step": 1340
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 4.05,
|
| 933 |
+
"learning_rate": 3.81981981981982e-05,
|
| 934 |
+
"loss": 0.0668,
|
| 935 |
+
"step": 1350
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 4.08,
|
| 939 |
+
"learning_rate": 3.6996996996996994e-05,
|
| 940 |
+
"loss": 0.1516,
|
| 941 |
+
"step": 1360
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 4.11,
|
| 945 |
+
"learning_rate": 3.57957957957958e-05,
|
| 946 |
+
"loss": 0.1323,
|
| 947 |
+
"step": 1370
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 4.14,
|
| 951 |
+
"learning_rate": 3.45945945945946e-05,
|
| 952 |
+
"loss": 0.237,
|
| 953 |
+
"step": 1380
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 4.17,
|
| 957 |
+
"learning_rate": 3.33933933933934e-05,
|
| 958 |
+
"loss": 0.1337,
|
| 959 |
+
"step": 1390
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 4.2,
|
| 963 |
+
"learning_rate": 3.2192192192192194e-05,
|
| 964 |
+
"loss": 0.1203,
|
| 965 |
+
"step": 1400
|
| 966 |
+
},
|
| 967 |
+
{
|
| 968 |
+
"epoch": 4.2,
|
| 969 |
+
"eval_accuracy": 0.9362380446333688,
|
| 970 |
+
"eval_loss": 0.25774362683296204,
|
| 971 |
+
"eval_runtime": 39.3333,
|
| 972 |
+
"eval_samples_per_second": 23.924,
|
| 973 |
+
"eval_steps_per_second": 3.0,
|
| 974 |
+
"step": 1400
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 4.23,
|
| 978 |
+
"learning_rate": 3.0990990990990995e-05,
|
| 979 |
+
"loss": 0.0531,
|
| 980 |
+
"step": 1410
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 4.26,
|
| 984 |
+
"learning_rate": 2.978978978978979e-05,
|
| 985 |
+
"loss": 0.1448,
|
| 986 |
+
"step": 1420
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 4.29,
|
| 990 |
+
"learning_rate": 2.858858858858859e-05,
|
| 991 |
+
"loss": 0.0946,
|
| 992 |
+
"step": 1430
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 4.32,
|
| 996 |
+
"learning_rate": 2.7387387387387387e-05,
|
| 997 |
+
"loss": 0.0927,
|
| 998 |
+
"step": 1440
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 4.35,
|
| 1002 |
+
"learning_rate": 2.618618618618619e-05,
|
| 1003 |
+
"loss": 0.1215,
|
| 1004 |
+
"step": 1450
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 4.38,
|
| 1008 |
+
"learning_rate": 2.4984984984984987e-05,
|
| 1009 |
+
"loss": 0.1332,
|
| 1010 |
+
"step": 1460
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 4.41,
|
| 1014 |
+
"learning_rate": 2.3783783783783785e-05,
|
| 1015 |
+
"loss": 0.1657,
|
| 1016 |
+
"step": 1470
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 4.44,
|
| 1020 |
+
"learning_rate": 2.2582582582582583e-05,
|
| 1021 |
+
"loss": 0.2,
|
| 1022 |
+
"step": 1480
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 4.47,
|
| 1026 |
+
"learning_rate": 2.1381381381381382e-05,
|
| 1027 |
+
"loss": 0.1323,
|
| 1028 |
+
"step": 1490
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 4.5,
|
| 1032 |
+
"learning_rate": 2.018018018018018e-05,
|
| 1033 |
+
"loss": 0.1594,
|
| 1034 |
+
"step": 1500
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 4.5,
|
| 1038 |
+
"eval_accuracy": 0.9458023379383634,
|
| 1039 |
+
"eval_loss": 0.22263780236244202,
|
| 1040 |
+
"eval_runtime": 39.564,
|
| 1041 |
+
"eval_samples_per_second": 23.784,
|
| 1042 |
+
"eval_steps_per_second": 2.983,
|
| 1043 |
+
"step": 1500
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 4.53,
|
| 1047 |
+
"learning_rate": 1.8978978978978982e-05,
|
| 1048 |
+
"loss": 0.1963,
|
| 1049 |
+
"step": 1510
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 4.56,
|
| 1053 |
+
"learning_rate": 1.777777777777778e-05,
|
| 1054 |
+
"loss": 0.18,
|
| 1055 |
+
"step": 1520
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 4.59,
|
| 1059 |
+
"learning_rate": 1.6576576576576578e-05,
|
| 1060 |
+
"loss": 0.1519,
|
| 1061 |
+
"step": 1530
|
| 1062 |
+
},
|
| 1063 |
+
{
|
| 1064 |
+
"epoch": 4.62,
|
| 1065 |
+
"learning_rate": 1.5375375375375377e-05,
|
| 1066 |
+
"loss": 0.1375,
|
| 1067 |
+
"step": 1540
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 4.65,
|
| 1071 |
+
"learning_rate": 1.4174174174174173e-05,
|
| 1072 |
+
"loss": 0.1323,
|
| 1073 |
+
"step": 1550
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 4.68,
|
| 1077 |
+
"learning_rate": 1.2972972972972975e-05,
|
| 1078 |
+
"loss": 0.128,
|
| 1079 |
+
"step": 1560
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 4.71,
|
| 1083 |
+
"learning_rate": 1.1771771771771773e-05,
|
| 1084 |
+
"loss": 0.0505,
|
| 1085 |
+
"step": 1570
|
| 1086 |
+
},
|
| 1087 |
+
{
|
| 1088 |
+
"epoch": 4.74,
|
| 1089 |
+
"learning_rate": 1.057057057057057e-05,
|
| 1090 |
+
"loss": 0.0957,
|
| 1091 |
+
"step": 1580
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 4.77,
|
| 1095 |
+
"learning_rate": 9.36936936936937e-06,
|
| 1096 |
+
"loss": 0.043,
|
| 1097 |
+
"step": 1590
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 4.8,
|
| 1101 |
+
"learning_rate": 8.168168168168168e-06,
|
| 1102 |
+
"loss": 0.1015,
|
| 1103 |
+
"step": 1600
|
| 1104 |
+
},
|
| 1105 |
+
{
|
| 1106 |
+
"epoch": 4.8,
|
| 1107 |
+
"eval_accuracy": 0.9436769394261424,
|
| 1108 |
+
"eval_loss": 0.236781507730484,
|
| 1109 |
+
"eval_runtime": 39.398,
|
| 1110 |
+
"eval_samples_per_second": 23.884,
|
| 1111 |
+
"eval_steps_per_second": 2.995,
|
| 1112 |
+
"step": 1600
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 4.83,
|
| 1116 |
+
"learning_rate": 6.966966966966967e-06,
|
| 1117 |
+
"loss": 0.1853,
|
| 1118 |
+
"step": 1610
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 4.86,
|
| 1122 |
+
"learning_rate": 5.765765765765766e-06,
|
| 1123 |
+
"loss": 0.0874,
|
| 1124 |
+
"step": 1620
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 4.89,
|
| 1128 |
+
"learning_rate": 4.5645645645645645e-06,
|
| 1129 |
+
"loss": 0.0949,
|
| 1130 |
+
"step": 1630
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 4.92,
|
| 1134 |
+
"learning_rate": 3.3633633633633636e-06,
|
| 1135 |
+
"loss": 0.1901,
|
| 1136 |
+
"step": 1640
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 4.95,
|
| 1140 |
+
"learning_rate": 2.1621621621621623e-06,
|
| 1141 |
+
"loss": 0.1235,
|
| 1142 |
+
"step": 1650
|
| 1143 |
+
},
|
| 1144 |
+
{
|
| 1145 |
+
"epoch": 4.98,
|
| 1146 |
+
"learning_rate": 9.60960960960961e-07,
|
| 1147 |
+
"loss": 0.0785,
|
| 1148 |
+
"step": 1660
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 5.0,
|
| 1152 |
+
"step": 1665,
|
| 1153 |
+
"total_flos": 2.0875695162281165e+18,
|
| 1154 |
+
"train_loss": 0.38661149321375665,
|
| 1155 |
+
"train_runtime": 2052.9844,
|
| 1156 |
+
"train_samples_per_second": 12.976,
|
| 1157 |
+
"train_steps_per_second": 0.811
|
| 1158 |
+
}
|
| 1159 |
+
],
|
| 1160 |
+
"max_steps": 1665,
|
| 1161 |
+
"num_train_epochs": 5,
|
| 1162 |
+
"total_flos": 2.0875695162281165e+18,
|
| 1163 |
+
"trial_name": null,
|
| 1164 |
+
"trial_params": null
|
| 1165 |
+
}
|