Uploaded Model
Browse files- all_results.json +16 -0
- eval_results.json +11 -0
- runs/Jul01_18-16-19_293c456ba153/events.out.tfevents.1688244311.293c456ba153.1472.9 +3 -0
- train_results.json +8 -0
- trainer_state.json +3133 -0
all_results.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"eval_accuracy": 0.933623782675551,
|
| 4 |
+
"eval_f1": 0.933623782675551,
|
| 5 |
+
"eval_loss": 0.21288499236106873,
|
| 6 |
+
"eval_precision": 0.933623782675551,
|
| 7 |
+
"eval_recall": 0.933623782675551,
|
| 8 |
+
"eval_runtime": 93.5334,
|
| 9 |
+
"eval_samples_per_second": 83.435,
|
| 10 |
+
"eval_steps_per_second": 10.435,
|
| 11 |
+
"total_flos": 3.943158668110371e+19,
|
| 12 |
+
"train_loss": 0.07091429132740952,
|
| 13 |
+
"train_runtime": 8488.5621,
|
| 14 |
+
"train_samples_per_second": 8.154,
|
| 15 |
+
"train_steps_per_second": 0.51
|
| 16 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"eval_accuracy": 0.933623782675551,
|
| 4 |
+
"eval_f1": 0.933623782675551,
|
| 5 |
+
"eval_loss": 0.21288499236106873,
|
| 6 |
+
"eval_precision": 0.933623782675551,
|
| 7 |
+
"eval_recall": 0.933623782675551,
|
| 8 |
+
"eval_runtime": 93.5334,
|
| 9 |
+
"eval_samples_per_second": 83.435,
|
| 10 |
+
"eval_steps_per_second": 10.435
|
| 11 |
+
}
|
runs/Jul01_18-16-19_293c456ba153/events.out.tfevents.1688244311.293c456ba153.1472.9
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c3a1c9638dfdbc733331f49556fea04a2bfb39997f14bcbe756a16084fe728eb
|
| 3 |
+
size 560
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"total_flos": 3.943158668110371e+19,
|
| 4 |
+
"train_loss": 0.07091429132740952,
|
| 5 |
+
"train_runtime": 8488.5621,
|
| 6 |
+
"train_samples_per_second": 8.154,
|
| 7 |
+
"train_steps_per_second": 0.51
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,3133 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.21288499236106873,
|
| 3 |
+
"best_model_checkpoint": "./vit-huge-binary-isic-sharpened-patch-14/checkpoint-2000",
|
| 4 |
+
"epoch": 4.0,
|
| 5 |
+
"global_step": 4328,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.01,
|
| 12 |
+
"learning_rate": 0.00019953789279112755,
|
| 13 |
+
"loss": 0.5732,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.02,
|
| 18 |
+
"learning_rate": 0.0001990757855822551,
|
| 19 |
+
"loss": 0.4357,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.03,
|
| 24 |
+
"learning_rate": 0.00019861367837338263,
|
| 25 |
+
"loss": 0.3054,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.04,
|
| 30 |
+
"learning_rate": 0.00019815157116451017,
|
| 31 |
+
"loss": 0.292,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.05,
|
| 36 |
+
"learning_rate": 0.0001976894639556377,
|
| 37 |
+
"loss": 0.3734,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.06,
|
| 42 |
+
"learning_rate": 0.00019722735674676528,
|
| 43 |
+
"loss": 0.3744,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.06,
|
| 48 |
+
"learning_rate": 0.0001967652495378928,
|
| 49 |
+
"loss": 0.3538,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.07,
|
| 54 |
+
"learning_rate": 0.00019630314232902034,
|
| 55 |
+
"loss": 0.3201,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.08,
|
| 60 |
+
"learning_rate": 0.00019584103512014788,
|
| 61 |
+
"loss": 0.3039,
|
| 62 |
+
"step": 90
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.09,
|
| 66 |
+
"learning_rate": 0.00019537892791127544,
|
| 67 |
+
"loss": 0.3116,
|
| 68 |
+
"step": 100
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.09,
|
| 72 |
+
"eval_accuracy": 0.8553305996924654,
|
| 73 |
+
"eval_f1": 0.8553305996924655,
|
| 74 |
+
"eval_loss": 0.3191303610801697,
|
| 75 |
+
"eval_precision": 0.8553305996924654,
|
| 76 |
+
"eval_recall": 0.8553305996924654,
|
| 77 |
+
"eval_runtime": 93.9458,
|
| 78 |
+
"eval_samples_per_second": 83.069,
|
| 79 |
+
"eval_steps_per_second": 10.389,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.1,
|
| 84 |
+
"learning_rate": 0.00019491682070240296,
|
| 85 |
+
"loss": 0.354,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.11,
|
| 90 |
+
"learning_rate": 0.0001944547134935305,
|
| 91 |
+
"loss": 0.2593,
|
| 92 |
+
"step": 120
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.12,
|
| 96 |
+
"learning_rate": 0.00019399260628465804,
|
| 97 |
+
"loss": 0.374,
|
| 98 |
+
"step": 130
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.13,
|
| 102 |
+
"learning_rate": 0.0001935304990757856,
|
| 103 |
+
"loss": 0.2888,
|
| 104 |
+
"step": 140
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.14,
|
| 108 |
+
"learning_rate": 0.00019306839186691312,
|
| 109 |
+
"loss": 0.2536,
|
| 110 |
+
"step": 150
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.15,
|
| 114 |
+
"learning_rate": 0.00019260628465804066,
|
| 115 |
+
"loss": 0.2267,
|
| 116 |
+
"step": 160
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.16,
|
| 120 |
+
"learning_rate": 0.00019214417744916823,
|
| 121 |
+
"loss": 0.2944,
|
| 122 |
+
"step": 170
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.17,
|
| 126 |
+
"learning_rate": 0.00019168207024029577,
|
| 127 |
+
"loss": 0.2981,
|
| 128 |
+
"step": 180
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.18,
|
| 132 |
+
"learning_rate": 0.0001912199630314233,
|
| 133 |
+
"loss": 0.302,
|
| 134 |
+
"step": 190
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.18,
|
| 138 |
+
"learning_rate": 0.00019075785582255082,
|
| 139 |
+
"loss": 0.3328,
|
| 140 |
+
"step": 200
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.18,
|
| 144 |
+
"eval_accuracy": 0.8152229625832906,
|
| 145 |
+
"eval_f1": 0.8152229625832906,
|
| 146 |
+
"eval_loss": 0.3595452904701233,
|
| 147 |
+
"eval_precision": 0.8152229625832906,
|
| 148 |
+
"eval_recall": 0.8152229625832906,
|
| 149 |
+
"eval_runtime": 94.0698,
|
| 150 |
+
"eval_samples_per_second": 82.96,
|
| 151 |
+
"eval_steps_per_second": 10.375,
|
| 152 |
+
"step": 200
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.19,
|
| 156 |
+
"learning_rate": 0.0001902957486136784,
|
| 157 |
+
"loss": 0.2301,
|
| 158 |
+
"step": 210
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.2,
|
| 162 |
+
"learning_rate": 0.00018983364140480593,
|
| 163 |
+
"loss": 0.4238,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.21,
|
| 168 |
+
"learning_rate": 0.00018937153419593347,
|
| 169 |
+
"loss": 0.237,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.22,
|
| 174 |
+
"learning_rate": 0.000188909426987061,
|
| 175 |
+
"loss": 0.2305,
|
| 176 |
+
"step": 240
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.23,
|
| 180 |
+
"learning_rate": 0.00018844731977818855,
|
| 181 |
+
"loss": 0.2962,
|
| 182 |
+
"step": 250
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.24,
|
| 186 |
+
"learning_rate": 0.0001879852125693161,
|
| 187 |
+
"loss": 0.1984,
|
| 188 |
+
"step": 260
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.25,
|
| 192 |
+
"learning_rate": 0.00018752310536044364,
|
| 193 |
+
"loss": 0.2392,
|
| 194 |
+
"step": 270
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.26,
|
| 198 |
+
"learning_rate": 0.00018706099815157118,
|
| 199 |
+
"loss": 0.2821,
|
| 200 |
+
"step": 280
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.27,
|
| 204 |
+
"learning_rate": 0.00018659889094269872,
|
| 205 |
+
"loss": 0.2291,
|
| 206 |
+
"step": 290
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.28,
|
| 210 |
+
"learning_rate": 0.00018613678373382626,
|
| 211 |
+
"loss": 0.2597,
|
| 212 |
+
"step": 300
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.28,
|
| 216 |
+
"eval_accuracy": 0.8732701178882625,
|
| 217 |
+
"eval_f1": 0.8732701178882625,
|
| 218 |
+
"eval_loss": 0.29005151987075806,
|
| 219 |
+
"eval_precision": 0.8732701178882625,
|
| 220 |
+
"eval_recall": 0.8732701178882625,
|
| 221 |
+
"eval_runtime": 93.7287,
|
| 222 |
+
"eval_samples_per_second": 83.262,
|
| 223 |
+
"eval_steps_per_second": 10.413,
|
| 224 |
+
"step": 300
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.29,
|
| 228 |
+
"learning_rate": 0.0001856746765249538,
|
| 229 |
+
"loss": 0.2859,
|
| 230 |
+
"step": 310
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.3,
|
| 234 |
+
"learning_rate": 0.00018521256931608134,
|
| 235 |
+
"loss": 0.2641,
|
| 236 |
+
"step": 320
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.3,
|
| 240 |
+
"learning_rate": 0.00018475046210720888,
|
| 241 |
+
"loss": 0.2536,
|
| 242 |
+
"step": 330
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.31,
|
| 246 |
+
"learning_rate": 0.00018428835489833642,
|
| 247 |
+
"loss": 0.1996,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.32,
|
| 252 |
+
"learning_rate": 0.00018382624768946396,
|
| 253 |
+
"loss": 0.2005,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.33,
|
| 258 |
+
"learning_rate": 0.0001833641404805915,
|
| 259 |
+
"loss": 0.29,
|
| 260 |
+
"step": 360
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.34,
|
| 264 |
+
"learning_rate": 0.00018290203327171904,
|
| 265 |
+
"loss": 0.209,
|
| 266 |
+
"step": 370
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.35,
|
| 270 |
+
"learning_rate": 0.00018243992606284658,
|
| 271 |
+
"loss": 0.2627,
|
| 272 |
+
"step": 380
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.36,
|
| 276 |
+
"learning_rate": 0.00018197781885397413,
|
| 277 |
+
"loss": 0.2659,
|
| 278 |
+
"step": 390
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 0.37,
|
| 282 |
+
"learning_rate": 0.0001815157116451017,
|
| 283 |
+
"loss": 0.2037,
|
| 284 |
+
"step": 400
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 0.37,
|
| 288 |
+
"eval_accuracy": 0.8912096360840595,
|
| 289 |
+
"eval_f1": 0.8912096360840595,
|
| 290 |
+
"eval_loss": 0.24775776267051697,
|
| 291 |
+
"eval_precision": 0.8912096360840595,
|
| 292 |
+
"eval_recall": 0.8912096360840595,
|
| 293 |
+
"eval_runtime": 94.6511,
|
| 294 |
+
"eval_samples_per_second": 82.45,
|
| 295 |
+
"eval_steps_per_second": 10.312,
|
| 296 |
+
"step": 400
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.38,
|
| 300 |
+
"learning_rate": 0.0001810536044362292,
|
| 301 |
+
"loss": 0.1986,
|
| 302 |
+
"step": 410
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.39,
|
| 306 |
+
"learning_rate": 0.00018059149722735675,
|
| 307 |
+
"loss": 0.1758,
|
| 308 |
+
"step": 420
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 0.4,
|
| 312 |
+
"learning_rate": 0.0001801293900184843,
|
| 313 |
+
"loss": 0.2557,
|
| 314 |
+
"step": 430
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.41,
|
| 318 |
+
"learning_rate": 0.00017966728280961186,
|
| 319 |
+
"loss": 0.2713,
|
| 320 |
+
"step": 440
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 0.42,
|
| 324 |
+
"learning_rate": 0.00017920517560073937,
|
| 325 |
+
"loss": 0.1341,
|
| 326 |
+
"step": 450
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 0.43,
|
| 330 |
+
"learning_rate": 0.0001787430683918669,
|
| 331 |
+
"loss": 0.2298,
|
| 332 |
+
"step": 460
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.43,
|
| 336 |
+
"learning_rate": 0.00017828096118299448,
|
| 337 |
+
"loss": 0.1818,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.44,
|
| 342 |
+
"learning_rate": 0.00017781885397412202,
|
| 343 |
+
"loss": 0.1684,
|
| 344 |
+
"step": 480
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 0.45,
|
| 348 |
+
"learning_rate": 0.00017735674676524953,
|
| 349 |
+
"loss": 0.2039,
|
| 350 |
+
"step": 490
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 0.46,
|
| 354 |
+
"learning_rate": 0.00017689463955637707,
|
| 355 |
+
"loss": 0.2415,
|
| 356 |
+
"step": 500
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 0.46,
|
| 360 |
+
"eval_accuracy": 0.8965914915427986,
|
| 361 |
+
"eval_f1": 0.8965914915427986,
|
| 362 |
+
"eval_loss": 0.24882297217845917,
|
| 363 |
+
"eval_precision": 0.8965914915427986,
|
| 364 |
+
"eval_recall": 0.8965914915427986,
|
| 365 |
+
"eval_runtime": 94.8507,
|
| 366 |
+
"eval_samples_per_second": 82.277,
|
| 367 |
+
"eval_steps_per_second": 10.29,
|
| 368 |
+
"step": 500
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 0.47,
|
| 372 |
+
"learning_rate": 0.00017643253234750464,
|
| 373 |
+
"loss": 0.1601,
|
| 374 |
+
"step": 510
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.48,
|
| 378 |
+
"learning_rate": 0.00017597042513863218,
|
| 379 |
+
"loss": 0.2957,
|
| 380 |
+
"step": 520
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.49,
|
| 384 |
+
"learning_rate": 0.0001755083179297597,
|
| 385 |
+
"loss": 0.165,
|
| 386 |
+
"step": 530
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 0.5,
|
| 390 |
+
"learning_rate": 0.00017504621072088724,
|
| 391 |
+
"loss": 0.1761,
|
| 392 |
+
"step": 540
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 0.51,
|
| 396 |
+
"learning_rate": 0.0001745841035120148,
|
| 397 |
+
"loss": 0.1448,
|
| 398 |
+
"step": 550
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 0.52,
|
| 402 |
+
"learning_rate": 0.00017412199630314234,
|
| 403 |
+
"loss": 0.2043,
|
| 404 |
+
"step": 560
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 0.53,
|
| 408 |
+
"learning_rate": 0.00017365988909426989,
|
| 409 |
+
"loss": 0.1434,
|
| 410 |
+
"step": 570
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.54,
|
| 414 |
+
"learning_rate": 0.00017319778188539743,
|
| 415 |
+
"loss": 0.1463,
|
| 416 |
+
"step": 580
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.55,
|
| 420 |
+
"learning_rate": 0.00017273567467652497,
|
| 421 |
+
"loss": 0.162,
|
| 422 |
+
"step": 590
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.55,
|
| 426 |
+
"learning_rate": 0.0001722735674676525,
|
| 427 |
+
"loss": 0.1483,
|
| 428 |
+
"step": 600
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 0.55,
|
| 432 |
+
"eval_accuracy": 0.8844182470527935,
|
| 433 |
+
"eval_f1": 0.8844182470527935,
|
| 434 |
+
"eval_loss": 0.2943035662174225,
|
| 435 |
+
"eval_precision": 0.8844182470527935,
|
| 436 |
+
"eval_recall": 0.8844182470527935,
|
| 437 |
+
"eval_runtime": 94.8571,
|
| 438 |
+
"eval_samples_per_second": 82.271,
|
| 439 |
+
"eval_steps_per_second": 10.289,
|
| 440 |
+
"step": 600
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 0.56,
|
| 444 |
+
"learning_rate": 0.00017181146025878005,
|
| 445 |
+
"loss": 0.2827,
|
| 446 |
+
"step": 610
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.57,
|
| 450 |
+
"learning_rate": 0.0001713493530499076,
|
| 451 |
+
"loss": 0.1908,
|
| 452 |
+
"step": 620
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.58,
|
| 456 |
+
"learning_rate": 0.00017088724584103513,
|
| 457 |
+
"loss": 0.134,
|
| 458 |
+
"step": 630
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.59,
|
| 462 |
+
"learning_rate": 0.00017042513863216267,
|
| 463 |
+
"loss": 0.1652,
|
| 464 |
+
"step": 640
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.6,
|
| 468 |
+
"learning_rate": 0.0001699630314232902,
|
| 469 |
+
"loss": 0.1357,
|
| 470 |
+
"step": 650
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 0.61,
|
| 474 |
+
"learning_rate": 0.00016950092421441775,
|
| 475 |
+
"loss": 0.2055,
|
| 476 |
+
"step": 660
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 0.62,
|
| 480 |
+
"learning_rate": 0.0001690388170055453,
|
| 481 |
+
"loss": 0.1381,
|
| 482 |
+
"step": 670
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.63,
|
| 486 |
+
"learning_rate": 0.00016857670979667283,
|
| 487 |
+
"loss": 0.1973,
|
| 488 |
+
"step": 680
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 0.64,
|
| 492 |
+
"learning_rate": 0.00016811460258780037,
|
| 493 |
+
"loss": 0.17,
|
| 494 |
+
"step": 690
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.65,
|
| 498 |
+
"learning_rate": 0.00016765249537892791,
|
| 499 |
+
"loss": 0.1126,
|
| 500 |
+
"step": 700
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.65,
|
| 504 |
+
"eval_accuracy": 0.8751922091235264,
|
| 505 |
+
"eval_f1": 0.8751922091235264,
|
| 506 |
+
"eval_loss": 0.3269084393978119,
|
| 507 |
+
"eval_precision": 0.8751922091235264,
|
| 508 |
+
"eval_recall": 0.8751922091235264,
|
| 509 |
+
"eval_runtime": 94.1477,
|
| 510 |
+
"eval_samples_per_second": 82.891,
|
| 511 |
+
"eval_steps_per_second": 10.367,
|
| 512 |
+
"step": 700
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 0.66,
|
| 516 |
+
"learning_rate": 0.00016719038817005546,
|
| 517 |
+
"loss": 0.1857,
|
| 518 |
+
"step": 710
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 0.67,
|
| 522 |
+
"learning_rate": 0.000166728280961183,
|
| 523 |
+
"loss": 0.1593,
|
| 524 |
+
"step": 720
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 0.67,
|
| 528 |
+
"learning_rate": 0.00016626617375231054,
|
| 529 |
+
"loss": 0.118,
|
| 530 |
+
"step": 730
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 0.68,
|
| 534 |
+
"learning_rate": 0.00016580406654343808,
|
| 535 |
+
"loss": 0.1207,
|
| 536 |
+
"step": 740
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.69,
|
| 540 |
+
"learning_rate": 0.00016534195933456562,
|
| 541 |
+
"loss": 0.1067,
|
| 542 |
+
"step": 750
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.7,
|
| 546 |
+
"learning_rate": 0.00016487985212569316,
|
| 547 |
+
"loss": 0.1537,
|
| 548 |
+
"step": 760
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.71,
|
| 552 |
+
"learning_rate": 0.00016441774491682073,
|
| 553 |
+
"loss": 0.1113,
|
| 554 |
+
"step": 770
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 0.72,
|
| 558 |
+
"learning_rate": 0.00016395563770794827,
|
| 559 |
+
"loss": 0.1337,
|
| 560 |
+
"step": 780
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 0.73,
|
| 564 |
+
"learning_rate": 0.00016349353049907578,
|
| 565 |
+
"loss": 0.1811,
|
| 566 |
+
"step": 790
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 0.74,
|
| 570 |
+
"learning_rate": 0.00016303142329020332,
|
| 571 |
+
"loss": 0.207,
|
| 572 |
+
"step": 800
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 0.74,
|
| 576 |
+
"eval_accuracy": 0.8868528959507944,
|
| 577 |
+
"eval_f1": 0.8868528959507944,
|
| 578 |
+
"eval_loss": 0.29836413264274597,
|
| 579 |
+
"eval_precision": 0.8868528959507944,
|
| 580 |
+
"eval_recall": 0.8868528959507944,
|
| 581 |
+
"eval_runtime": 95.3225,
|
| 582 |
+
"eval_samples_per_second": 81.869,
|
| 583 |
+
"eval_steps_per_second": 10.239,
|
| 584 |
+
"step": 800
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.75,
|
| 588 |
+
"learning_rate": 0.0001625693160813309,
|
| 589 |
+
"loss": 0.183,
|
| 590 |
+
"step": 810
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.76,
|
| 594 |
+
"learning_rate": 0.00016210720887245843,
|
| 595 |
+
"loss": 0.168,
|
| 596 |
+
"step": 820
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 0.77,
|
| 600 |
+
"learning_rate": 0.00016164510166358594,
|
| 601 |
+
"loss": 0.147,
|
| 602 |
+
"step": 830
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 0.78,
|
| 606 |
+
"learning_rate": 0.00016118299445471348,
|
| 607 |
+
"loss": 0.1924,
|
| 608 |
+
"step": 840
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 0.79,
|
| 612 |
+
"learning_rate": 0.00016072088724584105,
|
| 613 |
+
"loss": 0.1122,
|
| 614 |
+
"step": 850
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 0.79,
|
| 618 |
+
"learning_rate": 0.0001602587800369686,
|
| 619 |
+
"loss": 0.1421,
|
| 620 |
+
"step": 860
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.8,
|
| 624 |
+
"learning_rate": 0.0001597966728280961,
|
| 625 |
+
"loss": 0.1391,
|
| 626 |
+
"step": 870
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.81,
|
| 630 |
+
"learning_rate": 0.00015933456561922367,
|
| 631 |
+
"loss": 0.2099,
|
| 632 |
+
"step": 880
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.82,
|
| 636 |
+
"learning_rate": 0.00015887245841035122,
|
| 637 |
+
"loss": 0.1028,
|
| 638 |
+
"step": 890
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 0.83,
|
| 642 |
+
"learning_rate": 0.00015841035120147876,
|
| 643 |
+
"loss": 0.234,
|
| 644 |
+
"step": 900
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 0.83,
|
| 648 |
+
"eval_accuracy": 0.8856996412096361,
|
| 649 |
+
"eval_f1": 0.8856996412096362,
|
| 650 |
+
"eval_loss": 0.23936809599399567,
|
| 651 |
+
"eval_precision": 0.8856996412096361,
|
| 652 |
+
"eval_recall": 0.8856996412096361,
|
| 653 |
+
"eval_runtime": 94.789,
|
| 654 |
+
"eval_samples_per_second": 82.33,
|
| 655 |
+
"eval_steps_per_second": 10.297,
|
| 656 |
+
"step": 900
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 0.84,
|
| 660 |
+
"learning_rate": 0.00015794824399260627,
|
| 661 |
+
"loss": 0.1027,
|
| 662 |
+
"step": 910
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.85,
|
| 666 |
+
"learning_rate": 0.00015748613678373384,
|
| 667 |
+
"loss": 0.1248,
|
| 668 |
+
"step": 920
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.86,
|
| 672 |
+
"learning_rate": 0.00015702402957486138,
|
| 673 |
+
"loss": 0.1334,
|
| 674 |
+
"step": 930
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.87,
|
| 678 |
+
"learning_rate": 0.00015656192236598892,
|
| 679 |
+
"loss": 0.1109,
|
| 680 |
+
"step": 940
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 0.88,
|
| 684 |
+
"learning_rate": 0.00015609981515711646,
|
| 685 |
+
"loss": 0.0983,
|
| 686 |
+
"step": 950
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 0.89,
|
| 690 |
+
"learning_rate": 0.000155637707948244,
|
| 691 |
+
"loss": 0.0804,
|
| 692 |
+
"step": 960
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 0.9,
|
| 696 |
+
"learning_rate": 0.00015517560073937154,
|
| 697 |
+
"loss": 0.0837,
|
| 698 |
+
"step": 970
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 0.91,
|
| 702 |
+
"learning_rate": 0.00015471349353049908,
|
| 703 |
+
"loss": 0.1788,
|
| 704 |
+
"step": 980
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.91,
|
| 708 |
+
"learning_rate": 0.00015425138632162662,
|
| 709 |
+
"loss": 0.1913,
|
| 710 |
+
"step": 990
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.92,
|
| 714 |
+
"learning_rate": 0.00015378927911275416,
|
| 715 |
+
"loss": 0.1625,
|
| 716 |
+
"step": 1000
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.92,
|
| 720 |
+
"eval_accuracy": 0.8930035879036392,
|
| 721 |
+
"eval_f1": 0.8930035879036392,
|
| 722 |
+
"eval_loss": 0.2706281542778015,
|
| 723 |
+
"eval_precision": 0.8930035879036392,
|
| 724 |
+
"eval_recall": 0.8930035879036392,
|
| 725 |
+
"eval_runtime": 94.6616,
|
| 726 |
+
"eval_samples_per_second": 82.441,
|
| 727 |
+
"eval_steps_per_second": 10.31,
|
| 728 |
+
"step": 1000
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 0.93,
|
| 732 |
+
"learning_rate": 0.0001533271719038817,
|
| 733 |
+
"loss": 0.1515,
|
| 734 |
+
"step": 1010
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 0.94,
|
| 738 |
+
"learning_rate": 0.00015286506469500925,
|
| 739 |
+
"loss": 0.0941,
|
| 740 |
+
"step": 1020
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 0.95,
|
| 744 |
+
"learning_rate": 0.00015240295748613679,
|
| 745 |
+
"loss": 0.1245,
|
| 746 |
+
"step": 1030
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 0.96,
|
| 750 |
+
"learning_rate": 0.00015194085027726433,
|
| 751 |
+
"loss": 0.0967,
|
| 752 |
+
"step": 1040
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.97,
|
| 756 |
+
"learning_rate": 0.00015147874306839187,
|
| 757 |
+
"loss": 0.1997,
|
| 758 |
+
"step": 1050
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.98,
|
| 762 |
+
"learning_rate": 0.0001510166358595194,
|
| 763 |
+
"loss": 0.1668,
|
| 764 |
+
"step": 1060
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 0.99,
|
| 768 |
+
"learning_rate": 0.00015055452865064698,
|
| 769 |
+
"loss": 0.1185,
|
| 770 |
+
"step": 1070
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 1.0,
|
| 774 |
+
"learning_rate": 0.0001500924214417745,
|
| 775 |
+
"loss": 0.1416,
|
| 776 |
+
"step": 1080
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 1.01,
|
| 780 |
+
"learning_rate": 0.00014963031423290203,
|
| 781 |
+
"loss": 0.0646,
|
| 782 |
+
"step": 1090
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 1.02,
|
| 786 |
+
"learning_rate": 0.00014916820702402957,
|
| 787 |
+
"loss": 0.1131,
|
| 788 |
+
"step": 1100
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 1.02,
|
| 792 |
+
"eval_accuracy": 0.9208098411071246,
|
| 793 |
+
"eval_f1": 0.9208098411071246,
|
| 794 |
+
"eval_loss": 0.2155652791261673,
|
| 795 |
+
"eval_precision": 0.9208098411071246,
|
| 796 |
+
"eval_recall": 0.9208098411071246,
|
| 797 |
+
"eval_runtime": 96.0421,
|
| 798 |
+
"eval_samples_per_second": 81.256,
|
| 799 |
+
"eval_steps_per_second": 10.162,
|
| 800 |
+
"step": 1100
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 1.03,
|
| 804 |
+
"learning_rate": 0.00014870609981515714,
|
| 805 |
+
"loss": 0.1247,
|
| 806 |
+
"step": 1110
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 1.04,
|
| 810 |
+
"learning_rate": 0.00014824399260628468,
|
| 811 |
+
"loss": 0.1129,
|
| 812 |
+
"step": 1120
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 1.04,
|
| 816 |
+
"learning_rate": 0.0001477818853974122,
|
| 817 |
+
"loss": 0.0801,
|
| 818 |
+
"step": 1130
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 1.05,
|
| 822 |
+
"learning_rate": 0.00014731977818853976,
|
| 823 |
+
"loss": 0.0829,
|
| 824 |
+
"step": 1140
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 1.06,
|
| 828 |
+
"learning_rate": 0.0001468576709796673,
|
| 829 |
+
"loss": 0.0948,
|
| 830 |
+
"step": 1150
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 1.07,
|
| 834 |
+
"learning_rate": 0.00014639556377079484,
|
| 835 |
+
"loss": 0.0756,
|
| 836 |
+
"step": 1160
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 1.08,
|
| 840 |
+
"learning_rate": 0.00014593345656192236,
|
| 841 |
+
"loss": 0.1084,
|
| 842 |
+
"step": 1170
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 1.09,
|
| 846 |
+
"learning_rate": 0.00014547134935304992,
|
| 847 |
+
"loss": 0.0584,
|
| 848 |
+
"step": 1180
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 1.1,
|
| 852 |
+
"learning_rate": 0.00014500924214417746,
|
| 853 |
+
"loss": 0.0641,
|
| 854 |
+
"step": 1190
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 1.11,
|
| 858 |
+
"learning_rate": 0.000144547134935305,
|
| 859 |
+
"loss": 0.048,
|
| 860 |
+
"step": 1200
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 1.11,
|
| 864 |
+
"eval_accuracy": 0.902614044079959,
|
| 865 |
+
"eval_f1": 0.902614044079959,
|
| 866 |
+
"eval_loss": 0.2676137685775757,
|
| 867 |
+
"eval_precision": 0.902614044079959,
|
| 868 |
+
"eval_recall": 0.902614044079959,
|
| 869 |
+
"eval_runtime": 95.4306,
|
| 870 |
+
"eval_samples_per_second": 81.777,
|
| 871 |
+
"eval_steps_per_second": 10.227,
|
| 872 |
+
"step": 1200
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 1.12,
|
| 876 |
+
"learning_rate": 0.00014408502772643252,
|
| 877 |
+
"loss": 0.1314,
|
| 878 |
+
"step": 1210
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 1.13,
|
| 882 |
+
"learning_rate": 0.0001436229205175601,
|
| 883 |
+
"loss": 0.0481,
|
| 884 |
+
"step": 1220
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 1.14,
|
| 888 |
+
"learning_rate": 0.00014316081330868763,
|
| 889 |
+
"loss": 0.0473,
|
| 890 |
+
"step": 1230
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 1.15,
|
| 894 |
+
"learning_rate": 0.00014269870609981517,
|
| 895 |
+
"loss": 0.0504,
|
| 896 |
+
"step": 1240
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 1.16,
|
| 900 |
+
"learning_rate": 0.0001422365988909427,
|
| 901 |
+
"loss": 0.0526,
|
| 902 |
+
"step": 1250
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 1.16,
|
| 906 |
+
"learning_rate": 0.00014177449168207025,
|
| 907 |
+
"loss": 0.1015,
|
| 908 |
+
"step": 1260
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 1.17,
|
| 912 |
+
"learning_rate": 0.0001413123844731978,
|
| 913 |
+
"loss": 0.0173,
|
| 914 |
+
"step": 1270
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 1.18,
|
| 918 |
+
"learning_rate": 0.00014085027726432533,
|
| 919 |
+
"loss": 0.0714,
|
| 920 |
+
"step": 1280
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 1.19,
|
| 924 |
+
"learning_rate": 0.00014038817005545287,
|
| 925 |
+
"loss": 0.0518,
|
| 926 |
+
"step": 1290
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 1.2,
|
| 930 |
+
"learning_rate": 0.0001399260628465804,
|
| 931 |
+
"loss": 0.1235,
|
| 932 |
+
"step": 1300
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 1.2,
|
| 936 |
+
"eval_accuracy": 0.9024859046642747,
|
| 937 |
+
"eval_f1": 0.9024859046642747,
|
| 938 |
+
"eval_loss": 0.3325667083263397,
|
| 939 |
+
"eval_precision": 0.9024859046642747,
|
| 940 |
+
"eval_recall": 0.9024859046642747,
|
| 941 |
+
"eval_runtime": 94.6894,
|
| 942 |
+
"eval_samples_per_second": 82.417,
|
| 943 |
+
"eval_steps_per_second": 10.307,
|
| 944 |
+
"step": 1300
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 1.21,
|
| 948 |
+
"learning_rate": 0.00013946395563770795,
|
| 949 |
+
"loss": 0.1105,
|
| 950 |
+
"step": 1310
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 1.22,
|
| 954 |
+
"learning_rate": 0.0001390018484288355,
|
| 955 |
+
"loss": 0.0317,
|
| 956 |
+
"step": 1320
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 1.23,
|
| 960 |
+
"learning_rate": 0.00013853974121996306,
|
| 961 |
+
"loss": 0.0119,
|
| 962 |
+
"step": 1330
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 1.24,
|
| 966 |
+
"learning_rate": 0.00013807763401109058,
|
| 967 |
+
"loss": 0.0451,
|
| 968 |
+
"step": 1340
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 1.25,
|
| 972 |
+
"learning_rate": 0.00013761552680221812,
|
| 973 |
+
"loss": 0.0338,
|
| 974 |
+
"step": 1350
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 1.26,
|
| 978 |
+
"learning_rate": 0.00013715341959334566,
|
| 979 |
+
"loss": 0.0925,
|
| 980 |
+
"step": 1360
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 1.27,
|
| 984 |
+
"learning_rate": 0.00013669131238447322,
|
| 985 |
+
"loss": 0.05,
|
| 986 |
+
"step": 1370
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 1.28,
|
| 990 |
+
"learning_rate": 0.00013622920517560074,
|
| 991 |
+
"loss": 0.0053,
|
| 992 |
+
"step": 1380
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 1.28,
|
| 996 |
+
"learning_rate": 0.00013576709796672828,
|
| 997 |
+
"loss": 0.0155,
|
| 998 |
+
"step": 1390
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 1.29,
|
| 1002 |
+
"learning_rate": 0.00013530499075785582,
|
| 1003 |
+
"loss": 0.0093,
|
| 1004 |
+
"step": 1400
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 1.29,
|
| 1008 |
+
"eval_accuracy": 0.9106868272680677,
|
| 1009 |
+
"eval_f1": 0.9106868272680677,
|
| 1010 |
+
"eval_loss": 0.3238871097564697,
|
| 1011 |
+
"eval_precision": 0.9106868272680677,
|
| 1012 |
+
"eval_recall": 0.9106868272680677,
|
| 1013 |
+
"eval_runtime": 94.2987,
|
| 1014 |
+
"eval_samples_per_second": 82.758,
|
| 1015 |
+
"eval_steps_per_second": 10.35,
|
| 1016 |
+
"step": 1400
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 1.3,
|
| 1020 |
+
"learning_rate": 0.0001348428835489834,
|
| 1021 |
+
"loss": 0.0329,
|
| 1022 |
+
"step": 1410
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 1.31,
|
| 1026 |
+
"learning_rate": 0.0001343807763401109,
|
| 1027 |
+
"loss": 0.1286,
|
| 1028 |
+
"step": 1420
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 1.32,
|
| 1032 |
+
"learning_rate": 0.00013391866913123844,
|
| 1033 |
+
"loss": 0.0362,
|
| 1034 |
+
"step": 1430
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 1.33,
|
| 1038 |
+
"learning_rate": 0.000133456561922366,
|
| 1039 |
+
"loss": 0.056,
|
| 1040 |
+
"step": 1440
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 1.34,
|
| 1044 |
+
"learning_rate": 0.00013299445471349355,
|
| 1045 |
+
"loss": 0.0902,
|
| 1046 |
+
"step": 1450
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 1.35,
|
| 1050 |
+
"learning_rate": 0.00013253234750462106,
|
| 1051 |
+
"loss": 0.0593,
|
| 1052 |
+
"step": 1460
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 1.36,
|
| 1056 |
+
"learning_rate": 0.0001320702402957486,
|
| 1057 |
+
"loss": 0.0531,
|
| 1058 |
+
"step": 1470
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 1.37,
|
| 1062 |
+
"learning_rate": 0.00013160813308687617,
|
| 1063 |
+
"loss": 0.0572,
|
| 1064 |
+
"step": 1480
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 1.38,
|
| 1068 |
+
"learning_rate": 0.00013114602587800371,
|
| 1069 |
+
"loss": 0.1474,
|
| 1070 |
+
"step": 1490
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 1.39,
|
| 1074 |
+
"learning_rate": 0.00013068391866913125,
|
| 1075 |
+
"loss": 0.0851,
|
| 1076 |
+
"step": 1500
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 1.39,
|
| 1080 |
+
"eval_accuracy": 0.8971040492055357,
|
| 1081 |
+
"eval_f1": 0.8971040492055357,
|
| 1082 |
+
"eval_loss": 0.30670446157455444,
|
| 1083 |
+
"eval_precision": 0.8971040492055357,
|
| 1084 |
+
"eval_recall": 0.8971040492055357,
|
| 1085 |
+
"eval_runtime": 94.9658,
|
| 1086 |
+
"eval_samples_per_second": 82.177,
|
| 1087 |
+
"eval_steps_per_second": 10.277,
|
| 1088 |
+
"step": 1500
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 1.4,
|
| 1092 |
+
"learning_rate": 0.00013022181146025877,
|
| 1093 |
+
"loss": 0.0714,
|
| 1094 |
+
"step": 1510
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 1.4,
|
| 1098 |
+
"learning_rate": 0.00012975970425138634,
|
| 1099 |
+
"loss": 0.0505,
|
| 1100 |
+
"step": 1520
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 1.41,
|
| 1104 |
+
"learning_rate": 0.00012929759704251388,
|
| 1105 |
+
"loss": 0.0827,
|
| 1106 |
+
"step": 1530
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 1.42,
|
| 1110 |
+
"learning_rate": 0.00012883548983364142,
|
| 1111 |
+
"loss": 0.0374,
|
| 1112 |
+
"step": 1540
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 1.43,
|
| 1116 |
+
"learning_rate": 0.00012837338262476896,
|
| 1117 |
+
"loss": 0.0715,
|
| 1118 |
+
"step": 1550
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 1.44,
|
| 1122 |
+
"learning_rate": 0.0001279112754158965,
|
| 1123 |
+
"loss": 0.0216,
|
| 1124 |
+
"step": 1560
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 1.45,
|
| 1128 |
+
"learning_rate": 0.00012744916820702404,
|
| 1129 |
+
"loss": 0.0223,
|
| 1130 |
+
"step": 1570
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 1.46,
|
| 1134 |
+
"learning_rate": 0.00012698706099815158,
|
| 1135 |
+
"loss": 0.0945,
|
| 1136 |
+
"step": 1580
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 1.47,
|
| 1140 |
+
"learning_rate": 0.00012652495378927912,
|
| 1141 |
+
"loss": 0.0817,
|
| 1142 |
+
"step": 1590
|
| 1143 |
+
},
|
| 1144 |
+
{
|
| 1145 |
+
"epoch": 1.48,
|
| 1146 |
+
"learning_rate": 0.00012606284658040666,
|
| 1147 |
+
"loss": 0.0962,
|
| 1148 |
+
"step": 1600
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 1.48,
|
| 1152 |
+
"eval_accuracy": 0.8997949769349052,
|
| 1153 |
+
"eval_f1": 0.8997949769349052,
|
| 1154 |
+
"eval_loss": 0.31642210483551025,
|
| 1155 |
+
"eval_precision": 0.8997949769349052,
|
| 1156 |
+
"eval_recall": 0.8997949769349052,
|
| 1157 |
+
"eval_runtime": 94.5252,
|
| 1158 |
+
"eval_samples_per_second": 82.56,
|
| 1159 |
+
"eval_steps_per_second": 10.325,
|
| 1160 |
+
"step": 1600
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 1.49,
|
| 1164 |
+
"learning_rate": 0.0001256007393715342,
|
| 1165 |
+
"loss": 0.0105,
|
| 1166 |
+
"step": 1610
|
| 1167 |
+
},
|
| 1168 |
+
{
|
| 1169 |
+
"epoch": 1.5,
|
| 1170 |
+
"learning_rate": 0.00012513863216266174,
|
| 1171 |
+
"loss": 0.0262,
|
| 1172 |
+
"step": 1620
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 1.51,
|
| 1176 |
+
"learning_rate": 0.00012467652495378928,
|
| 1177 |
+
"loss": 0.1526,
|
| 1178 |
+
"step": 1630
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 1.52,
|
| 1182 |
+
"learning_rate": 0.00012421441774491682,
|
| 1183 |
+
"loss": 0.0759,
|
| 1184 |
+
"step": 1640
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 1.52,
|
| 1188 |
+
"learning_rate": 0.00012375231053604437,
|
| 1189 |
+
"loss": 0.016,
|
| 1190 |
+
"step": 1650
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"epoch": 1.53,
|
| 1194 |
+
"learning_rate": 0.0001232902033271719,
|
| 1195 |
+
"loss": 0.0586,
|
| 1196 |
+
"step": 1660
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 1.54,
|
| 1200 |
+
"learning_rate": 0.00012282809611829945,
|
| 1201 |
+
"loss": 0.1242,
|
| 1202 |
+
"step": 1670
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 1.55,
|
| 1206 |
+
"learning_rate": 0.000122365988909427,
|
| 1207 |
+
"loss": 0.0294,
|
| 1208 |
+
"step": 1680
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 1.56,
|
| 1212 |
+
"learning_rate": 0.00012190388170055453,
|
| 1213 |
+
"loss": 0.0231,
|
| 1214 |
+
"step": 1690
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 1.57,
|
| 1218 |
+
"learning_rate": 0.00012144177449168208,
|
| 1219 |
+
"loss": 0.0143,
|
| 1220 |
+
"step": 1700
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 1.57,
|
| 1224 |
+
"eval_accuracy": 0.9265761148129165,
|
| 1225 |
+
"eval_f1": 0.9265761148129165,
|
| 1226 |
+
"eval_loss": 0.22694824635982513,
|
| 1227 |
+
"eval_precision": 0.9265761148129165,
|
| 1228 |
+
"eval_recall": 0.9265761148129165,
|
| 1229 |
+
"eval_runtime": 94.6116,
|
| 1230 |
+
"eval_samples_per_second": 82.485,
|
| 1231 |
+
"eval_steps_per_second": 10.316,
|
| 1232 |
+
"step": 1700
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 1.58,
|
| 1236 |
+
"learning_rate": 0.00012097966728280962,
|
| 1237 |
+
"loss": 0.0102,
|
| 1238 |
+
"step": 1710
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 1.59,
|
| 1242 |
+
"learning_rate": 0.00012051756007393715,
|
| 1243 |
+
"loss": 0.0731,
|
| 1244 |
+
"step": 1720
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 1.6,
|
| 1248 |
+
"learning_rate": 0.0001200554528650647,
|
| 1249 |
+
"loss": 0.0087,
|
| 1250 |
+
"step": 1730
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 1.61,
|
| 1254 |
+
"learning_rate": 0.00011959334565619225,
|
| 1255 |
+
"loss": 0.053,
|
| 1256 |
+
"step": 1740
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 1.62,
|
| 1260 |
+
"learning_rate": 0.00011913123844731979,
|
| 1261 |
+
"loss": 0.0179,
|
| 1262 |
+
"step": 1750
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 1.63,
|
| 1266 |
+
"learning_rate": 0.00011866913123844731,
|
| 1267 |
+
"loss": 0.1918,
|
| 1268 |
+
"step": 1760
|
| 1269 |
+
},
|
| 1270 |
+
{
|
| 1271 |
+
"epoch": 1.64,
|
| 1272 |
+
"learning_rate": 0.00011820702402957487,
|
| 1273 |
+
"loss": 0.0386,
|
| 1274 |
+
"step": 1770
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 1.65,
|
| 1278 |
+
"learning_rate": 0.00011774491682070241,
|
| 1279 |
+
"loss": 0.0208,
|
| 1280 |
+
"step": 1780
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 1.65,
|
| 1284 |
+
"learning_rate": 0.00011728280961182996,
|
| 1285 |
+
"loss": 0.0044,
|
| 1286 |
+
"step": 1790
|
| 1287 |
+
},
|
| 1288 |
+
{
|
| 1289 |
+
"epoch": 1.66,
|
| 1290 |
+
"learning_rate": 0.00011682070240295748,
|
| 1291 |
+
"loss": 0.071,
|
| 1292 |
+
"step": 1800
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"epoch": 1.66,
|
| 1296 |
+
"eval_accuracy": 0.9118400820092261,
|
| 1297 |
+
"eval_f1": 0.9118400820092261,
|
| 1298 |
+
"eval_loss": 0.3436349630355835,
|
| 1299 |
+
"eval_precision": 0.9118400820092261,
|
| 1300 |
+
"eval_recall": 0.9118400820092261,
|
| 1301 |
+
"eval_runtime": 94.8946,
|
| 1302 |
+
"eval_samples_per_second": 82.239,
|
| 1303 |
+
"eval_steps_per_second": 10.285,
|
| 1304 |
+
"step": 1800
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 1.67,
|
| 1308 |
+
"learning_rate": 0.00011635859519408503,
|
| 1309 |
+
"loss": 0.0363,
|
| 1310 |
+
"step": 1810
|
| 1311 |
+
},
|
| 1312 |
+
{
|
| 1313 |
+
"epoch": 1.68,
|
| 1314 |
+
"learning_rate": 0.00011589648798521257,
|
| 1315 |
+
"loss": 0.0218,
|
| 1316 |
+
"step": 1820
|
| 1317 |
+
},
|
| 1318 |
+
{
|
| 1319 |
+
"epoch": 1.69,
|
| 1320 |
+
"learning_rate": 0.00011543438077634013,
|
| 1321 |
+
"loss": 0.0769,
|
| 1322 |
+
"step": 1830
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 1.7,
|
| 1326 |
+
"learning_rate": 0.00011497227356746765,
|
| 1327 |
+
"loss": 0.0351,
|
| 1328 |
+
"step": 1840
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 1.71,
|
| 1332 |
+
"learning_rate": 0.0001145101663585952,
|
| 1333 |
+
"loss": 0.077,
|
| 1334 |
+
"step": 1850
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 1.72,
|
| 1338 |
+
"learning_rate": 0.00011404805914972275,
|
| 1339 |
+
"loss": 0.0142,
|
| 1340 |
+
"step": 1860
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 1.73,
|
| 1344 |
+
"learning_rate": 0.00011358595194085029,
|
| 1345 |
+
"loss": 0.0371,
|
| 1346 |
+
"step": 1870
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 1.74,
|
| 1350 |
+
"learning_rate": 0.00011312384473197783,
|
| 1351 |
+
"loss": 0.0498,
|
| 1352 |
+
"step": 1880
|
| 1353 |
+
},
|
| 1354 |
+
{
|
| 1355 |
+
"epoch": 1.75,
|
| 1356 |
+
"learning_rate": 0.00011266173752310536,
|
| 1357 |
+
"loss": 0.0085,
|
| 1358 |
+
"step": 1890
|
| 1359 |
+
},
|
| 1360 |
+
{
|
| 1361 |
+
"epoch": 1.76,
|
| 1362 |
+
"learning_rate": 0.00011219963031423291,
|
| 1363 |
+
"loss": 0.0594,
|
| 1364 |
+
"step": 1900
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 1.76,
|
| 1368 |
+
"eval_accuracy": 0.8996668375192209,
|
| 1369 |
+
"eval_f1": 0.8996668375192209,
|
| 1370 |
+
"eval_loss": 0.3813391327857971,
|
| 1371 |
+
"eval_precision": 0.8996668375192209,
|
| 1372 |
+
"eval_recall": 0.8996668375192209,
|
| 1373 |
+
"eval_runtime": 94.4198,
|
| 1374 |
+
"eval_samples_per_second": 82.652,
|
| 1375 |
+
"eval_steps_per_second": 10.337,
|
| 1376 |
+
"step": 1900
|
| 1377 |
+
},
|
| 1378 |
+
{
|
| 1379 |
+
"epoch": 1.77,
|
| 1380 |
+
"learning_rate": 0.00011173752310536045,
|
| 1381 |
+
"loss": 0.1587,
|
| 1382 |
+
"step": 1910
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 1.77,
|
| 1386 |
+
"learning_rate": 0.000111275415896488,
|
| 1387 |
+
"loss": 0.0589,
|
| 1388 |
+
"step": 1920
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 1.78,
|
| 1392 |
+
"learning_rate": 0.00011081330868761552,
|
| 1393 |
+
"loss": 0.0239,
|
| 1394 |
+
"step": 1930
|
| 1395 |
+
},
|
| 1396 |
+
{
|
| 1397 |
+
"epoch": 1.79,
|
| 1398 |
+
"learning_rate": 0.00011035120147874307,
|
| 1399 |
+
"loss": 0.0649,
|
| 1400 |
+
"step": 1940
|
| 1401 |
+
},
|
| 1402 |
+
{
|
| 1403 |
+
"epoch": 1.8,
|
| 1404 |
+
"learning_rate": 0.00010988909426987061,
|
| 1405 |
+
"loss": 0.0337,
|
| 1406 |
+
"step": 1950
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 1.81,
|
| 1410 |
+
"learning_rate": 0.00010942698706099817,
|
| 1411 |
+
"loss": 0.0777,
|
| 1412 |
+
"step": 1960
|
| 1413 |
+
},
|
| 1414 |
+
{
|
| 1415 |
+
"epoch": 1.82,
|
| 1416 |
+
"learning_rate": 0.0001089648798521257,
|
| 1417 |
+
"loss": 0.0788,
|
| 1418 |
+
"step": 1970
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 1.83,
|
| 1422 |
+
"learning_rate": 0.00010850277264325324,
|
| 1423 |
+
"loss": 0.0358,
|
| 1424 |
+
"step": 1980
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 1.84,
|
| 1428 |
+
"learning_rate": 0.00010804066543438078,
|
| 1429 |
+
"loss": 0.059,
|
| 1430 |
+
"step": 1990
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 1.85,
|
| 1434 |
+
"learning_rate": 0.00010757855822550833,
|
| 1435 |
+
"loss": 0.0406,
|
| 1436 |
+
"step": 2000
|
| 1437 |
+
},
|
| 1438 |
+
{
|
| 1439 |
+
"epoch": 1.85,
|
| 1440 |
+
"eval_accuracy": 0.933623782675551,
|
| 1441 |
+
"eval_f1": 0.933623782675551,
|
| 1442 |
+
"eval_loss": 0.21288499236106873,
|
| 1443 |
+
"eval_precision": 0.933623782675551,
|
| 1444 |
+
"eval_recall": 0.933623782675551,
|
| 1445 |
+
"eval_runtime": 95.9077,
|
| 1446 |
+
"eval_samples_per_second": 81.37,
|
| 1447 |
+
"eval_steps_per_second": 10.176,
|
| 1448 |
+
"step": 2000
|
| 1449 |
+
},
|
| 1450 |
+
{
|
| 1451 |
+
"epoch": 1.86,
|
| 1452 |
+
"learning_rate": 0.00010711645101663586,
|
| 1453 |
+
"loss": 0.0426,
|
| 1454 |
+
"step": 2010
|
| 1455 |
+
},
|
| 1456 |
+
{
|
| 1457 |
+
"epoch": 1.87,
|
| 1458 |
+
"learning_rate": 0.0001066543438077634,
|
| 1459 |
+
"loss": 0.0358,
|
| 1460 |
+
"step": 2020
|
| 1461 |
+
},
|
| 1462 |
+
{
|
| 1463 |
+
"epoch": 1.88,
|
| 1464 |
+
"learning_rate": 0.00010619223659889095,
|
| 1465 |
+
"loss": 0.0231,
|
| 1466 |
+
"step": 2030
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 1.89,
|
| 1470 |
+
"learning_rate": 0.0001057301293900185,
|
| 1471 |
+
"loss": 0.0349,
|
| 1472 |
+
"step": 2040
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 1.89,
|
| 1476 |
+
"learning_rate": 0.00010526802218114602,
|
| 1477 |
+
"loss": 0.0079,
|
| 1478 |
+
"step": 2050
|
| 1479 |
+
},
|
| 1480 |
+
{
|
| 1481 |
+
"epoch": 1.9,
|
| 1482 |
+
"learning_rate": 0.00010480591497227356,
|
| 1483 |
+
"loss": 0.0262,
|
| 1484 |
+
"step": 2060
|
| 1485 |
+
},
|
| 1486 |
+
{
|
| 1487 |
+
"epoch": 1.91,
|
| 1488 |
+
"learning_rate": 0.00010434380776340112,
|
| 1489 |
+
"loss": 0.0441,
|
| 1490 |
+
"step": 2070
|
| 1491 |
+
},
|
| 1492 |
+
{
|
| 1493 |
+
"epoch": 1.92,
|
| 1494 |
+
"learning_rate": 0.00010388170055452866,
|
| 1495 |
+
"loss": 0.1052,
|
| 1496 |
+
"step": 2080
|
| 1497 |
+
},
|
| 1498 |
+
{
|
| 1499 |
+
"epoch": 1.93,
|
| 1500 |
+
"learning_rate": 0.00010341959334565621,
|
| 1501 |
+
"loss": 0.0417,
|
| 1502 |
+
"step": 2090
|
| 1503 |
+
},
|
| 1504 |
+
{
|
| 1505 |
+
"epoch": 1.94,
|
| 1506 |
+
"learning_rate": 0.00010295748613678373,
|
| 1507 |
+
"loss": 0.048,
|
| 1508 |
+
"step": 2100
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 1.94,
|
| 1512 |
+
"eval_accuracy": 0.9160686827268067,
|
| 1513 |
+
"eval_f1": 0.9160686827268067,
|
| 1514 |
+
"eval_loss": 0.31165143847465515,
|
| 1515 |
+
"eval_precision": 0.9160686827268067,
|
| 1516 |
+
"eval_recall": 0.9160686827268067,
|
| 1517 |
+
"eval_runtime": 94.3406,
|
| 1518 |
+
"eval_samples_per_second": 82.722,
|
| 1519 |
+
"eval_steps_per_second": 10.345,
|
| 1520 |
+
"step": 2100
|
| 1521 |
+
},
|
| 1522 |
+
{
|
| 1523 |
+
"epoch": 1.95,
|
| 1524 |
+
"learning_rate": 0.00010249537892791128,
|
| 1525 |
+
"loss": 0.0299,
|
| 1526 |
+
"step": 2110
|
| 1527 |
+
},
|
| 1528 |
+
{
|
| 1529 |
+
"epoch": 1.96,
|
| 1530 |
+
"learning_rate": 0.00010203327171903882,
|
| 1531 |
+
"loss": 0.0579,
|
| 1532 |
+
"step": 2120
|
| 1533 |
+
},
|
| 1534 |
+
{
|
| 1535 |
+
"epoch": 1.97,
|
| 1536 |
+
"learning_rate": 0.00010157116451016637,
|
| 1537 |
+
"loss": 0.015,
|
| 1538 |
+
"step": 2130
|
| 1539 |
+
},
|
| 1540 |
+
{
|
| 1541 |
+
"epoch": 1.98,
|
| 1542 |
+
"learning_rate": 0.0001011090573012939,
|
| 1543 |
+
"loss": 0.0403,
|
| 1544 |
+
"step": 2140
|
| 1545 |
+
},
|
| 1546 |
+
{
|
| 1547 |
+
"epoch": 1.99,
|
| 1548 |
+
"learning_rate": 0.00010064695009242144,
|
| 1549 |
+
"loss": 0.0375,
|
| 1550 |
+
"step": 2150
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 2.0,
|
| 1554 |
+
"learning_rate": 0.000100184842883549,
|
| 1555 |
+
"loss": 0.0328,
|
| 1556 |
+
"step": 2160
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 2.01,
|
| 1560 |
+
"learning_rate": 9.972273567467652e-05,
|
| 1561 |
+
"loss": 0.0407,
|
| 1562 |
+
"step": 2170
|
| 1563 |
+
},
|
| 1564 |
+
{
|
| 1565 |
+
"epoch": 2.01,
|
| 1566 |
+
"learning_rate": 9.926062846580408e-05,
|
| 1567 |
+
"loss": 0.0067,
|
| 1568 |
+
"step": 2180
|
| 1569 |
+
},
|
| 1570 |
+
{
|
| 1571 |
+
"epoch": 2.02,
|
| 1572 |
+
"learning_rate": 9.87985212569316e-05,
|
| 1573 |
+
"loss": 0.0374,
|
| 1574 |
+
"step": 2190
|
| 1575 |
+
},
|
| 1576 |
+
{
|
| 1577 |
+
"epoch": 2.03,
|
| 1578 |
+
"learning_rate": 9.833641404805916e-05,
|
| 1579 |
+
"loss": 0.0071,
|
| 1580 |
+
"step": 2200
|
| 1581 |
+
},
|
| 1582 |
+
{
|
| 1583 |
+
"epoch": 2.03,
|
| 1584 |
+
"eval_accuracy": 0.9246540235776525,
|
| 1585 |
+
"eval_f1": 0.9246540235776525,
|
| 1586 |
+
"eval_loss": 0.2732369899749756,
|
| 1587 |
+
"eval_precision": 0.9246540235776525,
|
| 1588 |
+
"eval_recall": 0.9246540235776525,
|
| 1589 |
+
"eval_runtime": 95.2591,
|
| 1590 |
+
"eval_samples_per_second": 81.924,
|
| 1591 |
+
"eval_steps_per_second": 10.246,
|
| 1592 |
+
"step": 2200
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 2.04,
|
| 1596 |
+
"learning_rate": 9.787430683918669e-05,
|
| 1597 |
+
"loss": 0.0076,
|
| 1598 |
+
"step": 2210
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 2.05,
|
| 1602 |
+
"learning_rate": 9.741219963031424e-05,
|
| 1603 |
+
"loss": 0.0266,
|
| 1604 |
+
"step": 2220
|
| 1605 |
+
},
|
| 1606 |
+
{
|
| 1607 |
+
"epoch": 2.06,
|
| 1608 |
+
"learning_rate": 9.695009242144177e-05,
|
| 1609 |
+
"loss": 0.0467,
|
| 1610 |
+
"step": 2230
|
| 1611 |
+
},
|
| 1612 |
+
{
|
| 1613 |
+
"epoch": 2.07,
|
| 1614 |
+
"learning_rate": 9.648798521256932e-05,
|
| 1615 |
+
"loss": 0.009,
|
| 1616 |
+
"step": 2240
|
| 1617 |
+
},
|
| 1618 |
+
{
|
| 1619 |
+
"epoch": 2.08,
|
| 1620 |
+
"learning_rate": 9.602587800369686e-05,
|
| 1621 |
+
"loss": 0.0048,
|
| 1622 |
+
"step": 2250
|
| 1623 |
+
},
|
| 1624 |
+
{
|
| 1625 |
+
"epoch": 2.09,
|
| 1626 |
+
"learning_rate": 9.55637707948244e-05,
|
| 1627 |
+
"loss": 0.0019,
|
| 1628 |
+
"step": 2260
|
| 1629 |
+
},
|
| 1630 |
+
{
|
| 1631 |
+
"epoch": 2.1,
|
| 1632 |
+
"learning_rate": 9.510166358595194e-05,
|
| 1633 |
+
"loss": 0.0131,
|
| 1634 |
+
"step": 2270
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 2.11,
|
| 1638 |
+
"learning_rate": 9.463955637707949e-05,
|
| 1639 |
+
"loss": 0.005,
|
| 1640 |
+
"step": 2280
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 2.12,
|
| 1644 |
+
"learning_rate": 9.417744916820703e-05,
|
| 1645 |
+
"loss": 0.002,
|
| 1646 |
+
"step": 2290
|
| 1647 |
+
},
|
| 1648 |
+
{
|
| 1649 |
+
"epoch": 2.13,
|
| 1650 |
+
"learning_rate": 9.371534195933457e-05,
|
| 1651 |
+
"loss": 0.0021,
|
| 1652 |
+
"step": 2300
|
| 1653 |
+
},
|
| 1654 |
+
{
|
| 1655 |
+
"epoch": 2.13,
|
| 1656 |
+
"eval_accuracy": 0.9274730907227063,
|
| 1657 |
+
"eval_f1": 0.9274730907227063,
|
| 1658 |
+
"eval_loss": 0.3055046498775482,
|
| 1659 |
+
"eval_precision": 0.9274730907227063,
|
| 1660 |
+
"eval_recall": 0.9274730907227063,
|
| 1661 |
+
"eval_runtime": 94.2262,
|
| 1662 |
+
"eval_samples_per_second": 82.822,
|
| 1663 |
+
"eval_steps_per_second": 10.358,
|
| 1664 |
+
"step": 2300
|
| 1665 |
+
},
|
| 1666 |
+
{
|
| 1667 |
+
"epoch": 2.13,
|
| 1668 |
+
"learning_rate": 9.325323475046212e-05,
|
| 1669 |
+
"loss": 0.0015,
|
| 1670 |
+
"step": 2310
|
| 1671 |
+
},
|
| 1672 |
+
{
|
| 1673 |
+
"epoch": 2.14,
|
| 1674 |
+
"learning_rate": 9.279112754158965e-05,
|
| 1675 |
+
"loss": 0.0252,
|
| 1676 |
+
"step": 2320
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 2.15,
|
| 1680 |
+
"learning_rate": 9.23290203327172e-05,
|
| 1681 |
+
"loss": 0.0019,
|
| 1682 |
+
"step": 2330
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 2.16,
|
| 1686 |
+
"learning_rate": 9.186691312384473e-05,
|
| 1687 |
+
"loss": 0.0507,
|
| 1688 |
+
"step": 2340
|
| 1689 |
+
},
|
| 1690 |
+
{
|
| 1691 |
+
"epoch": 2.17,
|
| 1692 |
+
"learning_rate": 9.140480591497228e-05,
|
| 1693 |
+
"loss": 0.0024,
|
| 1694 |
+
"step": 2350
|
| 1695 |
+
},
|
| 1696 |
+
{
|
| 1697 |
+
"epoch": 2.18,
|
| 1698 |
+
"learning_rate": 9.094269870609981e-05,
|
| 1699 |
+
"loss": 0.008,
|
| 1700 |
+
"step": 2360
|
| 1701 |
+
},
|
| 1702 |
+
{
|
| 1703 |
+
"epoch": 2.19,
|
| 1704 |
+
"learning_rate": 9.048059149722737e-05,
|
| 1705 |
+
"loss": 0.008,
|
| 1706 |
+
"step": 2370
|
| 1707 |
+
},
|
| 1708 |
+
{
|
| 1709 |
+
"epoch": 2.2,
|
| 1710 |
+
"learning_rate": 9.001848428835489e-05,
|
| 1711 |
+
"loss": 0.0038,
|
| 1712 |
+
"step": 2380
|
| 1713 |
+
},
|
| 1714 |
+
{
|
| 1715 |
+
"epoch": 2.21,
|
| 1716 |
+
"learning_rate": 8.955637707948245e-05,
|
| 1717 |
+
"loss": 0.0024,
|
| 1718 |
+
"step": 2390
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 2.22,
|
| 1722 |
+
"learning_rate": 8.909426987060999e-05,
|
| 1723 |
+
"loss": 0.0722,
|
| 1724 |
+
"step": 2400
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 2.22,
|
| 1728 |
+
"eval_accuracy": 0.9250384418247053,
|
| 1729 |
+
"eval_f1": 0.9250384418247052,
|
| 1730 |
+
"eval_loss": 0.3441855013370514,
|
| 1731 |
+
"eval_precision": 0.9250384418247053,
|
| 1732 |
+
"eval_recall": 0.9250384418247053,
|
| 1733 |
+
"eval_runtime": 94.2676,
|
| 1734 |
+
"eval_samples_per_second": 82.786,
|
| 1735 |
+
"eval_steps_per_second": 10.354,
|
| 1736 |
+
"step": 2400
|
| 1737 |
+
},
|
| 1738 |
+
{
|
| 1739 |
+
"epoch": 2.23,
|
| 1740 |
+
"learning_rate": 8.863216266173753e-05,
|
| 1741 |
+
"loss": 0.0172,
|
| 1742 |
+
"step": 2410
|
| 1743 |
+
},
|
| 1744 |
+
{
|
| 1745 |
+
"epoch": 2.24,
|
| 1746 |
+
"learning_rate": 8.817005545286507e-05,
|
| 1747 |
+
"loss": 0.0038,
|
| 1748 |
+
"step": 2420
|
| 1749 |
+
},
|
| 1750 |
+
{
|
| 1751 |
+
"epoch": 2.25,
|
| 1752 |
+
"learning_rate": 8.770794824399261e-05,
|
| 1753 |
+
"loss": 0.0211,
|
| 1754 |
+
"step": 2430
|
| 1755 |
+
},
|
| 1756 |
+
{
|
| 1757 |
+
"epoch": 2.26,
|
| 1758 |
+
"learning_rate": 8.724584103512015e-05,
|
| 1759 |
+
"loss": 0.0568,
|
| 1760 |
+
"step": 2440
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 2.26,
|
| 1764 |
+
"learning_rate": 8.678373382624769e-05,
|
| 1765 |
+
"loss": 0.007,
|
| 1766 |
+
"step": 2450
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 2.27,
|
| 1770 |
+
"learning_rate": 8.632162661737525e-05,
|
| 1771 |
+
"loss": 0.0037,
|
| 1772 |
+
"step": 2460
|
| 1773 |
+
},
|
| 1774 |
+
{
|
| 1775 |
+
"epoch": 2.28,
|
| 1776 |
+
"learning_rate": 8.585951940850277e-05,
|
| 1777 |
+
"loss": 0.0247,
|
| 1778 |
+
"step": 2470
|
| 1779 |
+
},
|
| 1780 |
+
{
|
| 1781 |
+
"epoch": 2.29,
|
| 1782 |
+
"learning_rate": 8.539741219963033e-05,
|
| 1783 |
+
"loss": 0.0011,
|
| 1784 |
+
"step": 2480
|
| 1785 |
+
},
|
| 1786 |
+
{
|
| 1787 |
+
"epoch": 2.3,
|
| 1788 |
+
"learning_rate": 8.493530499075785e-05,
|
| 1789 |
+
"loss": 0.0025,
|
| 1790 |
+
"step": 2490
|
| 1791 |
+
},
|
| 1792 |
+
{
|
| 1793 |
+
"epoch": 2.31,
|
| 1794 |
+
"learning_rate": 8.447319778188541e-05,
|
| 1795 |
+
"loss": 0.0146,
|
| 1796 |
+
"step": 2500
|
| 1797 |
+
},
|
| 1798 |
+
{
|
| 1799 |
+
"epoch": 2.31,
|
| 1800 |
+
"eval_accuracy": 0.9314454126089186,
|
| 1801 |
+
"eval_f1": 0.9314454126089186,
|
| 1802 |
+
"eval_loss": 0.29841846227645874,
|
| 1803 |
+
"eval_precision": 0.9314454126089186,
|
| 1804 |
+
"eval_recall": 0.9314454126089186,
|
| 1805 |
+
"eval_runtime": 93.978,
|
| 1806 |
+
"eval_samples_per_second": 83.041,
|
| 1807 |
+
"eval_steps_per_second": 10.385,
|
| 1808 |
+
"step": 2500
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 2.32,
|
| 1812 |
+
"learning_rate": 8.401109057301294e-05,
|
| 1813 |
+
"loss": 0.0621,
|
| 1814 |
+
"step": 2510
|
| 1815 |
+
},
|
| 1816 |
+
{
|
| 1817 |
+
"epoch": 2.33,
|
| 1818 |
+
"learning_rate": 8.354898336414049e-05,
|
| 1819 |
+
"loss": 0.0361,
|
| 1820 |
+
"step": 2520
|
| 1821 |
+
},
|
| 1822 |
+
{
|
| 1823 |
+
"epoch": 2.34,
|
| 1824 |
+
"learning_rate": 8.308687615526802e-05,
|
| 1825 |
+
"loss": 0.0517,
|
| 1826 |
+
"step": 2530
|
| 1827 |
+
},
|
| 1828 |
+
{
|
| 1829 |
+
"epoch": 2.35,
|
| 1830 |
+
"learning_rate": 8.262476894639557e-05,
|
| 1831 |
+
"loss": 0.0026,
|
| 1832 |
+
"step": 2540
|
| 1833 |
+
},
|
| 1834 |
+
{
|
| 1835 |
+
"epoch": 2.36,
|
| 1836 |
+
"learning_rate": 8.216266173752311e-05,
|
| 1837 |
+
"loss": 0.0047,
|
| 1838 |
+
"step": 2550
|
| 1839 |
+
},
|
| 1840 |
+
{
|
| 1841 |
+
"epoch": 2.37,
|
| 1842 |
+
"learning_rate": 8.170055452865065e-05,
|
| 1843 |
+
"loss": 0.0038,
|
| 1844 |
+
"step": 2560
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 2.38,
|
| 1848 |
+
"learning_rate": 8.12384473197782e-05,
|
| 1849 |
+
"loss": 0.0109,
|
| 1850 |
+
"step": 2570
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 2.38,
|
| 1854 |
+
"learning_rate": 8.077634011090573e-05,
|
| 1855 |
+
"loss": 0.051,
|
| 1856 |
+
"step": 2580
|
| 1857 |
+
},
|
| 1858 |
+
{
|
| 1859 |
+
"epoch": 2.39,
|
| 1860 |
+
"learning_rate": 8.031423290203328e-05,
|
| 1861 |
+
"loss": 0.0026,
|
| 1862 |
+
"step": 2590
|
| 1863 |
+
},
|
| 1864 |
+
{
|
| 1865 |
+
"epoch": 2.4,
|
| 1866 |
+
"learning_rate": 7.985212569316082e-05,
|
| 1867 |
+
"loss": 0.0031,
|
| 1868 |
+
"step": 2600
|
| 1869 |
+
},
|
| 1870 |
+
{
|
| 1871 |
+
"epoch": 2.4,
|
| 1872 |
+
"eval_accuracy": 0.929779600205023,
|
| 1873 |
+
"eval_f1": 0.929779600205023,
|
| 1874 |
+
"eval_loss": 0.3211658000946045,
|
| 1875 |
+
"eval_precision": 0.929779600205023,
|
| 1876 |
+
"eval_recall": 0.929779600205023,
|
| 1877 |
+
"eval_runtime": 94.0484,
|
| 1878 |
+
"eval_samples_per_second": 82.979,
|
| 1879 |
+
"eval_steps_per_second": 10.378,
|
| 1880 |
+
"step": 2600
|
| 1881 |
+
},
|
| 1882 |
+
{
|
| 1883 |
+
"epoch": 2.41,
|
| 1884 |
+
"learning_rate": 7.939001848428836e-05,
|
| 1885 |
+
"loss": 0.0153,
|
| 1886 |
+
"step": 2610
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 2.42,
|
| 1890 |
+
"learning_rate": 7.89279112754159e-05,
|
| 1891 |
+
"loss": 0.0019,
|
| 1892 |
+
"step": 2620
|
| 1893 |
+
},
|
| 1894 |
+
{
|
| 1895 |
+
"epoch": 2.43,
|
| 1896 |
+
"learning_rate": 7.846580406654345e-05,
|
| 1897 |
+
"loss": 0.0014,
|
| 1898 |
+
"step": 2630
|
| 1899 |
+
},
|
| 1900 |
+
{
|
| 1901 |
+
"epoch": 2.44,
|
| 1902 |
+
"learning_rate": 7.800369685767098e-05,
|
| 1903 |
+
"loss": 0.0012,
|
| 1904 |
+
"step": 2640
|
| 1905 |
+
},
|
| 1906 |
+
{
|
| 1907 |
+
"epoch": 2.45,
|
| 1908 |
+
"learning_rate": 7.754158964879853e-05,
|
| 1909 |
+
"loss": 0.0011,
|
| 1910 |
+
"step": 2650
|
| 1911 |
+
},
|
| 1912 |
+
{
|
| 1913 |
+
"epoch": 2.46,
|
| 1914 |
+
"learning_rate": 7.707948243992606e-05,
|
| 1915 |
+
"loss": 0.001,
|
| 1916 |
+
"step": 2660
|
| 1917 |
+
},
|
| 1918 |
+
{
|
| 1919 |
+
"epoch": 2.47,
|
| 1920 |
+
"learning_rate": 7.661737523105361e-05,
|
| 1921 |
+
"loss": 0.0024,
|
| 1922 |
+
"step": 2670
|
| 1923 |
+
},
|
| 1924 |
+
{
|
| 1925 |
+
"epoch": 2.48,
|
| 1926 |
+
"learning_rate": 7.615526802218114e-05,
|
| 1927 |
+
"loss": 0.001,
|
| 1928 |
+
"step": 2680
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 2.49,
|
| 1932 |
+
"learning_rate": 7.56931608133087e-05,
|
| 1933 |
+
"loss": 0.0611,
|
| 1934 |
+
"step": 2690
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 2.5,
|
| 1938 |
+
"learning_rate": 7.523105360443624e-05,
|
| 1939 |
+
"loss": 0.0167,
|
| 1940 |
+
"step": 2700
|
| 1941 |
+
},
|
| 1942 |
+
{
|
| 1943 |
+
"epoch": 2.5,
|
| 1944 |
+
"eval_accuracy": 0.9319579702716556,
|
| 1945 |
+
"eval_f1": 0.9319579702716556,
|
| 1946 |
+
"eval_loss": 0.3110896348953247,
|
| 1947 |
+
"eval_precision": 0.9319579702716556,
|
| 1948 |
+
"eval_recall": 0.9319579702716556,
|
| 1949 |
+
"eval_runtime": 94.4758,
|
| 1950 |
+
"eval_samples_per_second": 82.603,
|
| 1951 |
+
"eval_steps_per_second": 10.331,
|
| 1952 |
+
"step": 2700
|
| 1953 |
+
},
|
| 1954 |
+
{
|
| 1955 |
+
"epoch": 2.5,
|
| 1956 |
+
"learning_rate": 7.476894639556378e-05,
|
| 1957 |
+
"loss": 0.0286,
|
| 1958 |
+
"step": 2710
|
| 1959 |
+
},
|
| 1960 |
+
{
|
| 1961 |
+
"epoch": 2.51,
|
| 1962 |
+
"learning_rate": 7.430683918669132e-05,
|
| 1963 |
+
"loss": 0.0365,
|
| 1964 |
+
"step": 2720
|
| 1965 |
+
},
|
| 1966 |
+
{
|
| 1967 |
+
"epoch": 2.52,
|
| 1968 |
+
"learning_rate": 7.384473197781886e-05,
|
| 1969 |
+
"loss": 0.0041,
|
| 1970 |
+
"step": 2730
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 2.53,
|
| 1974 |
+
"learning_rate": 7.33826247689464e-05,
|
| 1975 |
+
"loss": 0.0449,
|
| 1976 |
+
"step": 2740
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 2.54,
|
| 1980 |
+
"learning_rate": 7.292051756007394e-05,
|
| 1981 |
+
"loss": 0.0126,
|
| 1982 |
+
"step": 2750
|
| 1983 |
+
},
|
| 1984 |
+
{
|
| 1985 |
+
"epoch": 2.55,
|
| 1986 |
+
"learning_rate": 7.245841035120148e-05,
|
| 1987 |
+
"loss": 0.0011,
|
| 1988 |
+
"step": 2760
|
| 1989 |
+
},
|
| 1990 |
+
{
|
| 1991 |
+
"epoch": 2.56,
|
| 1992 |
+
"learning_rate": 7.199630314232902e-05,
|
| 1993 |
+
"loss": 0.0283,
|
| 1994 |
+
"step": 2770
|
| 1995 |
+
},
|
| 1996 |
+
{
|
| 1997 |
+
"epoch": 2.57,
|
| 1998 |
+
"learning_rate": 7.153419593345656e-05,
|
| 1999 |
+
"loss": 0.0013,
|
| 2000 |
+
"step": 2780
|
| 2001 |
+
},
|
| 2002 |
+
{
|
| 2003 |
+
"epoch": 2.58,
|
| 2004 |
+
"learning_rate": 7.10720887245841e-05,
|
| 2005 |
+
"loss": 0.0012,
|
| 2006 |
+
"step": 2790
|
| 2007 |
+
},
|
| 2008 |
+
{
|
| 2009 |
+
"epoch": 2.59,
|
| 2010 |
+
"learning_rate": 7.060998151571166e-05,
|
| 2011 |
+
"loss": 0.0017,
|
| 2012 |
+
"step": 2800
|
| 2013 |
+
},
|
| 2014 |
+
{
|
| 2015 |
+
"epoch": 2.59,
|
| 2016 |
+
"eval_accuracy": 0.9306765761148129,
|
| 2017 |
+
"eval_f1": 0.9306765761148129,
|
| 2018 |
+
"eval_loss": 0.2883150577545166,
|
| 2019 |
+
"eval_precision": 0.9306765761148129,
|
| 2020 |
+
"eval_recall": 0.9306765761148129,
|
| 2021 |
+
"eval_runtime": 94.2594,
|
| 2022 |
+
"eval_samples_per_second": 82.793,
|
| 2023 |
+
"eval_steps_per_second": 10.354,
|
| 2024 |
+
"step": 2800
|
| 2025 |
+
},
|
| 2026 |
+
{
|
| 2027 |
+
"epoch": 2.6,
|
| 2028 |
+
"learning_rate": 7.014787430683918e-05,
|
| 2029 |
+
"loss": 0.0019,
|
| 2030 |
+
"step": 2810
|
| 2031 |
+
},
|
| 2032 |
+
{
|
| 2033 |
+
"epoch": 2.61,
|
| 2034 |
+
"learning_rate": 6.968576709796674e-05,
|
| 2035 |
+
"loss": 0.0032,
|
| 2036 |
+
"step": 2820
|
| 2037 |
+
},
|
| 2038 |
+
{
|
| 2039 |
+
"epoch": 2.62,
|
| 2040 |
+
"learning_rate": 6.922365988909427e-05,
|
| 2041 |
+
"loss": 0.0009,
|
| 2042 |
+
"step": 2830
|
| 2043 |
+
},
|
| 2044 |
+
{
|
| 2045 |
+
"epoch": 2.62,
|
| 2046 |
+
"learning_rate": 6.876155268022182e-05,
|
| 2047 |
+
"loss": 0.0015,
|
| 2048 |
+
"step": 2840
|
| 2049 |
+
},
|
| 2050 |
+
{
|
| 2051 |
+
"epoch": 2.63,
|
| 2052 |
+
"learning_rate": 6.829944547134936e-05,
|
| 2053 |
+
"loss": 0.0008,
|
| 2054 |
+
"step": 2850
|
| 2055 |
+
},
|
| 2056 |
+
{
|
| 2057 |
+
"epoch": 2.64,
|
| 2058 |
+
"learning_rate": 6.78373382624769e-05,
|
| 2059 |
+
"loss": 0.0008,
|
| 2060 |
+
"step": 2860
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 2.65,
|
| 2064 |
+
"learning_rate": 6.737523105360444e-05,
|
| 2065 |
+
"loss": 0.0021,
|
| 2066 |
+
"step": 2870
|
| 2067 |
+
},
|
| 2068 |
+
{
|
| 2069 |
+
"epoch": 2.66,
|
| 2070 |
+
"learning_rate": 6.691312384473198e-05,
|
| 2071 |
+
"loss": 0.0009,
|
| 2072 |
+
"step": 2880
|
| 2073 |
+
},
|
| 2074 |
+
{
|
| 2075 |
+
"epoch": 2.67,
|
| 2076 |
+
"learning_rate": 6.645101663585952e-05,
|
| 2077 |
+
"loss": 0.0016,
|
| 2078 |
+
"step": 2890
|
| 2079 |
+
},
|
| 2080 |
+
{
|
| 2081 |
+
"epoch": 2.68,
|
| 2082 |
+
"learning_rate": 6.598890942698706e-05,
|
| 2083 |
+
"loss": 0.0007,
|
| 2084 |
+
"step": 2900
|
| 2085 |
+
},
|
| 2086 |
+
{
|
| 2087 |
+
"epoch": 2.68,
|
| 2088 |
+
"eval_accuracy": 0.9320861096873398,
|
| 2089 |
+
"eval_f1": 0.9320861096873398,
|
| 2090 |
+
"eval_loss": 0.31885990500450134,
|
| 2091 |
+
"eval_precision": 0.9320861096873398,
|
| 2092 |
+
"eval_recall": 0.9320861096873398,
|
| 2093 |
+
"eval_runtime": 93.7458,
|
| 2094 |
+
"eval_samples_per_second": 83.246,
|
| 2095 |
+
"eval_steps_per_second": 10.411,
|
| 2096 |
+
"step": 2900
|
| 2097 |
+
},
|
| 2098 |
+
{
|
| 2099 |
+
"epoch": 2.69,
|
| 2100 |
+
"learning_rate": 6.55268022181146e-05,
|
| 2101 |
+
"loss": 0.0008,
|
| 2102 |
+
"step": 2910
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 2.7,
|
| 2106 |
+
"learning_rate": 6.506469500924215e-05,
|
| 2107 |
+
"loss": 0.0016,
|
| 2108 |
+
"step": 2920
|
| 2109 |
+
},
|
| 2110 |
+
{
|
| 2111 |
+
"epoch": 2.71,
|
| 2112 |
+
"learning_rate": 6.460258780036969e-05,
|
| 2113 |
+
"loss": 0.0006,
|
| 2114 |
+
"step": 2930
|
| 2115 |
+
},
|
| 2116 |
+
{
|
| 2117 |
+
"epoch": 2.72,
|
| 2118 |
+
"learning_rate": 6.414048059149723e-05,
|
| 2119 |
+
"loss": 0.0037,
|
| 2120 |
+
"step": 2940
|
| 2121 |
+
},
|
| 2122 |
+
{
|
| 2123 |
+
"epoch": 2.73,
|
| 2124 |
+
"learning_rate": 6.372458410351202e-05,
|
| 2125 |
+
"loss": 0.0266,
|
| 2126 |
+
"step": 2950
|
| 2127 |
+
},
|
| 2128 |
+
{
|
| 2129 |
+
"epoch": 2.74,
|
| 2130 |
+
"learning_rate": 6.326247689463956e-05,
|
| 2131 |
+
"loss": 0.0007,
|
| 2132 |
+
"step": 2960
|
| 2133 |
+
},
|
| 2134 |
+
{
|
| 2135 |
+
"epoch": 2.74,
|
| 2136 |
+
"learning_rate": 6.28003696857671e-05,
|
| 2137 |
+
"loss": 0.0007,
|
| 2138 |
+
"step": 2970
|
| 2139 |
+
},
|
| 2140 |
+
{
|
| 2141 |
+
"epoch": 2.75,
|
| 2142 |
+
"learning_rate": 6.233826247689464e-05,
|
| 2143 |
+
"loss": 0.001,
|
| 2144 |
+
"step": 2980
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 2.76,
|
| 2148 |
+
"learning_rate": 6.187615526802218e-05,
|
| 2149 |
+
"loss": 0.0143,
|
| 2150 |
+
"step": 2990
|
| 2151 |
+
},
|
| 2152 |
+
{
|
| 2153 |
+
"epoch": 2.77,
|
| 2154 |
+
"learning_rate": 6.141404805914972e-05,
|
| 2155 |
+
"loss": 0.0012,
|
| 2156 |
+
"step": 3000
|
| 2157 |
+
},
|
| 2158 |
+
{
|
| 2159 |
+
"epoch": 2.77,
|
| 2160 |
+
"eval_accuracy": 0.9383649410558688,
|
| 2161 |
+
"eval_f1": 0.9383649410558688,
|
| 2162 |
+
"eval_loss": 0.29957300424575806,
|
| 2163 |
+
"eval_precision": 0.9383649410558688,
|
| 2164 |
+
"eval_recall": 0.9383649410558688,
|
| 2165 |
+
"eval_runtime": 94.4006,
|
| 2166 |
+
"eval_samples_per_second": 82.669,
|
| 2167 |
+
"eval_steps_per_second": 10.339,
|
| 2168 |
+
"step": 3000
|
| 2169 |
+
},
|
| 2170 |
+
{
|
| 2171 |
+
"epoch": 2.78,
|
| 2172 |
+
"learning_rate": 6.0951940850277264e-05,
|
| 2173 |
+
"loss": 0.0035,
|
| 2174 |
+
"step": 3010
|
| 2175 |
+
},
|
| 2176 |
+
{
|
| 2177 |
+
"epoch": 2.79,
|
| 2178 |
+
"learning_rate": 6.048983364140481e-05,
|
| 2179 |
+
"loss": 0.0008,
|
| 2180 |
+
"step": 3020
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"epoch": 2.8,
|
| 2184 |
+
"learning_rate": 6.002772643253235e-05,
|
| 2185 |
+
"loss": 0.0006,
|
| 2186 |
+
"step": 3030
|
| 2187 |
+
},
|
| 2188 |
+
{
|
| 2189 |
+
"epoch": 2.81,
|
| 2190 |
+
"learning_rate": 5.956561922365989e-05,
|
| 2191 |
+
"loss": 0.01,
|
| 2192 |
+
"step": 3040
|
| 2193 |
+
},
|
| 2194 |
+
{
|
| 2195 |
+
"epoch": 2.82,
|
| 2196 |
+
"learning_rate": 5.9103512014787434e-05,
|
| 2197 |
+
"loss": 0.0011,
|
| 2198 |
+
"step": 3050
|
| 2199 |
+
},
|
| 2200 |
+
{
|
| 2201 |
+
"epoch": 2.83,
|
| 2202 |
+
"learning_rate": 5.864140480591498e-05,
|
| 2203 |
+
"loss": 0.0155,
|
| 2204 |
+
"step": 3060
|
| 2205 |
+
},
|
| 2206 |
+
{
|
| 2207 |
+
"epoch": 2.84,
|
| 2208 |
+
"learning_rate": 5.8179297597042515e-05,
|
| 2209 |
+
"loss": 0.0009,
|
| 2210 |
+
"step": 3070
|
| 2211 |
+
},
|
| 2212 |
+
{
|
| 2213 |
+
"epoch": 2.85,
|
| 2214 |
+
"learning_rate": 5.771719038817006e-05,
|
| 2215 |
+
"loss": 0.0005,
|
| 2216 |
+
"step": 3080
|
| 2217 |
+
},
|
| 2218 |
+
{
|
| 2219 |
+
"epoch": 2.86,
|
| 2220 |
+
"learning_rate": 5.72550831792976e-05,
|
| 2221 |
+
"loss": 0.0012,
|
| 2222 |
+
"step": 3090
|
| 2223 |
+
},
|
| 2224 |
+
{
|
| 2225 |
+
"epoch": 2.87,
|
| 2226 |
+
"learning_rate": 5.6792975970425144e-05,
|
| 2227 |
+
"loss": 0.0006,
|
| 2228 |
+
"step": 3100
|
| 2229 |
+
},
|
| 2230 |
+
{
|
| 2231 |
+
"epoch": 2.87,
|
| 2232 |
+
"eval_accuracy": 0.9281137878011276,
|
| 2233 |
+
"eval_f1": 0.9281137878011276,
|
| 2234 |
+
"eval_loss": 0.3553410470485687,
|
| 2235 |
+
"eval_precision": 0.9281137878011276,
|
| 2236 |
+
"eval_recall": 0.9281137878011276,
|
| 2237 |
+
"eval_runtime": 93.6408,
|
| 2238 |
+
"eval_samples_per_second": 83.34,
|
| 2239 |
+
"eval_steps_per_second": 10.423,
|
| 2240 |
+
"step": 3100
|
| 2241 |
+
},
|
| 2242 |
+
{
|
| 2243 |
+
"epoch": 2.87,
|
| 2244 |
+
"learning_rate": 5.633086876155268e-05,
|
| 2245 |
+
"loss": 0.0481,
|
| 2246 |
+
"step": 3110
|
| 2247 |
+
},
|
| 2248 |
+
{
|
| 2249 |
+
"epoch": 2.88,
|
| 2250 |
+
"learning_rate": 5.5868761552680226e-05,
|
| 2251 |
+
"loss": 0.0064,
|
| 2252 |
+
"step": 3120
|
| 2253 |
+
},
|
| 2254 |
+
{
|
| 2255 |
+
"epoch": 2.89,
|
| 2256 |
+
"learning_rate": 5.540665434380776e-05,
|
| 2257 |
+
"loss": 0.0008,
|
| 2258 |
+
"step": 3130
|
| 2259 |
+
},
|
| 2260 |
+
{
|
| 2261 |
+
"epoch": 2.9,
|
| 2262 |
+
"learning_rate": 5.494454713493531e-05,
|
| 2263 |
+
"loss": 0.0008,
|
| 2264 |
+
"step": 3140
|
| 2265 |
+
},
|
| 2266 |
+
{
|
| 2267 |
+
"epoch": 2.91,
|
| 2268 |
+
"learning_rate": 5.448243992606285e-05,
|
| 2269 |
+
"loss": 0.0393,
|
| 2270 |
+
"step": 3150
|
| 2271 |
+
},
|
| 2272 |
+
{
|
| 2273 |
+
"epoch": 2.92,
|
| 2274 |
+
"learning_rate": 5.402033271719039e-05,
|
| 2275 |
+
"loss": 0.0102,
|
| 2276 |
+
"step": 3160
|
| 2277 |
+
},
|
| 2278 |
+
{
|
| 2279 |
+
"epoch": 2.93,
|
| 2280 |
+
"learning_rate": 5.355822550831793e-05,
|
| 2281 |
+
"loss": 0.0015,
|
| 2282 |
+
"step": 3170
|
| 2283 |
+
},
|
| 2284 |
+
{
|
| 2285 |
+
"epoch": 2.94,
|
| 2286 |
+
"learning_rate": 5.309611829944548e-05,
|
| 2287 |
+
"loss": 0.0009,
|
| 2288 |
+
"step": 3180
|
| 2289 |
+
},
|
| 2290 |
+
{
|
| 2291 |
+
"epoch": 2.95,
|
| 2292 |
+
"learning_rate": 5.263401109057301e-05,
|
| 2293 |
+
"loss": 0.0007,
|
| 2294 |
+
"step": 3190
|
| 2295 |
+
},
|
| 2296 |
+
{
|
| 2297 |
+
"epoch": 2.96,
|
| 2298 |
+
"learning_rate": 5.217190388170056e-05,
|
| 2299 |
+
"loss": 0.0007,
|
| 2300 |
+
"step": 3200
|
| 2301 |
+
},
|
| 2302 |
+
{
|
| 2303 |
+
"epoch": 2.96,
|
| 2304 |
+
"eval_accuracy": 0.9284982060481805,
|
| 2305 |
+
"eval_f1": 0.9284982060481805,
|
| 2306 |
+
"eval_loss": 0.3595002293586731,
|
| 2307 |
+
"eval_precision": 0.9284982060481805,
|
| 2308 |
+
"eval_recall": 0.9284982060481805,
|
| 2309 |
+
"eval_runtime": 94.7075,
|
| 2310 |
+
"eval_samples_per_second": 82.401,
|
| 2311 |
+
"eval_steps_per_second": 10.305,
|
| 2312 |
+
"step": 3200
|
| 2313 |
+
},
|
| 2314 |
+
{
|
| 2315 |
+
"epoch": 2.97,
|
| 2316 |
+
"learning_rate": 5.1709796672828106e-05,
|
| 2317 |
+
"loss": 0.0008,
|
| 2318 |
+
"step": 3210
|
| 2319 |
+
},
|
| 2320 |
+
{
|
| 2321 |
+
"epoch": 2.98,
|
| 2322 |
+
"learning_rate": 5.124768946395564e-05,
|
| 2323 |
+
"loss": 0.0122,
|
| 2324 |
+
"step": 3220
|
| 2325 |
+
},
|
| 2326 |
+
{
|
| 2327 |
+
"epoch": 2.99,
|
| 2328 |
+
"learning_rate": 5.078558225508319e-05,
|
| 2329 |
+
"loss": 0.0015,
|
| 2330 |
+
"step": 3230
|
| 2331 |
+
},
|
| 2332 |
+
{
|
| 2333 |
+
"epoch": 2.99,
|
| 2334 |
+
"learning_rate": 5.032347504621072e-05,
|
| 2335 |
+
"loss": 0.0462,
|
| 2336 |
+
"step": 3240
|
| 2337 |
+
},
|
| 2338 |
+
{
|
| 2339 |
+
"epoch": 3.0,
|
| 2340 |
+
"learning_rate": 4.986136783733826e-05,
|
| 2341 |
+
"loss": 0.0007,
|
| 2342 |
+
"step": 3250
|
| 2343 |
+
},
|
| 2344 |
+
{
|
| 2345 |
+
"epoch": 3.01,
|
| 2346 |
+
"learning_rate": 4.93992606284658e-05,
|
| 2347 |
+
"loss": 0.0008,
|
| 2348 |
+
"step": 3260
|
| 2349 |
+
},
|
| 2350 |
+
{
|
| 2351 |
+
"epoch": 3.02,
|
| 2352 |
+
"learning_rate": 4.893715341959334e-05,
|
| 2353 |
+
"loss": 0.0007,
|
| 2354 |
+
"step": 3270
|
| 2355 |
+
},
|
| 2356 |
+
{
|
| 2357 |
+
"epoch": 3.03,
|
| 2358 |
+
"learning_rate": 4.8475046210720884e-05,
|
| 2359 |
+
"loss": 0.0007,
|
| 2360 |
+
"step": 3280
|
| 2361 |
+
},
|
| 2362 |
+
{
|
| 2363 |
+
"epoch": 3.04,
|
| 2364 |
+
"learning_rate": 4.801293900184843e-05,
|
| 2365 |
+
"loss": 0.0007,
|
| 2366 |
+
"step": 3290
|
| 2367 |
+
},
|
| 2368 |
+
{
|
| 2369 |
+
"epoch": 3.05,
|
| 2370 |
+
"learning_rate": 4.755083179297597e-05,
|
| 2371 |
+
"loss": 0.0238,
|
| 2372 |
+
"step": 3300
|
| 2373 |
+
},
|
| 2374 |
+
{
|
| 2375 |
+
"epoch": 3.05,
|
| 2376 |
+
"eval_accuracy": 0.9349051768323936,
|
| 2377 |
+
"eval_f1": 0.9349051768323936,
|
| 2378 |
+
"eval_loss": 0.3350887596607208,
|
| 2379 |
+
"eval_precision": 0.9349051768323936,
|
| 2380 |
+
"eval_recall": 0.9349051768323936,
|
| 2381 |
+
"eval_runtime": 93.8092,
|
| 2382 |
+
"eval_samples_per_second": 83.19,
|
| 2383 |
+
"eval_steps_per_second": 10.404,
|
| 2384 |
+
"step": 3300
|
| 2385 |
+
},
|
| 2386 |
+
{
|
| 2387 |
+
"epoch": 3.06,
|
| 2388 |
+
"learning_rate": 4.708872458410351e-05,
|
| 2389 |
+
"loss": 0.0008,
|
| 2390 |
+
"step": 3310
|
| 2391 |
+
},
|
| 2392 |
+
{
|
| 2393 |
+
"epoch": 3.07,
|
| 2394 |
+
"learning_rate": 4.662661737523106e-05,
|
| 2395 |
+
"loss": 0.0008,
|
| 2396 |
+
"step": 3320
|
| 2397 |
+
},
|
| 2398 |
+
{
|
| 2399 |
+
"epoch": 3.08,
|
| 2400 |
+
"learning_rate": 4.61645101663586e-05,
|
| 2401 |
+
"loss": 0.0007,
|
| 2402 |
+
"step": 3330
|
| 2403 |
+
},
|
| 2404 |
+
{
|
| 2405 |
+
"epoch": 3.09,
|
| 2406 |
+
"learning_rate": 4.570240295748614e-05,
|
| 2407 |
+
"loss": 0.0007,
|
| 2408 |
+
"step": 3340
|
| 2409 |
+
},
|
| 2410 |
+
{
|
| 2411 |
+
"epoch": 3.1,
|
| 2412 |
+
"learning_rate": 4.524029574861368e-05,
|
| 2413 |
+
"loss": 0.0032,
|
| 2414 |
+
"step": 3350
|
| 2415 |
+
},
|
| 2416 |
+
{
|
| 2417 |
+
"epoch": 3.11,
|
| 2418 |
+
"learning_rate": 4.4778188539741223e-05,
|
| 2419 |
+
"loss": 0.0085,
|
| 2420 |
+
"step": 3360
|
| 2421 |
+
},
|
| 2422 |
+
{
|
| 2423 |
+
"epoch": 3.11,
|
| 2424 |
+
"learning_rate": 4.4316081330868764e-05,
|
| 2425 |
+
"loss": 0.0006,
|
| 2426 |
+
"step": 3370
|
| 2427 |
+
},
|
| 2428 |
+
{
|
| 2429 |
+
"epoch": 3.12,
|
| 2430 |
+
"learning_rate": 4.3853974121996305e-05,
|
| 2431 |
+
"loss": 0.0218,
|
| 2432 |
+
"step": 3380
|
| 2433 |
+
},
|
| 2434 |
+
{
|
| 2435 |
+
"epoch": 3.13,
|
| 2436 |
+
"learning_rate": 4.3391866913123846e-05,
|
| 2437 |
+
"loss": 0.0006,
|
| 2438 |
+
"step": 3390
|
| 2439 |
+
},
|
| 2440 |
+
{
|
| 2441 |
+
"epoch": 3.14,
|
| 2442 |
+
"learning_rate": 4.2929759704251386e-05,
|
| 2443 |
+
"loss": 0.0065,
|
| 2444 |
+
"step": 3400
|
| 2445 |
+
},
|
| 2446 |
+
{
|
| 2447 |
+
"epoch": 3.14,
|
| 2448 |
+
"eval_accuracy": 0.9375961045617632,
|
| 2449 |
+
"eval_f1": 0.9375961045617632,
|
| 2450 |
+
"eval_loss": 0.3165816366672516,
|
| 2451 |
+
"eval_precision": 0.9375961045617632,
|
| 2452 |
+
"eval_recall": 0.9375961045617632,
|
| 2453 |
+
"eval_runtime": 93.6238,
|
| 2454 |
+
"eval_samples_per_second": 83.355,
|
| 2455 |
+
"eval_steps_per_second": 10.425,
|
| 2456 |
+
"step": 3400
|
| 2457 |
+
},
|
| 2458 |
+
{
|
| 2459 |
+
"epoch": 3.15,
|
| 2460 |
+
"learning_rate": 4.246765249537893e-05,
|
| 2461 |
+
"loss": 0.0006,
|
| 2462 |
+
"step": 3410
|
| 2463 |
+
},
|
| 2464 |
+
{
|
| 2465 |
+
"epoch": 3.16,
|
| 2466 |
+
"learning_rate": 4.200554528650647e-05,
|
| 2467 |
+
"loss": 0.0005,
|
| 2468 |
+
"step": 3420
|
| 2469 |
+
},
|
| 2470 |
+
{
|
| 2471 |
+
"epoch": 3.17,
|
| 2472 |
+
"learning_rate": 4.154343807763401e-05,
|
| 2473 |
+
"loss": 0.0005,
|
| 2474 |
+
"step": 3430
|
| 2475 |
+
},
|
| 2476 |
+
{
|
| 2477 |
+
"epoch": 3.18,
|
| 2478 |
+
"learning_rate": 4.1081330868761556e-05,
|
| 2479 |
+
"loss": 0.0005,
|
| 2480 |
+
"step": 3440
|
| 2481 |
+
},
|
| 2482 |
+
{
|
| 2483 |
+
"epoch": 3.19,
|
| 2484 |
+
"learning_rate": 4.06192236598891e-05,
|
| 2485 |
+
"loss": 0.0006,
|
| 2486 |
+
"step": 3450
|
| 2487 |
+
},
|
| 2488 |
+
{
|
| 2489 |
+
"epoch": 3.2,
|
| 2490 |
+
"learning_rate": 4.015711645101664e-05,
|
| 2491 |
+
"loss": 0.0005,
|
| 2492 |
+
"step": 3460
|
| 2493 |
+
},
|
| 2494 |
+
{
|
| 2495 |
+
"epoch": 3.21,
|
| 2496 |
+
"learning_rate": 3.969500924214418e-05,
|
| 2497 |
+
"loss": 0.0445,
|
| 2498 |
+
"step": 3470
|
| 2499 |
+
},
|
| 2500 |
+
{
|
| 2501 |
+
"epoch": 3.22,
|
| 2502 |
+
"learning_rate": 3.9232902033271726e-05,
|
| 2503 |
+
"loss": 0.0007,
|
| 2504 |
+
"step": 3480
|
| 2505 |
+
},
|
| 2506 |
+
{
|
| 2507 |
+
"epoch": 3.23,
|
| 2508 |
+
"learning_rate": 3.8770794824399266e-05,
|
| 2509 |
+
"loss": 0.0009,
|
| 2510 |
+
"step": 3490
|
| 2511 |
+
},
|
| 2512 |
+
{
|
| 2513 |
+
"epoch": 3.23,
|
| 2514 |
+
"learning_rate": 3.830868761552681e-05,
|
| 2515 |
+
"loss": 0.0009,
|
| 2516 |
+
"step": 3500
|
| 2517 |
+
},
|
| 2518 |
+
{
|
| 2519 |
+
"epoch": 3.23,
|
| 2520 |
+
"eval_accuracy": 0.933111225012814,
|
| 2521 |
+
"eval_f1": 0.933111225012814,
|
| 2522 |
+
"eval_loss": 0.33037713170051575,
|
| 2523 |
+
"eval_precision": 0.933111225012814,
|
| 2524 |
+
"eval_recall": 0.933111225012814,
|
| 2525 |
+
"eval_runtime": 94.2067,
|
| 2526 |
+
"eval_samples_per_second": 82.839,
|
| 2527 |
+
"eval_steps_per_second": 10.36,
|
| 2528 |
+
"step": 3500
|
| 2529 |
+
},
|
| 2530 |
+
{
|
| 2531 |
+
"epoch": 3.24,
|
| 2532 |
+
"learning_rate": 3.784658040665435e-05,
|
| 2533 |
+
"loss": 0.0008,
|
| 2534 |
+
"step": 3510
|
| 2535 |
+
},
|
| 2536 |
+
{
|
| 2537 |
+
"epoch": 3.25,
|
| 2538 |
+
"learning_rate": 3.738447319778189e-05,
|
| 2539 |
+
"loss": 0.0055,
|
| 2540 |
+
"step": 3520
|
| 2541 |
+
},
|
| 2542 |
+
{
|
| 2543 |
+
"epoch": 3.26,
|
| 2544 |
+
"learning_rate": 3.692236598890943e-05,
|
| 2545 |
+
"loss": 0.0008,
|
| 2546 |
+
"step": 3530
|
| 2547 |
+
},
|
| 2548 |
+
{
|
| 2549 |
+
"epoch": 3.27,
|
| 2550 |
+
"learning_rate": 3.646025878003697e-05,
|
| 2551 |
+
"loss": 0.0006,
|
| 2552 |
+
"step": 3540
|
| 2553 |
+
},
|
| 2554 |
+
{
|
| 2555 |
+
"epoch": 3.28,
|
| 2556 |
+
"learning_rate": 3.599815157116451e-05,
|
| 2557 |
+
"loss": 0.0209,
|
| 2558 |
+
"step": 3550
|
| 2559 |
+
},
|
| 2560 |
+
{
|
| 2561 |
+
"epoch": 3.29,
|
| 2562 |
+
"learning_rate": 3.553604436229205e-05,
|
| 2563 |
+
"loss": 0.0007,
|
| 2564 |
+
"step": 3560
|
| 2565 |
+
},
|
| 2566 |
+
{
|
| 2567 |
+
"epoch": 3.3,
|
| 2568 |
+
"learning_rate": 3.507393715341959e-05,
|
| 2569 |
+
"loss": 0.0006,
|
| 2570 |
+
"step": 3570
|
| 2571 |
+
},
|
| 2572 |
+
{
|
| 2573 |
+
"epoch": 3.31,
|
| 2574 |
+
"learning_rate": 3.461182994454713e-05,
|
| 2575 |
+
"loss": 0.0009,
|
| 2576 |
+
"step": 3580
|
| 2577 |
+
},
|
| 2578 |
+
{
|
| 2579 |
+
"epoch": 3.32,
|
| 2580 |
+
"learning_rate": 3.414972273567468e-05,
|
| 2581 |
+
"loss": 0.0013,
|
| 2582 |
+
"step": 3590
|
| 2583 |
+
},
|
| 2584 |
+
{
|
| 2585 |
+
"epoch": 3.33,
|
| 2586 |
+
"learning_rate": 3.368761552680222e-05,
|
| 2587 |
+
"loss": 0.0006,
|
| 2588 |
+
"step": 3600
|
| 2589 |
+
},
|
| 2590 |
+
{
|
| 2591 |
+
"epoch": 3.33,
|
| 2592 |
+
"eval_accuracy": 0.9347770374167094,
|
| 2593 |
+
"eval_f1": 0.9347770374167094,
|
| 2594 |
+
"eval_loss": 0.3214694857597351,
|
| 2595 |
+
"eval_precision": 0.9347770374167094,
|
| 2596 |
+
"eval_recall": 0.9347770374167094,
|
| 2597 |
+
"eval_runtime": 93.9759,
|
| 2598 |
+
"eval_samples_per_second": 83.043,
|
| 2599 |
+
"eval_steps_per_second": 10.386,
|
| 2600 |
+
"step": 3600
|
| 2601 |
+
},
|
| 2602 |
+
{
|
| 2603 |
+
"epoch": 3.34,
|
| 2604 |
+
"learning_rate": 3.322550831792976e-05,
|
| 2605 |
+
"loss": 0.0014,
|
| 2606 |
+
"step": 3610
|
| 2607 |
+
},
|
| 2608 |
+
{
|
| 2609 |
+
"epoch": 3.35,
|
| 2610 |
+
"learning_rate": 3.27634011090573e-05,
|
| 2611 |
+
"loss": 0.0013,
|
| 2612 |
+
"step": 3620
|
| 2613 |
+
},
|
| 2614 |
+
{
|
| 2615 |
+
"epoch": 3.35,
|
| 2616 |
+
"learning_rate": 3.2301293900184843e-05,
|
| 2617 |
+
"loss": 0.0005,
|
| 2618 |
+
"step": 3630
|
| 2619 |
+
},
|
| 2620 |
+
{
|
| 2621 |
+
"epoch": 3.36,
|
| 2622 |
+
"learning_rate": 3.1839186691312384e-05,
|
| 2623 |
+
"loss": 0.0005,
|
| 2624 |
+
"step": 3640
|
| 2625 |
+
},
|
| 2626 |
+
{
|
| 2627 |
+
"epoch": 3.37,
|
| 2628 |
+
"learning_rate": 3.1377079482439925e-05,
|
| 2629 |
+
"loss": 0.0006,
|
| 2630 |
+
"step": 3650
|
| 2631 |
+
},
|
| 2632 |
+
{
|
| 2633 |
+
"epoch": 3.38,
|
| 2634 |
+
"learning_rate": 3.091497227356747e-05,
|
| 2635 |
+
"loss": 0.0005,
|
| 2636 |
+
"step": 3660
|
| 2637 |
+
},
|
| 2638 |
+
{
|
| 2639 |
+
"epoch": 3.39,
|
| 2640 |
+
"learning_rate": 3.0452865064695013e-05,
|
| 2641 |
+
"loss": 0.0005,
|
| 2642 |
+
"step": 3670
|
| 2643 |
+
},
|
| 2644 |
+
{
|
| 2645 |
+
"epoch": 3.4,
|
| 2646 |
+
"learning_rate": 2.9990757855822554e-05,
|
| 2647 |
+
"loss": 0.0009,
|
| 2648 |
+
"step": 3680
|
| 2649 |
+
},
|
| 2650 |
+
{
|
| 2651 |
+
"epoch": 3.41,
|
| 2652 |
+
"learning_rate": 2.9528650646950095e-05,
|
| 2653 |
+
"loss": 0.001,
|
| 2654 |
+
"step": 3690
|
| 2655 |
+
},
|
| 2656 |
+
{
|
| 2657 |
+
"epoch": 3.42,
|
| 2658 |
+
"learning_rate": 2.9066543438077635e-05,
|
| 2659 |
+
"loss": 0.0005,
|
| 2660 |
+
"step": 3700
|
| 2661 |
+
},
|
| 2662 |
+
{
|
| 2663 |
+
"epoch": 3.42,
|
| 2664 |
+
"eval_accuracy": 0.9352895950794464,
|
| 2665 |
+
"eval_f1": 0.9352895950794464,
|
| 2666 |
+
"eval_loss": 0.34141379594802856,
|
| 2667 |
+
"eval_precision": 0.9352895950794464,
|
| 2668 |
+
"eval_recall": 0.9352895950794464,
|
| 2669 |
+
"eval_runtime": 94.4131,
|
| 2670 |
+
"eval_samples_per_second": 82.658,
|
| 2671 |
+
"eval_steps_per_second": 10.338,
|
| 2672 |
+
"step": 3700
|
| 2673 |
+
},
|
| 2674 |
+
{
|
| 2675 |
+
"epoch": 3.43,
|
| 2676 |
+
"learning_rate": 2.860443622920518e-05,
|
| 2677 |
+
"loss": 0.0006,
|
| 2678 |
+
"step": 3710
|
| 2679 |
+
},
|
| 2680 |
+
{
|
| 2681 |
+
"epoch": 3.44,
|
| 2682 |
+
"learning_rate": 2.814232902033272e-05,
|
| 2683 |
+
"loss": 0.0098,
|
| 2684 |
+
"step": 3720
|
| 2685 |
+
},
|
| 2686 |
+
{
|
| 2687 |
+
"epoch": 3.45,
|
| 2688 |
+
"learning_rate": 2.768022181146026e-05,
|
| 2689 |
+
"loss": 0.0004,
|
| 2690 |
+
"step": 3730
|
| 2691 |
+
},
|
| 2692 |
+
{
|
| 2693 |
+
"epoch": 3.46,
|
| 2694 |
+
"learning_rate": 2.72181146025878e-05,
|
| 2695 |
+
"loss": 0.0005,
|
| 2696 |
+
"step": 3740
|
| 2697 |
+
},
|
| 2698 |
+
{
|
| 2699 |
+
"epoch": 3.47,
|
| 2700 |
+
"learning_rate": 2.6756007393715342e-05,
|
| 2701 |
+
"loss": 0.019,
|
| 2702 |
+
"step": 3750
|
| 2703 |
+
},
|
| 2704 |
+
{
|
| 2705 |
+
"epoch": 3.48,
|
| 2706 |
+
"learning_rate": 2.6293900184842883e-05,
|
| 2707 |
+
"loss": 0.0006,
|
| 2708 |
+
"step": 3760
|
| 2709 |
+
},
|
| 2710 |
+
{
|
| 2711 |
+
"epoch": 3.48,
|
| 2712 |
+
"learning_rate": 2.5831792975970427e-05,
|
| 2713 |
+
"loss": 0.0448,
|
| 2714 |
+
"step": 3770
|
| 2715 |
+
},
|
| 2716 |
+
{
|
| 2717 |
+
"epoch": 3.49,
|
| 2718 |
+
"learning_rate": 2.5369685767097968e-05,
|
| 2719 |
+
"loss": 0.0006,
|
| 2720 |
+
"step": 3780
|
| 2721 |
+
},
|
| 2722 |
+
{
|
| 2723 |
+
"epoch": 3.5,
|
| 2724 |
+
"learning_rate": 2.490757855822551e-05,
|
| 2725 |
+
"loss": 0.0006,
|
| 2726 |
+
"step": 3790
|
| 2727 |
+
},
|
| 2728 |
+
{
|
| 2729 |
+
"epoch": 3.51,
|
| 2730 |
+
"learning_rate": 2.4445471349353053e-05,
|
| 2731 |
+
"loss": 0.0006,
|
| 2732 |
+
"step": 3800
|
| 2733 |
+
},
|
| 2734 |
+
{
|
| 2735 |
+
"epoch": 3.51,
|
| 2736 |
+
"eval_accuracy": 0.935033316248078,
|
| 2737 |
+
"eval_f1": 0.935033316248078,
|
| 2738 |
+
"eval_loss": 0.3321364223957062,
|
| 2739 |
+
"eval_precision": 0.935033316248078,
|
| 2740 |
+
"eval_recall": 0.935033316248078,
|
| 2741 |
+
"eval_runtime": 94.2057,
|
| 2742 |
+
"eval_samples_per_second": 82.84,
|
| 2743 |
+
"eval_steps_per_second": 10.36,
|
| 2744 |
+
"step": 3800
|
| 2745 |
+
},
|
| 2746 |
+
{
|
| 2747 |
+
"epoch": 3.52,
|
| 2748 |
+
"learning_rate": 2.3983364140480594e-05,
|
| 2749 |
+
"loss": 0.0006,
|
| 2750 |
+
"step": 3810
|
| 2751 |
+
},
|
| 2752 |
+
{
|
| 2753 |
+
"epoch": 3.53,
|
| 2754 |
+
"learning_rate": 2.3521256931608134e-05,
|
| 2755 |
+
"loss": 0.0006,
|
| 2756 |
+
"step": 3820
|
| 2757 |
+
},
|
| 2758 |
+
{
|
| 2759 |
+
"epoch": 3.54,
|
| 2760 |
+
"learning_rate": 2.3059149722735675e-05,
|
| 2761 |
+
"loss": 0.0006,
|
| 2762 |
+
"step": 3830
|
| 2763 |
+
},
|
| 2764 |
+
{
|
| 2765 |
+
"epoch": 3.55,
|
| 2766 |
+
"learning_rate": 2.259704251386322e-05,
|
| 2767 |
+
"loss": 0.0016,
|
| 2768 |
+
"step": 3840
|
| 2769 |
+
},
|
| 2770 |
+
{
|
| 2771 |
+
"epoch": 3.56,
|
| 2772 |
+
"learning_rate": 2.213493530499076e-05,
|
| 2773 |
+
"loss": 0.0017,
|
| 2774 |
+
"step": 3850
|
| 2775 |
+
},
|
| 2776 |
+
{
|
| 2777 |
+
"epoch": 3.57,
|
| 2778 |
+
"learning_rate": 2.16728280961183e-05,
|
| 2779 |
+
"loss": 0.0005,
|
| 2780 |
+
"step": 3860
|
| 2781 |
+
},
|
| 2782 |
+
{
|
| 2783 |
+
"epoch": 3.58,
|
| 2784 |
+
"learning_rate": 2.121072088724584e-05,
|
| 2785 |
+
"loss": 0.0384,
|
| 2786 |
+
"step": 3870
|
| 2787 |
+
},
|
| 2788 |
+
{
|
| 2789 |
+
"epoch": 3.59,
|
| 2790 |
+
"learning_rate": 2.0748613678373382e-05,
|
| 2791 |
+
"loss": 0.0009,
|
| 2792 |
+
"step": 3880
|
| 2793 |
+
},
|
| 2794 |
+
{
|
| 2795 |
+
"epoch": 3.6,
|
| 2796 |
+
"learning_rate": 2.0286506469500923e-05,
|
| 2797 |
+
"loss": 0.0005,
|
| 2798 |
+
"step": 3890
|
| 2799 |
+
},
|
| 2800 |
+
{
|
| 2801 |
+
"epoch": 3.6,
|
| 2802 |
+
"learning_rate": 1.9824399260628467e-05,
|
| 2803 |
+
"loss": 0.0006,
|
| 2804 |
+
"step": 3900
|
| 2805 |
+
},
|
| 2806 |
+
{
|
| 2807 |
+
"epoch": 3.6,
|
| 2808 |
+
"eval_accuracy": 0.9378523833931317,
|
| 2809 |
+
"eval_f1": 0.9378523833931317,
|
| 2810 |
+
"eval_loss": 0.33057039976119995,
|
| 2811 |
+
"eval_precision": 0.9378523833931317,
|
| 2812 |
+
"eval_recall": 0.9378523833931317,
|
| 2813 |
+
"eval_runtime": 93.9934,
|
| 2814 |
+
"eval_samples_per_second": 83.027,
|
| 2815 |
+
"eval_steps_per_second": 10.384,
|
| 2816 |
+
"step": 3900
|
| 2817 |
+
},
|
| 2818 |
+
{
|
| 2819 |
+
"epoch": 3.61,
|
| 2820 |
+
"learning_rate": 1.9362292051756008e-05,
|
| 2821 |
+
"loss": 0.0056,
|
| 2822 |
+
"step": 3910
|
| 2823 |
+
},
|
| 2824 |
+
{
|
| 2825 |
+
"epoch": 3.62,
|
| 2826 |
+
"learning_rate": 1.890018484288355e-05,
|
| 2827 |
+
"loss": 0.0005,
|
| 2828 |
+
"step": 3920
|
| 2829 |
+
},
|
| 2830 |
+
{
|
| 2831 |
+
"epoch": 3.63,
|
| 2832 |
+
"learning_rate": 1.8438077634011092e-05,
|
| 2833 |
+
"loss": 0.0005,
|
| 2834 |
+
"step": 3930
|
| 2835 |
+
},
|
| 2836 |
+
{
|
| 2837 |
+
"epoch": 3.64,
|
| 2838 |
+
"learning_rate": 1.7975970425138633e-05,
|
| 2839 |
+
"loss": 0.0005,
|
| 2840 |
+
"step": 3940
|
| 2841 |
+
},
|
| 2842 |
+
{
|
| 2843 |
+
"epoch": 3.65,
|
| 2844 |
+
"learning_rate": 1.7513863216266174e-05,
|
| 2845 |
+
"loss": 0.0005,
|
| 2846 |
+
"step": 3950
|
| 2847 |
+
},
|
| 2848 |
+
{
|
| 2849 |
+
"epoch": 3.66,
|
| 2850 |
+
"learning_rate": 1.7051756007393715e-05,
|
| 2851 |
+
"loss": 0.0005,
|
| 2852 |
+
"step": 3960
|
| 2853 |
+
},
|
| 2854 |
+
{
|
| 2855 |
+
"epoch": 3.67,
|
| 2856 |
+
"learning_rate": 1.6589648798521255e-05,
|
| 2857 |
+
"loss": 0.0005,
|
| 2858 |
+
"step": 3970
|
| 2859 |
+
},
|
| 2860 |
+
{
|
| 2861 |
+
"epoch": 3.68,
|
| 2862 |
+
"learning_rate": 1.61275415896488e-05,
|
| 2863 |
+
"loss": 0.0005,
|
| 2864 |
+
"step": 3980
|
| 2865 |
+
},
|
| 2866 |
+
{
|
| 2867 |
+
"epoch": 3.69,
|
| 2868 |
+
"learning_rate": 1.5665434380776344e-05,
|
| 2869 |
+
"loss": 0.0005,
|
| 2870 |
+
"step": 3990
|
| 2871 |
+
},
|
| 2872 |
+
{
|
| 2873 |
+
"epoch": 3.7,
|
| 2874 |
+
"learning_rate": 1.5203327171903883e-05,
|
| 2875 |
+
"loss": 0.0411,
|
| 2876 |
+
"step": 4000
|
| 2877 |
+
},
|
| 2878 |
+
{
|
| 2879 |
+
"epoch": 3.7,
|
| 2880 |
+
"eval_accuracy": 0.9374679651460789,
|
| 2881 |
+
"eval_f1": 0.9374679651460789,
|
| 2882 |
+
"eval_loss": 0.3225729167461395,
|
| 2883 |
+
"eval_precision": 0.9374679651460789,
|
| 2884 |
+
"eval_recall": 0.9374679651460789,
|
| 2885 |
+
"eval_runtime": 93.7031,
|
| 2886 |
+
"eval_samples_per_second": 83.284,
|
| 2887 |
+
"eval_steps_per_second": 10.416,
|
| 2888 |
+
"step": 4000
|
| 2889 |
+
},
|
| 2890 |
+
{
|
| 2891 |
+
"epoch": 3.71,
|
| 2892 |
+
"learning_rate": 1.4741219963031425e-05,
|
| 2893 |
+
"loss": 0.0005,
|
| 2894 |
+
"step": 4010
|
| 2895 |
+
},
|
| 2896 |
+
{
|
| 2897 |
+
"epoch": 3.72,
|
| 2898 |
+
"learning_rate": 1.4279112754158966e-05,
|
| 2899 |
+
"loss": 0.0006,
|
| 2900 |
+
"step": 4020
|
| 2901 |
+
},
|
| 2902 |
+
{
|
| 2903 |
+
"epoch": 3.72,
|
| 2904 |
+
"learning_rate": 1.3817005545286506e-05,
|
| 2905 |
+
"loss": 0.0006,
|
| 2906 |
+
"step": 4030
|
| 2907 |
+
},
|
| 2908 |
+
{
|
| 2909 |
+
"epoch": 3.73,
|
| 2910 |
+
"learning_rate": 1.3354898336414049e-05,
|
| 2911 |
+
"loss": 0.0005,
|
| 2912 |
+
"step": 4040
|
| 2913 |
+
},
|
| 2914 |
+
{
|
| 2915 |
+
"epoch": 3.74,
|
| 2916 |
+
"learning_rate": 1.289279112754159e-05,
|
| 2917 |
+
"loss": 0.0005,
|
| 2918 |
+
"step": 4050
|
| 2919 |
+
},
|
| 2920 |
+
{
|
| 2921 |
+
"epoch": 3.75,
|
| 2922 |
+
"learning_rate": 1.2430683918669132e-05,
|
| 2923 |
+
"loss": 0.0005,
|
| 2924 |
+
"step": 4060
|
| 2925 |
+
},
|
| 2926 |
+
{
|
| 2927 |
+
"epoch": 3.76,
|
| 2928 |
+
"learning_rate": 1.1968576709796673e-05,
|
| 2929 |
+
"loss": 0.0006,
|
| 2930 |
+
"step": 4070
|
| 2931 |
+
},
|
| 2932 |
+
{
|
| 2933 |
+
"epoch": 3.77,
|
| 2934 |
+
"learning_rate": 1.1506469500924215e-05,
|
| 2935 |
+
"loss": 0.0006,
|
| 2936 |
+
"step": 4080
|
| 2937 |
+
},
|
| 2938 |
+
{
|
| 2939 |
+
"epoch": 3.78,
|
| 2940 |
+
"learning_rate": 1.1044362292051756e-05,
|
| 2941 |
+
"loss": 0.0005,
|
| 2942 |
+
"step": 4090
|
| 2943 |
+
},
|
| 2944 |
+
{
|
| 2945 |
+
"epoch": 3.79,
|
| 2946 |
+
"learning_rate": 1.0582255083179297e-05,
|
| 2947 |
+
"loss": 0.0006,
|
| 2948 |
+
"step": 4100
|
| 2949 |
+
},
|
| 2950 |
+
{
|
| 2951 |
+
"epoch": 3.79,
|
| 2952 |
+
"eval_accuracy": 0.9377242439774475,
|
| 2953 |
+
"eval_f1": 0.9377242439774475,
|
| 2954 |
+
"eval_loss": 0.3234710097312927,
|
| 2955 |
+
"eval_precision": 0.9377242439774475,
|
| 2956 |
+
"eval_recall": 0.9377242439774475,
|
| 2957 |
+
"eval_runtime": 93.455,
|
| 2958 |
+
"eval_samples_per_second": 83.505,
|
| 2959 |
+
"eval_steps_per_second": 10.444,
|
| 2960 |
+
"step": 4100
|
| 2961 |
+
},
|
| 2962 |
+
{
|
| 2963 |
+
"epoch": 3.8,
|
| 2964 |
+
"learning_rate": 1.012014787430684e-05,
|
| 2965 |
+
"loss": 0.0005,
|
| 2966 |
+
"step": 4110
|
| 2967 |
+
},
|
| 2968 |
+
{
|
| 2969 |
+
"epoch": 3.81,
|
| 2970 |
+
"learning_rate": 9.658040665434381e-06,
|
| 2971 |
+
"loss": 0.0005,
|
| 2972 |
+
"step": 4120
|
| 2973 |
+
},
|
| 2974 |
+
{
|
| 2975 |
+
"epoch": 3.82,
|
| 2976 |
+
"learning_rate": 9.195933456561922e-06,
|
| 2977 |
+
"loss": 0.0005,
|
| 2978 |
+
"step": 4130
|
| 2979 |
+
},
|
| 2980 |
+
{
|
| 2981 |
+
"epoch": 3.83,
|
| 2982 |
+
"learning_rate": 8.733826247689465e-06,
|
| 2983 |
+
"loss": 0.0005,
|
| 2984 |
+
"step": 4140
|
| 2985 |
+
},
|
| 2986 |
+
{
|
| 2987 |
+
"epoch": 3.84,
|
| 2988 |
+
"learning_rate": 8.271719038817007e-06,
|
| 2989 |
+
"loss": 0.0005,
|
| 2990 |
+
"step": 4150
|
| 2991 |
+
},
|
| 2992 |
+
{
|
| 2993 |
+
"epoch": 3.84,
|
| 2994 |
+
"learning_rate": 7.809611829944548e-06,
|
| 2995 |
+
"loss": 0.0005,
|
| 2996 |
+
"step": 4160
|
| 2997 |
+
},
|
| 2998 |
+
{
|
| 2999 |
+
"epoch": 3.85,
|
| 3000 |
+
"learning_rate": 7.347504621072089e-06,
|
| 3001 |
+
"loss": 0.0006,
|
| 3002 |
+
"step": 4170
|
| 3003 |
+
},
|
| 3004 |
+
{
|
| 3005 |
+
"epoch": 3.86,
|
| 3006 |
+
"learning_rate": 6.88539741219963e-06,
|
| 3007 |
+
"loss": 0.0005,
|
| 3008 |
+
"step": 4180
|
| 3009 |
+
},
|
| 3010 |
+
{
|
| 3011 |
+
"epoch": 3.87,
|
| 3012 |
+
"learning_rate": 6.423290203327172e-06,
|
| 3013 |
+
"loss": 0.0729,
|
| 3014 |
+
"step": 4190
|
| 3015 |
+
},
|
| 3016 |
+
{
|
| 3017 |
+
"epoch": 3.88,
|
| 3018 |
+
"learning_rate": 5.961182994454713e-06,
|
| 3019 |
+
"loss": 0.0354,
|
| 3020 |
+
"step": 4200
|
| 3021 |
+
},
|
| 3022 |
+
{
|
| 3023 |
+
"epoch": 3.88,
|
| 3024 |
+
"eval_accuracy": 0.9356740133264992,
|
| 3025 |
+
"eval_f1": 0.9356740133264994,
|
| 3026 |
+
"eval_loss": 0.326831191778183,
|
| 3027 |
+
"eval_precision": 0.9356740133264992,
|
| 3028 |
+
"eval_recall": 0.9356740133264992,
|
| 3029 |
+
"eval_runtime": 94.0495,
|
| 3030 |
+
"eval_samples_per_second": 82.978,
|
| 3031 |
+
"eval_steps_per_second": 10.378,
|
| 3032 |
+
"step": 4200
|
| 3033 |
+
},
|
| 3034 |
+
{
|
| 3035 |
+
"epoch": 3.89,
|
| 3036 |
+
"learning_rate": 5.499075785582256e-06,
|
| 3037 |
+
"loss": 0.0007,
|
| 3038 |
+
"step": 4210
|
| 3039 |
+
},
|
| 3040 |
+
{
|
| 3041 |
+
"epoch": 3.9,
|
| 3042 |
+
"learning_rate": 5.036968576709796e-06,
|
| 3043 |
+
"loss": 0.0009,
|
| 3044 |
+
"step": 4220
|
| 3045 |
+
},
|
| 3046 |
+
{
|
| 3047 |
+
"epoch": 3.91,
|
| 3048 |
+
"learning_rate": 4.574861367837339e-06,
|
| 3049 |
+
"loss": 0.0007,
|
| 3050 |
+
"step": 4230
|
| 3051 |
+
},
|
| 3052 |
+
{
|
| 3053 |
+
"epoch": 3.92,
|
| 3054 |
+
"learning_rate": 4.11275415896488e-06,
|
| 3055 |
+
"loss": 0.0007,
|
| 3056 |
+
"step": 4240
|
| 3057 |
+
},
|
| 3058 |
+
{
|
| 3059 |
+
"epoch": 3.93,
|
| 3060 |
+
"learning_rate": 3.650646950092421e-06,
|
| 3061 |
+
"loss": 0.0008,
|
| 3062 |
+
"step": 4250
|
| 3063 |
+
},
|
| 3064 |
+
{
|
| 3065 |
+
"epoch": 3.94,
|
| 3066 |
+
"learning_rate": 3.188539741219963e-06,
|
| 3067 |
+
"loss": 0.0007,
|
| 3068 |
+
"step": 4260
|
| 3069 |
+
},
|
| 3070 |
+
{
|
| 3071 |
+
"epoch": 3.95,
|
| 3072 |
+
"learning_rate": 2.7264325323475047e-06,
|
| 3073 |
+
"loss": 0.0007,
|
| 3074 |
+
"step": 4270
|
| 3075 |
+
},
|
| 3076 |
+
{
|
| 3077 |
+
"epoch": 3.96,
|
| 3078 |
+
"learning_rate": 2.2643253234750463e-06,
|
| 3079 |
+
"loss": 0.0037,
|
| 3080 |
+
"step": 4280
|
| 3081 |
+
},
|
| 3082 |
+
{
|
| 3083 |
+
"epoch": 3.96,
|
| 3084 |
+
"learning_rate": 1.8022181146025879e-06,
|
| 3085 |
+
"loss": 0.0007,
|
| 3086 |
+
"step": 4290
|
| 3087 |
+
},
|
| 3088 |
+
{
|
| 3089 |
+
"epoch": 3.97,
|
| 3090 |
+
"learning_rate": 1.3401109057301294e-06,
|
| 3091 |
+
"loss": 0.0328,
|
| 3092 |
+
"step": 4300
|
| 3093 |
+
},
|
| 3094 |
+
{
|
| 3095 |
+
"epoch": 3.97,
|
| 3096 |
+
"eval_accuracy": 0.9358021527421835,
|
| 3097 |
+
"eval_f1": 0.9358021527421835,
|
| 3098 |
+
"eval_loss": 0.3264217674732208,
|
| 3099 |
+
"eval_precision": 0.9358021527421835,
|
| 3100 |
+
"eval_recall": 0.9358021527421835,
|
| 3101 |
+
"eval_runtime": 94.2652,
|
| 3102 |
+
"eval_samples_per_second": 82.788,
|
| 3103 |
+
"eval_steps_per_second": 10.354,
|
| 3104 |
+
"step": 4300
|
| 3105 |
+
},
|
| 3106 |
+
{
|
| 3107 |
+
"epoch": 3.98,
|
| 3108 |
+
"learning_rate": 8.78003696857671e-07,
|
| 3109 |
+
"loss": 0.0008,
|
| 3110 |
+
"step": 4310
|
| 3111 |
+
},
|
| 3112 |
+
{
|
| 3113 |
+
"epoch": 3.99,
|
| 3114 |
+
"learning_rate": 4.158964879852126e-07,
|
| 3115 |
+
"loss": 0.0006,
|
| 3116 |
+
"step": 4320
|
| 3117 |
+
},
|
| 3118 |
+
{
|
| 3119 |
+
"epoch": 4.0,
|
| 3120 |
+
"step": 4328,
|
| 3121 |
+
"total_flos": 3.943158668110371e+19,
|
| 3122 |
+
"train_loss": 0.07091429132740952,
|
| 3123 |
+
"train_runtime": 8488.5621,
|
| 3124 |
+
"train_samples_per_second": 8.154,
|
| 3125 |
+
"train_steps_per_second": 0.51
|
| 3126 |
+
}
|
| 3127 |
+
],
|
| 3128 |
+
"max_steps": 4328,
|
| 3129 |
+
"num_train_epochs": 4,
|
| 3130 |
+
"total_flos": 3.943158668110371e+19,
|
| 3131 |
+
"trial_name": null,
|
| 3132 |
+
"trial_params": null
|
| 3133 |
+
}
|