Nguyen Tien
commited on
Commit
•
402f486
1
Parent(s):
e47ed66
vuihocrnd/teacher-status-van-tiny-256-0
Browse files- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +1236 -0
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 29.68,
|
| 3 |
+
"total_flos": 8.181902891907809e+17,
|
| 4 |
+
"train_loss": 0.24775470698133428,
|
| 5 |
+
"train_runtime": 3242.8553,
|
| 6 |
+
"train_samples_per_second": 56.145,
|
| 7 |
+
"train_steps_per_second": 0.435
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 29.68,
|
| 3 |
+
"total_flos": 8.181902891907809e+17,
|
| 4 |
+
"train_loss": 0.24775470698133428,
|
| 5 |
+
"train_runtime": 3242.8553,
|
| 6 |
+
"train_samples_per_second": 56.145,
|
| 7 |
+
"train_steps_per_second": 0.435
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1236 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9872068230277186,
|
| 3 |
+
"best_model_checkpoint": "teacher-status-van-tiny-256-0/checkpoint-1140",
|
| 4 |
+
"epoch": 29.68421052631579,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1410,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.21,
|
| 13 |
+
"learning_rate": 3.5460992907801423e-06,
|
| 14 |
+
"loss": 0.693,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.42,
|
| 19 |
+
"learning_rate": 7.092198581560285e-06,
|
| 20 |
+
"loss": 0.692,
|
| 21 |
+
"step": 20
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.63,
|
| 25 |
+
"learning_rate": 1.0638297872340426e-05,
|
| 26 |
+
"loss": 0.6887,
|
| 27 |
+
"step": 30
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.84,
|
| 31 |
+
"learning_rate": 1.418439716312057e-05,
|
| 32 |
+
"loss": 0.6788,
|
| 33 |
+
"step": 40
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.99,
|
| 37 |
+
"eval_accuracy": 0.6933333333333334,
|
| 38 |
+
"eval_f1_score": 0.8188976377952756,
|
| 39 |
+
"eval_loss": 0.6436793804168701,
|
| 40 |
+
"eval_precision": 0.6933333333333334,
|
| 41 |
+
"eval_recall": 1.0,
|
| 42 |
+
"eval_runtime": 3.9449,
|
| 43 |
+
"eval_samples_per_second": 171.109,
|
| 44 |
+
"eval_steps_per_second": 5.577,
|
| 45 |
+
"step": 47
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 1.05,
|
| 49 |
+
"learning_rate": 1.773049645390071e-05,
|
| 50 |
+
"loss": 0.6568,
|
| 51 |
+
"step": 50
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 1.26,
|
| 55 |
+
"learning_rate": 2.1276595744680852e-05,
|
| 56 |
+
"loss": 0.6118,
|
| 57 |
+
"step": 60
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 1.47,
|
| 61 |
+
"learning_rate": 2.4822695035460995e-05,
|
| 62 |
+
"loss": 0.5534,
|
| 63 |
+
"step": 70
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 1.68,
|
| 67 |
+
"learning_rate": 2.836879432624114e-05,
|
| 68 |
+
"loss": 0.4849,
|
| 69 |
+
"step": 80
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 1.89,
|
| 73 |
+
"learning_rate": 3.191489361702128e-05,
|
| 74 |
+
"loss": 0.463,
|
| 75 |
+
"step": 90
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 2.0,
|
| 79 |
+
"eval_accuracy": 0.8755555555555555,
|
| 80 |
+
"eval_f1_score": 0.9161676646706586,
|
| 81 |
+
"eval_loss": 0.3405998945236206,
|
| 82 |
+
"eval_precision": 0.8595505617977528,
|
| 83 |
+
"eval_recall": 0.9807692307692307,
|
| 84 |
+
"eval_runtime": 4.4067,
|
| 85 |
+
"eval_samples_per_second": 153.174,
|
| 86 |
+
"eval_steps_per_second": 4.992,
|
| 87 |
+
"step": 95
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 2.11,
|
| 91 |
+
"learning_rate": 3.546099290780142e-05,
|
| 92 |
+
"loss": 0.4401,
|
| 93 |
+
"step": 100
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 2.32,
|
| 97 |
+
"learning_rate": 3.900709219858156e-05,
|
| 98 |
+
"loss": 0.4196,
|
| 99 |
+
"step": 110
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 2.53,
|
| 103 |
+
"learning_rate": 4.2553191489361704e-05,
|
| 104 |
+
"loss": 0.3933,
|
| 105 |
+
"step": 120
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 2.74,
|
| 109 |
+
"learning_rate": 4.609929078014185e-05,
|
| 110 |
+
"loss": 0.3977,
|
| 111 |
+
"step": 130
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 2.95,
|
| 115 |
+
"learning_rate": 4.964539007092199e-05,
|
| 116 |
+
"loss": 0.3596,
|
| 117 |
+
"step": 140
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 2.99,
|
| 121 |
+
"eval_accuracy": 0.9303703703703704,
|
| 122 |
+
"eval_f1_score": 0.9503695881731784,
|
| 123 |
+
"eval_loss": 0.2071676254272461,
|
| 124 |
+
"eval_precision": 0.9394572025052192,
|
| 125 |
+
"eval_recall": 0.9615384615384616,
|
| 126 |
+
"eval_runtime": 3.9276,
|
| 127 |
+
"eval_samples_per_second": 171.861,
|
| 128 |
+
"eval_steps_per_second": 5.601,
|
| 129 |
+
"step": 142
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 3.16,
|
| 133 |
+
"learning_rate": 4.964539007092199e-05,
|
| 134 |
+
"loss": 0.3506,
|
| 135 |
+
"step": 150
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 3.37,
|
| 139 |
+
"learning_rate": 4.9251379038613084e-05,
|
| 140 |
+
"loss": 0.354,
|
| 141 |
+
"step": 160
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 3.58,
|
| 145 |
+
"learning_rate": 4.885736800630418e-05,
|
| 146 |
+
"loss": 0.3132,
|
| 147 |
+
"step": 170
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 3.79,
|
| 151 |
+
"learning_rate": 4.846335697399527e-05,
|
| 152 |
+
"loss": 0.3324,
|
| 153 |
+
"step": 180
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 4.0,
|
| 157 |
+
"learning_rate": 4.806934594168637e-05,
|
| 158 |
+
"loss": 0.3505,
|
| 159 |
+
"step": 190
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 4.0,
|
| 163 |
+
"eval_accuracy": 0.9525925925925925,
|
| 164 |
+
"eval_f1_score": 0.9661016949152542,
|
| 165 |
+
"eval_loss": 0.15637531876564026,
|
| 166 |
+
"eval_precision": 0.957983193277311,
|
| 167 |
+
"eval_recall": 0.9743589743589743,
|
| 168 |
+
"eval_runtime": 4.0891,
|
| 169 |
+
"eval_samples_per_second": 165.073,
|
| 170 |
+
"eval_steps_per_second": 5.38,
|
| 171 |
+
"step": 190
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 4.21,
|
| 175 |
+
"learning_rate": 4.7675334909377466e-05,
|
| 176 |
+
"loss": 0.3181,
|
| 177 |
+
"step": 200
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 4.42,
|
| 181 |
+
"learning_rate": 4.728132387706856e-05,
|
| 182 |
+
"loss": 0.3174,
|
| 183 |
+
"step": 210
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 4.63,
|
| 187 |
+
"learning_rate": 4.6887312844759653e-05,
|
| 188 |
+
"loss": 0.3161,
|
| 189 |
+
"step": 220
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 4.84,
|
| 193 |
+
"learning_rate": 4.6493301812450754e-05,
|
| 194 |
+
"loss": 0.2962,
|
| 195 |
+
"step": 230
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 4.99,
|
| 199 |
+
"eval_accuracy": 0.9555555555555556,
|
| 200 |
+
"eval_f1_score": 0.9680851063829786,
|
| 201 |
+
"eval_loss": 0.12618891894817352,
|
| 202 |
+
"eval_precision": 0.9639830508474576,
|
| 203 |
+
"eval_recall": 0.9722222222222222,
|
| 204 |
+
"eval_runtime": 4.4801,
|
| 205 |
+
"eval_samples_per_second": 150.665,
|
| 206 |
+
"eval_steps_per_second": 4.911,
|
| 207 |
+
"step": 237
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 5.05,
|
| 211 |
+
"learning_rate": 4.609929078014185e-05,
|
| 212 |
+
"loss": 0.3017,
|
| 213 |
+
"step": 240
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 5.26,
|
| 217 |
+
"learning_rate": 4.570527974783294e-05,
|
| 218 |
+
"loss": 0.2852,
|
| 219 |
+
"step": 250
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 5.47,
|
| 223 |
+
"learning_rate": 4.5311268715524035e-05,
|
| 224 |
+
"loss": 0.3222,
|
| 225 |
+
"step": 260
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 5.68,
|
| 229 |
+
"learning_rate": 4.491725768321513e-05,
|
| 230 |
+
"loss": 0.2662,
|
| 231 |
+
"step": 270
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 5.89,
|
| 235 |
+
"learning_rate": 4.452324665090622e-05,
|
| 236 |
+
"loss": 0.2762,
|
| 237 |
+
"step": 280
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 6.0,
|
| 241 |
+
"eval_accuracy": 0.9644444444444444,
|
| 242 |
+
"eval_f1_score": 0.9745222929936307,
|
| 243 |
+
"eval_loss": 0.10375303775072098,
|
| 244 |
+
"eval_precision": 0.9683544303797469,
|
| 245 |
+
"eval_recall": 0.9807692307692307,
|
| 246 |
+
"eval_runtime": 3.8894,
|
| 247 |
+
"eval_samples_per_second": 173.548,
|
| 248 |
+
"eval_steps_per_second": 5.656,
|
| 249 |
+
"step": 285
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 6.11,
|
| 253 |
+
"learning_rate": 4.412923561859732e-05,
|
| 254 |
+
"loss": 0.2803,
|
| 255 |
+
"step": 290
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 6.32,
|
| 259 |
+
"learning_rate": 4.373522458628842e-05,
|
| 260 |
+
"loss": 0.2672,
|
| 261 |
+
"step": 300
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 6.53,
|
| 265 |
+
"learning_rate": 4.334121355397952e-05,
|
| 266 |
+
"loss": 0.2768,
|
| 267 |
+
"step": 310
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 6.74,
|
| 271 |
+
"learning_rate": 4.294720252167061e-05,
|
| 272 |
+
"loss": 0.2709,
|
| 273 |
+
"step": 320
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 6.95,
|
| 277 |
+
"learning_rate": 4.2553191489361704e-05,
|
| 278 |
+
"loss": 0.2604,
|
| 279 |
+
"step": 330
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 6.99,
|
| 283 |
+
"eval_accuracy": 0.9718518518518519,
|
| 284 |
+
"eval_f1_score": 0.979765708200213,
|
| 285 |
+
"eval_loss": 0.09324438869953156,
|
| 286 |
+
"eval_precision": 0.9766454352441614,
|
| 287 |
+
"eval_recall": 0.9829059829059829,
|
| 288 |
+
"eval_runtime": 3.9359,
|
| 289 |
+
"eval_samples_per_second": 171.498,
|
| 290 |
+
"eval_steps_per_second": 5.59,
|
| 291 |
+
"step": 332
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 7.16,
|
| 295 |
+
"learning_rate": 4.21591804570528e-05,
|
| 296 |
+
"loss": 0.2647,
|
| 297 |
+
"step": 340
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 7.37,
|
| 301 |
+
"learning_rate": 4.176516942474389e-05,
|
| 302 |
+
"loss": 0.2632,
|
| 303 |
+
"step": 350
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 7.58,
|
| 307 |
+
"learning_rate": 4.1371158392434986e-05,
|
| 308 |
+
"loss": 0.2688,
|
| 309 |
+
"step": 360
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 7.79,
|
| 313 |
+
"learning_rate": 4.0977147360126086e-05,
|
| 314 |
+
"loss": 0.2699,
|
| 315 |
+
"step": 370
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 8.0,
|
| 319 |
+
"learning_rate": 4.058313632781718e-05,
|
| 320 |
+
"loss": 0.2427,
|
| 321 |
+
"step": 380
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 8.0,
|
| 325 |
+
"eval_accuracy": 0.9718518518518519,
|
| 326 |
+
"eval_f1_score": 0.9796791443850267,
|
| 327 |
+
"eval_loss": 0.09280087053775787,
|
| 328 |
+
"eval_precision": 0.9807280513918629,
|
| 329 |
+
"eval_recall": 0.9786324786324786,
|
| 330 |
+
"eval_runtime": 4.2848,
|
| 331 |
+
"eval_samples_per_second": 157.534,
|
| 332 |
+
"eval_steps_per_second": 5.134,
|
| 333 |
+
"step": 380
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 8.21,
|
| 337 |
+
"learning_rate": 4.018912529550828e-05,
|
| 338 |
+
"loss": 0.241,
|
| 339 |
+
"step": 390
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 8.42,
|
| 343 |
+
"learning_rate": 3.9795114263199374e-05,
|
| 344 |
+
"loss": 0.2311,
|
| 345 |
+
"step": 400
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 8.63,
|
| 349 |
+
"learning_rate": 3.940110323089047e-05,
|
| 350 |
+
"loss": 0.2447,
|
| 351 |
+
"step": 410
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 8.84,
|
| 355 |
+
"learning_rate": 3.900709219858156e-05,
|
| 356 |
+
"loss": 0.2465,
|
| 357 |
+
"step": 420
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 8.99,
|
| 361 |
+
"eval_accuracy": 0.9718518518518519,
|
| 362 |
+
"eval_f1_score": 0.9796791443850267,
|
| 363 |
+
"eval_loss": 0.08982550352811813,
|
| 364 |
+
"eval_precision": 0.9807280513918629,
|
| 365 |
+
"eval_recall": 0.9786324786324786,
|
| 366 |
+
"eval_runtime": 3.8511,
|
| 367 |
+
"eval_samples_per_second": 175.276,
|
| 368 |
+
"eval_steps_per_second": 5.713,
|
| 369 |
+
"step": 427
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 9.05,
|
| 373 |
+
"learning_rate": 3.8613081166272655e-05,
|
| 374 |
+
"loss": 0.2579,
|
| 375 |
+
"step": 430
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 9.26,
|
| 379 |
+
"learning_rate": 3.8219070133963755e-05,
|
| 380 |
+
"loss": 0.2393,
|
| 381 |
+
"step": 440
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 9.47,
|
| 385 |
+
"learning_rate": 3.782505910165485e-05,
|
| 386 |
+
"loss": 0.2532,
|
| 387 |
+
"step": 450
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 9.68,
|
| 391 |
+
"learning_rate": 3.743104806934594e-05,
|
| 392 |
+
"loss": 0.2501,
|
| 393 |
+
"step": 460
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 9.89,
|
| 397 |
+
"learning_rate": 3.7037037037037037e-05,
|
| 398 |
+
"loss": 0.2519,
|
| 399 |
+
"step": 470
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 10.0,
|
| 403 |
+
"eval_accuracy": 0.9688888888888889,
|
| 404 |
+
"eval_f1_score": 0.9775401069518715,
|
| 405 |
+
"eval_loss": 0.09134020656347275,
|
| 406 |
+
"eval_precision": 0.9785867237687366,
|
| 407 |
+
"eval_recall": 0.9764957264957265,
|
| 408 |
+
"eval_runtime": 4.1234,
|
| 409 |
+
"eval_samples_per_second": 163.699,
|
| 410 |
+
"eval_steps_per_second": 5.335,
|
| 411 |
+
"step": 475
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 10.11,
|
| 415 |
+
"learning_rate": 3.664302600472813e-05,
|
| 416 |
+
"loss": 0.2177,
|
| 417 |
+
"step": 480
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 10.32,
|
| 421 |
+
"learning_rate": 3.624901497241923e-05,
|
| 422 |
+
"loss": 0.2248,
|
| 423 |
+
"step": 490
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 10.53,
|
| 427 |
+
"learning_rate": 3.5855003940110324e-05,
|
| 428 |
+
"loss": 0.2583,
|
| 429 |
+
"step": 500
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 10.74,
|
| 433 |
+
"learning_rate": 3.546099290780142e-05,
|
| 434 |
+
"loss": 0.2344,
|
| 435 |
+
"step": 510
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 10.95,
|
| 439 |
+
"learning_rate": 3.506698187549252e-05,
|
| 440 |
+
"loss": 0.2258,
|
| 441 |
+
"step": 520
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 10.99,
|
| 445 |
+
"eval_accuracy": 0.9733333333333334,
|
| 446 |
+
"eval_f1_score": 0.980891719745223,
|
| 447 |
+
"eval_loss": 0.08469923585653305,
|
| 448 |
+
"eval_precision": 0.9746835443037974,
|
| 449 |
+
"eval_recall": 0.9871794871794872,
|
| 450 |
+
"eval_runtime": 4.0414,
|
| 451 |
+
"eval_samples_per_second": 167.022,
|
| 452 |
+
"eval_steps_per_second": 5.444,
|
| 453 |
+
"step": 522
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 11.16,
|
| 457 |
+
"learning_rate": 3.467297084318361e-05,
|
| 458 |
+
"loss": 0.2357,
|
| 459 |
+
"step": 530
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 11.37,
|
| 463 |
+
"learning_rate": 3.4278959810874706e-05,
|
| 464 |
+
"loss": 0.2057,
|
| 465 |
+
"step": 540
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 11.58,
|
| 469 |
+
"learning_rate": 3.38849487785658e-05,
|
| 470 |
+
"loss": 0.2107,
|
| 471 |
+
"step": 550
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 11.79,
|
| 475 |
+
"learning_rate": 3.349093774625689e-05,
|
| 476 |
+
"loss": 0.228,
|
| 477 |
+
"step": 560
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 12.0,
|
| 481 |
+
"learning_rate": 3.309692671394799e-05,
|
| 482 |
+
"loss": 0.2184,
|
| 483 |
+
"step": 570
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 12.0,
|
| 487 |
+
"eval_accuracy": 0.9792592592592593,
|
| 488 |
+
"eval_f1_score": 0.9851063829787234,
|
| 489 |
+
"eval_loss": 0.08121450245380402,
|
| 490 |
+
"eval_precision": 0.9809322033898306,
|
| 491 |
+
"eval_recall": 0.9893162393162394,
|
| 492 |
+
"eval_runtime": 3.8823,
|
| 493 |
+
"eval_samples_per_second": 173.868,
|
| 494 |
+
"eval_steps_per_second": 5.667,
|
| 495 |
+
"step": 570
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 12.21,
|
| 499 |
+
"learning_rate": 3.270291568163909e-05,
|
| 500 |
+
"loss": 0.1992,
|
| 501 |
+
"step": 580
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 12.42,
|
| 505 |
+
"learning_rate": 3.230890464933019e-05,
|
| 506 |
+
"loss": 0.2289,
|
| 507 |
+
"step": 590
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 12.63,
|
| 511 |
+
"learning_rate": 3.191489361702128e-05,
|
| 512 |
+
"loss": 0.2029,
|
| 513 |
+
"step": 600
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 12.84,
|
| 517 |
+
"learning_rate": 3.1520882584712375e-05,
|
| 518 |
+
"loss": 0.2208,
|
| 519 |
+
"step": 610
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 12.99,
|
| 523 |
+
"eval_accuracy": 0.9807407407407407,
|
| 524 |
+
"eval_f1_score": 0.9861259338313767,
|
| 525 |
+
"eval_loss": 0.06925630569458008,
|
| 526 |
+
"eval_precision": 0.9850746268656716,
|
| 527 |
+
"eval_recall": 0.9871794871794872,
|
| 528 |
+
"eval_runtime": 4.4316,
|
| 529 |
+
"eval_samples_per_second": 152.316,
|
| 530 |
+
"eval_steps_per_second": 4.964,
|
| 531 |
+
"step": 617
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 13.05,
|
| 535 |
+
"learning_rate": 3.112687155240347e-05,
|
| 536 |
+
"loss": 0.2284,
|
| 537 |
+
"step": 620
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 13.26,
|
| 541 |
+
"learning_rate": 3.073286052009456e-05,
|
| 542 |
+
"loss": 0.2129,
|
| 543 |
+
"step": 630
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 13.47,
|
| 547 |
+
"learning_rate": 3.033884948778566e-05,
|
| 548 |
+
"loss": 0.2219,
|
| 549 |
+
"step": 640
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 13.68,
|
| 553 |
+
"learning_rate": 2.9944838455476754e-05,
|
| 554 |
+
"loss": 0.219,
|
| 555 |
+
"step": 650
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 13.89,
|
| 559 |
+
"learning_rate": 2.9550827423167847e-05,
|
| 560 |
+
"loss": 0.2201,
|
| 561 |
+
"step": 660
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 14.0,
|
| 565 |
+
"eval_accuracy": 0.9762962962962963,
|
| 566 |
+
"eval_f1_score": 0.9829424307036249,
|
| 567 |
+
"eval_loss": 0.06279809772968292,
|
| 568 |
+
"eval_precision": 0.9808510638297873,
|
| 569 |
+
"eval_recall": 0.9850427350427351,
|
| 570 |
+
"eval_runtime": 3.8891,
|
| 571 |
+
"eval_samples_per_second": 173.56,
|
| 572 |
+
"eval_steps_per_second": 5.657,
|
| 573 |
+
"step": 665
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 14.11,
|
| 577 |
+
"learning_rate": 2.9156816390858944e-05,
|
| 578 |
+
"loss": 0.223,
|
| 579 |
+
"step": 670
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 14.32,
|
| 583 |
+
"learning_rate": 2.8762805358550045e-05,
|
| 584 |
+
"loss": 0.2151,
|
| 585 |
+
"step": 680
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 14.53,
|
| 589 |
+
"learning_rate": 2.836879432624114e-05,
|
| 590 |
+
"loss": 0.2096,
|
| 591 |
+
"step": 690
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 14.74,
|
| 595 |
+
"learning_rate": 2.7974783293932232e-05,
|
| 596 |
+
"loss": 0.2081,
|
| 597 |
+
"step": 700
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 14.95,
|
| 601 |
+
"learning_rate": 2.758077226162333e-05,
|
| 602 |
+
"loss": 0.2251,
|
| 603 |
+
"step": 710
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 14.99,
|
| 607 |
+
"eval_accuracy": 0.9733333333333334,
|
| 608 |
+
"eval_f1_score": 0.9809725158562368,
|
| 609 |
+
"eval_loss": 0.08107414096593857,
|
| 610 |
+
"eval_precision": 0.9707112970711297,
|
| 611 |
+
"eval_recall": 0.9914529914529915,
|
| 612 |
+
"eval_runtime": 3.8972,
|
| 613 |
+
"eval_samples_per_second": 173.203,
|
| 614 |
+
"eval_steps_per_second": 5.645,
|
| 615 |
+
"step": 712
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 15.16,
|
| 619 |
+
"learning_rate": 2.7186761229314423e-05,
|
| 620 |
+
"loss": 0.2067,
|
| 621 |
+
"step": 720
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 15.37,
|
| 625 |
+
"learning_rate": 2.6792750197005517e-05,
|
| 626 |
+
"loss": 0.1864,
|
| 627 |
+
"step": 730
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 15.58,
|
| 631 |
+
"learning_rate": 2.639873916469661e-05,
|
| 632 |
+
"loss": 0.208,
|
| 633 |
+
"step": 740
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 15.79,
|
| 637 |
+
"learning_rate": 2.6004728132387708e-05,
|
| 638 |
+
"loss": 0.1931,
|
| 639 |
+
"step": 750
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 16.0,
|
| 643 |
+
"learning_rate": 2.56107171000788e-05,
|
| 644 |
+
"loss": 0.2135,
|
| 645 |
+
"step": 760
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 16.0,
|
| 649 |
+
"eval_accuracy": 0.9762962962962963,
|
| 650 |
+
"eval_f1_score": 0.9829424307036249,
|
| 651 |
+
"eval_loss": 0.0718333050608635,
|
| 652 |
+
"eval_precision": 0.9808510638297873,
|
| 653 |
+
"eval_recall": 0.9850427350427351,
|
| 654 |
+
"eval_runtime": 4.4867,
|
| 655 |
+
"eval_samples_per_second": 150.444,
|
| 656 |
+
"eval_steps_per_second": 4.903,
|
| 657 |
+
"step": 760
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 16.21,
|
| 661 |
+
"learning_rate": 2.5216706067769895e-05,
|
| 662 |
+
"loss": 0.2,
|
| 663 |
+
"step": 770
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 16.42,
|
| 667 |
+
"learning_rate": 2.4822695035460995e-05,
|
| 668 |
+
"loss": 0.2025,
|
| 669 |
+
"step": 780
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 16.63,
|
| 673 |
+
"learning_rate": 2.442868400315209e-05,
|
| 674 |
+
"loss": 0.2017,
|
| 675 |
+
"step": 790
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 16.84,
|
| 679 |
+
"learning_rate": 2.4034672970843186e-05,
|
| 680 |
+
"loss": 0.1851,
|
| 681 |
+
"step": 800
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 16.99,
|
| 685 |
+
"eval_accuracy": 0.9762962962962963,
|
| 686 |
+
"eval_f1_score": 0.9829787234042553,
|
| 687 |
+
"eval_loss": 0.07912527769804001,
|
| 688 |
+
"eval_precision": 0.9788135593220338,
|
| 689 |
+
"eval_recall": 0.9871794871794872,
|
| 690 |
+
"eval_runtime": 3.9283,
|
| 691 |
+
"eval_samples_per_second": 171.83,
|
| 692 |
+
"eval_steps_per_second": 5.6,
|
| 693 |
+
"step": 807
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 17.05,
|
| 697 |
+
"learning_rate": 2.364066193853428e-05,
|
| 698 |
+
"loss": 0.1901,
|
| 699 |
+
"step": 810
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 17.26,
|
| 703 |
+
"learning_rate": 2.3246650906225377e-05,
|
| 704 |
+
"loss": 0.2272,
|
| 705 |
+
"step": 820
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 17.47,
|
| 709 |
+
"learning_rate": 2.285263987391647e-05,
|
| 710 |
+
"loss": 0.1965,
|
| 711 |
+
"step": 830
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 17.68,
|
| 715 |
+
"learning_rate": 2.2458628841607564e-05,
|
| 716 |
+
"loss": 0.1854,
|
| 717 |
+
"step": 840
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 17.89,
|
| 721 |
+
"learning_rate": 2.206461780929866e-05,
|
| 722 |
+
"loss": 0.2152,
|
| 723 |
+
"step": 850
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 18.0,
|
| 727 |
+
"eval_accuracy": 0.9748148148148148,
|
| 728 |
+
"eval_f1_score": 0.9818181818181818,
|
| 729 |
+
"eval_loss": 0.0737040787935257,
|
| 730 |
+
"eval_precision": 0.9828693790149893,
|
| 731 |
+
"eval_recall": 0.9807692307692307,
|
| 732 |
+
"eval_runtime": 3.9311,
|
| 733 |
+
"eval_samples_per_second": 171.706,
|
| 734 |
+
"eval_steps_per_second": 5.596,
|
| 735 |
+
"step": 855
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 18.11,
|
| 739 |
+
"learning_rate": 2.167060677698976e-05,
|
| 740 |
+
"loss": 0.1991,
|
| 741 |
+
"step": 860
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 18.32,
|
| 745 |
+
"learning_rate": 2.1276595744680852e-05,
|
| 746 |
+
"loss": 0.1637,
|
| 747 |
+
"step": 870
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 18.53,
|
| 751 |
+
"learning_rate": 2.0882584712371946e-05,
|
| 752 |
+
"loss": 0.1906,
|
| 753 |
+
"step": 880
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 18.74,
|
| 757 |
+
"learning_rate": 2.0488573680063043e-05,
|
| 758 |
+
"loss": 0.1899,
|
| 759 |
+
"step": 890
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 18.95,
|
| 763 |
+
"learning_rate": 2.009456264775414e-05,
|
| 764 |
+
"loss": 0.1871,
|
| 765 |
+
"step": 900
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 18.99,
|
| 769 |
+
"eval_accuracy": 0.9762962962962963,
|
| 770 |
+
"eval_f1_score": 0.9829787234042553,
|
| 771 |
+
"eval_loss": 0.08143588900566101,
|
| 772 |
+
"eval_precision": 0.9788135593220338,
|
| 773 |
+
"eval_recall": 0.9871794871794872,
|
| 774 |
+
"eval_runtime": 4.2729,
|
| 775 |
+
"eval_samples_per_second": 157.973,
|
| 776 |
+
"eval_steps_per_second": 5.149,
|
| 777 |
+
"step": 902
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 19.16,
|
| 781 |
+
"learning_rate": 1.9700551615445234e-05,
|
| 782 |
+
"loss": 0.1708,
|
| 783 |
+
"step": 910
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 19.37,
|
| 787 |
+
"learning_rate": 1.9306540583136327e-05,
|
| 788 |
+
"loss": 0.1864,
|
| 789 |
+
"step": 920
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 19.58,
|
| 793 |
+
"learning_rate": 1.8912529550827425e-05,
|
| 794 |
+
"loss": 0.1991,
|
| 795 |
+
"step": 930
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 19.79,
|
| 799 |
+
"learning_rate": 1.8518518518518518e-05,
|
| 800 |
+
"loss": 0.2152,
|
| 801 |
+
"step": 940
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 20.0,
|
| 805 |
+
"learning_rate": 1.8124507486209615e-05,
|
| 806 |
+
"loss": 0.1714,
|
| 807 |
+
"step": 950
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 20.0,
|
| 811 |
+
"eval_accuracy": 0.9762962962962963,
|
| 812 |
+
"eval_f1_score": 0.9830148619957537,
|
| 813 |
+
"eval_loss": 0.06924613565206528,
|
| 814 |
+
"eval_precision": 0.9767932489451476,
|
| 815 |
+
"eval_recall": 0.9893162393162394,
|
| 816 |
+
"eval_runtime": 3.9174,
|
| 817 |
+
"eval_samples_per_second": 172.306,
|
| 818 |
+
"eval_steps_per_second": 5.616,
|
| 819 |
+
"step": 950
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 20.21,
|
| 823 |
+
"learning_rate": 1.773049645390071e-05,
|
| 824 |
+
"loss": 0.1878,
|
| 825 |
+
"step": 960
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 20.42,
|
| 829 |
+
"learning_rate": 1.7336485421591806e-05,
|
| 830 |
+
"loss": 0.1782,
|
| 831 |
+
"step": 970
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 20.63,
|
| 835 |
+
"learning_rate": 1.69424743892829e-05,
|
| 836 |
+
"loss": 0.187,
|
| 837 |
+
"step": 980
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 20.84,
|
| 841 |
+
"learning_rate": 1.6548463356973994e-05,
|
| 842 |
+
"loss": 0.188,
|
| 843 |
+
"step": 990
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 20.99,
|
| 847 |
+
"eval_accuracy": 0.9777777777777777,
|
| 848 |
+
"eval_f1_score": 0.983991462113127,
|
| 849 |
+
"eval_loss": 0.06410012394189835,
|
| 850 |
+
"eval_precision": 0.9829424307036247,
|
| 851 |
+
"eval_recall": 0.9850427350427351,
|
| 852 |
+
"eval_runtime": 4.4961,
|
| 853 |
+
"eval_samples_per_second": 150.132,
|
| 854 |
+
"eval_steps_per_second": 4.893,
|
| 855 |
+
"step": 997
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 21.05,
|
| 859 |
+
"learning_rate": 1.6154452324665094e-05,
|
| 860 |
+
"loss": 0.1543,
|
| 861 |
+
"step": 1000
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 21.26,
|
| 865 |
+
"learning_rate": 1.5760441292356188e-05,
|
| 866 |
+
"loss": 0.1752,
|
| 867 |
+
"step": 1010
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 21.47,
|
| 871 |
+
"learning_rate": 1.536643026004728e-05,
|
| 872 |
+
"loss": 0.1606,
|
| 873 |
+
"step": 1020
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 21.68,
|
| 877 |
+
"learning_rate": 1.4972419227738377e-05,
|
| 878 |
+
"loss": 0.184,
|
| 879 |
+
"step": 1030
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 21.89,
|
| 883 |
+
"learning_rate": 1.4578408195429472e-05,
|
| 884 |
+
"loss": 0.191,
|
| 885 |
+
"step": 1040
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 22.0,
|
| 889 |
+
"eval_accuracy": 0.9792592592592593,
|
| 890 |
+
"eval_f1_score": 0.9850746268656716,
|
| 891 |
+
"eval_loss": 0.06437370181083679,
|
| 892 |
+
"eval_precision": 0.9829787234042553,
|
| 893 |
+
"eval_recall": 0.9871794871794872,
|
| 894 |
+
"eval_runtime": 3.9414,
|
| 895 |
+
"eval_samples_per_second": 171.258,
|
| 896 |
+
"eval_steps_per_second": 5.582,
|
| 897 |
+
"step": 1045
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 22.11,
|
| 901 |
+
"learning_rate": 1.418439716312057e-05,
|
| 902 |
+
"loss": 0.177,
|
| 903 |
+
"step": 1050
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 22.32,
|
| 907 |
+
"learning_rate": 1.3790386130811665e-05,
|
| 908 |
+
"loss": 0.1727,
|
| 909 |
+
"step": 1060
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 22.53,
|
| 913 |
+
"learning_rate": 1.3396375098502758e-05,
|
| 914 |
+
"loss": 0.1872,
|
| 915 |
+
"step": 1070
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 22.74,
|
| 919 |
+
"learning_rate": 1.3002364066193854e-05,
|
| 920 |
+
"loss": 0.1558,
|
| 921 |
+
"step": 1080
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 22.95,
|
| 925 |
+
"learning_rate": 1.2608353033884947e-05,
|
| 926 |
+
"loss": 0.2025,
|
| 927 |
+
"step": 1090
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 22.99,
|
| 931 |
+
"eval_accuracy": 0.9792592592592593,
|
| 932 |
+
"eval_f1_score": 0.9850107066381155,
|
| 933 |
+
"eval_loss": 0.06750550121068954,
|
| 934 |
+
"eval_precision": 0.9871244635193133,
|
| 935 |
+
"eval_recall": 0.9829059829059829,
|
| 936 |
+
"eval_runtime": 3.9141,
|
| 937 |
+
"eval_samples_per_second": 172.455,
|
| 938 |
+
"eval_steps_per_second": 5.621,
|
| 939 |
+
"step": 1092
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 23.16,
|
| 943 |
+
"learning_rate": 1.2214342001576045e-05,
|
| 944 |
+
"loss": 0.1766,
|
| 945 |
+
"step": 1100
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 23.37,
|
| 949 |
+
"learning_rate": 1.182033096926714e-05,
|
| 950 |
+
"loss": 0.167,
|
| 951 |
+
"step": 1110
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 23.58,
|
| 955 |
+
"learning_rate": 1.1426319936958235e-05,
|
| 956 |
+
"loss": 0.1995,
|
| 957 |
+
"step": 1120
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 23.79,
|
| 961 |
+
"learning_rate": 1.103230890464933e-05,
|
| 962 |
+
"loss": 0.1775,
|
| 963 |
+
"step": 1130
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 24.0,
|
| 967 |
+
"learning_rate": 1.0638297872340426e-05,
|
| 968 |
+
"loss": 0.1753,
|
| 969 |
+
"step": 1140
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 24.0,
|
| 973 |
+
"eval_accuracy": 0.9822222222222222,
|
| 974 |
+
"eval_f1_score": 0.9872068230277186,
|
| 975 |
+
"eval_loss": 0.06550905108451843,
|
| 976 |
+
"eval_precision": 0.9851063829787234,
|
| 977 |
+
"eval_recall": 0.9893162393162394,
|
| 978 |
+
"eval_runtime": 4.3235,
|
| 979 |
+
"eval_samples_per_second": 156.125,
|
| 980 |
+
"eval_steps_per_second": 5.089,
|
| 981 |
+
"step": 1140
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 24.21,
|
| 985 |
+
"learning_rate": 1.0244286840031522e-05,
|
| 986 |
+
"loss": 0.1825,
|
| 987 |
+
"step": 1150
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 24.42,
|
| 991 |
+
"learning_rate": 9.850275807722617e-06,
|
| 992 |
+
"loss": 0.1587,
|
| 993 |
+
"step": 1160
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 24.63,
|
| 997 |
+
"learning_rate": 9.456264775413712e-06,
|
| 998 |
+
"loss": 0.1846,
|
| 999 |
+
"step": 1170
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 24.84,
|
| 1003 |
+
"learning_rate": 9.062253743104808e-06,
|
| 1004 |
+
"loss": 0.1857,
|
| 1005 |
+
"step": 1180
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 24.99,
|
| 1009 |
+
"eval_accuracy": 0.9792592592592593,
|
| 1010 |
+
"eval_f1_score": 0.9851380042462845,
|
| 1011 |
+
"eval_loss": 0.07306463271379471,
|
| 1012 |
+
"eval_precision": 0.9789029535864979,
|
| 1013 |
+
"eval_recall": 0.9914529914529915,
|
| 1014 |
+
"eval_runtime": 3.9407,
|
| 1015 |
+
"eval_samples_per_second": 171.288,
|
| 1016 |
+
"eval_steps_per_second": 5.583,
|
| 1017 |
+
"step": 1187
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 25.05,
|
| 1021 |
+
"learning_rate": 8.668242710795903e-06,
|
| 1022 |
+
"loss": 0.1747,
|
| 1023 |
+
"step": 1190
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 25.26,
|
| 1027 |
+
"learning_rate": 8.274231678486997e-06,
|
| 1028 |
+
"loss": 0.165,
|
| 1029 |
+
"step": 1200
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 25.47,
|
| 1033 |
+
"learning_rate": 7.880220646178094e-06,
|
| 1034 |
+
"loss": 0.1774,
|
| 1035 |
+
"step": 1210
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 25.68,
|
| 1039 |
+
"learning_rate": 7.486209613869188e-06,
|
| 1040 |
+
"loss": 0.1762,
|
| 1041 |
+
"step": 1220
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 25.89,
|
| 1045 |
+
"learning_rate": 7.092198581560285e-06,
|
| 1046 |
+
"loss": 0.2007,
|
| 1047 |
+
"step": 1230
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 26.0,
|
| 1051 |
+
"eval_accuracy": 0.9792592592592593,
|
| 1052 |
+
"eval_f1_score": 0.9851380042462845,
|
| 1053 |
+
"eval_loss": 0.06768698245286942,
|
| 1054 |
+
"eval_precision": 0.9789029535864979,
|
| 1055 |
+
"eval_recall": 0.9914529914529915,
|
| 1056 |
+
"eval_runtime": 4.3978,
|
| 1057 |
+
"eval_samples_per_second": 153.486,
|
| 1058 |
+
"eval_steps_per_second": 5.002,
|
| 1059 |
+
"step": 1235
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 26.11,
|
| 1063 |
+
"learning_rate": 6.698187549251379e-06,
|
| 1064 |
+
"loss": 0.1588,
|
| 1065 |
+
"step": 1240
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 26.32,
|
| 1069 |
+
"learning_rate": 6.304176516942474e-06,
|
| 1070 |
+
"loss": 0.166,
|
| 1071 |
+
"step": 1250
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 26.53,
|
| 1075 |
+
"learning_rate": 5.91016548463357e-06,
|
| 1076 |
+
"loss": 0.191,
|
| 1077 |
+
"step": 1260
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 26.74,
|
| 1081 |
+
"learning_rate": 5.516154452324665e-06,
|
| 1082 |
+
"loss": 0.1603,
|
| 1083 |
+
"step": 1270
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 26.95,
|
| 1087 |
+
"learning_rate": 5.122143420015761e-06,
|
| 1088 |
+
"loss": 0.2086,
|
| 1089 |
+
"step": 1280
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 26.99,
|
| 1093 |
+
"eval_accuracy": 0.9792592592592593,
|
| 1094 |
+
"eval_f1_score": 0.9851063829787234,
|
| 1095 |
+
"eval_loss": 0.0640312060713768,
|
| 1096 |
+
"eval_precision": 0.9809322033898306,
|
| 1097 |
+
"eval_recall": 0.9893162393162394,
|
| 1098 |
+
"eval_runtime": 3.8919,
|
| 1099 |
+
"eval_samples_per_second": 173.437,
|
| 1100 |
+
"eval_steps_per_second": 5.653,
|
| 1101 |
+
"step": 1282
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 27.16,
|
| 1105 |
+
"learning_rate": 4.728132387706856e-06,
|
| 1106 |
+
"loss": 0.1807,
|
| 1107 |
+
"step": 1290
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 27.37,
|
| 1111 |
+
"learning_rate": 4.3341213553979515e-06,
|
| 1112 |
+
"loss": 0.1697,
|
| 1113 |
+
"step": 1300
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 27.58,
|
| 1117 |
+
"learning_rate": 3.940110323089047e-06,
|
| 1118 |
+
"loss": 0.1799,
|
| 1119 |
+
"step": 1310
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 27.79,
|
| 1123 |
+
"learning_rate": 3.5460992907801423e-06,
|
| 1124 |
+
"loss": 0.1551,
|
| 1125 |
+
"step": 1320
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 28.0,
|
| 1129 |
+
"learning_rate": 3.152088258471237e-06,
|
| 1130 |
+
"loss": 0.1666,
|
| 1131 |
+
"step": 1330
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 28.0,
|
| 1135 |
+
"eval_accuracy": 0.9777777777777777,
|
| 1136 |
+
"eval_f1_score": 0.9840595111583422,
|
| 1137 |
+
"eval_loss": 0.07120572775602341,
|
| 1138 |
+
"eval_precision": 0.9788583509513742,
|
| 1139 |
+
"eval_recall": 0.9893162393162394,
|
| 1140 |
+
"eval_runtime": 3.8788,
|
| 1141 |
+
"eval_samples_per_second": 174.025,
|
| 1142 |
+
"eval_steps_per_second": 5.672,
|
| 1143 |
+
"step": 1330
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 28.21,
|
| 1147 |
+
"learning_rate": 2.7580772261623327e-06,
|
| 1148 |
+
"loss": 0.1736,
|
| 1149 |
+
"step": 1340
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 28.42,
|
| 1153 |
+
"learning_rate": 2.364066193853428e-06,
|
| 1154 |
+
"loss": 0.2003,
|
| 1155 |
+
"step": 1350
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 28.63,
|
| 1159 |
+
"learning_rate": 1.9700551615445235e-06,
|
| 1160 |
+
"loss": 0.1777,
|
| 1161 |
+
"step": 1360
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 28.84,
|
| 1165 |
+
"learning_rate": 1.5760441292356184e-06,
|
| 1166 |
+
"loss": 0.157,
|
| 1167 |
+
"step": 1370
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 28.99,
|
| 1171 |
+
"eval_accuracy": 0.9807407407407407,
|
| 1172 |
+
"eval_f1_score": 0.9861554845580405,
|
| 1173 |
+
"eval_loss": 0.06606751680374146,
|
| 1174 |
+
"eval_precision": 0.9830148619957537,
|
| 1175 |
+
"eval_recall": 0.9893162393162394,
|
| 1176 |
+
"eval_runtime": 4.4114,
|
| 1177 |
+
"eval_samples_per_second": 153.014,
|
| 1178 |
+
"eval_steps_per_second": 4.987,
|
| 1179 |
+
"step": 1377
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 29.05,
|
| 1183 |
+
"learning_rate": 1.182033096926714e-06,
|
| 1184 |
+
"loss": 0.169,
|
| 1185 |
+
"step": 1380
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 29.26,
|
| 1189 |
+
"learning_rate": 7.880220646178092e-07,
|
| 1190 |
+
"loss": 0.1736,
|
| 1191 |
+
"step": 1390
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 29.47,
|
| 1195 |
+
"learning_rate": 3.940110323089046e-07,
|
| 1196 |
+
"loss": 0.1748,
|
| 1197 |
+
"step": 1400
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 29.68,
|
| 1201 |
+
"learning_rate": 0.0,
|
| 1202 |
+
"loss": 0.1758,
|
| 1203 |
+
"step": 1410
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 29.68,
|
| 1207 |
+
"eval_accuracy": 0.9777777777777777,
|
| 1208 |
+
"eval_f1_score": 0.9840595111583422,
|
| 1209 |
+
"eval_loss": 0.06716117262840271,
|
| 1210 |
+
"eval_precision": 0.9788583509513742,
|
| 1211 |
+
"eval_recall": 0.9893162393162394,
|
| 1212 |
+
"eval_runtime": 4.087,
|
| 1213 |
+
"eval_samples_per_second": 165.159,
|
| 1214 |
+
"eval_steps_per_second": 5.383,
|
| 1215 |
+
"step": 1410
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 29.68,
|
| 1219 |
+
"step": 1410,
|
| 1220 |
+
"total_flos": 8.181902891907809e+17,
|
| 1221 |
+
"train_loss": 0.24775470698133428,
|
| 1222 |
+
"train_runtime": 3242.8553,
|
| 1223 |
+
"train_samples_per_second": 56.145,
|
| 1224 |
+
"train_steps_per_second": 0.435
|
| 1225 |
+
}
|
| 1226 |
+
],
|
| 1227 |
+
"logging_steps": 10,
|
| 1228 |
+
"max_steps": 1410,
|
| 1229 |
+
"num_input_tokens_seen": 0,
|
| 1230 |
+
"num_train_epochs": 30,
|
| 1231 |
+
"save_steps": 500,
|
| 1232 |
+
"total_flos": 8.181902891907809e+17,
|
| 1233 |
+
"train_batch_size": 32,
|
| 1234 |
+
"trial_name": null,
|
| 1235 |
+
"trial_params": null
|
| 1236 |
+
}
|