🍻 cheers
Browse files- all_results.json +12 -0
- eval_results.json +8 -0
- runs/Jun30_21-42-57_bernard/events.out.tfevents.1656623935.bernard.1891493.2 +3 -0
- train_results.json +7 -0
- trainer_state.json +3550 -0
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 8.0,
|
| 3 |
+
"eval_accuracy": 0.9298380878951427,
|
| 4 |
+
"eval_loss": 0.3000366985797882,
|
| 5 |
+
"eval_runtime": 43.3065,
|
| 6 |
+
"eval_samples_per_second": 59.899,
|
| 7 |
+
"eval_steps_per_second": 7.505,
|
| 8 |
+
"train_loss": 0.5634685837152139,
|
| 9 |
+
"train_runtime": 5666.239,
|
| 10 |
+
"train_samples_per_second": 14.415,
|
| 11 |
+
"train_steps_per_second": 0.902
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 8.0,
|
| 3 |
+
"eval_accuracy": 0.9298380878951427,
|
| 4 |
+
"eval_loss": 0.3000366985797882,
|
| 5 |
+
"eval_runtime": 43.3065,
|
| 6 |
+
"eval_samples_per_second": 59.899,
|
| 7 |
+
"eval_steps_per_second": 7.505
|
| 8 |
+
}
|
runs/Jun30_21-42-57_bernard/events.out.tfevents.1656623935.bernard.1891493.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:19e3cfd1d1a43a342697d644f09fc6a91e05a0093eb55be5be3b8175ec10a598
|
| 3 |
+
size 363
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 8.0,
|
| 3 |
+
"train_loss": 0.5634685837152139,
|
| 4 |
+
"train_runtime": 5666.239,
|
| 5 |
+
"train_samples_per_second": 14.415,
|
| 6 |
+
"train_steps_per_second": 0.902
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,3550 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.3000366985797882,
|
| 3 |
+
"best_model_checkpoint": "./new_exper3/checkpoint-4200",
|
| 4 |
+
"epoch": 8.0,
|
| 5 |
+
"global_step": 5112,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.02,
|
| 12 |
+
"learning_rate": 9.980438184663537e-05,
|
| 13 |
+
"loss": 4.9498,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.03,
|
| 18 |
+
"learning_rate": 9.960876369327074e-05,
|
| 19 |
+
"loss": 4.8556,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.05,
|
| 24 |
+
"learning_rate": 9.94131455399061e-05,
|
| 25 |
+
"loss": 4.7389,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.06,
|
| 30 |
+
"learning_rate": 9.921752738654147e-05,
|
| 31 |
+
"loss": 4.6112,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.08,
|
| 36 |
+
"learning_rate": 9.902190923317684e-05,
|
| 37 |
+
"loss": 4.54,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.09,
|
| 42 |
+
"learning_rate": 9.882629107981222e-05,
|
| 43 |
+
"loss": 4.448,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.11,
|
| 48 |
+
"learning_rate": 9.863067292644758e-05,
|
| 49 |
+
"loss": 4.3441,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.13,
|
| 54 |
+
"learning_rate": 9.843505477308295e-05,
|
| 55 |
+
"loss": 4.2899,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.14,
|
| 60 |
+
"learning_rate": 9.823943661971832e-05,
|
| 61 |
+
"loss": 4.2878,
|
| 62 |
+
"step": 90
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.16,
|
| 66 |
+
"learning_rate": 9.804381846635369e-05,
|
| 67 |
+
"loss": 4.093,
|
| 68 |
+
"step": 100
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.16,
|
| 72 |
+
"eval_accuracy": 0.18851195065535853,
|
| 73 |
+
"eval_loss": 4.104459285736084,
|
| 74 |
+
"eval_runtime": 43.0936,
|
| 75 |
+
"eval_samples_per_second": 60.195,
|
| 76 |
+
"eval_steps_per_second": 7.542,
|
| 77 |
+
"step": 100
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 0.17,
|
| 81 |
+
"learning_rate": 9.784820031298904e-05,
|
| 82 |
+
"loss": 4.1228,
|
| 83 |
+
"step": 110
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 0.19,
|
| 87 |
+
"learning_rate": 9.765258215962441e-05,
|
| 88 |
+
"loss": 4.0244,
|
| 89 |
+
"step": 120
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.2,
|
| 93 |
+
"learning_rate": 9.745696400625978e-05,
|
| 94 |
+
"loss": 3.9376,
|
| 95 |
+
"step": 130
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.22,
|
| 99 |
+
"learning_rate": 9.726134585289515e-05,
|
| 100 |
+
"loss": 3.7948,
|
| 101 |
+
"step": 140
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.23,
|
| 105 |
+
"learning_rate": 9.706572769953052e-05,
|
| 106 |
+
"loss": 3.8001,
|
| 107 |
+
"step": 150
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.25,
|
| 111 |
+
"learning_rate": 9.687010954616589e-05,
|
| 112 |
+
"loss": 3.7539,
|
| 113 |
+
"step": 160
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.27,
|
| 117 |
+
"learning_rate": 9.667449139280126e-05,
|
| 118 |
+
"loss": 3.6066,
|
| 119 |
+
"step": 170
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 0.28,
|
| 123 |
+
"learning_rate": 9.647887323943663e-05,
|
| 124 |
+
"loss": 3.5595,
|
| 125 |
+
"step": 180
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 0.3,
|
| 129 |
+
"learning_rate": 9.628325508607199e-05,
|
| 130 |
+
"loss": 3.4972,
|
| 131 |
+
"step": 190
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 0.31,
|
| 135 |
+
"learning_rate": 9.608763693270736e-05,
|
| 136 |
+
"loss": 3.5057,
|
| 137 |
+
"step": 200
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.31,
|
| 141 |
+
"eval_accuracy": 0.323053199691596,
|
| 142 |
+
"eval_loss": 3.444770336151123,
|
| 143 |
+
"eval_runtime": 43.0641,
|
| 144 |
+
"eval_samples_per_second": 60.236,
|
| 145 |
+
"eval_steps_per_second": 7.547,
|
| 146 |
+
"step": 200
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.33,
|
| 150 |
+
"learning_rate": 9.589201877934273e-05,
|
| 151 |
+
"loss": 3.3105,
|
| 152 |
+
"step": 210
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.34,
|
| 156 |
+
"learning_rate": 9.56964006259781e-05,
|
| 157 |
+
"loss": 3.4108,
|
| 158 |
+
"step": 220
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.36,
|
| 162 |
+
"learning_rate": 9.550078247261345e-05,
|
| 163 |
+
"loss": 3.4285,
|
| 164 |
+
"step": 230
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.38,
|
| 168 |
+
"learning_rate": 9.530516431924882e-05,
|
| 169 |
+
"loss": 3.213,
|
| 170 |
+
"step": 240
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.39,
|
| 174 |
+
"learning_rate": 9.510954616588421e-05,
|
| 175 |
+
"loss": 3.1473,
|
| 176 |
+
"step": 250
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.41,
|
| 180 |
+
"learning_rate": 9.491392801251958e-05,
|
| 181 |
+
"loss": 3.1898,
|
| 182 |
+
"step": 260
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.42,
|
| 186 |
+
"learning_rate": 9.471830985915493e-05,
|
| 187 |
+
"loss": 3.1523,
|
| 188 |
+
"step": 270
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.44,
|
| 192 |
+
"learning_rate": 9.45226917057903e-05,
|
| 193 |
+
"loss": 3.186,
|
| 194 |
+
"step": 280
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.45,
|
| 198 |
+
"learning_rate": 9.432707355242567e-05,
|
| 199 |
+
"loss": 2.9603,
|
| 200 |
+
"step": 290
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.47,
|
| 204 |
+
"learning_rate": 9.413145539906104e-05,
|
| 205 |
+
"loss": 2.9116,
|
| 206 |
+
"step": 300
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.47,
|
| 210 |
+
"eval_accuracy": 0.45373939861218193,
|
| 211 |
+
"eval_loss": 2.9483001232147217,
|
| 212 |
+
"eval_runtime": 42.4599,
|
| 213 |
+
"eval_samples_per_second": 61.093,
|
| 214 |
+
"eval_steps_per_second": 7.654,
|
| 215 |
+
"step": 300
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 0.49,
|
| 219 |
+
"learning_rate": 9.39358372456964e-05,
|
| 220 |
+
"loss": 3.0387,
|
| 221 |
+
"step": 310
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 0.5,
|
| 225 |
+
"learning_rate": 9.374021909233177e-05,
|
| 226 |
+
"loss": 2.8818,
|
| 227 |
+
"step": 320
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.52,
|
| 231 |
+
"learning_rate": 9.354460093896714e-05,
|
| 232 |
+
"loss": 2.9362,
|
| 233 |
+
"step": 330
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.53,
|
| 237 |
+
"learning_rate": 9.334898278560251e-05,
|
| 238 |
+
"loss": 2.9021,
|
| 239 |
+
"step": 340
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 0.55,
|
| 243 |
+
"learning_rate": 9.315336463223788e-05,
|
| 244 |
+
"loss": 2.7243,
|
| 245 |
+
"step": 350
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 0.56,
|
| 249 |
+
"learning_rate": 9.295774647887325e-05,
|
| 250 |
+
"loss": 2.6124,
|
| 251 |
+
"step": 360
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 0.58,
|
| 255 |
+
"learning_rate": 9.276212832550862e-05,
|
| 256 |
+
"loss": 2.6288,
|
| 257 |
+
"step": 370
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 0.59,
|
| 261 |
+
"learning_rate": 9.256651017214399e-05,
|
| 262 |
+
"loss": 2.6455,
|
| 263 |
+
"step": 380
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 0.61,
|
| 267 |
+
"learning_rate": 9.237089201877934e-05,
|
| 268 |
+
"loss": 2.6136,
|
| 269 |
+
"step": 390
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.63,
|
| 273 |
+
"learning_rate": 9.217527386541471e-05,
|
| 274 |
+
"loss": 2.561,
|
| 275 |
+
"step": 400
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.63,
|
| 279 |
+
"eval_accuracy": 0.525828835774865,
|
| 280 |
+
"eval_loss": 2.5700132846832275,
|
| 281 |
+
"eval_runtime": 42.7904,
|
| 282 |
+
"eval_samples_per_second": 60.621,
|
| 283 |
+
"eval_steps_per_second": 7.595,
|
| 284 |
+
"step": 400
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 0.64,
|
| 288 |
+
"learning_rate": 9.197965571205008e-05,
|
| 289 |
+
"loss": 2.5745,
|
| 290 |
+
"step": 410
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.66,
|
| 294 |
+
"learning_rate": 9.178403755868545e-05,
|
| 295 |
+
"loss": 2.5422,
|
| 296 |
+
"step": 420
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.67,
|
| 300 |
+
"learning_rate": 9.158841940532081e-05,
|
| 301 |
+
"loss": 2.4631,
|
| 302 |
+
"step": 430
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.69,
|
| 306 |
+
"learning_rate": 9.139280125195618e-05,
|
| 307 |
+
"loss": 2.3095,
|
| 308 |
+
"step": 440
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 0.7,
|
| 312 |
+
"learning_rate": 9.119718309859156e-05,
|
| 313 |
+
"loss": 2.3756,
|
| 314 |
+
"step": 450
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.72,
|
| 318 |
+
"learning_rate": 9.100156494522693e-05,
|
| 319 |
+
"loss": 2.485,
|
| 320 |
+
"step": 460
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 0.74,
|
| 324 |
+
"learning_rate": 9.080594679186229e-05,
|
| 325 |
+
"loss": 2.3036,
|
| 326 |
+
"step": 470
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 0.75,
|
| 330 |
+
"learning_rate": 9.061032863849766e-05,
|
| 331 |
+
"loss": 2.2608,
|
| 332 |
+
"step": 480
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.77,
|
| 336 |
+
"learning_rate": 9.041471048513303e-05,
|
| 337 |
+
"loss": 2.296,
|
| 338 |
+
"step": 490
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.78,
|
| 342 |
+
"learning_rate": 9.02190923317684e-05,
|
| 343 |
+
"loss": 2.1611,
|
| 344 |
+
"step": 500
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 0.78,
|
| 348 |
+
"eval_accuracy": 0.6144949884348496,
|
| 349 |
+
"eval_loss": 2.172065258026123,
|
| 350 |
+
"eval_runtime": 42.9818,
|
| 351 |
+
"eval_samples_per_second": 60.351,
|
| 352 |
+
"eval_steps_per_second": 7.561,
|
| 353 |
+
"step": 500
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.8,
|
| 357 |
+
"learning_rate": 9.002347417840375e-05,
|
| 358 |
+
"loss": 2.0372,
|
| 359 |
+
"step": 510
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.81,
|
| 363 |
+
"learning_rate": 8.982785602503912e-05,
|
| 364 |
+
"loss": 2.0652,
|
| 365 |
+
"step": 520
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 0.83,
|
| 369 |
+
"learning_rate": 8.963223787167449e-05,
|
| 370 |
+
"loss": 2.1529,
|
| 371 |
+
"step": 530
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 0.85,
|
| 375 |
+
"learning_rate": 8.943661971830986e-05,
|
| 376 |
+
"loss": 1.9779,
|
| 377 |
+
"step": 540
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 0.86,
|
| 381 |
+
"learning_rate": 8.924100156494523e-05,
|
| 382 |
+
"loss": 1.9492,
|
| 383 |
+
"step": 550
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 0.88,
|
| 387 |
+
"learning_rate": 8.90453834115806e-05,
|
| 388 |
+
"loss": 1.9624,
|
| 389 |
+
"step": 560
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.89,
|
| 393 |
+
"learning_rate": 8.884976525821597e-05,
|
| 394 |
+
"loss": 1.8139,
|
| 395 |
+
"step": 570
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.91,
|
| 399 |
+
"learning_rate": 8.865414710485134e-05,
|
| 400 |
+
"loss": 1.9124,
|
| 401 |
+
"step": 580
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.92,
|
| 405 |
+
"learning_rate": 8.845852895148671e-05,
|
| 406 |
+
"loss": 1.7514,
|
| 407 |
+
"step": 590
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 0.94,
|
| 411 |
+
"learning_rate": 8.826291079812207e-05,
|
| 412 |
+
"loss": 1.715,
|
| 413 |
+
"step": 600
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 0.94,
|
| 417 |
+
"eval_accuracy": 0.6407093292212799,
|
| 418 |
+
"eval_loss": 1.8254655599594116,
|
| 419 |
+
"eval_runtime": 42.9275,
|
| 420 |
+
"eval_samples_per_second": 60.428,
|
| 421 |
+
"eval_steps_per_second": 7.571,
|
| 422 |
+
"step": 600
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.95,
|
| 426 |
+
"learning_rate": 8.806729264475744e-05,
|
| 427 |
+
"loss": 1.864,
|
| 428 |
+
"step": 610
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 0.97,
|
| 432 |
+
"learning_rate": 8.78716744913928e-05,
|
| 433 |
+
"loss": 1.8157,
|
| 434 |
+
"step": 620
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 0.99,
|
| 438 |
+
"learning_rate": 8.767605633802817e-05,
|
| 439 |
+
"loss": 1.8333,
|
| 440 |
+
"step": 630
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 1.0,
|
| 444 |
+
"learning_rate": 8.748043818466354e-05,
|
| 445 |
+
"loss": 1.6364,
|
| 446 |
+
"step": 640
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 1.02,
|
| 450 |
+
"learning_rate": 8.728482003129891e-05,
|
| 451 |
+
"loss": 1.5205,
|
| 452 |
+
"step": 650
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 1.03,
|
| 456 |
+
"learning_rate": 8.708920187793428e-05,
|
| 457 |
+
"loss": 1.5193,
|
| 458 |
+
"step": 660
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.05,
|
| 462 |
+
"learning_rate": 8.689358372456965e-05,
|
| 463 |
+
"loss": 1.5602,
|
| 464 |
+
"step": 670
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 1.06,
|
| 468 |
+
"learning_rate": 8.669796557120501e-05,
|
| 469 |
+
"loss": 1.3509,
|
| 470 |
+
"step": 680
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 1.08,
|
| 474 |
+
"learning_rate": 8.650234741784038e-05,
|
| 475 |
+
"loss": 1.408,
|
| 476 |
+
"step": 690
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 1.1,
|
| 480 |
+
"learning_rate": 8.630672926447575e-05,
|
| 481 |
+
"loss": 1.2752,
|
| 482 |
+
"step": 700
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 1.1,
|
| 486 |
+
"eval_accuracy": 0.70508866615266,
|
| 487 |
+
"eval_loss": 1.5340100526809692,
|
| 488 |
+
"eval_runtime": 42.6015,
|
| 489 |
+
"eval_samples_per_second": 60.89,
|
| 490 |
+
"eval_steps_per_second": 7.629,
|
| 491 |
+
"step": 700
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 1.11,
|
| 495 |
+
"learning_rate": 8.611111111111112e-05,
|
| 496 |
+
"loss": 1.184,
|
| 497 |
+
"step": 710
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 1.13,
|
| 501 |
+
"learning_rate": 8.591549295774647e-05,
|
| 502 |
+
"loss": 1.284,
|
| 503 |
+
"step": 720
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 1.14,
|
| 507 |
+
"learning_rate": 8.571987480438184e-05,
|
| 508 |
+
"loss": 1.2331,
|
| 509 |
+
"step": 730
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 1.16,
|
| 513 |
+
"learning_rate": 8.552425665101721e-05,
|
| 514 |
+
"loss": 1.2059,
|
| 515 |
+
"step": 740
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 1.17,
|
| 519 |
+
"learning_rate": 8.53286384976526e-05,
|
| 520 |
+
"loss": 1.3036,
|
| 521 |
+
"step": 750
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.19,
|
| 525 |
+
"learning_rate": 8.513302034428795e-05,
|
| 526 |
+
"loss": 1.2848,
|
| 527 |
+
"step": 760
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 1.21,
|
| 531 |
+
"learning_rate": 8.493740219092332e-05,
|
| 532 |
+
"loss": 1.073,
|
| 533 |
+
"step": 770
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 1.22,
|
| 537 |
+
"learning_rate": 8.474178403755869e-05,
|
| 538 |
+
"loss": 1.4211,
|
| 539 |
+
"step": 780
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 1.24,
|
| 543 |
+
"learning_rate": 8.454616588419406e-05,
|
| 544 |
+
"loss": 1.067,
|
| 545 |
+
"step": 790
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 1.25,
|
| 549 |
+
"learning_rate": 8.435054773082942e-05,
|
| 550 |
+
"loss": 1.2487,
|
| 551 |
+
"step": 800
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 1.25,
|
| 555 |
+
"eval_accuracy": 0.7201233616037008,
|
| 556 |
+
"eval_loss": 1.353263258934021,
|
| 557 |
+
"eval_runtime": 42.5111,
|
| 558 |
+
"eval_samples_per_second": 61.019,
|
| 559 |
+
"eval_steps_per_second": 7.645,
|
| 560 |
+
"step": 800
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 1.27,
|
| 564 |
+
"learning_rate": 8.415492957746479e-05,
|
| 565 |
+
"loss": 1.2377,
|
| 566 |
+
"step": 810
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 1.28,
|
| 570 |
+
"learning_rate": 8.395931142410016e-05,
|
| 571 |
+
"loss": 1.1797,
|
| 572 |
+
"step": 820
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 1.3,
|
| 576 |
+
"learning_rate": 8.376369327073553e-05,
|
| 577 |
+
"loss": 1.2482,
|
| 578 |
+
"step": 830
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 1.31,
|
| 582 |
+
"learning_rate": 8.35680751173709e-05,
|
| 583 |
+
"loss": 1.0641,
|
| 584 |
+
"step": 840
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 1.33,
|
| 588 |
+
"learning_rate": 8.337245696400627e-05,
|
| 589 |
+
"loss": 1.14,
|
| 590 |
+
"step": 850
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 1.35,
|
| 594 |
+
"learning_rate": 8.317683881064164e-05,
|
| 595 |
+
"loss": 1.1587,
|
| 596 |
+
"step": 860
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 1.36,
|
| 600 |
+
"learning_rate": 8.298122065727701e-05,
|
| 601 |
+
"loss": 1.1029,
|
| 602 |
+
"step": 870
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 1.38,
|
| 606 |
+
"learning_rate": 8.278560250391236e-05,
|
| 607 |
+
"loss": 0.9988,
|
| 608 |
+
"step": 880
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 1.39,
|
| 612 |
+
"learning_rate": 8.258998435054773e-05,
|
| 613 |
+
"loss": 1.0692,
|
| 614 |
+
"step": 890
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 1.41,
|
| 618 |
+
"learning_rate": 8.23943661971831e-05,
|
| 619 |
+
"loss": 1.0333,
|
| 620 |
+
"step": 900
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 1.41,
|
| 624 |
+
"eval_accuracy": 0.7825751734772552,
|
| 625 |
+
"eval_loss": 1.1474497318267822,
|
| 626 |
+
"eval_runtime": 43.2872,
|
| 627 |
+
"eval_samples_per_second": 59.925,
|
| 628 |
+
"eval_steps_per_second": 7.508,
|
| 629 |
+
"step": 900
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 1.42,
|
| 633 |
+
"learning_rate": 8.219874804381847e-05,
|
| 634 |
+
"loss": 1.0357,
|
| 635 |
+
"step": 910
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 1.44,
|
| 639 |
+
"learning_rate": 8.200312989045383e-05,
|
| 640 |
+
"loss": 0.8625,
|
| 641 |
+
"step": 920
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 1.46,
|
| 645 |
+
"learning_rate": 8.18075117370892e-05,
|
| 646 |
+
"loss": 1.0712,
|
| 647 |
+
"step": 930
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 1.47,
|
| 651 |
+
"learning_rate": 8.161189358372458e-05,
|
| 652 |
+
"loss": 1.1329,
|
| 653 |
+
"step": 940
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 1.49,
|
| 657 |
+
"learning_rate": 8.141627543035995e-05,
|
| 658 |
+
"loss": 1.0017,
|
| 659 |
+
"step": 950
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 1.5,
|
| 663 |
+
"learning_rate": 8.122065727699531e-05,
|
| 664 |
+
"loss": 1.1086,
|
| 665 |
+
"step": 960
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 1.52,
|
| 669 |
+
"learning_rate": 8.102503912363068e-05,
|
| 670 |
+
"loss": 0.8891,
|
| 671 |
+
"step": 970
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 1.53,
|
| 675 |
+
"learning_rate": 8.082942097026605e-05,
|
| 676 |
+
"loss": 0.8059,
|
| 677 |
+
"step": 980
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 1.55,
|
| 681 |
+
"learning_rate": 8.063380281690142e-05,
|
| 682 |
+
"loss": 1.0192,
|
| 683 |
+
"step": 990
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 1.56,
|
| 687 |
+
"learning_rate": 8.043818466353677e-05,
|
| 688 |
+
"loss": 0.8856,
|
| 689 |
+
"step": 1000
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.56,
|
| 693 |
+
"eval_accuracy": 0.7644564379336931,
|
| 694 |
+
"eval_loss": 1.0914219617843628,
|
| 695 |
+
"eval_runtime": 42.8447,
|
| 696 |
+
"eval_samples_per_second": 60.544,
|
| 697 |
+
"eval_steps_per_second": 7.586,
|
| 698 |
+
"step": 1000
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 1.58,
|
| 702 |
+
"learning_rate": 8.024256651017214e-05,
|
| 703 |
+
"loss": 0.911,
|
| 704 |
+
"step": 1010
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 1.6,
|
| 708 |
+
"learning_rate": 8.004694835680751e-05,
|
| 709 |
+
"loss": 0.8939,
|
| 710 |
+
"step": 1020
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 1.61,
|
| 714 |
+
"learning_rate": 7.985133020344288e-05,
|
| 715 |
+
"loss": 0.7816,
|
| 716 |
+
"step": 1030
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 1.63,
|
| 720 |
+
"learning_rate": 7.965571205007825e-05,
|
| 721 |
+
"loss": 0.8397,
|
| 722 |
+
"step": 1040
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 1.64,
|
| 726 |
+
"learning_rate": 7.946009389671362e-05,
|
| 727 |
+
"loss": 0.8172,
|
| 728 |
+
"step": 1050
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 1.66,
|
| 732 |
+
"learning_rate": 7.926447574334899e-05,
|
| 733 |
+
"loss": 0.7408,
|
| 734 |
+
"step": 1060
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 1.67,
|
| 738 |
+
"learning_rate": 7.906885758998436e-05,
|
| 739 |
+
"loss": 0.6926,
|
| 740 |
+
"step": 1070
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 1.69,
|
| 744 |
+
"learning_rate": 7.887323943661972e-05,
|
| 745 |
+
"loss": 0.8984,
|
| 746 |
+
"step": 1080
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 1.71,
|
| 750 |
+
"learning_rate": 7.867762128325509e-05,
|
| 751 |
+
"loss": 0.7221,
|
| 752 |
+
"step": 1090
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 1.72,
|
| 756 |
+
"learning_rate": 7.848200312989046e-05,
|
| 757 |
+
"loss": 0.7512,
|
| 758 |
+
"step": 1100
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 1.72,
|
| 762 |
+
"eval_accuracy": 0.8118735543562067,
|
| 763 |
+
"eval_loss": 0.8893365263938904,
|
| 764 |
+
"eval_runtime": 42.2991,
|
| 765 |
+
"eval_samples_per_second": 61.325,
|
| 766 |
+
"eval_steps_per_second": 7.683,
|
| 767 |
+
"step": 1100
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 1.74,
|
| 771 |
+
"learning_rate": 7.828638497652583e-05,
|
| 772 |
+
"loss": 0.7297,
|
| 773 |
+
"step": 1110
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 1.75,
|
| 777 |
+
"learning_rate": 7.809076682316118e-05,
|
| 778 |
+
"loss": 0.6638,
|
| 779 |
+
"step": 1120
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 1.77,
|
| 783 |
+
"learning_rate": 7.789514866979655e-05,
|
| 784 |
+
"loss": 0.7419,
|
| 785 |
+
"step": 1130
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 1.78,
|
| 789 |
+
"learning_rate": 7.769953051643193e-05,
|
| 790 |
+
"loss": 0.7263,
|
| 791 |
+
"step": 1140
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 1.8,
|
| 795 |
+
"learning_rate": 7.75039123630673e-05,
|
| 796 |
+
"loss": 0.6707,
|
| 797 |
+
"step": 1150
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 1.82,
|
| 801 |
+
"learning_rate": 7.730829420970266e-05,
|
| 802 |
+
"loss": 0.7675,
|
| 803 |
+
"step": 1160
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 1.83,
|
| 807 |
+
"learning_rate": 7.711267605633803e-05,
|
| 808 |
+
"loss": 0.9189,
|
| 809 |
+
"step": 1170
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 1.85,
|
| 813 |
+
"learning_rate": 7.69170579029734e-05,
|
| 814 |
+
"loss": 0.5663,
|
| 815 |
+
"step": 1180
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 1.86,
|
| 819 |
+
"learning_rate": 7.672143974960877e-05,
|
| 820 |
+
"loss": 0.679,
|
| 821 |
+
"step": 1190
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 1.88,
|
| 825 |
+
"learning_rate": 7.652582159624414e-05,
|
| 826 |
+
"loss": 0.747,
|
| 827 |
+
"step": 1200
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 1.88,
|
| 831 |
+
"eval_accuracy": 0.8303777949113339,
|
| 832 |
+
"eval_loss": 0.8370148539543152,
|
| 833 |
+
"eval_runtime": 42.5695,
|
| 834 |
+
"eval_samples_per_second": 60.936,
|
| 835 |
+
"eval_steps_per_second": 7.635,
|
| 836 |
+
"step": 1200
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 1.89,
|
| 840 |
+
"learning_rate": 7.63302034428795e-05,
|
| 841 |
+
"loss": 0.8146,
|
| 842 |
+
"step": 1210
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 1.91,
|
| 846 |
+
"learning_rate": 7.613458528951487e-05,
|
| 847 |
+
"loss": 0.715,
|
| 848 |
+
"step": 1220
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 1.92,
|
| 852 |
+
"learning_rate": 7.593896713615024e-05,
|
| 853 |
+
"loss": 0.8337,
|
| 854 |
+
"step": 1230
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 1.94,
|
| 858 |
+
"learning_rate": 7.57433489827856e-05,
|
| 859 |
+
"loss": 0.6553,
|
| 860 |
+
"step": 1240
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 1.96,
|
| 864 |
+
"learning_rate": 7.554773082942097e-05,
|
| 865 |
+
"loss": 0.7805,
|
| 866 |
+
"step": 1250
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 1.97,
|
| 870 |
+
"learning_rate": 7.535211267605634e-05,
|
| 871 |
+
"loss": 0.6115,
|
| 872 |
+
"step": 1260
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 1.99,
|
| 876 |
+
"learning_rate": 7.515649452269171e-05,
|
| 877 |
+
"loss": 0.7046,
|
| 878 |
+
"step": 1270
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 2.0,
|
| 882 |
+
"learning_rate": 7.496087636932708e-05,
|
| 883 |
+
"loss": 0.551,
|
| 884 |
+
"step": 1280
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 2.02,
|
| 888 |
+
"learning_rate": 7.476525821596244e-05,
|
| 889 |
+
"loss": 0.4497,
|
| 890 |
+
"step": 1290
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 2.03,
|
| 894 |
+
"learning_rate": 7.456964006259781e-05,
|
| 895 |
+
"loss": 0.5082,
|
| 896 |
+
"step": 1300
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 2.03,
|
| 900 |
+
"eval_accuracy": 0.856592135697764,
|
| 901 |
+
"eval_loss": 0.7130723595619202,
|
| 902 |
+
"eval_runtime": 43.188,
|
| 903 |
+
"eval_samples_per_second": 60.063,
|
| 904 |
+
"eval_steps_per_second": 7.525,
|
| 905 |
+
"step": 1300
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 2.05,
|
| 909 |
+
"learning_rate": 7.437402190923318e-05,
|
| 910 |
+
"loss": 0.347,
|
| 911 |
+
"step": 1310
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 2.07,
|
| 915 |
+
"learning_rate": 7.417840375586855e-05,
|
| 916 |
+
"loss": 0.463,
|
| 917 |
+
"step": 1320
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 2.08,
|
| 921 |
+
"learning_rate": 7.398278560250392e-05,
|
| 922 |
+
"loss": 0.4014,
|
| 923 |
+
"step": 1330
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 2.1,
|
| 927 |
+
"learning_rate": 7.378716744913929e-05,
|
| 928 |
+
"loss": 0.488,
|
| 929 |
+
"step": 1340
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 2.11,
|
| 933 |
+
"learning_rate": 7.359154929577466e-05,
|
| 934 |
+
"loss": 0.4239,
|
| 935 |
+
"step": 1350
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 2.13,
|
| 939 |
+
"learning_rate": 7.339593114241003e-05,
|
| 940 |
+
"loss": 0.4246,
|
| 941 |
+
"step": 1360
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 2.14,
|
| 945 |
+
"learning_rate": 7.320031298904538e-05,
|
| 946 |
+
"loss": 0.3698,
|
| 947 |
+
"step": 1370
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 2.16,
|
| 951 |
+
"learning_rate": 7.300469483568075e-05,
|
| 952 |
+
"loss": 0.4264,
|
| 953 |
+
"step": 1380
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 2.18,
|
| 957 |
+
"learning_rate": 7.280907668231612e-05,
|
| 958 |
+
"loss": 0.3167,
|
| 959 |
+
"step": 1390
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 2.19,
|
| 963 |
+
"learning_rate": 7.261345852895149e-05,
|
| 964 |
+
"loss": 0.4449,
|
| 965 |
+
"step": 1400
|
| 966 |
+
},
|
| 967 |
+
{
|
| 968 |
+
"epoch": 2.19,
|
| 969 |
+
"eval_accuracy": 0.8546646106399384,
|
| 970 |
+
"eval_loss": 0.6572707295417786,
|
| 971 |
+
"eval_runtime": 43.2163,
|
| 972 |
+
"eval_samples_per_second": 60.024,
|
| 973 |
+
"eval_steps_per_second": 7.52,
|
| 974 |
+
"step": 1400
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 2.21,
|
| 978 |
+
"learning_rate": 7.241784037558685e-05,
|
| 979 |
+
"loss": 0.3504,
|
| 980 |
+
"step": 1410
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 2.22,
|
| 984 |
+
"learning_rate": 7.222222222222222e-05,
|
| 985 |
+
"loss": 0.397,
|
| 986 |
+
"step": 1420
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 2.24,
|
| 990 |
+
"learning_rate": 7.202660406885759e-05,
|
| 991 |
+
"loss": 0.4599,
|
| 992 |
+
"step": 1430
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 2.25,
|
| 996 |
+
"learning_rate": 7.183098591549297e-05,
|
| 997 |
+
"loss": 0.4151,
|
| 998 |
+
"step": 1440
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 2.27,
|
| 1002 |
+
"learning_rate": 7.163536776212833e-05,
|
| 1003 |
+
"loss": 0.3605,
|
| 1004 |
+
"step": 1450
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 2.28,
|
| 1008 |
+
"learning_rate": 7.14397496087637e-05,
|
| 1009 |
+
"loss": 0.3248,
|
| 1010 |
+
"step": 1460
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 2.3,
|
| 1014 |
+
"learning_rate": 7.124413145539907e-05,
|
| 1015 |
+
"loss": 0.32,
|
| 1016 |
+
"step": 1470
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 2.32,
|
| 1020 |
+
"learning_rate": 7.104851330203444e-05,
|
| 1021 |
+
"loss": 0.4012,
|
| 1022 |
+
"step": 1480
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 2.33,
|
| 1026 |
+
"learning_rate": 7.08528951486698e-05,
|
| 1027 |
+
"loss": 0.3526,
|
| 1028 |
+
"step": 1490
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 2.35,
|
| 1032 |
+
"learning_rate": 7.065727699530516e-05,
|
| 1033 |
+
"loss": 0.2912,
|
| 1034 |
+
"step": 1500
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 2.35,
|
| 1038 |
+
"eval_accuracy": 0.8596761757902853,
|
| 1039 |
+
"eval_loss": 0.6183947324752808,
|
| 1040 |
+
"eval_runtime": 43.0374,
|
| 1041 |
+
"eval_samples_per_second": 60.273,
|
| 1042 |
+
"eval_steps_per_second": 7.552,
|
| 1043 |
+
"step": 1500
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 2.36,
|
| 1047 |
+
"learning_rate": 7.046165884194053e-05,
|
| 1048 |
+
"loss": 0.427,
|
| 1049 |
+
"step": 1510
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 2.38,
|
| 1053 |
+
"learning_rate": 7.02660406885759e-05,
|
| 1054 |
+
"loss": 0.4321,
|
| 1055 |
+
"step": 1520
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 2.39,
|
| 1059 |
+
"learning_rate": 7.007042253521127e-05,
|
| 1060 |
+
"loss": 0.363,
|
| 1061 |
+
"step": 1530
|
| 1062 |
+
},
|
| 1063 |
+
{
|
| 1064 |
+
"epoch": 2.41,
|
| 1065 |
+
"learning_rate": 6.987480438184664e-05,
|
| 1066 |
+
"loss": 0.2761,
|
| 1067 |
+
"step": 1540
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 2.43,
|
| 1071 |
+
"learning_rate": 6.967918622848201e-05,
|
| 1072 |
+
"loss": 0.3189,
|
| 1073 |
+
"step": 1550
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 2.44,
|
| 1077 |
+
"learning_rate": 6.948356807511738e-05,
|
| 1078 |
+
"loss": 0.3227,
|
| 1079 |
+
"step": 1560
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 2.46,
|
| 1083 |
+
"learning_rate": 6.928794992175274e-05,
|
| 1084 |
+
"loss": 0.2792,
|
| 1085 |
+
"step": 1570
|
| 1086 |
+
},
|
| 1087 |
+
{
|
| 1088 |
+
"epoch": 2.47,
|
| 1089 |
+
"learning_rate": 6.909233176838811e-05,
|
| 1090 |
+
"loss": 0.1959,
|
| 1091 |
+
"step": 1580
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 2.49,
|
| 1095 |
+
"learning_rate": 6.889671361502348e-05,
|
| 1096 |
+
"loss": 0.2785,
|
| 1097 |
+
"step": 1590
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 2.5,
|
| 1101 |
+
"learning_rate": 6.870109546165885e-05,
|
| 1102 |
+
"loss": 0.285,
|
| 1103 |
+
"step": 1600
|
| 1104 |
+
},
|
| 1105 |
+
{
|
| 1106 |
+
"epoch": 2.5,
|
| 1107 |
+
"eval_accuracy": 0.8569776407093292,
|
| 1108 |
+
"eval_loss": 0.5973872542381287,
|
| 1109 |
+
"eval_runtime": 42.9634,
|
| 1110 |
+
"eval_samples_per_second": 60.377,
|
| 1111 |
+
"eval_steps_per_second": 7.565,
|
| 1112 |
+
"step": 1600
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 2.52,
|
| 1116 |
+
"learning_rate": 6.85054773082942e-05,
|
| 1117 |
+
"loss": 0.2649,
|
| 1118 |
+
"step": 1610
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 2.54,
|
| 1122 |
+
"learning_rate": 6.830985915492957e-05,
|
| 1123 |
+
"loss": 0.3259,
|
| 1124 |
+
"step": 1620
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 2.55,
|
| 1128 |
+
"learning_rate": 6.811424100156496e-05,
|
| 1129 |
+
"loss": 0.3085,
|
| 1130 |
+
"step": 1630
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 2.57,
|
| 1134 |
+
"learning_rate": 6.791862284820033e-05,
|
| 1135 |
+
"loss": 0.3485,
|
| 1136 |
+
"step": 1640
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 2.58,
|
| 1140 |
+
"learning_rate": 6.772300469483568e-05,
|
| 1141 |
+
"loss": 0.2735,
|
| 1142 |
+
"step": 1650
|
| 1143 |
+
},
|
| 1144 |
+
{
|
| 1145 |
+
"epoch": 2.6,
|
| 1146 |
+
"learning_rate": 6.752738654147105e-05,
|
| 1147 |
+
"loss": 0.3112,
|
| 1148 |
+
"step": 1660
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 2.61,
|
| 1152 |
+
"learning_rate": 6.733176838810642e-05,
|
| 1153 |
+
"loss": 0.3373,
|
| 1154 |
+
"step": 1670
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 2.63,
|
| 1158 |
+
"learning_rate": 6.713615023474179e-05,
|
| 1159 |
+
"loss": 0.1682,
|
| 1160 |
+
"step": 1680
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 2.64,
|
| 1164 |
+
"learning_rate": 6.694053208137715e-05,
|
| 1165 |
+
"loss": 0.2515,
|
| 1166 |
+
"step": 1690
|
| 1167 |
+
},
|
| 1168 |
+
{
|
| 1169 |
+
"epoch": 2.66,
|
| 1170 |
+
"learning_rate": 6.674491392801252e-05,
|
| 1171 |
+
"loss": 0.2267,
|
| 1172 |
+
"step": 1700
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 2.66,
|
| 1176 |
+
"eval_accuracy": 0.8646877409406323,
|
| 1177 |
+
"eval_loss": 0.5621365904808044,
|
| 1178 |
+
"eval_runtime": 43.0986,
|
| 1179 |
+
"eval_samples_per_second": 60.188,
|
| 1180 |
+
"eval_steps_per_second": 7.541,
|
| 1181 |
+
"step": 1700
|
| 1182 |
+
},
|
| 1183 |
+
{
|
| 1184 |
+
"epoch": 2.68,
|
| 1185 |
+
"learning_rate": 6.654929577464789e-05,
|
| 1186 |
+
"loss": 0.1861,
|
| 1187 |
+
"step": 1710
|
| 1188 |
+
},
|
| 1189 |
+
{
|
| 1190 |
+
"epoch": 2.69,
|
| 1191 |
+
"learning_rate": 6.635367762128326e-05,
|
| 1192 |
+
"loss": 0.3325,
|
| 1193 |
+
"step": 1720
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 2.71,
|
| 1197 |
+
"learning_rate": 6.615805946791863e-05,
|
| 1198 |
+
"loss": 0.3621,
|
| 1199 |
+
"step": 1730
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 2.72,
|
| 1203 |
+
"learning_rate": 6.5962441314554e-05,
|
| 1204 |
+
"loss": 0.3046,
|
| 1205 |
+
"step": 1740
|
| 1206 |
+
},
|
| 1207 |
+
{
|
| 1208 |
+
"epoch": 2.74,
|
| 1209 |
+
"learning_rate": 6.576682316118937e-05,
|
| 1210 |
+
"loss": 0.347,
|
| 1211 |
+
"step": 1750
|
| 1212 |
+
},
|
| 1213 |
+
{
|
| 1214 |
+
"epoch": 2.75,
|
| 1215 |
+
"learning_rate": 6.557120500782473e-05,
|
| 1216 |
+
"loss": 0.3916,
|
| 1217 |
+
"step": 1760
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 2.77,
|
| 1221 |
+
"learning_rate": 6.53755868544601e-05,
|
| 1222 |
+
"loss": 0.3221,
|
| 1223 |
+
"step": 1770
|
| 1224 |
+
},
|
| 1225 |
+
{
|
| 1226 |
+
"epoch": 2.79,
|
| 1227 |
+
"learning_rate": 6.517996870109546e-05,
|
| 1228 |
+
"loss": 0.1877,
|
| 1229 |
+
"step": 1780
|
| 1230 |
+
},
|
| 1231 |
+
{
|
| 1232 |
+
"epoch": 2.8,
|
| 1233 |
+
"learning_rate": 6.498435054773083e-05,
|
| 1234 |
+
"loss": 0.3638,
|
| 1235 |
+
"step": 1790
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 2.82,
|
| 1239 |
+
"learning_rate": 6.47887323943662e-05,
|
| 1240 |
+
"loss": 0.2553,
|
| 1241 |
+
"step": 1800
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 2.82,
|
| 1245 |
+
"eval_accuracy": 0.8816499614494988,
|
| 1246 |
+
"eval_loss": 0.5043683052062988,
|
| 1247 |
+
"eval_runtime": 42.7859,
|
| 1248 |
+
"eval_samples_per_second": 60.628,
|
| 1249 |
+
"eval_steps_per_second": 7.596,
|
| 1250 |
+
"step": 1800
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 2.83,
|
| 1254 |
+
"learning_rate": 6.459311424100157e-05,
|
| 1255 |
+
"loss": 0.3439,
|
| 1256 |
+
"step": 1810
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 2.85,
|
| 1260 |
+
"learning_rate": 6.439749608763693e-05,
|
| 1261 |
+
"loss": 0.2463,
|
| 1262 |
+
"step": 1820
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 2.86,
|
| 1266 |
+
"learning_rate": 6.420187793427231e-05,
|
| 1267 |
+
"loss": 0.2192,
|
| 1268 |
+
"step": 1830
|
| 1269 |
+
},
|
| 1270 |
+
{
|
| 1271 |
+
"epoch": 2.88,
|
| 1272 |
+
"learning_rate": 6.400625978090768e-05,
|
| 1273 |
+
"loss": 0.236,
|
| 1274 |
+
"step": 1840
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 2.9,
|
| 1278 |
+
"learning_rate": 6.381064162754305e-05,
|
| 1279 |
+
"loss": 0.2441,
|
| 1280 |
+
"step": 1850
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 2.91,
|
| 1284 |
+
"learning_rate": 6.36150234741784e-05,
|
| 1285 |
+
"loss": 0.2125,
|
| 1286 |
+
"step": 1860
|
| 1287 |
+
},
|
| 1288 |
+
{
|
| 1289 |
+
"epoch": 2.93,
|
| 1290 |
+
"learning_rate": 6.341940532081377e-05,
|
| 1291 |
+
"loss": 0.2112,
|
| 1292 |
+
"step": 1870
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"epoch": 2.94,
|
| 1296 |
+
"learning_rate": 6.322378716744914e-05,
|
| 1297 |
+
"loss": 0.2905,
|
| 1298 |
+
"step": 1880
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 2.96,
|
| 1302 |
+
"learning_rate": 6.302816901408451e-05,
|
| 1303 |
+
"loss": 0.3244,
|
| 1304 |
+
"step": 1890
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 2.97,
|
| 1308 |
+
"learning_rate": 6.283255086071987e-05,
|
| 1309 |
+
"loss": 0.2029,
|
| 1310 |
+
"step": 1900
|
| 1311 |
+
},
|
| 1312 |
+
{
|
| 1313 |
+
"epoch": 2.97,
|
| 1314 |
+
"eval_accuracy": 0.8955281418658443,
|
| 1315 |
+
"eval_loss": 0.43422141671180725,
|
| 1316 |
+
"eval_runtime": 42.7572,
|
| 1317 |
+
"eval_samples_per_second": 60.668,
|
| 1318 |
+
"eval_steps_per_second": 7.601,
|
| 1319 |
+
"step": 1900
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 2.99,
|
| 1323 |
+
"learning_rate": 6.263693270735524e-05,
|
| 1324 |
+
"loss": 0.2284,
|
| 1325 |
+
"step": 1910
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 3.0,
|
| 1329 |
+
"learning_rate": 6.244131455399061e-05,
|
| 1330 |
+
"loss": 0.2399,
|
| 1331 |
+
"step": 1920
|
| 1332 |
+
},
|
| 1333 |
+
{
|
| 1334 |
+
"epoch": 3.02,
|
| 1335 |
+
"learning_rate": 6.224569640062598e-05,
|
| 1336 |
+
"loss": 0.1875,
|
| 1337 |
+
"step": 1930
|
| 1338 |
+
},
|
| 1339 |
+
{
|
| 1340 |
+
"epoch": 3.04,
|
| 1341 |
+
"learning_rate": 6.205007824726135e-05,
|
| 1342 |
+
"loss": 0.1721,
|
| 1343 |
+
"step": 1940
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 3.05,
|
| 1347 |
+
"learning_rate": 6.185446009389672e-05,
|
| 1348 |
+
"loss": 0.2115,
|
| 1349 |
+
"step": 1950
|
| 1350 |
+
},
|
| 1351 |
+
{
|
| 1352 |
+
"epoch": 3.07,
|
| 1353 |
+
"learning_rate": 6.165884194053209e-05,
|
| 1354 |
+
"loss": 0.1698,
|
| 1355 |
+
"step": 1960
|
| 1356 |
+
},
|
| 1357 |
+
{
|
| 1358 |
+
"epoch": 3.08,
|
| 1359 |
+
"learning_rate": 6.146322378716746e-05,
|
| 1360 |
+
"loss": 0.1321,
|
| 1361 |
+
"step": 1970
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 3.1,
|
| 1365 |
+
"learning_rate": 6.126760563380281e-05,
|
| 1366 |
+
"loss": 0.1165,
|
| 1367 |
+
"step": 1980
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 3.11,
|
| 1371 |
+
"learning_rate": 6.107198748043818e-05,
|
| 1372 |
+
"loss": 0.1121,
|
| 1373 |
+
"step": 1990
|
| 1374 |
+
},
|
| 1375 |
+
{
|
| 1376 |
+
"epoch": 3.13,
|
| 1377 |
+
"learning_rate": 6.0876369327073554e-05,
|
| 1378 |
+
"loss": 0.1763,
|
| 1379 |
+
"step": 2000
|
| 1380 |
+
},
|
| 1381 |
+
{
|
| 1382 |
+
"epoch": 3.13,
|
| 1383 |
+
"eval_accuracy": 0.8905165767154973,
|
| 1384 |
+
"eval_loss": 0.44871243834495544,
|
| 1385 |
+
"eval_runtime": 42.6933,
|
| 1386 |
+
"eval_samples_per_second": 60.759,
|
| 1387 |
+
"eval_steps_per_second": 7.612,
|
| 1388 |
+
"step": 2000
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 3.15,
|
| 1392 |
+
"learning_rate": 6.068075117370893e-05,
|
| 1393 |
+
"loss": 0.1473,
|
| 1394 |
+
"step": 2010
|
| 1395 |
+
},
|
| 1396 |
+
{
|
| 1397 |
+
"epoch": 3.16,
|
| 1398 |
+
"learning_rate": 6.0485133020344286e-05,
|
| 1399 |
+
"loss": 0.1697,
|
| 1400 |
+
"step": 2020
|
| 1401 |
+
},
|
| 1402 |
+
{
|
| 1403 |
+
"epoch": 3.18,
|
| 1404 |
+
"learning_rate": 6.0289514866979656e-05,
|
| 1405 |
+
"loss": 0.1712,
|
| 1406 |
+
"step": 2030
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 3.19,
|
| 1410 |
+
"learning_rate": 6.0093896713615026e-05,
|
| 1411 |
+
"loss": 0.1468,
|
| 1412 |
+
"step": 2040
|
| 1413 |
+
},
|
| 1414 |
+
{
|
| 1415 |
+
"epoch": 3.21,
|
| 1416 |
+
"learning_rate": 5.9898278560250395e-05,
|
| 1417 |
+
"loss": 0.1395,
|
| 1418 |
+
"step": 2050
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 3.22,
|
| 1422 |
+
"learning_rate": 5.970266040688576e-05,
|
| 1423 |
+
"loss": 0.1122,
|
| 1424 |
+
"step": 2060
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 3.24,
|
| 1428 |
+
"learning_rate": 5.950704225352113e-05,
|
| 1429 |
+
"loss": 0.1426,
|
| 1430 |
+
"step": 2070
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 3.26,
|
| 1434 |
+
"learning_rate": 5.93114241001565e-05,
|
| 1435 |
+
"loss": 0.111,
|
| 1436 |
+
"step": 2080
|
| 1437 |
+
},
|
| 1438 |
+
{
|
| 1439 |
+
"epoch": 3.27,
|
| 1440 |
+
"learning_rate": 5.911580594679187e-05,
|
| 1441 |
+
"loss": 0.141,
|
| 1442 |
+
"step": 2090
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 3.29,
|
| 1446 |
+
"learning_rate": 5.892018779342723e-05,
|
| 1447 |
+
"loss": 0.1418,
|
| 1448 |
+
"step": 2100
|
| 1449 |
+
},
|
| 1450 |
+
{
|
| 1451 |
+
"epoch": 3.29,
|
| 1452 |
+
"eval_accuracy": 0.9005397070161912,
|
| 1453 |
+
"eval_loss": 0.41731029748916626,
|
| 1454 |
+
"eval_runtime": 42.6624,
|
| 1455 |
+
"eval_samples_per_second": 60.803,
|
| 1456 |
+
"eval_steps_per_second": 7.618,
|
| 1457 |
+
"step": 2100
|
| 1458 |
+
},
|
| 1459 |
+
{
|
| 1460 |
+
"epoch": 3.3,
|
| 1461 |
+
"learning_rate": 5.87245696400626e-05,
|
| 1462 |
+
"loss": 0.1462,
|
| 1463 |
+
"step": 2110
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 3.32,
|
| 1467 |
+
"learning_rate": 5.852895148669797e-05,
|
| 1468 |
+
"loss": 0.0985,
|
| 1469 |
+
"step": 2120
|
| 1470 |
+
},
|
| 1471 |
+
{
|
| 1472 |
+
"epoch": 3.33,
|
| 1473 |
+
"learning_rate": 5.833333333333334e-05,
|
| 1474 |
+
"loss": 0.133,
|
| 1475 |
+
"step": 2130
|
| 1476 |
+
},
|
| 1477 |
+
{
|
| 1478 |
+
"epoch": 3.35,
|
| 1479 |
+
"learning_rate": 5.81377151799687e-05,
|
| 1480 |
+
"loss": 0.1414,
|
| 1481 |
+
"step": 2140
|
| 1482 |
+
},
|
| 1483 |
+
{
|
| 1484 |
+
"epoch": 3.36,
|
| 1485 |
+
"learning_rate": 5.794209702660407e-05,
|
| 1486 |
+
"loss": 0.1297,
|
| 1487 |
+
"step": 2150
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 3.38,
|
| 1491 |
+
"learning_rate": 5.774647887323944e-05,
|
| 1492 |
+
"loss": 0.1346,
|
| 1493 |
+
"step": 2160
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 3.4,
|
| 1497 |
+
"learning_rate": 5.755086071987481e-05,
|
| 1498 |
+
"loss": 0.1237,
|
| 1499 |
+
"step": 2170
|
| 1500 |
+
},
|
| 1501 |
+
{
|
| 1502 |
+
"epoch": 3.41,
|
| 1503 |
+
"learning_rate": 5.735524256651017e-05,
|
| 1504 |
+
"loss": 0.1664,
|
| 1505 |
+
"step": 2180
|
| 1506 |
+
},
|
| 1507 |
+
{
|
| 1508 |
+
"epoch": 3.43,
|
| 1509 |
+
"learning_rate": 5.715962441314554e-05,
|
| 1510 |
+
"loss": 0.0701,
|
| 1511 |
+
"step": 2190
|
| 1512 |
+
},
|
| 1513 |
+
{
|
| 1514 |
+
"epoch": 3.44,
|
| 1515 |
+
"learning_rate": 5.6964006259780914e-05,
|
| 1516 |
+
"loss": 0.0563,
|
| 1517 |
+
"step": 2200
|
| 1518 |
+
},
|
| 1519 |
+
{
|
| 1520 |
+
"epoch": 3.44,
|
| 1521 |
+
"eval_accuracy": 0.9047802621434079,
|
| 1522 |
+
"eval_loss": 0.387023389339447,
|
| 1523 |
+
"eval_runtime": 42.2972,
|
| 1524 |
+
"eval_samples_per_second": 61.328,
|
| 1525 |
+
"eval_steps_per_second": 7.684,
|
| 1526 |
+
"step": 2200
|
| 1527 |
+
},
|
| 1528 |
+
{
|
| 1529 |
+
"epoch": 3.46,
|
| 1530 |
+
"learning_rate": 5.6768388106416284e-05,
|
| 1531 |
+
"loss": 0.0832,
|
| 1532 |
+
"step": 2210
|
| 1533 |
+
},
|
| 1534 |
+
{
|
| 1535 |
+
"epoch": 3.47,
|
| 1536 |
+
"learning_rate": 5.657276995305164e-05,
|
| 1537 |
+
"loss": 0.0966,
|
| 1538 |
+
"step": 2220
|
| 1539 |
+
},
|
| 1540 |
+
{
|
| 1541 |
+
"epoch": 3.49,
|
| 1542 |
+
"learning_rate": 5.637715179968701e-05,
|
| 1543 |
+
"loss": 0.0926,
|
| 1544 |
+
"step": 2230
|
| 1545 |
+
},
|
| 1546 |
+
{
|
| 1547 |
+
"epoch": 3.51,
|
| 1548 |
+
"learning_rate": 5.618153364632238e-05,
|
| 1549 |
+
"loss": 0.1285,
|
| 1550 |
+
"step": 2240
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 3.52,
|
| 1554 |
+
"learning_rate": 5.598591549295775e-05,
|
| 1555 |
+
"loss": 0.0809,
|
| 1556 |
+
"step": 2250
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 3.54,
|
| 1560 |
+
"learning_rate": 5.579029733959311e-05,
|
| 1561 |
+
"loss": 0.1119,
|
| 1562 |
+
"step": 2260
|
| 1563 |
+
},
|
| 1564 |
+
{
|
| 1565 |
+
"epoch": 3.55,
|
| 1566 |
+
"learning_rate": 5.559467918622848e-05,
|
| 1567 |
+
"loss": 0.067,
|
| 1568 |
+
"step": 2270
|
| 1569 |
+
},
|
| 1570 |
+
{
|
| 1571 |
+
"epoch": 3.57,
|
| 1572 |
+
"learning_rate": 5.539906103286385e-05,
|
| 1573 |
+
"loss": 0.1022,
|
| 1574 |
+
"step": 2280
|
| 1575 |
+
},
|
| 1576 |
+
{
|
| 1577 |
+
"epoch": 3.58,
|
| 1578 |
+
"learning_rate": 5.520344287949922e-05,
|
| 1579 |
+
"loss": 0.1318,
|
| 1580 |
+
"step": 2290
|
| 1581 |
+
},
|
| 1582 |
+
{
|
| 1583 |
+
"epoch": 3.6,
|
| 1584 |
+
"learning_rate": 5.5007824726134584e-05,
|
| 1585 |
+
"loss": 0.0579,
|
| 1586 |
+
"step": 2300
|
| 1587 |
+
},
|
| 1588 |
+
{
|
| 1589 |
+
"epoch": 3.6,
|
| 1590 |
+
"eval_accuracy": 0.9036237471087124,
|
| 1591 |
+
"eval_loss": 0.38491636514663696,
|
| 1592 |
+
"eval_runtime": 42.9889,
|
| 1593 |
+
"eval_samples_per_second": 60.341,
|
| 1594 |
+
"eval_steps_per_second": 7.56,
|
| 1595 |
+
"step": 2300
|
| 1596 |
+
},
|
| 1597 |
+
{
|
| 1598 |
+
"epoch": 3.62,
|
| 1599 |
+
"learning_rate": 5.4812206572769954e-05,
|
| 1600 |
+
"loss": 0.1294,
|
| 1601 |
+
"step": 2310
|
| 1602 |
+
},
|
| 1603 |
+
{
|
| 1604 |
+
"epoch": 3.63,
|
| 1605 |
+
"learning_rate": 5.461658841940532e-05,
|
| 1606 |
+
"loss": 0.0777,
|
| 1607 |
+
"step": 2320
|
| 1608 |
+
},
|
| 1609 |
+
{
|
| 1610 |
+
"epoch": 3.65,
|
| 1611 |
+
"learning_rate": 5.442097026604069e-05,
|
| 1612 |
+
"loss": 0.0754,
|
| 1613 |
+
"step": 2330
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 3.66,
|
| 1617 |
+
"learning_rate": 5.422535211267606e-05,
|
| 1618 |
+
"loss": 0.1463,
|
| 1619 |
+
"step": 2340
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 3.68,
|
| 1623 |
+
"learning_rate": 5.4029733959311426e-05,
|
| 1624 |
+
"loss": 0.0578,
|
| 1625 |
+
"step": 2350
|
| 1626 |
+
},
|
| 1627 |
+
{
|
| 1628 |
+
"epoch": 3.69,
|
| 1629 |
+
"learning_rate": 5.3834115805946795e-05,
|
| 1630 |
+
"loss": 0.1084,
|
| 1631 |
+
"step": 2360
|
| 1632 |
+
},
|
| 1633 |
+
{
|
| 1634 |
+
"epoch": 3.71,
|
| 1635 |
+
"learning_rate": 5.3638497652582165e-05,
|
| 1636 |
+
"loss": 0.0534,
|
| 1637 |
+
"step": 2370
|
| 1638 |
+
},
|
| 1639 |
+
{
|
| 1640 |
+
"epoch": 3.72,
|
| 1641 |
+
"learning_rate": 5.3442879499217535e-05,
|
| 1642 |
+
"loss": 0.0598,
|
| 1643 |
+
"step": 2380
|
| 1644 |
+
},
|
| 1645 |
+
{
|
| 1646 |
+
"epoch": 3.74,
|
| 1647 |
+
"learning_rate": 5.32472613458529e-05,
|
| 1648 |
+
"loss": 0.1353,
|
| 1649 |
+
"step": 2390
|
| 1650 |
+
},
|
| 1651 |
+
{
|
| 1652 |
+
"epoch": 3.76,
|
| 1653 |
+
"learning_rate": 5.305164319248827e-05,
|
| 1654 |
+
"loss": 0.166,
|
| 1655 |
+
"step": 2400
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 3.76,
|
| 1659 |
+
"eval_accuracy": 0.9024672320740169,
|
| 1660 |
+
"eval_loss": 0.3933294415473938,
|
| 1661 |
+
"eval_runtime": 42.6729,
|
| 1662 |
+
"eval_samples_per_second": 60.788,
|
| 1663 |
+
"eval_steps_per_second": 7.616,
|
| 1664 |
+
"step": 2400
|
| 1665 |
+
},
|
| 1666 |
+
{
|
| 1667 |
+
"epoch": 3.77,
|
| 1668 |
+
"learning_rate": 5.285602503912364e-05,
|
| 1669 |
+
"loss": 0.0961,
|
| 1670 |
+
"step": 2410
|
| 1671 |
+
},
|
| 1672 |
+
{
|
| 1673 |
+
"epoch": 3.79,
|
| 1674 |
+
"learning_rate": 5.266040688575901e-05,
|
| 1675 |
+
"loss": 0.0647,
|
| 1676 |
+
"step": 2420
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 3.8,
|
| 1680 |
+
"learning_rate": 5.246478873239436e-05,
|
| 1681 |
+
"loss": 0.0744,
|
| 1682 |
+
"step": 2430
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 3.82,
|
| 1686 |
+
"learning_rate": 5.226917057902973e-05,
|
| 1687 |
+
"loss": 0.1046,
|
| 1688 |
+
"step": 2440
|
| 1689 |
+
},
|
| 1690 |
+
{
|
| 1691 |
+
"epoch": 3.83,
|
| 1692 |
+
"learning_rate": 5.207355242566511e-05,
|
| 1693 |
+
"loss": 0.0925,
|
| 1694 |
+
"step": 2450
|
| 1695 |
+
},
|
| 1696 |
+
{
|
| 1697 |
+
"epoch": 3.85,
|
| 1698 |
+
"learning_rate": 5.187793427230048e-05,
|
| 1699 |
+
"loss": 0.1343,
|
| 1700 |
+
"step": 2460
|
| 1701 |
+
},
|
| 1702 |
+
{
|
| 1703 |
+
"epoch": 3.87,
|
| 1704 |
+
"learning_rate": 5.1682316118935835e-05,
|
| 1705 |
+
"loss": 0.0721,
|
| 1706 |
+
"step": 2470
|
| 1707 |
+
},
|
| 1708 |
+
{
|
| 1709 |
+
"epoch": 3.88,
|
| 1710 |
+
"learning_rate": 5.1486697965571205e-05,
|
| 1711 |
+
"loss": 0.1446,
|
| 1712 |
+
"step": 2480
|
| 1713 |
+
},
|
| 1714 |
+
{
|
| 1715 |
+
"epoch": 3.9,
|
| 1716 |
+
"learning_rate": 5.1291079812206575e-05,
|
| 1717 |
+
"loss": 0.0807,
|
| 1718 |
+
"step": 2490
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 3.91,
|
| 1722 |
+
"learning_rate": 5.109546165884195e-05,
|
| 1723 |
+
"loss": 0.11,
|
| 1724 |
+
"step": 2500
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 3.91,
|
| 1728 |
+
"eval_accuracy": 0.9055512721665382,
|
| 1729 |
+
"eval_loss": 0.39182865619659424,
|
| 1730 |
+
"eval_runtime": 42.4672,
|
| 1731 |
+
"eval_samples_per_second": 61.082,
|
| 1732 |
+
"eval_steps_per_second": 7.653,
|
| 1733 |
+
"step": 2500
|
| 1734 |
+
},
|
| 1735 |
+
{
|
| 1736 |
+
"epoch": 3.93,
|
| 1737 |
+
"learning_rate": 5.089984350547731e-05,
|
| 1738 |
+
"loss": 0.1331,
|
| 1739 |
+
"step": 2510
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 3.94,
|
| 1743 |
+
"learning_rate": 5.070422535211268e-05,
|
| 1744 |
+
"loss": 0.0506,
|
| 1745 |
+
"step": 2520
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 3.96,
|
| 1749 |
+
"learning_rate": 5.0508607198748047e-05,
|
| 1750 |
+
"loss": 0.1025,
|
| 1751 |
+
"step": 2530
|
| 1752 |
+
},
|
| 1753 |
+
{
|
| 1754 |
+
"epoch": 3.97,
|
| 1755 |
+
"learning_rate": 5.0312989045383416e-05,
|
| 1756 |
+
"loss": 0.0792,
|
| 1757 |
+
"step": 2540
|
| 1758 |
+
},
|
| 1759 |
+
{
|
| 1760 |
+
"epoch": 3.99,
|
| 1761 |
+
"learning_rate": 5.011737089201878e-05,
|
| 1762 |
+
"loss": 0.099,
|
| 1763 |
+
"step": 2550
|
| 1764 |
+
},
|
| 1765 |
+
{
|
| 1766 |
+
"epoch": 4.01,
|
| 1767 |
+
"learning_rate": 4.992175273865415e-05,
|
| 1768 |
+
"loss": 0.0861,
|
| 1769 |
+
"step": 2560
|
| 1770 |
+
},
|
| 1771 |
+
{
|
| 1772 |
+
"epoch": 4.02,
|
| 1773 |
+
"learning_rate": 4.972613458528952e-05,
|
| 1774 |
+
"loss": 0.0467,
|
| 1775 |
+
"step": 2570
|
| 1776 |
+
},
|
| 1777 |
+
{
|
| 1778 |
+
"epoch": 4.04,
|
| 1779 |
+
"learning_rate": 4.953051643192488e-05,
|
| 1780 |
+
"loss": 0.0587,
|
| 1781 |
+
"step": 2580
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 4.05,
|
| 1785 |
+
"learning_rate": 4.933489827856025e-05,
|
| 1786 |
+
"loss": 0.064,
|
| 1787 |
+
"step": 2590
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 4.07,
|
| 1791 |
+
"learning_rate": 4.913928012519562e-05,
|
| 1792 |
+
"loss": 0.0356,
|
| 1793 |
+
"step": 2600
|
| 1794 |
+
},
|
| 1795 |
+
{
|
| 1796 |
+
"epoch": 4.07,
|
| 1797 |
+
"eval_accuracy": 0.9202004626060138,
|
| 1798 |
+
"eval_loss": 0.3298385739326477,
|
| 1799 |
+
"eval_runtime": 42.9604,
|
| 1800 |
+
"eval_samples_per_second": 60.381,
|
| 1801 |
+
"eval_steps_per_second": 7.565,
|
| 1802 |
+
"step": 2600
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 4.08,
|
| 1806 |
+
"learning_rate": 4.894366197183099e-05,
|
| 1807 |
+
"loss": 0.0376,
|
| 1808 |
+
"step": 2610
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 4.1,
|
| 1812 |
+
"learning_rate": 4.8748043818466354e-05,
|
| 1813 |
+
"loss": 0.0275,
|
| 1814 |
+
"step": 2620
|
| 1815 |
+
},
|
| 1816 |
+
{
|
| 1817 |
+
"epoch": 4.12,
|
| 1818 |
+
"learning_rate": 4.855242566510172e-05,
|
| 1819 |
+
"loss": 0.0297,
|
| 1820 |
+
"step": 2630
|
| 1821 |
+
},
|
| 1822 |
+
{
|
| 1823 |
+
"epoch": 4.13,
|
| 1824 |
+
"learning_rate": 4.835680751173709e-05,
|
| 1825 |
+
"loss": 0.0323,
|
| 1826 |
+
"step": 2640
|
| 1827 |
+
},
|
| 1828 |
+
{
|
| 1829 |
+
"epoch": 4.15,
|
| 1830 |
+
"learning_rate": 4.816118935837246e-05,
|
| 1831 |
+
"loss": 0.0561,
|
| 1832 |
+
"step": 2650
|
| 1833 |
+
},
|
| 1834 |
+
{
|
| 1835 |
+
"epoch": 4.16,
|
| 1836 |
+
"learning_rate": 4.7965571205007826e-05,
|
| 1837 |
+
"loss": 0.0489,
|
| 1838 |
+
"step": 2660
|
| 1839 |
+
},
|
| 1840 |
+
{
|
| 1841 |
+
"epoch": 4.18,
|
| 1842 |
+
"learning_rate": 4.7769953051643195e-05,
|
| 1843 |
+
"loss": 0.0448,
|
| 1844 |
+
"step": 2670
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 4.19,
|
| 1848 |
+
"learning_rate": 4.757433489827856e-05,
|
| 1849 |
+
"loss": 0.0398,
|
| 1850 |
+
"step": 2680
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 4.21,
|
| 1854 |
+
"learning_rate": 4.737871674491393e-05,
|
| 1855 |
+
"loss": 0.0588,
|
| 1856 |
+
"step": 2690
|
| 1857 |
+
},
|
| 1858 |
+
{
|
| 1859 |
+
"epoch": 4.23,
|
| 1860 |
+
"learning_rate": 4.71830985915493e-05,
|
| 1861 |
+
"loss": 0.0513,
|
| 1862 |
+
"step": 2700
|
| 1863 |
+
},
|
| 1864 |
+
{
|
| 1865 |
+
"epoch": 4.23,
|
| 1866 |
+
"eval_accuracy": 0.9209714726291441,
|
| 1867 |
+
"eval_loss": 0.337054580450058,
|
| 1868 |
+
"eval_runtime": 42.6677,
|
| 1869 |
+
"eval_samples_per_second": 60.795,
|
| 1870 |
+
"eval_steps_per_second": 7.617,
|
| 1871 |
+
"step": 2700
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 4.24,
|
| 1875 |
+
"learning_rate": 4.698748043818467e-05,
|
| 1876 |
+
"loss": 0.0396,
|
| 1877 |
+
"step": 2710
|
| 1878 |
+
},
|
| 1879 |
+
{
|
| 1880 |
+
"epoch": 4.26,
|
| 1881 |
+
"learning_rate": 4.679186228482003e-05,
|
| 1882 |
+
"loss": 0.0352,
|
| 1883 |
+
"step": 2720
|
| 1884 |
+
},
|
| 1885 |
+
{
|
| 1886 |
+
"epoch": 4.27,
|
| 1887 |
+
"learning_rate": 4.65962441314554e-05,
|
| 1888 |
+
"loss": 0.0695,
|
| 1889 |
+
"step": 2730
|
| 1890 |
+
},
|
| 1891 |
+
{
|
| 1892 |
+
"epoch": 4.29,
|
| 1893 |
+
"learning_rate": 4.640062597809077e-05,
|
| 1894 |
+
"loss": 0.0614,
|
| 1895 |
+
"step": 2740
|
| 1896 |
+
},
|
| 1897 |
+
{
|
| 1898 |
+
"epoch": 4.3,
|
| 1899 |
+
"learning_rate": 4.620500782472614e-05,
|
| 1900 |
+
"loss": 0.0702,
|
| 1901 |
+
"step": 2750
|
| 1902 |
+
},
|
| 1903 |
+
{
|
| 1904 |
+
"epoch": 4.32,
|
| 1905 |
+
"learning_rate": 4.60093896713615e-05,
|
| 1906 |
+
"loss": 0.037,
|
| 1907 |
+
"step": 2760
|
| 1908 |
+
},
|
| 1909 |
+
{
|
| 1910 |
+
"epoch": 4.33,
|
| 1911 |
+
"learning_rate": 4.581377151799687e-05,
|
| 1912 |
+
"loss": 0.0567,
|
| 1913 |
+
"step": 2770
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 4.35,
|
| 1917 |
+
"learning_rate": 4.5618153364632235e-05,
|
| 1918 |
+
"loss": 0.0327,
|
| 1919 |
+
"step": 2780
|
| 1920 |
+
},
|
| 1921 |
+
{
|
| 1922 |
+
"epoch": 4.37,
|
| 1923 |
+
"learning_rate": 4.542253521126761e-05,
|
| 1924 |
+
"loss": 0.0358,
|
| 1925 |
+
"step": 2790
|
| 1926 |
+
},
|
| 1927 |
+
{
|
| 1928 |
+
"epoch": 4.38,
|
| 1929 |
+
"learning_rate": 4.5226917057902975e-05,
|
| 1930 |
+
"loss": 0.0762,
|
| 1931 |
+
"step": 2800
|
| 1932 |
+
},
|
| 1933 |
+
{
|
| 1934 |
+
"epoch": 4.38,
|
| 1935 |
+
"eval_accuracy": 0.9225134926754048,
|
| 1936 |
+
"eval_loss": 0.32532238960266113,
|
| 1937 |
+
"eval_runtime": 42.6755,
|
| 1938 |
+
"eval_samples_per_second": 60.784,
|
| 1939 |
+
"eval_steps_per_second": 7.616,
|
| 1940 |
+
"step": 2800
|
| 1941 |
+
},
|
| 1942 |
+
{
|
| 1943 |
+
"epoch": 4.4,
|
| 1944 |
+
"learning_rate": 4.5031298904538344e-05,
|
| 1945 |
+
"loss": 0.0223,
|
| 1946 |
+
"step": 2810
|
| 1947 |
+
},
|
| 1948 |
+
{
|
| 1949 |
+
"epoch": 4.41,
|
| 1950 |
+
"learning_rate": 4.483568075117371e-05,
|
| 1951 |
+
"loss": 0.028,
|
| 1952 |
+
"step": 2820
|
| 1953 |
+
},
|
| 1954 |
+
{
|
| 1955 |
+
"epoch": 4.43,
|
| 1956 |
+
"learning_rate": 4.464006259780908e-05,
|
| 1957 |
+
"loss": 0.0572,
|
| 1958 |
+
"step": 2830
|
| 1959 |
+
},
|
| 1960 |
+
{
|
| 1961 |
+
"epoch": 4.44,
|
| 1962 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 1963 |
+
"loss": 0.0487,
|
| 1964 |
+
"step": 2840
|
| 1965 |
+
},
|
| 1966 |
+
{
|
| 1967 |
+
"epoch": 4.46,
|
| 1968 |
+
"learning_rate": 4.4248826291079816e-05,
|
| 1969 |
+
"loss": 0.0711,
|
| 1970 |
+
"step": 2850
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 4.48,
|
| 1974 |
+
"learning_rate": 4.405320813771518e-05,
|
| 1975 |
+
"loss": 0.0334,
|
| 1976 |
+
"step": 2860
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 4.49,
|
| 1980 |
+
"learning_rate": 4.385758998435055e-05,
|
| 1981 |
+
"loss": 0.0219,
|
| 1982 |
+
"step": 2870
|
| 1983 |
+
},
|
| 1984 |
+
{
|
| 1985 |
+
"epoch": 4.51,
|
| 1986 |
+
"learning_rate": 4.366197183098591e-05,
|
| 1987 |
+
"loss": 0.0405,
|
| 1988 |
+
"step": 2880
|
| 1989 |
+
},
|
| 1990 |
+
{
|
| 1991 |
+
"epoch": 4.52,
|
| 1992 |
+
"learning_rate": 4.346635367762129e-05,
|
| 1993 |
+
"loss": 0.0329,
|
| 1994 |
+
"step": 2890
|
| 1995 |
+
},
|
| 1996 |
+
{
|
| 1997 |
+
"epoch": 4.54,
|
| 1998 |
+
"learning_rate": 4.327073552425665e-05,
|
| 1999 |
+
"loss": 0.018,
|
| 2000 |
+
"step": 2900
|
| 2001 |
+
},
|
| 2002 |
+
{
|
| 2003 |
+
"epoch": 4.54,
|
| 2004 |
+
"eval_accuracy": 0.9148033924441018,
|
| 2005 |
+
"eval_loss": 0.34668266773223877,
|
| 2006 |
+
"eval_runtime": 42.9733,
|
| 2007 |
+
"eval_samples_per_second": 60.363,
|
| 2008 |
+
"eval_steps_per_second": 7.563,
|
| 2009 |
+
"step": 2900
|
| 2010 |
+
},
|
| 2011 |
+
{
|
| 2012 |
+
"epoch": 4.55,
|
| 2013 |
+
"learning_rate": 4.307511737089202e-05,
|
| 2014 |
+
"loss": 0.0413,
|
| 2015 |
+
"step": 2910
|
| 2016 |
+
},
|
| 2017 |
+
{
|
| 2018 |
+
"epoch": 4.57,
|
| 2019 |
+
"learning_rate": 4.287949921752739e-05,
|
| 2020 |
+
"loss": 0.018,
|
| 2021 |
+
"step": 2920
|
| 2022 |
+
},
|
| 2023 |
+
{
|
| 2024 |
+
"epoch": 4.59,
|
| 2025 |
+
"learning_rate": 4.2683881064162754e-05,
|
| 2026 |
+
"loss": 0.0417,
|
| 2027 |
+
"step": 2930
|
| 2028 |
+
},
|
| 2029 |
+
{
|
| 2030 |
+
"epoch": 4.6,
|
| 2031 |
+
"learning_rate": 4.248826291079812e-05,
|
| 2032 |
+
"loss": 0.0254,
|
| 2033 |
+
"step": 2940
|
| 2034 |
+
},
|
| 2035 |
+
{
|
| 2036 |
+
"epoch": 4.62,
|
| 2037 |
+
"learning_rate": 4.229264475743349e-05,
|
| 2038 |
+
"loss": 0.0411,
|
| 2039 |
+
"step": 2950
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 4.63,
|
| 2043 |
+
"learning_rate": 4.209702660406886e-05,
|
| 2044 |
+
"loss": 0.0625,
|
| 2045 |
+
"step": 2960
|
| 2046 |
+
},
|
| 2047 |
+
{
|
| 2048 |
+
"epoch": 4.65,
|
| 2049 |
+
"learning_rate": 4.1901408450704226e-05,
|
| 2050 |
+
"loss": 0.0416,
|
| 2051 |
+
"step": 2970
|
| 2052 |
+
},
|
| 2053 |
+
{
|
| 2054 |
+
"epoch": 4.66,
|
| 2055 |
+
"learning_rate": 4.1705790297339595e-05,
|
| 2056 |
+
"loss": 0.0486,
|
| 2057 |
+
"step": 2980
|
| 2058 |
+
},
|
| 2059 |
+
{
|
| 2060 |
+
"epoch": 4.68,
|
| 2061 |
+
"learning_rate": 4.1510172143974965e-05,
|
| 2062 |
+
"loss": 0.0378,
|
| 2063 |
+
"step": 2990
|
| 2064 |
+
},
|
| 2065 |
+
{
|
| 2066 |
+
"epoch": 4.69,
|
| 2067 |
+
"learning_rate": 4.1314553990610335e-05,
|
| 2068 |
+
"loss": 0.0263,
|
| 2069 |
+
"step": 3000
|
| 2070 |
+
},
|
| 2071 |
+
{
|
| 2072 |
+
"epoch": 4.69,
|
| 2073 |
+
"eval_accuracy": 0.9144178874325366,
|
| 2074 |
+
"eval_loss": 0.3544096052646637,
|
| 2075 |
+
"eval_runtime": 43.2558,
|
| 2076 |
+
"eval_samples_per_second": 59.969,
|
| 2077 |
+
"eval_steps_per_second": 7.513,
|
| 2078 |
+
"step": 3000
|
| 2079 |
+
},
|
| 2080 |
+
{
|
| 2081 |
+
"epoch": 4.71,
|
| 2082 |
+
"learning_rate": 4.11189358372457e-05,
|
| 2083 |
+
"loss": 0.0449,
|
| 2084 |
+
"step": 3010
|
| 2085 |
+
},
|
| 2086 |
+
{
|
| 2087 |
+
"epoch": 4.73,
|
| 2088 |
+
"learning_rate": 4.092331768388107e-05,
|
| 2089 |
+
"loss": 0.0758,
|
| 2090 |
+
"step": 3020
|
| 2091 |
+
},
|
| 2092 |
+
{
|
| 2093 |
+
"epoch": 4.74,
|
| 2094 |
+
"learning_rate": 4.072769953051643e-05,
|
| 2095 |
+
"loss": 0.0418,
|
| 2096 |
+
"step": 3030
|
| 2097 |
+
},
|
| 2098 |
+
{
|
| 2099 |
+
"epoch": 4.76,
|
| 2100 |
+
"learning_rate": 4.053208137715181e-05,
|
| 2101 |
+
"loss": 0.0392,
|
| 2102 |
+
"step": 3040
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 4.77,
|
| 2106 |
+
"learning_rate": 4.033646322378717e-05,
|
| 2107 |
+
"loss": 0.0195,
|
| 2108 |
+
"step": 3050
|
| 2109 |
+
},
|
| 2110 |
+
{
|
| 2111 |
+
"epoch": 4.79,
|
| 2112 |
+
"learning_rate": 4.014084507042254e-05,
|
| 2113 |
+
"loss": 0.0317,
|
| 2114 |
+
"step": 3060
|
| 2115 |
+
},
|
| 2116 |
+
{
|
| 2117 |
+
"epoch": 4.8,
|
| 2118 |
+
"learning_rate": 3.99452269170579e-05,
|
| 2119 |
+
"loss": 0.0162,
|
| 2120 |
+
"step": 3070
|
| 2121 |
+
},
|
| 2122 |
+
{
|
| 2123 |
+
"epoch": 4.82,
|
| 2124 |
+
"learning_rate": 3.974960876369327e-05,
|
| 2125 |
+
"loss": 0.0256,
|
| 2126 |
+
"step": 3080
|
| 2127 |
+
},
|
| 2128 |
+
{
|
| 2129 |
+
"epoch": 4.84,
|
| 2130 |
+
"learning_rate": 3.955399061032864e-05,
|
| 2131 |
+
"loss": 0.017,
|
| 2132 |
+
"step": 3090
|
| 2133 |
+
},
|
| 2134 |
+
{
|
| 2135 |
+
"epoch": 4.85,
|
| 2136 |
+
"learning_rate": 3.935837245696401e-05,
|
| 2137 |
+
"loss": 0.0205,
|
| 2138 |
+
"step": 3100
|
| 2139 |
+
},
|
| 2140 |
+
{
|
| 2141 |
+
"epoch": 4.85,
|
| 2142 |
+
"eval_accuracy": 0.9221279876638396,
|
| 2143 |
+
"eval_loss": 0.33404412865638733,
|
| 2144 |
+
"eval_runtime": 43.1306,
|
| 2145 |
+
"eval_samples_per_second": 60.143,
|
| 2146 |
+
"eval_steps_per_second": 7.535,
|
| 2147 |
+
"step": 3100
|
| 2148 |
+
},
|
| 2149 |
+
{
|
| 2150 |
+
"epoch": 4.87,
|
| 2151 |
+
"learning_rate": 3.9162754303599375e-05,
|
| 2152 |
+
"loss": 0.0549,
|
| 2153 |
+
"step": 3110
|
| 2154 |
+
},
|
| 2155 |
+
{
|
| 2156 |
+
"epoch": 4.88,
|
| 2157 |
+
"learning_rate": 3.8967136150234744e-05,
|
| 2158 |
+
"loss": 0.066,
|
| 2159 |
+
"step": 3120
|
| 2160 |
+
},
|
| 2161 |
+
{
|
| 2162 |
+
"epoch": 4.9,
|
| 2163 |
+
"learning_rate": 3.877151799687011e-05,
|
| 2164 |
+
"loss": 0.0307,
|
| 2165 |
+
"step": 3130
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 4.91,
|
| 2169 |
+
"learning_rate": 3.8575899843505484e-05,
|
| 2170 |
+
"loss": 0.0212,
|
| 2171 |
+
"step": 3140
|
| 2172 |
+
},
|
| 2173 |
+
{
|
| 2174 |
+
"epoch": 4.93,
|
| 2175 |
+
"learning_rate": 3.8380281690140847e-05,
|
| 2176 |
+
"loss": 0.0311,
|
| 2177 |
+
"step": 3150
|
| 2178 |
+
},
|
| 2179 |
+
{
|
| 2180 |
+
"epoch": 4.95,
|
| 2181 |
+
"learning_rate": 3.8184663536776216e-05,
|
| 2182 |
+
"loss": 0.0146,
|
| 2183 |
+
"step": 3160
|
| 2184 |
+
},
|
| 2185 |
+
{
|
| 2186 |
+
"epoch": 4.96,
|
| 2187 |
+
"learning_rate": 3.798904538341158e-05,
|
| 2188 |
+
"loss": 0.0173,
|
| 2189 |
+
"step": 3170
|
| 2190 |
+
},
|
| 2191 |
+
{
|
| 2192 |
+
"epoch": 4.98,
|
| 2193 |
+
"learning_rate": 3.779342723004695e-05,
|
| 2194 |
+
"loss": 0.0336,
|
| 2195 |
+
"step": 3180
|
| 2196 |
+
},
|
| 2197 |
+
{
|
| 2198 |
+
"epoch": 4.99,
|
| 2199 |
+
"learning_rate": 3.759780907668232e-05,
|
| 2200 |
+
"loss": 0.0295,
|
| 2201 |
+
"step": 3190
|
| 2202 |
+
},
|
| 2203 |
+
{
|
| 2204 |
+
"epoch": 5.01,
|
| 2205 |
+
"learning_rate": 3.740219092331769e-05,
|
| 2206 |
+
"loss": 0.0237,
|
| 2207 |
+
"step": 3200
|
| 2208 |
+
},
|
| 2209 |
+
{
|
| 2210 |
+
"epoch": 5.01,
|
| 2211 |
+
"eval_accuracy": 0.9144178874325366,
|
| 2212 |
+
"eval_loss": 0.33526894450187683,
|
| 2213 |
+
"eval_runtime": 42.9414,
|
| 2214 |
+
"eval_samples_per_second": 60.408,
|
| 2215 |
+
"eval_steps_per_second": 7.568,
|
| 2216 |
+
"step": 3200
|
| 2217 |
+
},
|
| 2218 |
+
{
|
| 2219 |
+
"epoch": 5.02,
|
| 2220 |
+
"learning_rate": 3.720657276995305e-05,
|
| 2221 |
+
"loss": 0.0137,
|
| 2222 |
+
"step": 3210
|
| 2223 |
+
},
|
| 2224 |
+
{
|
| 2225 |
+
"epoch": 5.04,
|
| 2226 |
+
"learning_rate": 3.701095461658842e-05,
|
| 2227 |
+
"loss": 0.0161,
|
| 2228 |
+
"step": 3220
|
| 2229 |
+
},
|
| 2230 |
+
{
|
| 2231 |
+
"epoch": 5.05,
|
| 2232 |
+
"learning_rate": 3.681533646322379e-05,
|
| 2233 |
+
"loss": 0.0217,
|
| 2234 |
+
"step": 3230
|
| 2235 |
+
},
|
| 2236 |
+
{
|
| 2237 |
+
"epoch": 5.07,
|
| 2238 |
+
"learning_rate": 3.661971830985916e-05,
|
| 2239 |
+
"loss": 0.0184,
|
| 2240 |
+
"step": 3240
|
| 2241 |
+
},
|
| 2242 |
+
{
|
| 2243 |
+
"epoch": 5.09,
|
| 2244 |
+
"learning_rate": 3.642410015649452e-05,
|
| 2245 |
+
"loss": 0.0177,
|
| 2246 |
+
"step": 3250
|
| 2247 |
+
},
|
| 2248 |
+
{
|
| 2249 |
+
"epoch": 5.1,
|
| 2250 |
+
"learning_rate": 3.622848200312989e-05,
|
| 2251 |
+
"loss": 0.051,
|
| 2252 |
+
"step": 3260
|
| 2253 |
+
},
|
| 2254 |
+
{
|
| 2255 |
+
"epoch": 5.12,
|
| 2256 |
+
"learning_rate": 3.6032863849765256e-05,
|
| 2257 |
+
"loss": 0.012,
|
| 2258 |
+
"step": 3270
|
| 2259 |
+
},
|
| 2260 |
+
{
|
| 2261 |
+
"epoch": 5.13,
|
| 2262 |
+
"learning_rate": 3.5837245696400626e-05,
|
| 2263 |
+
"loss": 0.0156,
|
| 2264 |
+
"step": 3280
|
| 2265 |
+
},
|
| 2266 |
+
{
|
| 2267 |
+
"epoch": 5.15,
|
| 2268 |
+
"learning_rate": 3.5641627543035995e-05,
|
| 2269 |
+
"loss": 0.0129,
|
| 2270 |
+
"step": 3290
|
| 2271 |
+
},
|
| 2272 |
+
{
|
| 2273 |
+
"epoch": 5.16,
|
| 2274 |
+
"learning_rate": 3.5446009389671365e-05,
|
| 2275 |
+
"loss": 0.013,
|
| 2276 |
+
"step": 3300
|
| 2277 |
+
},
|
| 2278 |
+
{
|
| 2279 |
+
"epoch": 5.16,
|
| 2280 |
+
"eval_accuracy": 0.9228989976869699,
|
| 2281 |
+
"eval_loss": 0.3218042850494385,
|
| 2282 |
+
"eval_runtime": 42.5041,
|
| 2283 |
+
"eval_samples_per_second": 61.029,
|
| 2284 |
+
"eval_steps_per_second": 7.646,
|
| 2285 |
+
"step": 3300
|
| 2286 |
+
},
|
| 2287 |
+
{
|
| 2288 |
+
"epoch": 5.18,
|
| 2289 |
+
"learning_rate": 3.525039123630673e-05,
|
| 2290 |
+
"loss": 0.0106,
|
| 2291 |
+
"step": 3310
|
| 2292 |
+
},
|
| 2293 |
+
{
|
| 2294 |
+
"epoch": 5.2,
|
| 2295 |
+
"learning_rate": 3.50547730829421e-05,
|
| 2296 |
+
"loss": 0.0132,
|
| 2297 |
+
"step": 3320
|
| 2298 |
+
},
|
| 2299 |
+
{
|
| 2300 |
+
"epoch": 5.21,
|
| 2301 |
+
"learning_rate": 3.485915492957747e-05,
|
| 2302 |
+
"loss": 0.0212,
|
| 2303 |
+
"step": 3330
|
| 2304 |
+
},
|
| 2305 |
+
{
|
| 2306 |
+
"epoch": 5.23,
|
| 2307 |
+
"learning_rate": 3.466353677621284e-05,
|
| 2308 |
+
"loss": 0.0124,
|
| 2309 |
+
"step": 3340
|
| 2310 |
+
},
|
| 2311 |
+
{
|
| 2312 |
+
"epoch": 5.24,
|
| 2313 |
+
"learning_rate": 3.44679186228482e-05,
|
| 2314 |
+
"loss": 0.0135,
|
| 2315 |
+
"step": 3350
|
| 2316 |
+
},
|
| 2317 |
+
{
|
| 2318 |
+
"epoch": 5.26,
|
| 2319 |
+
"learning_rate": 3.427230046948357e-05,
|
| 2320 |
+
"loss": 0.0112,
|
| 2321 |
+
"step": 3360
|
| 2322 |
+
},
|
| 2323 |
+
{
|
| 2324 |
+
"epoch": 5.27,
|
| 2325 |
+
"learning_rate": 3.407668231611893e-05,
|
| 2326 |
+
"loss": 0.0175,
|
| 2327 |
+
"step": 3370
|
| 2328 |
+
},
|
| 2329 |
+
{
|
| 2330 |
+
"epoch": 5.29,
|
| 2331 |
+
"learning_rate": 3.38810641627543e-05,
|
| 2332 |
+
"loss": 0.0234,
|
| 2333 |
+
"step": 3380
|
| 2334 |
+
},
|
| 2335 |
+
{
|
| 2336 |
+
"epoch": 5.31,
|
| 2337 |
+
"learning_rate": 3.368544600938967e-05,
|
| 2338 |
+
"loss": 0.0133,
|
| 2339 |
+
"step": 3390
|
| 2340 |
+
},
|
| 2341 |
+
{
|
| 2342 |
+
"epoch": 5.32,
|
| 2343 |
+
"learning_rate": 3.348982785602504e-05,
|
| 2344 |
+
"loss": 0.0116,
|
| 2345 |
+
"step": 3400
|
| 2346 |
+
},
|
| 2347 |
+
{
|
| 2348 |
+
"epoch": 5.32,
|
| 2349 |
+
"eval_accuracy": 0.9290670778720124,
|
| 2350 |
+
"eval_loss": 0.308786541223526,
|
| 2351 |
+
"eval_runtime": 43.1692,
|
| 2352 |
+
"eval_samples_per_second": 60.089,
|
| 2353 |
+
"eval_steps_per_second": 7.529,
|
| 2354 |
+
"step": 3400
|
| 2355 |
+
},
|
| 2356 |
+
{
|
| 2357 |
+
"epoch": 5.34,
|
| 2358 |
+
"learning_rate": 3.3294209702660405e-05,
|
| 2359 |
+
"loss": 0.011,
|
| 2360 |
+
"step": 3410
|
| 2361 |
+
},
|
| 2362 |
+
{
|
| 2363 |
+
"epoch": 5.35,
|
| 2364 |
+
"learning_rate": 3.3098591549295775e-05,
|
| 2365 |
+
"loss": 0.0119,
|
| 2366 |
+
"step": 3420
|
| 2367 |
+
},
|
| 2368 |
+
{
|
| 2369 |
+
"epoch": 5.37,
|
| 2370 |
+
"learning_rate": 3.2902973395931144e-05,
|
| 2371 |
+
"loss": 0.0175,
|
| 2372 |
+
"step": 3430
|
| 2373 |
+
},
|
| 2374 |
+
{
|
| 2375 |
+
"epoch": 5.38,
|
| 2376 |
+
"learning_rate": 3.2707355242566514e-05,
|
| 2377 |
+
"loss": 0.0116,
|
| 2378 |
+
"step": 3440
|
| 2379 |
+
},
|
| 2380 |
+
{
|
| 2381 |
+
"epoch": 5.4,
|
| 2382 |
+
"learning_rate": 3.251173708920188e-05,
|
| 2383 |
+
"loss": 0.0113,
|
| 2384 |
+
"step": 3450
|
| 2385 |
+
},
|
| 2386 |
+
{
|
| 2387 |
+
"epoch": 5.41,
|
| 2388 |
+
"learning_rate": 3.2316118935837247e-05,
|
| 2389 |
+
"loss": 0.0152,
|
| 2390 |
+
"step": 3460
|
| 2391 |
+
},
|
| 2392 |
+
{
|
| 2393 |
+
"epoch": 5.43,
|
| 2394 |
+
"learning_rate": 3.212050078247261e-05,
|
| 2395 |
+
"loss": 0.012,
|
| 2396 |
+
"step": 3470
|
| 2397 |
+
},
|
| 2398 |
+
{
|
| 2399 |
+
"epoch": 5.45,
|
| 2400 |
+
"learning_rate": 3.1924882629107986e-05,
|
| 2401 |
+
"loss": 0.0096,
|
| 2402 |
+
"step": 3480
|
| 2403 |
+
},
|
| 2404 |
+
{
|
| 2405 |
+
"epoch": 5.46,
|
| 2406 |
+
"learning_rate": 3.1729264475743356e-05,
|
| 2407 |
+
"loss": 0.0109,
|
| 2408 |
+
"step": 3490
|
| 2409 |
+
},
|
| 2410 |
+
{
|
| 2411 |
+
"epoch": 5.48,
|
| 2412 |
+
"learning_rate": 3.153364632237872e-05,
|
| 2413 |
+
"loss": 0.0119,
|
| 2414 |
+
"step": 3500
|
| 2415 |
+
},
|
| 2416 |
+
{
|
| 2417 |
+
"epoch": 5.48,
|
| 2418 |
+
"eval_accuracy": 0.9279105628373169,
|
| 2419 |
+
"eval_loss": 0.3046722412109375,
|
| 2420 |
+
"eval_runtime": 42.5452,
|
| 2421 |
+
"eval_samples_per_second": 60.97,
|
| 2422 |
+
"eval_steps_per_second": 7.639,
|
| 2423 |
+
"step": 3500
|
| 2424 |
+
},
|
| 2425 |
+
{
|
| 2426 |
+
"epoch": 5.49,
|
| 2427 |
+
"learning_rate": 3.133802816901409e-05,
|
| 2428 |
+
"loss": 0.0091,
|
| 2429 |
+
"step": 3510
|
| 2430 |
+
},
|
| 2431 |
+
{
|
| 2432 |
+
"epoch": 5.51,
|
| 2433 |
+
"learning_rate": 3.114241001564945e-05,
|
| 2434 |
+
"loss": 0.0089,
|
| 2435 |
+
"step": 3520
|
| 2436 |
+
},
|
| 2437 |
+
{
|
| 2438 |
+
"epoch": 5.52,
|
| 2439 |
+
"learning_rate": 3.094679186228482e-05,
|
| 2440 |
+
"loss": 0.0113,
|
| 2441 |
+
"step": 3530
|
| 2442 |
+
},
|
| 2443 |
+
{
|
| 2444 |
+
"epoch": 5.54,
|
| 2445 |
+
"learning_rate": 3.075117370892019e-05,
|
| 2446 |
+
"loss": 0.0162,
|
| 2447 |
+
"step": 3540
|
| 2448 |
+
},
|
| 2449 |
+
{
|
| 2450 |
+
"epoch": 5.56,
|
| 2451 |
+
"learning_rate": 3.055555555555556e-05,
|
| 2452 |
+
"loss": 0.0089,
|
| 2453 |
+
"step": 3550
|
| 2454 |
+
},
|
| 2455 |
+
{
|
| 2456 |
+
"epoch": 5.57,
|
| 2457 |
+
"learning_rate": 3.0359937402190923e-05,
|
| 2458 |
+
"loss": 0.0105,
|
| 2459 |
+
"step": 3560
|
| 2460 |
+
},
|
| 2461 |
+
{
|
| 2462 |
+
"epoch": 5.59,
|
| 2463 |
+
"learning_rate": 3.0164319248826296e-05,
|
| 2464 |
+
"loss": 0.037,
|
| 2465 |
+
"step": 3570
|
| 2466 |
+
},
|
| 2467 |
+
{
|
| 2468 |
+
"epoch": 5.6,
|
| 2469 |
+
"learning_rate": 2.996870109546166e-05,
|
| 2470 |
+
"loss": 0.0097,
|
| 2471 |
+
"step": 3580
|
| 2472 |
+
},
|
| 2473 |
+
{
|
| 2474 |
+
"epoch": 5.62,
|
| 2475 |
+
"learning_rate": 2.977308294209703e-05,
|
| 2476 |
+
"loss": 0.0087,
|
| 2477 |
+
"step": 3590
|
| 2478 |
+
},
|
| 2479 |
+
{
|
| 2480 |
+
"epoch": 5.63,
|
| 2481 |
+
"learning_rate": 2.9577464788732395e-05,
|
| 2482 |
+
"loss": 0.0098,
|
| 2483 |
+
"step": 3600
|
| 2484 |
+
},
|
| 2485 |
+
{
|
| 2486 |
+
"epoch": 5.63,
|
| 2487 |
+
"eval_accuracy": 0.9282960678488821,
|
| 2488 |
+
"eval_loss": 0.30633866786956787,
|
| 2489 |
+
"eval_runtime": 42.8022,
|
| 2490 |
+
"eval_samples_per_second": 60.604,
|
| 2491 |
+
"eval_steps_per_second": 7.593,
|
| 2492 |
+
"step": 3600
|
| 2493 |
+
},
|
| 2494 |
+
{
|
| 2495 |
+
"epoch": 5.65,
|
| 2496 |
+
"learning_rate": 2.9381846635367765e-05,
|
| 2497 |
+
"loss": 0.009,
|
| 2498 |
+
"step": 3610
|
| 2499 |
+
},
|
| 2500 |
+
{
|
| 2501 |
+
"epoch": 5.67,
|
| 2502 |
+
"learning_rate": 2.918622848200313e-05,
|
| 2503 |
+
"loss": 0.0263,
|
| 2504 |
+
"step": 3620
|
| 2505 |
+
},
|
| 2506 |
+
{
|
| 2507 |
+
"epoch": 5.68,
|
| 2508 |
+
"learning_rate": 2.89906103286385e-05,
|
| 2509 |
+
"loss": 0.0112,
|
| 2510 |
+
"step": 3630
|
| 2511 |
+
},
|
| 2512 |
+
{
|
| 2513 |
+
"epoch": 5.7,
|
| 2514 |
+
"learning_rate": 2.8794992175273867e-05,
|
| 2515 |
+
"loss": 0.0104,
|
| 2516 |
+
"step": 3640
|
| 2517 |
+
},
|
| 2518 |
+
{
|
| 2519 |
+
"epoch": 5.71,
|
| 2520 |
+
"learning_rate": 2.8599374021909237e-05,
|
| 2521 |
+
"loss": 0.0082,
|
| 2522 |
+
"step": 3650
|
| 2523 |
+
},
|
| 2524 |
+
{
|
| 2525 |
+
"epoch": 5.73,
|
| 2526 |
+
"learning_rate": 2.84037558685446e-05,
|
| 2527 |
+
"loss": 0.0091,
|
| 2528 |
+
"step": 3660
|
| 2529 |
+
},
|
| 2530 |
+
{
|
| 2531 |
+
"epoch": 5.74,
|
| 2532 |
+
"learning_rate": 2.8208137715179973e-05,
|
| 2533 |
+
"loss": 0.0099,
|
| 2534 |
+
"step": 3670
|
| 2535 |
+
},
|
| 2536 |
+
{
|
| 2537 |
+
"epoch": 5.76,
|
| 2538 |
+
"learning_rate": 2.8012519561815336e-05,
|
| 2539 |
+
"loss": 0.0355,
|
| 2540 |
+
"step": 3680
|
| 2541 |
+
},
|
| 2542 |
+
{
|
| 2543 |
+
"epoch": 5.77,
|
| 2544 |
+
"learning_rate": 2.7816901408450706e-05,
|
| 2545 |
+
"loss": 0.0088,
|
| 2546 |
+
"step": 3690
|
| 2547 |
+
},
|
| 2548 |
+
{
|
| 2549 |
+
"epoch": 5.79,
|
| 2550 |
+
"learning_rate": 2.7621283255086072e-05,
|
| 2551 |
+
"loss": 0.0086,
|
| 2552 |
+
"step": 3700
|
| 2553 |
+
},
|
| 2554 |
+
{
|
| 2555 |
+
"epoch": 5.79,
|
| 2556 |
+
"eval_accuracy": 0.9267540478026214,
|
| 2557 |
+
"eval_loss": 0.30737537145614624,
|
| 2558 |
+
"eval_runtime": 42.6258,
|
| 2559 |
+
"eval_samples_per_second": 60.855,
|
| 2560 |
+
"eval_steps_per_second": 7.624,
|
| 2561 |
+
"step": 3700
|
| 2562 |
+
},
|
| 2563 |
+
{
|
| 2564 |
+
"epoch": 5.81,
|
| 2565 |
+
"learning_rate": 2.7425665101721442e-05,
|
| 2566 |
+
"loss": 0.0097,
|
| 2567 |
+
"step": 3710
|
| 2568 |
+
},
|
| 2569 |
+
{
|
| 2570 |
+
"epoch": 5.82,
|
| 2571 |
+
"learning_rate": 2.7230046948356808e-05,
|
| 2572 |
+
"loss": 0.0092,
|
| 2573 |
+
"step": 3720
|
| 2574 |
+
},
|
| 2575 |
+
{
|
| 2576 |
+
"epoch": 5.84,
|
| 2577 |
+
"learning_rate": 2.7034428794992178e-05,
|
| 2578 |
+
"loss": 0.0085,
|
| 2579 |
+
"step": 3730
|
| 2580 |
+
},
|
| 2581 |
+
{
|
| 2582 |
+
"epoch": 5.85,
|
| 2583 |
+
"learning_rate": 2.6838810641627544e-05,
|
| 2584 |
+
"loss": 0.0089,
|
| 2585 |
+
"step": 3740
|
| 2586 |
+
},
|
| 2587 |
+
{
|
| 2588 |
+
"epoch": 5.87,
|
| 2589 |
+
"learning_rate": 2.6643192488262914e-05,
|
| 2590 |
+
"loss": 0.0341,
|
| 2591 |
+
"step": 3750
|
| 2592 |
+
},
|
| 2593 |
+
{
|
| 2594 |
+
"epoch": 5.88,
|
| 2595 |
+
"learning_rate": 2.6447574334898277e-05,
|
| 2596 |
+
"loss": 0.0357,
|
| 2597 |
+
"step": 3760
|
| 2598 |
+
},
|
| 2599 |
+
{
|
| 2600 |
+
"epoch": 5.9,
|
| 2601 |
+
"learning_rate": 2.625195618153365e-05,
|
| 2602 |
+
"loss": 0.0088,
|
| 2603 |
+
"step": 3770
|
| 2604 |
+
},
|
| 2605 |
+
{
|
| 2606 |
+
"epoch": 5.92,
|
| 2607 |
+
"learning_rate": 2.6056338028169013e-05,
|
| 2608 |
+
"loss": 0.0101,
|
| 2609 |
+
"step": 3780
|
| 2610 |
+
},
|
| 2611 |
+
{
|
| 2612 |
+
"epoch": 5.93,
|
| 2613 |
+
"learning_rate": 2.5860719874804386e-05,
|
| 2614 |
+
"loss": 0.0124,
|
| 2615 |
+
"step": 3790
|
| 2616 |
+
},
|
| 2617 |
+
{
|
| 2618 |
+
"epoch": 5.95,
|
| 2619 |
+
"learning_rate": 2.566510172143975e-05,
|
| 2620 |
+
"loss": 0.0081,
|
| 2621 |
+
"step": 3800
|
| 2622 |
+
},
|
| 2623 |
+
{
|
| 2624 |
+
"epoch": 5.95,
|
| 2625 |
+
"eval_accuracy": 0.9236700077101002,
|
| 2626 |
+
"eval_loss": 0.32199642062187195,
|
| 2627 |
+
"eval_runtime": 43.3628,
|
| 2628 |
+
"eval_samples_per_second": 59.821,
|
| 2629 |
+
"eval_steps_per_second": 7.495,
|
| 2630 |
+
"step": 3800
|
| 2631 |
+
},
|
| 2632 |
+
{
|
| 2633 |
+
"epoch": 5.96,
|
| 2634 |
+
"learning_rate": 2.546948356807512e-05,
|
| 2635 |
+
"loss": 0.0096,
|
| 2636 |
+
"step": 3810
|
| 2637 |
+
},
|
| 2638 |
+
{
|
| 2639 |
+
"epoch": 5.98,
|
| 2640 |
+
"learning_rate": 2.5273865414710485e-05,
|
| 2641 |
+
"loss": 0.0217,
|
| 2642 |
+
"step": 3820
|
| 2643 |
+
},
|
| 2644 |
+
{
|
| 2645 |
+
"epoch": 5.99,
|
| 2646 |
+
"learning_rate": 2.5078247261345855e-05,
|
| 2647 |
+
"loss": 0.0112,
|
| 2648 |
+
"step": 3830
|
| 2649 |
+
},
|
| 2650 |
+
{
|
| 2651 |
+
"epoch": 6.01,
|
| 2652 |
+
"learning_rate": 2.4882629107981224e-05,
|
| 2653 |
+
"loss": 0.0115,
|
| 2654 |
+
"step": 3840
|
| 2655 |
+
},
|
| 2656 |
+
{
|
| 2657 |
+
"epoch": 6.03,
|
| 2658 |
+
"learning_rate": 2.468701095461659e-05,
|
| 2659 |
+
"loss": 0.0081,
|
| 2660 |
+
"step": 3850
|
| 2661 |
+
},
|
| 2662 |
+
{
|
| 2663 |
+
"epoch": 6.04,
|
| 2664 |
+
"learning_rate": 2.4491392801251957e-05,
|
| 2665 |
+
"loss": 0.0076,
|
| 2666 |
+
"step": 3860
|
| 2667 |
+
},
|
| 2668 |
+
{
|
| 2669 |
+
"epoch": 6.06,
|
| 2670 |
+
"learning_rate": 2.4295774647887327e-05,
|
| 2671 |
+
"loss": 0.0078,
|
| 2672 |
+
"step": 3870
|
| 2673 |
+
},
|
| 2674 |
+
{
|
| 2675 |
+
"epoch": 6.07,
|
| 2676 |
+
"learning_rate": 2.4100156494522693e-05,
|
| 2677 |
+
"loss": 0.0082,
|
| 2678 |
+
"step": 3880
|
| 2679 |
+
},
|
| 2680 |
+
{
|
| 2681 |
+
"epoch": 6.09,
|
| 2682 |
+
"learning_rate": 2.3904538341158063e-05,
|
| 2683 |
+
"loss": 0.0079,
|
| 2684 |
+
"step": 3890
|
| 2685 |
+
},
|
| 2686 |
+
{
|
| 2687 |
+
"epoch": 6.1,
|
| 2688 |
+
"learning_rate": 2.370892018779343e-05,
|
| 2689 |
+
"loss": 0.0078,
|
| 2690 |
+
"step": 3900
|
| 2691 |
+
},
|
| 2692 |
+
{
|
| 2693 |
+
"epoch": 6.1,
|
| 2694 |
+
"eval_accuracy": 0.9267540478026214,
|
| 2695 |
+
"eval_loss": 0.30635374784469604,
|
| 2696 |
+
"eval_runtime": 43.3159,
|
| 2697 |
+
"eval_samples_per_second": 59.886,
|
| 2698 |
+
"eval_steps_per_second": 7.503,
|
| 2699 |
+
"step": 3900
|
| 2700 |
+
},
|
| 2701 |
+
{
|
| 2702 |
+
"epoch": 6.12,
|
| 2703 |
+
"learning_rate": 2.3513302034428795e-05,
|
| 2704 |
+
"loss": 0.008,
|
| 2705 |
+
"step": 3910
|
| 2706 |
+
},
|
| 2707 |
+
{
|
| 2708 |
+
"epoch": 6.13,
|
| 2709 |
+
"learning_rate": 2.3317683881064165e-05,
|
| 2710 |
+
"loss": 0.0081,
|
| 2711 |
+
"step": 3920
|
| 2712 |
+
},
|
| 2713 |
+
{
|
| 2714 |
+
"epoch": 6.15,
|
| 2715 |
+
"learning_rate": 2.312206572769953e-05,
|
| 2716 |
+
"loss": 0.0074,
|
| 2717 |
+
"step": 3930
|
| 2718 |
+
},
|
| 2719 |
+
{
|
| 2720 |
+
"epoch": 6.17,
|
| 2721 |
+
"learning_rate": 2.29264475743349e-05,
|
| 2722 |
+
"loss": 0.0075,
|
| 2723 |
+
"step": 3940
|
| 2724 |
+
},
|
| 2725 |
+
{
|
| 2726 |
+
"epoch": 6.18,
|
| 2727 |
+
"learning_rate": 2.2730829420970267e-05,
|
| 2728 |
+
"loss": 0.0082,
|
| 2729 |
+
"step": 3950
|
| 2730 |
+
},
|
| 2731 |
+
{
|
| 2732 |
+
"epoch": 6.2,
|
| 2733 |
+
"learning_rate": 2.2535211267605634e-05,
|
| 2734 |
+
"loss": 0.0079,
|
| 2735 |
+
"step": 3960
|
| 2736 |
+
},
|
| 2737 |
+
{
|
| 2738 |
+
"epoch": 6.21,
|
| 2739 |
+
"learning_rate": 2.2339593114241003e-05,
|
| 2740 |
+
"loss": 0.0075,
|
| 2741 |
+
"step": 3970
|
| 2742 |
+
},
|
| 2743 |
+
{
|
| 2744 |
+
"epoch": 6.23,
|
| 2745 |
+
"learning_rate": 2.214397496087637e-05,
|
| 2746 |
+
"loss": 0.0074,
|
| 2747 |
+
"step": 3980
|
| 2748 |
+
},
|
| 2749 |
+
{
|
| 2750 |
+
"epoch": 6.24,
|
| 2751 |
+
"learning_rate": 2.194835680751174e-05,
|
| 2752 |
+
"loss": 0.0067,
|
| 2753 |
+
"step": 3990
|
| 2754 |
+
},
|
| 2755 |
+
{
|
| 2756 |
+
"epoch": 6.26,
|
| 2757 |
+
"learning_rate": 2.1752738654147106e-05,
|
| 2758 |
+
"loss": 0.0074,
|
| 2759 |
+
"step": 4000
|
| 2760 |
+
},
|
| 2761 |
+
{
|
| 2762 |
+
"epoch": 6.26,
|
| 2763 |
+
"eval_accuracy": 0.9279105628373169,
|
| 2764 |
+
"eval_loss": 0.30622774362564087,
|
| 2765 |
+
"eval_runtime": 42.6237,
|
| 2766 |
+
"eval_samples_per_second": 60.858,
|
| 2767 |
+
"eval_steps_per_second": 7.625,
|
| 2768 |
+
"step": 4000
|
| 2769 |
+
},
|
| 2770 |
+
{
|
| 2771 |
+
"epoch": 6.28,
|
| 2772 |
+
"learning_rate": 2.1557120500782476e-05,
|
| 2773 |
+
"loss": 0.0077,
|
| 2774 |
+
"step": 4010
|
| 2775 |
+
},
|
| 2776 |
+
{
|
| 2777 |
+
"epoch": 6.29,
|
| 2778 |
+
"learning_rate": 2.1361502347417842e-05,
|
| 2779 |
+
"loss": 0.0074,
|
| 2780 |
+
"step": 4020
|
| 2781 |
+
},
|
| 2782 |
+
{
|
| 2783 |
+
"epoch": 6.31,
|
| 2784 |
+
"learning_rate": 2.1165884194053208e-05,
|
| 2785 |
+
"loss": 0.0076,
|
| 2786 |
+
"step": 4030
|
| 2787 |
+
},
|
| 2788 |
+
{
|
| 2789 |
+
"epoch": 6.32,
|
| 2790 |
+
"learning_rate": 2.0970266040688578e-05,
|
| 2791 |
+
"loss": 0.0077,
|
| 2792 |
+
"step": 4040
|
| 2793 |
+
},
|
| 2794 |
+
{
|
| 2795 |
+
"epoch": 6.34,
|
| 2796 |
+
"learning_rate": 2.0774647887323944e-05,
|
| 2797 |
+
"loss": 0.0075,
|
| 2798 |
+
"step": 4050
|
| 2799 |
+
},
|
| 2800 |
+
{
|
| 2801 |
+
"epoch": 6.35,
|
| 2802 |
+
"learning_rate": 2.0579029733959314e-05,
|
| 2803 |
+
"loss": 0.0066,
|
| 2804 |
+
"step": 4060
|
| 2805 |
+
},
|
| 2806 |
+
{
|
| 2807 |
+
"epoch": 6.37,
|
| 2808 |
+
"learning_rate": 2.038341158059468e-05,
|
| 2809 |
+
"loss": 0.0077,
|
| 2810 |
+
"step": 4070
|
| 2811 |
+
},
|
| 2812 |
+
{
|
| 2813 |
+
"epoch": 6.38,
|
| 2814 |
+
"learning_rate": 2.0187793427230047e-05,
|
| 2815 |
+
"loss": 0.0076,
|
| 2816 |
+
"step": 4080
|
| 2817 |
+
},
|
| 2818 |
+
{
|
| 2819 |
+
"epoch": 6.4,
|
| 2820 |
+
"learning_rate": 1.9992175273865416e-05,
|
| 2821 |
+
"loss": 0.0073,
|
| 2822 |
+
"step": 4090
|
| 2823 |
+
},
|
| 2824 |
+
{
|
| 2825 |
+
"epoch": 6.42,
|
| 2826 |
+
"learning_rate": 1.9796557120500783e-05,
|
| 2827 |
+
"loss": 0.0068,
|
| 2828 |
+
"step": 4100
|
| 2829 |
+
},
|
| 2830 |
+
{
|
| 2831 |
+
"epoch": 6.42,
|
| 2832 |
+
"eval_accuracy": 0.9290670778720124,
|
| 2833 |
+
"eval_loss": 0.3051210343837738,
|
| 2834 |
+
"eval_runtime": 43.4448,
|
| 2835 |
+
"eval_samples_per_second": 59.708,
|
| 2836 |
+
"eval_steps_per_second": 7.481,
|
| 2837 |
+
"step": 4100
|
| 2838 |
+
},
|
| 2839 |
+
{
|
| 2840 |
+
"epoch": 6.43,
|
| 2841 |
+
"learning_rate": 1.9600938967136152e-05,
|
| 2842 |
+
"loss": 0.0067,
|
| 2843 |
+
"step": 4110
|
| 2844 |
+
},
|
| 2845 |
+
{
|
| 2846 |
+
"epoch": 6.45,
|
| 2847 |
+
"learning_rate": 1.940532081377152e-05,
|
| 2848 |
+
"loss": 0.0382,
|
| 2849 |
+
"step": 4120
|
| 2850 |
+
},
|
| 2851 |
+
{
|
| 2852 |
+
"epoch": 6.46,
|
| 2853 |
+
"learning_rate": 1.9209702660406885e-05,
|
| 2854 |
+
"loss": 0.0071,
|
| 2855 |
+
"step": 4130
|
| 2856 |
+
},
|
| 2857 |
+
{
|
| 2858 |
+
"epoch": 6.48,
|
| 2859 |
+
"learning_rate": 1.9014084507042255e-05,
|
| 2860 |
+
"loss": 0.0155,
|
| 2861 |
+
"step": 4140
|
| 2862 |
+
},
|
| 2863 |
+
{
|
| 2864 |
+
"epoch": 6.49,
|
| 2865 |
+
"learning_rate": 1.881846635367762e-05,
|
| 2866 |
+
"loss": 0.0075,
|
| 2867 |
+
"step": 4150
|
| 2868 |
+
},
|
| 2869 |
+
{
|
| 2870 |
+
"epoch": 6.51,
|
| 2871 |
+
"learning_rate": 1.862284820031299e-05,
|
| 2872 |
+
"loss": 0.0073,
|
| 2873 |
+
"step": 4160
|
| 2874 |
+
},
|
| 2875 |
+
{
|
| 2876 |
+
"epoch": 6.53,
|
| 2877 |
+
"learning_rate": 1.8427230046948357e-05,
|
| 2878 |
+
"loss": 0.0076,
|
| 2879 |
+
"step": 4170
|
| 2880 |
+
},
|
| 2881 |
+
{
|
| 2882 |
+
"epoch": 6.54,
|
| 2883 |
+
"learning_rate": 1.8231611893583723e-05,
|
| 2884 |
+
"loss": 0.0064,
|
| 2885 |
+
"step": 4180
|
| 2886 |
+
},
|
| 2887 |
+
{
|
| 2888 |
+
"epoch": 6.56,
|
| 2889 |
+
"learning_rate": 1.8035993740219093e-05,
|
| 2890 |
+
"loss": 0.0097,
|
| 2891 |
+
"step": 4190
|
| 2892 |
+
},
|
| 2893 |
+
{
|
| 2894 |
+
"epoch": 6.57,
|
| 2895 |
+
"learning_rate": 1.784037558685446e-05,
|
| 2896 |
+
"loss": 0.006,
|
| 2897 |
+
"step": 4200
|
| 2898 |
+
},
|
| 2899 |
+
{
|
| 2900 |
+
"epoch": 6.57,
|
| 2901 |
+
"eval_accuracy": 0.9298380878951427,
|
| 2902 |
+
"eval_loss": 0.3000366985797882,
|
| 2903 |
+
"eval_runtime": 42.6162,
|
| 2904 |
+
"eval_samples_per_second": 60.869,
|
| 2905 |
+
"eval_steps_per_second": 7.626,
|
| 2906 |
+
"step": 4200
|
| 2907 |
+
},
|
| 2908 |
+
{
|
| 2909 |
+
"epoch": 6.59,
|
| 2910 |
+
"learning_rate": 1.764475743348983e-05,
|
| 2911 |
+
"loss": 0.0077,
|
| 2912 |
+
"step": 4210
|
| 2913 |
+
},
|
| 2914 |
+
{
|
| 2915 |
+
"epoch": 6.6,
|
| 2916 |
+
"learning_rate": 1.7449139280125195e-05,
|
| 2917 |
+
"loss": 0.0076,
|
| 2918 |
+
"step": 4220
|
| 2919 |
+
},
|
| 2920 |
+
{
|
| 2921 |
+
"epoch": 6.62,
|
| 2922 |
+
"learning_rate": 1.7253521126760565e-05,
|
| 2923 |
+
"loss": 0.0069,
|
| 2924 |
+
"step": 4230
|
| 2925 |
+
},
|
| 2926 |
+
{
|
| 2927 |
+
"epoch": 6.64,
|
| 2928 |
+
"learning_rate": 1.705790297339593e-05,
|
| 2929 |
+
"loss": 0.0067,
|
| 2930 |
+
"step": 4240
|
| 2931 |
+
},
|
| 2932 |
+
{
|
| 2933 |
+
"epoch": 6.65,
|
| 2934 |
+
"learning_rate": 1.6862284820031298e-05,
|
| 2935 |
+
"loss": 0.0075,
|
| 2936 |
+
"step": 4250
|
| 2937 |
+
},
|
| 2938 |
+
{
|
| 2939 |
+
"epoch": 6.67,
|
| 2940 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 2941 |
+
"loss": 0.0068,
|
| 2942 |
+
"step": 4260
|
| 2943 |
+
},
|
| 2944 |
+
{
|
| 2945 |
+
"epoch": 6.68,
|
| 2946 |
+
"learning_rate": 1.6471048513302034e-05,
|
| 2947 |
+
"loss": 0.0062,
|
| 2948 |
+
"step": 4270
|
| 2949 |
+
},
|
| 2950 |
+
{
|
| 2951 |
+
"epoch": 6.7,
|
| 2952 |
+
"learning_rate": 1.6275430359937403e-05,
|
| 2953 |
+
"loss": 0.0066,
|
| 2954 |
+
"step": 4280
|
| 2955 |
+
},
|
| 2956 |
+
{
|
| 2957 |
+
"epoch": 6.71,
|
| 2958 |
+
"learning_rate": 1.607981220657277e-05,
|
| 2959 |
+
"loss": 0.0072,
|
| 2960 |
+
"step": 4290
|
| 2961 |
+
},
|
| 2962 |
+
{
|
| 2963 |
+
"epoch": 6.73,
|
| 2964 |
+
"learning_rate": 1.5884194053208136e-05,
|
| 2965 |
+
"loss": 0.0075,
|
| 2966 |
+
"step": 4300
|
| 2967 |
+
},
|
| 2968 |
+
{
|
| 2969 |
+
"epoch": 6.73,
|
| 2970 |
+
"eval_accuracy": 0.930994602929838,
|
| 2971 |
+
"eval_loss": 0.30098453164100647,
|
| 2972 |
+
"eval_runtime": 42.908,
|
| 2973 |
+
"eval_samples_per_second": 60.455,
|
| 2974 |
+
"eval_steps_per_second": 7.574,
|
| 2975 |
+
"step": 4300
|
| 2976 |
+
},
|
| 2977 |
+
{
|
| 2978 |
+
"epoch": 6.74,
|
| 2979 |
+
"learning_rate": 1.5688575899843506e-05,
|
| 2980 |
+
"loss": 0.0066,
|
| 2981 |
+
"step": 4310
|
| 2982 |
+
},
|
| 2983 |
+
{
|
| 2984 |
+
"epoch": 6.76,
|
| 2985 |
+
"learning_rate": 1.5492957746478872e-05,
|
| 2986 |
+
"loss": 0.0061,
|
| 2987 |
+
"step": 4320
|
| 2988 |
+
},
|
| 2989 |
+
{
|
| 2990 |
+
"epoch": 6.78,
|
| 2991 |
+
"learning_rate": 1.5297339593114242e-05,
|
| 2992 |
+
"loss": 0.0073,
|
| 2993 |
+
"step": 4330
|
| 2994 |
+
},
|
| 2995 |
+
{
|
| 2996 |
+
"epoch": 6.79,
|
| 2997 |
+
"learning_rate": 1.5101721439749608e-05,
|
| 2998 |
+
"loss": 0.013,
|
| 2999 |
+
"step": 4340
|
| 3000 |
+
},
|
| 3001 |
+
{
|
| 3002 |
+
"epoch": 6.81,
|
| 3003 |
+
"learning_rate": 1.4906103286384976e-05,
|
| 3004 |
+
"loss": 0.0071,
|
| 3005 |
+
"step": 4350
|
| 3006 |
+
},
|
| 3007 |
+
{
|
| 3008 |
+
"epoch": 6.82,
|
| 3009 |
+
"learning_rate": 1.4710485133020346e-05,
|
| 3010 |
+
"loss": 0.0063,
|
| 3011 |
+
"step": 4360
|
| 3012 |
+
},
|
| 3013 |
+
{
|
| 3014 |
+
"epoch": 6.84,
|
| 3015 |
+
"learning_rate": 1.4514866979655714e-05,
|
| 3016 |
+
"loss": 0.0071,
|
| 3017 |
+
"step": 4370
|
| 3018 |
+
},
|
| 3019 |
+
{
|
| 3020 |
+
"epoch": 6.85,
|
| 3021 |
+
"learning_rate": 1.4319248826291082e-05,
|
| 3022 |
+
"loss": 0.0067,
|
| 3023 |
+
"step": 4380
|
| 3024 |
+
},
|
| 3025 |
+
{
|
| 3026 |
+
"epoch": 6.87,
|
| 3027 |
+
"learning_rate": 1.412363067292645e-05,
|
| 3028 |
+
"loss": 0.0475,
|
| 3029 |
+
"step": 4390
|
| 3030 |
+
},
|
| 3031 |
+
{
|
| 3032 |
+
"epoch": 6.89,
|
| 3033 |
+
"learning_rate": 1.3928012519561818e-05,
|
| 3034 |
+
"loss": 0.0057,
|
| 3035 |
+
"step": 4400
|
| 3036 |
+
},
|
| 3037 |
+
{
|
| 3038 |
+
"epoch": 6.89,
|
| 3039 |
+
"eval_accuracy": 0.9298380878951427,
|
| 3040 |
+
"eval_loss": 0.3036852180957794,
|
| 3041 |
+
"eval_runtime": 42.308,
|
| 3042 |
+
"eval_samples_per_second": 61.312,
|
| 3043 |
+
"eval_steps_per_second": 7.682,
|
| 3044 |
+
"step": 4400
|
| 3045 |
+
},
|
| 3046 |
+
{
|
| 3047 |
+
"epoch": 6.9,
|
| 3048 |
+
"learning_rate": 1.3732394366197184e-05,
|
| 3049 |
+
"loss": 0.0058,
|
| 3050 |
+
"step": 4410
|
| 3051 |
+
},
|
| 3052 |
+
{
|
| 3053 |
+
"epoch": 6.92,
|
| 3054 |
+
"learning_rate": 1.3536776212832552e-05,
|
| 3055 |
+
"loss": 0.0068,
|
| 3056 |
+
"step": 4420
|
| 3057 |
+
},
|
| 3058 |
+
{
|
| 3059 |
+
"epoch": 6.93,
|
| 3060 |
+
"learning_rate": 1.334115805946792e-05,
|
| 3061 |
+
"loss": 0.0061,
|
| 3062 |
+
"step": 4430
|
| 3063 |
+
},
|
| 3064 |
+
{
|
| 3065 |
+
"epoch": 6.95,
|
| 3066 |
+
"learning_rate": 1.3145539906103288e-05,
|
| 3067 |
+
"loss": 0.0245,
|
| 3068 |
+
"step": 4440
|
| 3069 |
+
},
|
| 3070 |
+
{
|
| 3071 |
+
"epoch": 6.96,
|
| 3072 |
+
"learning_rate": 1.2949921752738656e-05,
|
| 3073 |
+
"loss": 0.0304,
|
| 3074 |
+
"step": 4450
|
| 3075 |
+
},
|
| 3076 |
+
{
|
| 3077 |
+
"epoch": 6.98,
|
| 3078 |
+
"learning_rate": 1.2754303599374023e-05,
|
| 3079 |
+
"loss": 0.0068,
|
| 3080 |
+
"step": 4460
|
| 3081 |
+
},
|
| 3082 |
+
{
|
| 3083 |
+
"epoch": 7.0,
|
| 3084 |
+
"learning_rate": 1.255868544600939e-05,
|
| 3085 |
+
"loss": 0.0066,
|
| 3086 |
+
"step": 4470
|
| 3087 |
+
},
|
| 3088 |
+
{
|
| 3089 |
+
"epoch": 7.01,
|
| 3090 |
+
"learning_rate": 1.2363067292644757e-05,
|
| 3091 |
+
"loss": 0.0071,
|
| 3092 |
+
"step": 4480
|
| 3093 |
+
},
|
| 3094 |
+
{
|
| 3095 |
+
"epoch": 7.03,
|
| 3096 |
+
"learning_rate": 1.2167449139280125e-05,
|
| 3097 |
+
"loss": 0.0053,
|
| 3098 |
+
"step": 4490
|
| 3099 |
+
},
|
| 3100 |
+
{
|
| 3101 |
+
"epoch": 7.04,
|
| 3102 |
+
"learning_rate": 1.1971830985915493e-05,
|
| 3103 |
+
"loss": 0.0058,
|
| 3104 |
+
"step": 4500
|
| 3105 |
+
},
|
| 3106 |
+
{
|
| 3107 |
+
"epoch": 7.04,
|
| 3108 |
+
"eval_accuracy": 0.9279105628373169,
|
| 3109 |
+
"eval_loss": 0.30713140964508057,
|
| 3110 |
+
"eval_runtime": 42.5583,
|
| 3111 |
+
"eval_samples_per_second": 60.952,
|
| 3112 |
+
"eval_steps_per_second": 7.637,
|
| 3113 |
+
"step": 4500
|
| 3114 |
+
},
|
| 3115 |
+
{
|
| 3116 |
+
"epoch": 7.06,
|
| 3117 |
+
"learning_rate": 1.1776212832550863e-05,
|
| 3118 |
+
"loss": 0.0061,
|
| 3119 |
+
"step": 4510
|
| 3120 |
+
},
|
| 3121 |
+
{
|
| 3122 |
+
"epoch": 7.07,
|
| 3123 |
+
"learning_rate": 1.1580594679186229e-05,
|
| 3124 |
+
"loss": 0.0064,
|
| 3125 |
+
"step": 4520
|
| 3126 |
+
},
|
| 3127 |
+
{
|
| 3128 |
+
"epoch": 7.09,
|
| 3129 |
+
"learning_rate": 1.1384976525821597e-05,
|
| 3130 |
+
"loss": 0.0069,
|
| 3131 |
+
"step": 4530
|
| 3132 |
+
},
|
| 3133 |
+
{
|
| 3134 |
+
"epoch": 7.1,
|
| 3135 |
+
"learning_rate": 1.1189358372456965e-05,
|
| 3136 |
+
"loss": 0.0057,
|
| 3137 |
+
"step": 4540
|
| 3138 |
+
},
|
| 3139 |
+
{
|
| 3140 |
+
"epoch": 7.12,
|
| 3141 |
+
"learning_rate": 1.0993740219092333e-05,
|
| 3142 |
+
"loss": 0.0061,
|
| 3143 |
+
"step": 4550
|
| 3144 |
+
},
|
| 3145 |
+
{
|
| 3146 |
+
"epoch": 7.14,
|
| 3147 |
+
"learning_rate": 1.0798122065727701e-05,
|
| 3148 |
+
"loss": 0.0062,
|
| 3149 |
+
"step": 4560
|
| 3150 |
+
},
|
| 3151 |
+
{
|
| 3152 |
+
"epoch": 7.15,
|
| 3153 |
+
"learning_rate": 1.0602503912363067e-05,
|
| 3154 |
+
"loss": 0.0062,
|
| 3155 |
+
"step": 4570
|
| 3156 |
+
},
|
| 3157 |
+
{
|
| 3158 |
+
"epoch": 7.17,
|
| 3159 |
+
"learning_rate": 1.0406885758998435e-05,
|
| 3160 |
+
"loss": 0.0058,
|
| 3161 |
+
"step": 4580
|
| 3162 |
+
},
|
| 3163 |
+
{
|
| 3164 |
+
"epoch": 7.18,
|
| 3165 |
+
"learning_rate": 1.0211267605633803e-05,
|
| 3166 |
+
"loss": 0.0073,
|
| 3167 |
+
"step": 4590
|
| 3168 |
+
},
|
| 3169 |
+
{
|
| 3170 |
+
"epoch": 7.2,
|
| 3171 |
+
"learning_rate": 1.0015649452269172e-05,
|
| 3172 |
+
"loss": 0.0075,
|
| 3173 |
+
"step": 4600
|
| 3174 |
+
},
|
| 3175 |
+
{
|
| 3176 |
+
"epoch": 7.2,
|
| 3177 |
+
"eval_accuracy": 0.9282960678488821,
|
| 3178 |
+
"eval_loss": 0.307522177696228,
|
| 3179 |
+
"eval_runtime": 43.0156,
|
| 3180 |
+
"eval_samples_per_second": 60.304,
|
| 3181 |
+
"eval_steps_per_second": 7.555,
|
| 3182 |
+
"step": 4600
|
| 3183 |
+
},
|
| 3184 |
+
{
|
| 3185 |
+
"epoch": 7.21,
|
| 3186 |
+
"learning_rate": 9.82003129890454e-06,
|
| 3187 |
+
"loss": 0.0059,
|
| 3188 |
+
"step": 4610
|
| 3189 |
+
},
|
| 3190 |
+
{
|
| 3191 |
+
"epoch": 7.23,
|
| 3192 |
+
"learning_rate": 9.624413145539906e-06,
|
| 3193 |
+
"loss": 0.0064,
|
| 3194 |
+
"step": 4620
|
| 3195 |
+
},
|
| 3196 |
+
{
|
| 3197 |
+
"epoch": 7.25,
|
| 3198 |
+
"learning_rate": 9.428794992175274e-06,
|
| 3199 |
+
"loss": 0.0063,
|
| 3200 |
+
"step": 4630
|
| 3201 |
+
},
|
| 3202 |
+
{
|
| 3203 |
+
"epoch": 7.26,
|
| 3204 |
+
"learning_rate": 9.233176838810642e-06,
|
| 3205 |
+
"loss": 0.0052,
|
| 3206 |
+
"step": 4640
|
| 3207 |
+
},
|
| 3208 |
+
{
|
| 3209 |
+
"epoch": 7.28,
|
| 3210 |
+
"learning_rate": 9.03755868544601e-06,
|
| 3211 |
+
"loss": 0.0053,
|
| 3212 |
+
"step": 4650
|
| 3213 |
+
},
|
| 3214 |
+
{
|
| 3215 |
+
"epoch": 7.29,
|
| 3216 |
+
"learning_rate": 8.841940532081378e-06,
|
| 3217 |
+
"loss": 0.0059,
|
| 3218 |
+
"step": 4660
|
| 3219 |
+
},
|
| 3220 |
+
{
|
| 3221 |
+
"epoch": 7.31,
|
| 3222 |
+
"learning_rate": 8.646322378716746e-06,
|
| 3223 |
+
"loss": 0.0059,
|
| 3224 |
+
"step": 4670
|
| 3225 |
+
},
|
| 3226 |
+
{
|
| 3227 |
+
"epoch": 7.32,
|
| 3228 |
+
"learning_rate": 8.450704225352112e-06,
|
| 3229 |
+
"loss": 0.0058,
|
| 3230 |
+
"step": 4680
|
| 3231 |
+
},
|
| 3232 |
+
{
|
| 3233 |
+
"epoch": 7.34,
|
| 3234 |
+
"learning_rate": 8.25508607198748e-06,
|
| 3235 |
+
"loss": 0.0054,
|
| 3236 |
+
"step": 4690
|
| 3237 |
+
},
|
| 3238 |
+
{
|
| 3239 |
+
"epoch": 7.36,
|
| 3240 |
+
"learning_rate": 8.059467918622848e-06,
|
| 3241 |
+
"loss": 0.0066,
|
| 3242 |
+
"step": 4700
|
| 3243 |
+
},
|
| 3244 |
+
{
|
| 3245 |
+
"epoch": 7.36,
|
| 3246 |
+
"eval_accuracy": 0.9294525828835775,
|
| 3247 |
+
"eval_loss": 0.30765867233276367,
|
| 3248 |
+
"eval_runtime": 43.157,
|
| 3249 |
+
"eval_samples_per_second": 60.106,
|
| 3250 |
+
"eval_steps_per_second": 7.531,
|
| 3251 |
+
"step": 4700
|
| 3252 |
+
},
|
| 3253 |
+
{
|
| 3254 |
+
"epoch": 7.37,
|
| 3255 |
+
"learning_rate": 7.863849765258216e-06,
|
| 3256 |
+
"loss": 0.0054,
|
| 3257 |
+
"step": 4710
|
| 3258 |
+
},
|
| 3259 |
+
{
|
| 3260 |
+
"epoch": 7.39,
|
| 3261 |
+
"learning_rate": 7.668231611893584e-06,
|
| 3262 |
+
"loss": 0.0064,
|
| 3263 |
+
"step": 4720
|
| 3264 |
+
},
|
| 3265 |
+
{
|
| 3266 |
+
"epoch": 7.4,
|
| 3267 |
+
"learning_rate": 7.4726134585289515e-06,
|
| 3268 |
+
"loss": 0.0059,
|
| 3269 |
+
"step": 4730
|
| 3270 |
+
},
|
| 3271 |
+
{
|
| 3272 |
+
"epoch": 7.42,
|
| 3273 |
+
"learning_rate": 7.2769953051643195e-06,
|
| 3274 |
+
"loss": 0.0057,
|
| 3275 |
+
"step": 4740
|
| 3276 |
+
},
|
| 3277 |
+
{
|
| 3278 |
+
"epoch": 7.43,
|
| 3279 |
+
"learning_rate": 7.081377151799687e-06,
|
| 3280 |
+
"loss": 0.0066,
|
| 3281 |
+
"step": 4750
|
| 3282 |
+
},
|
| 3283 |
+
{
|
| 3284 |
+
"epoch": 7.45,
|
| 3285 |
+
"learning_rate": 6.885758998435055e-06,
|
| 3286 |
+
"loss": 0.0113,
|
| 3287 |
+
"step": 4760
|
| 3288 |
+
},
|
| 3289 |
+
{
|
| 3290 |
+
"epoch": 7.46,
|
| 3291 |
+
"learning_rate": 6.690140845070423e-06,
|
| 3292 |
+
"loss": 0.0059,
|
| 3293 |
+
"step": 4770
|
| 3294 |
+
},
|
| 3295 |
+
{
|
| 3296 |
+
"epoch": 7.48,
|
| 3297 |
+
"learning_rate": 6.49452269170579e-06,
|
| 3298 |
+
"loss": 0.0061,
|
| 3299 |
+
"step": 4780
|
| 3300 |
+
},
|
| 3301 |
+
{
|
| 3302 |
+
"epoch": 7.5,
|
| 3303 |
+
"learning_rate": 6.298904538341158e-06,
|
| 3304 |
+
"loss": 0.0069,
|
| 3305 |
+
"step": 4790
|
| 3306 |
+
},
|
| 3307 |
+
{
|
| 3308 |
+
"epoch": 7.51,
|
| 3309 |
+
"learning_rate": 6.103286384976526e-06,
|
| 3310 |
+
"loss": 0.0056,
|
| 3311 |
+
"step": 4800
|
| 3312 |
+
},
|
| 3313 |
+
{
|
| 3314 |
+
"epoch": 7.51,
|
| 3315 |
+
"eval_accuracy": 0.9294525828835775,
|
| 3316 |
+
"eval_loss": 0.30838659405708313,
|
| 3317 |
+
"eval_runtime": 43.0465,
|
| 3318 |
+
"eval_samples_per_second": 60.26,
|
| 3319 |
+
"eval_steps_per_second": 7.55,
|
| 3320 |
+
"step": 4800
|
| 3321 |
+
},
|
| 3322 |
+
{
|
| 3323 |
+
"epoch": 7.53,
|
| 3324 |
+
"learning_rate": 5.907668231611894e-06,
|
| 3325 |
+
"loss": 0.0059,
|
| 3326 |
+
"step": 4810
|
| 3327 |
+
},
|
| 3328 |
+
{
|
| 3329 |
+
"epoch": 7.54,
|
| 3330 |
+
"learning_rate": 5.712050078247261e-06,
|
| 3331 |
+
"loss": 0.0054,
|
| 3332 |
+
"step": 4820
|
| 3333 |
+
},
|
| 3334 |
+
{
|
| 3335 |
+
"epoch": 7.56,
|
| 3336 |
+
"learning_rate": 5.516431924882629e-06,
|
| 3337 |
+
"loss": 0.0054,
|
| 3338 |
+
"step": 4830
|
| 3339 |
+
},
|
| 3340 |
+
{
|
| 3341 |
+
"epoch": 7.57,
|
| 3342 |
+
"learning_rate": 5.320813771517997e-06,
|
| 3343 |
+
"loss": 0.0059,
|
| 3344 |
+
"step": 4840
|
| 3345 |
+
},
|
| 3346 |
+
{
|
| 3347 |
+
"epoch": 7.59,
|
| 3348 |
+
"learning_rate": 5.125195618153364e-06,
|
| 3349 |
+
"loss": 0.0061,
|
| 3350 |
+
"step": 4850
|
| 3351 |
+
},
|
| 3352 |
+
{
|
| 3353 |
+
"epoch": 7.61,
|
| 3354 |
+
"learning_rate": 4.929577464788732e-06,
|
| 3355 |
+
"loss": 0.0062,
|
| 3356 |
+
"step": 4860
|
| 3357 |
+
},
|
| 3358 |
+
{
|
| 3359 |
+
"epoch": 7.62,
|
| 3360 |
+
"learning_rate": 4.7339593114241e-06,
|
| 3361 |
+
"loss": 0.0215,
|
| 3362 |
+
"step": 4870
|
| 3363 |
+
},
|
| 3364 |
+
{
|
| 3365 |
+
"epoch": 7.64,
|
| 3366 |
+
"learning_rate": 4.538341158059468e-06,
|
| 3367 |
+
"loss": 0.0057,
|
| 3368 |
+
"step": 4880
|
| 3369 |
+
},
|
| 3370 |
+
{
|
| 3371 |
+
"epoch": 7.65,
|
| 3372 |
+
"learning_rate": 4.342723004694836e-06,
|
| 3373 |
+
"loss": 0.0061,
|
| 3374 |
+
"step": 4890
|
| 3375 |
+
},
|
| 3376 |
+
{
|
| 3377 |
+
"epoch": 7.67,
|
| 3378 |
+
"learning_rate": 4.1471048513302035e-06,
|
| 3379 |
+
"loss": 0.0053,
|
| 3380 |
+
"step": 4900
|
| 3381 |
+
},
|
| 3382 |
+
{
|
| 3383 |
+
"epoch": 7.67,
|
| 3384 |
+
"eval_accuracy": 0.930994602929838,
|
| 3385 |
+
"eval_loss": 0.3063901364803314,
|
| 3386 |
+
"eval_runtime": 42.9974,
|
| 3387 |
+
"eval_samples_per_second": 60.329,
|
| 3388 |
+
"eval_steps_per_second": 7.559,
|
| 3389 |
+
"step": 4900
|
| 3390 |
+
},
|
| 3391 |
+
{
|
| 3392 |
+
"epoch": 7.68,
|
| 3393 |
+
"learning_rate": 3.9514866979655715e-06,
|
| 3394 |
+
"loss": 0.006,
|
| 3395 |
+
"step": 4910
|
| 3396 |
+
},
|
| 3397 |
+
{
|
| 3398 |
+
"epoch": 7.7,
|
| 3399 |
+
"learning_rate": 3.755868544600939e-06,
|
| 3400 |
+
"loss": 0.0053,
|
| 3401 |
+
"step": 4920
|
| 3402 |
+
},
|
| 3403 |
+
{
|
| 3404 |
+
"epoch": 7.72,
|
| 3405 |
+
"learning_rate": 3.560250391236307e-06,
|
| 3406 |
+
"loss": 0.0051,
|
| 3407 |
+
"step": 4930
|
| 3408 |
+
},
|
| 3409 |
+
{
|
| 3410 |
+
"epoch": 7.73,
|
| 3411 |
+
"learning_rate": 3.3646322378716747e-06,
|
| 3412 |
+
"loss": 0.0057,
|
| 3413 |
+
"step": 4940
|
| 3414 |
+
},
|
| 3415 |
+
{
|
| 3416 |
+
"epoch": 7.75,
|
| 3417 |
+
"learning_rate": 3.1690140845070423e-06,
|
| 3418 |
+
"loss": 0.0259,
|
| 3419 |
+
"step": 4950
|
| 3420 |
+
},
|
| 3421 |
+
{
|
| 3422 |
+
"epoch": 7.76,
|
| 3423 |
+
"learning_rate": 2.97339593114241e-06,
|
| 3424 |
+
"loss": 0.0055,
|
| 3425 |
+
"step": 4960
|
| 3426 |
+
},
|
| 3427 |
+
{
|
| 3428 |
+
"epoch": 7.78,
|
| 3429 |
+
"learning_rate": 2.777777777777778e-06,
|
| 3430 |
+
"loss": 0.0051,
|
| 3431 |
+
"step": 4970
|
| 3432 |
+
},
|
| 3433 |
+
{
|
| 3434 |
+
"epoch": 7.79,
|
| 3435 |
+
"learning_rate": 2.582159624413146e-06,
|
| 3436 |
+
"loss": 0.006,
|
| 3437 |
+
"step": 4980
|
| 3438 |
+
},
|
| 3439 |
+
{
|
| 3440 |
+
"epoch": 7.81,
|
| 3441 |
+
"learning_rate": 2.3865414710485135e-06,
|
| 3442 |
+
"loss": 0.0062,
|
| 3443 |
+
"step": 4990
|
| 3444 |
+
},
|
| 3445 |
+
{
|
| 3446 |
+
"epoch": 7.82,
|
| 3447 |
+
"learning_rate": 2.190923317683881e-06,
|
| 3448 |
+
"loss": 0.0057,
|
| 3449 |
+
"step": 5000
|
| 3450 |
+
},
|
| 3451 |
+
{
|
| 3452 |
+
"epoch": 7.82,
|
| 3453 |
+
"eval_accuracy": 0.9317656129529683,
|
| 3454 |
+
"eval_loss": 0.3068486750125885,
|
| 3455 |
+
"eval_runtime": 42.7527,
|
| 3456 |
+
"eval_samples_per_second": 60.675,
|
| 3457 |
+
"eval_steps_per_second": 7.602,
|
| 3458 |
+
"step": 5000
|
| 3459 |
+
},
|
| 3460 |
+
{
|
| 3461 |
+
"epoch": 7.84,
|
| 3462 |
+
"learning_rate": 1.995305164319249e-06,
|
| 3463 |
+
"loss": 0.0057,
|
| 3464 |
+
"step": 5010
|
| 3465 |
+
},
|
| 3466 |
+
{
|
| 3467 |
+
"epoch": 7.86,
|
| 3468 |
+
"learning_rate": 1.7996870109546167e-06,
|
| 3469 |
+
"loss": 0.0063,
|
| 3470 |
+
"step": 5020
|
| 3471 |
+
},
|
| 3472 |
+
{
|
| 3473 |
+
"epoch": 7.87,
|
| 3474 |
+
"learning_rate": 1.6040688575899843e-06,
|
| 3475 |
+
"loss": 0.0063,
|
| 3476 |
+
"step": 5030
|
| 3477 |
+
},
|
| 3478 |
+
{
|
| 3479 |
+
"epoch": 7.89,
|
| 3480 |
+
"learning_rate": 1.4084507042253521e-06,
|
| 3481 |
+
"loss": 0.0061,
|
| 3482 |
+
"step": 5040
|
| 3483 |
+
},
|
| 3484 |
+
{
|
| 3485 |
+
"epoch": 7.9,
|
| 3486 |
+
"learning_rate": 1.21283255086072e-06,
|
| 3487 |
+
"loss": 0.0051,
|
| 3488 |
+
"step": 5050
|
| 3489 |
+
},
|
| 3490 |
+
{
|
| 3491 |
+
"epoch": 7.92,
|
| 3492 |
+
"learning_rate": 1.0172143974960877e-06,
|
| 3493 |
+
"loss": 0.0061,
|
| 3494 |
+
"step": 5060
|
| 3495 |
+
},
|
| 3496 |
+
{
|
| 3497 |
+
"epoch": 7.93,
|
| 3498 |
+
"learning_rate": 8.215962441314555e-07,
|
| 3499 |
+
"loss": 0.0061,
|
| 3500 |
+
"step": 5070
|
| 3501 |
+
},
|
| 3502 |
+
{
|
| 3503 |
+
"epoch": 7.95,
|
| 3504 |
+
"learning_rate": 6.259780907668232e-07,
|
| 3505 |
+
"loss": 0.0049,
|
| 3506 |
+
"step": 5080
|
| 3507 |
+
},
|
| 3508 |
+
{
|
| 3509 |
+
"epoch": 7.97,
|
| 3510 |
+
"learning_rate": 4.303599374021909e-07,
|
| 3511 |
+
"loss": 0.0049,
|
| 3512 |
+
"step": 5090
|
| 3513 |
+
},
|
| 3514 |
+
{
|
| 3515 |
+
"epoch": 7.98,
|
| 3516 |
+
"learning_rate": 2.347417840375587e-07,
|
| 3517 |
+
"loss": 0.0055,
|
| 3518 |
+
"step": 5100
|
| 3519 |
+
},
|
| 3520 |
+
{
|
| 3521 |
+
"epoch": 7.98,
|
| 3522 |
+
"eval_accuracy": 0.9317656129529683,
|
| 3523 |
+
"eval_loss": 0.30683887004852295,
|
| 3524 |
+
"eval_runtime": 43.5191,
|
| 3525 |
+
"eval_samples_per_second": 59.606,
|
| 3526 |
+
"eval_steps_per_second": 7.468,
|
| 3527 |
+
"step": 5100
|
| 3528 |
+
},
|
| 3529 |
+
{
|
| 3530 |
+
"epoch": 8.0,
|
| 3531 |
+
"learning_rate": 3.912363067292645e-08,
|
| 3532 |
+
"loss": 0.0062,
|
| 3533 |
+
"step": 5110
|
| 3534 |
+
},
|
| 3535 |
+
{
|
| 3536 |
+
"epoch": 8.0,
|
| 3537 |
+
"step": 5112,
|
| 3538 |
+
"total_flos": 6.337884979995771e+18,
|
| 3539 |
+
"train_loss": 0.5634685837152139,
|
| 3540 |
+
"train_runtime": 5666.239,
|
| 3541 |
+
"train_samples_per_second": 14.415,
|
| 3542 |
+
"train_steps_per_second": 0.902
|
| 3543 |
+
}
|
| 3544 |
+
],
|
| 3545 |
+
"max_steps": 5112,
|
| 3546 |
+
"num_train_epochs": 8,
|
| 3547 |
+
"total_flos": 6.337884979995771e+18,
|
| 3548 |
+
"trial_name": null,
|
| 3549 |
+
"trial_params": null
|
| 3550 |
+
}
|