Model save
Browse files- README.md +0 -2
- all_results.json +8 -0
- runs/May31_14-52-19_091cc5c3f6ef/events.out.tfevents.1748710744.091cc5c3f6ef.35.1 +2 -2
- test_results.json +8 -0
- trainer_state.json +2201 -0
README.md
CHANGED
|
@@ -21,8 +21,6 @@ It achieves the following results on the evaluation set:
|
|
| 21 |
- Loss: 0.6522
|
| 22 |
- Accuracy: 0.8173
|
| 23 |
|
| 24 |
-
- hidden_dropout_prob=0.1,
|
| 25 |
-
|
| 26 |
## Model description
|
| 27 |
|
| 28 |
More information needed
|
|
|
|
| 21 |
- Loss: 0.6522
|
| 22 |
- Accuracy: 0.8173
|
| 23 |
|
|
|
|
|
|
|
| 24 |
## Model description
|
| 25 |
|
| 26 |
More information needed
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 9.083477758521086,
|
| 3 |
+
"eval_accuracy": 0.8172690763052208,
|
| 4 |
+
"eval_loss": 0.6521589756011963,
|
| 5 |
+
"eval_runtime": 71.0552,
|
| 6 |
+
"eval_samples_per_second": 7.009,
|
| 7 |
+
"eval_steps_per_second": 0.887
|
| 8 |
+
}
|
runs/May31_14-52-19_091cc5c3f6ef/events.out.tfevents.1748710744.091cc5c3f6ef.35.1
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:981363655c819dac42048f1f68a349869e3558b618cb6835e2e722aab847cb94
|
| 3 |
+
size 1380
|
test_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 9.083477758521086,
|
| 3 |
+
"eval_accuracy": 0.8172690763052208,
|
| 4 |
+
"eval_loss": 0.6521589756011963,
|
| 5 |
+
"eval_runtime": 71.0552,
|
| 6 |
+
"eval_samples_per_second": 7.009,
|
| 7 |
+
"eval_steps_per_second": 0.887
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2201 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 1734,
|
| 3 |
+
"best_metric": 0.8220858895705522,
|
| 4 |
+
"best_model_checkpoint": "RALL_RGBCROP_Aug16F-1DO1/checkpoint-1734",
|
| 5 |
+
"epoch": 9.083477758521086,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 2890,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.0028885037550548816,
|
| 14 |
+
"grad_norm": 8.37844467163086,
|
| 15 |
+
"learning_rate": 1.2968299711815564e-07,
|
| 16 |
+
"loss": 0.7077,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.005777007510109763,
|
| 21 |
+
"grad_norm": 12.892661094665527,
|
| 22 |
+
"learning_rate": 2.7377521613832854e-07,
|
| 23 |
+
"loss": 0.7416,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.008665511265164644,
|
| 28 |
+
"grad_norm": 8.258193969726562,
|
| 29 |
+
"learning_rate": 4.1786743515850145e-07,
|
| 30 |
+
"loss": 0.7147,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.011554015020219527,
|
| 35 |
+
"grad_norm": 8.39278507232666,
|
| 36 |
+
"learning_rate": 5.619596541786745e-07,
|
| 37 |
+
"loss": 0.6718,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.014442518775274409,
|
| 42 |
+
"grad_norm": 7.893959045410156,
|
| 43 |
+
"learning_rate": 7.060518731988474e-07,
|
| 44 |
+
"loss": 0.7027,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.01733102253032929,
|
| 49 |
+
"grad_norm": 8.608739852905273,
|
| 50 |
+
"learning_rate": 8.501440922190203e-07,
|
| 51 |
+
"loss": 0.7158,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.020219526285384173,
|
| 56 |
+
"grad_norm": 9.674214363098145,
|
| 57 |
+
"learning_rate": 9.94236311239193e-07,
|
| 58 |
+
"loss": 0.7614,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.023108030040439053,
|
| 63 |
+
"grad_norm": 7.737273693084717,
|
| 64 |
+
"learning_rate": 1.138328530259366e-06,
|
| 65 |
+
"loss": 0.6871,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.025996533795493933,
|
| 70 |
+
"grad_norm": 8.532608032226562,
|
| 71 |
+
"learning_rate": 1.282420749279539e-06,
|
| 72 |
+
"loss": 0.7358,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.028885037550548817,
|
| 77 |
+
"grad_norm": 7.309403419494629,
|
| 78 |
+
"learning_rate": 1.426512968299712e-06,
|
| 79 |
+
"loss": 0.6698,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.0317735413056037,
|
| 84 |
+
"grad_norm": 8.677237510681152,
|
| 85 |
+
"learning_rate": 1.5706051873198849e-06,
|
| 86 |
+
"loss": 0.6867,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.03466204506065858,
|
| 91 |
+
"grad_norm": 7.54386568069458,
|
| 92 |
+
"learning_rate": 1.7146974063400579e-06,
|
| 93 |
+
"loss": 0.7063,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.03755054881571346,
|
| 98 |
+
"grad_norm": 8.105358123779297,
|
| 99 |
+
"learning_rate": 1.8587896253602309e-06,
|
| 100 |
+
"loss": 0.648,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.040439052570768345,
|
| 105 |
+
"grad_norm": 7.151630401611328,
|
| 106 |
+
"learning_rate": 2.0028818443804035e-06,
|
| 107 |
+
"loss": 0.6525,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.043327556325823226,
|
| 112 |
+
"grad_norm": 8.37738037109375,
|
| 113 |
+
"learning_rate": 2.1469740634005763e-06,
|
| 114 |
+
"loss": 0.6615,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.046216060080878106,
|
| 119 |
+
"grad_norm": 8.140033721923828,
|
| 120 |
+
"learning_rate": 2.2910662824207495e-06,
|
| 121 |
+
"loss": 0.6703,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.049104563835932986,
|
| 126 |
+
"grad_norm": 7.80758810043335,
|
| 127 |
+
"learning_rate": 2.4351585014409223e-06,
|
| 128 |
+
"loss": 0.6309,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.05199306759098787,
|
| 133 |
+
"grad_norm": 6.859084129333496,
|
| 134 |
+
"learning_rate": 2.579250720461095e-06,
|
| 135 |
+
"loss": 0.64,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.05488157134604275,
|
| 140 |
+
"grad_norm": 8.606156349182129,
|
| 141 |
+
"learning_rate": 2.7233429394812683e-06,
|
| 142 |
+
"loss": 0.593,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.057770075101097634,
|
| 147 |
+
"grad_norm": 6.8152313232421875,
|
| 148 |
+
"learning_rate": 2.867435158501441e-06,
|
| 149 |
+
"loss": 0.6037,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.060658578856152515,
|
| 154 |
+
"grad_norm": 6.530623912811279,
|
| 155 |
+
"learning_rate": 3.0115273775216143e-06,
|
| 156 |
+
"loss": 0.6197,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.0635470826112074,
|
| 161 |
+
"grad_norm": 7.118127822875977,
|
| 162 |
+
"learning_rate": 3.1556195965417867e-06,
|
| 163 |
+
"loss": 0.6244,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.06643558636626228,
|
| 168 |
+
"grad_norm": 6.540687084197998,
|
| 169 |
+
"learning_rate": 3.29971181556196e-06,
|
| 170 |
+
"loss": 0.6235,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.06932409012131716,
|
| 175 |
+
"grad_norm": 6.988425254821777,
|
| 176 |
+
"learning_rate": 3.4438040345821327e-06,
|
| 177 |
+
"loss": 0.5487,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.07221259387637204,
|
| 182 |
+
"grad_norm": 6.784511089324951,
|
| 183 |
+
"learning_rate": 3.587896253602306e-06,
|
| 184 |
+
"loss": 0.5492,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.07510109763142692,
|
| 189 |
+
"grad_norm": 6.616488933563232,
|
| 190 |
+
"learning_rate": 3.7319884726224787e-06,
|
| 191 |
+
"loss": 0.5659,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.0779896013864818,
|
| 196 |
+
"grad_norm": 7.42545747756958,
|
| 197 |
+
"learning_rate": 3.876080691642652e-06,
|
| 198 |
+
"loss": 0.5038,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.08087810514153669,
|
| 203 |
+
"grad_norm": 6.44716215133667,
|
| 204 |
+
"learning_rate": 4.020172910662825e-06,
|
| 205 |
+
"loss": 0.5263,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.08347775852108608,
|
| 210 |
+
"eval_accuracy": 0.6134969325153374,
|
| 211 |
+
"eval_loss": 0.6351147294044495,
|
| 212 |
+
"eval_runtime": 75.0993,
|
| 213 |
+
"eval_samples_per_second": 6.511,
|
| 214 |
+
"eval_steps_per_second": 0.826,
|
| 215 |
+
"step": 289
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 1.0002888503755054,
|
| 219 |
+
"grad_norm": 8.028291702270508,
|
| 220 |
+
"learning_rate": 4.1642651296829975e-06,
|
| 221 |
+
"loss": 0.5092,
|
| 222 |
+
"step": 290
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 1.0031773541305604,
|
| 226 |
+
"grad_norm": 8.235032081604004,
|
| 227 |
+
"learning_rate": 4.30835734870317e-06,
|
| 228 |
+
"loss": 0.4796,
|
| 229 |
+
"step": 300
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 1.0060658578856152,
|
| 233 |
+
"grad_norm": 7.71317720413208,
|
| 234 |
+
"learning_rate": 4.452449567723343e-06,
|
| 235 |
+
"loss": 0.4452,
|
| 236 |
+
"step": 310
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 1.0089543616406702,
|
| 240 |
+
"grad_norm": 5.7118144035339355,
|
| 241 |
+
"learning_rate": 4.596541786743517e-06,
|
| 242 |
+
"loss": 0.4561,
|
| 243 |
+
"step": 320
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 1.011842865395725,
|
| 247 |
+
"grad_norm": 7.083165168762207,
|
| 248 |
+
"learning_rate": 4.740634005763689e-06,
|
| 249 |
+
"loss": 0.4049,
|
| 250 |
+
"step": 330
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 1.01473136915078,
|
| 254 |
+
"grad_norm": 4.181227207183838,
|
| 255 |
+
"learning_rate": 4.884726224783862e-06,
|
| 256 |
+
"loss": 0.4103,
|
| 257 |
+
"step": 340
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 1.0176198729058348,
|
| 261 |
+
"grad_norm": 9.941950798034668,
|
| 262 |
+
"learning_rate": 4.996789727126807e-06,
|
| 263 |
+
"loss": 0.3803,
|
| 264 |
+
"step": 350
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 1.0205083766608896,
|
| 268 |
+
"grad_norm": 8.401833534240723,
|
| 269 |
+
"learning_rate": 4.980738362760835e-06,
|
| 270 |
+
"loss": 0.3703,
|
| 271 |
+
"step": 360
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 1.0233968804159446,
|
| 275 |
+
"grad_norm": 5.167896270751953,
|
| 276 |
+
"learning_rate": 4.9646869983948645e-06,
|
| 277 |
+
"loss": 0.352,
|
| 278 |
+
"step": 370
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 1.0262853841709993,
|
| 282 |
+
"grad_norm": 11.792040824890137,
|
| 283 |
+
"learning_rate": 4.948635634028893e-06,
|
| 284 |
+
"loss": 0.378,
|
| 285 |
+
"step": 380
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 1.0291738879260544,
|
| 289 |
+
"grad_norm": 7.333316326141357,
|
| 290 |
+
"learning_rate": 4.9325842696629215e-06,
|
| 291 |
+
"loss": 0.3654,
|
| 292 |
+
"step": 390
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 1.0320623916811091,
|
| 296 |
+
"grad_norm": 5.1884942054748535,
|
| 297 |
+
"learning_rate": 4.916532905296951e-06,
|
| 298 |
+
"loss": 0.3294,
|
| 299 |
+
"step": 400
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 1.0349508954361641,
|
| 303 |
+
"grad_norm": 11.97611141204834,
|
| 304 |
+
"learning_rate": 4.90048154093098e-06,
|
| 305 |
+
"loss": 0.3134,
|
| 306 |
+
"step": 410
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 1.037839399191219,
|
| 310 |
+
"grad_norm": 10.419317245483398,
|
| 311 |
+
"learning_rate": 4.884430176565008e-06,
|
| 312 |
+
"loss": 0.3299,
|
| 313 |
+
"step": 420
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 1.040727902946274,
|
| 317 |
+
"grad_norm": 8.307182312011719,
|
| 318 |
+
"learning_rate": 4.868378812199037e-06,
|
| 319 |
+
"loss": 0.3303,
|
| 320 |
+
"step": 430
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 1.0436164067013287,
|
| 324 |
+
"grad_norm": 4.807034015655518,
|
| 325 |
+
"learning_rate": 4.8523274478330665e-06,
|
| 326 |
+
"loss": 0.2441,
|
| 327 |
+
"step": 440
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 1.0465049104563835,
|
| 331 |
+
"grad_norm": 8.766178131103516,
|
| 332 |
+
"learning_rate": 4.836276083467095e-06,
|
| 333 |
+
"loss": 0.3258,
|
| 334 |
+
"step": 450
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 1.0493934142114385,
|
| 338 |
+
"grad_norm": 3.609104633331299,
|
| 339 |
+
"learning_rate": 4.820224719101124e-06,
|
| 340 |
+
"loss": 0.2477,
|
| 341 |
+
"step": 460
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 1.0522819179664933,
|
| 345 |
+
"grad_norm": 8.949795722961426,
|
| 346 |
+
"learning_rate": 4.804173354735153e-06,
|
| 347 |
+
"loss": 0.2654,
|
| 348 |
+
"step": 470
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 1.0551704217215483,
|
| 352 |
+
"grad_norm": 6.772108554840088,
|
| 353 |
+
"learning_rate": 4.788121990369181e-06,
|
| 354 |
+
"loss": 0.2769,
|
| 355 |
+
"step": 480
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 1.058058925476603,
|
| 359 |
+
"grad_norm": 5.552646636962891,
|
| 360 |
+
"learning_rate": 4.772070626003211e-06,
|
| 361 |
+
"loss": 0.3607,
|
| 362 |
+
"step": 490
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 1.060947429231658,
|
| 366 |
+
"grad_norm": 7.810203552246094,
|
| 367 |
+
"learning_rate": 4.75601926163724e-06,
|
| 368 |
+
"loss": 0.263,
|
| 369 |
+
"step": 500
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 1.0638359329867129,
|
| 373 |
+
"grad_norm": 9.738797187805176,
|
| 374 |
+
"learning_rate": 4.7399678972712685e-06,
|
| 375 |
+
"loss": 0.2365,
|
| 376 |
+
"step": 510
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 1.0667244367417679,
|
| 380 |
+
"grad_norm": 14.024474143981934,
|
| 381 |
+
"learning_rate": 4.723916532905297e-06,
|
| 382 |
+
"loss": 0.3409,
|
| 383 |
+
"step": 520
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 1.0696129404968227,
|
| 387 |
+
"grad_norm": 6.747750282287598,
|
| 388 |
+
"learning_rate": 4.707865168539326e-06,
|
| 389 |
+
"loss": 0.1955,
|
| 390 |
+
"step": 530
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 1.0725014442518774,
|
| 394 |
+
"grad_norm": 6.048046588897705,
|
| 395 |
+
"learning_rate": 4.691813804173355e-06,
|
| 396 |
+
"loss": 0.2507,
|
| 397 |
+
"step": 540
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 1.0753899480069324,
|
| 401 |
+
"grad_norm": 6.181787967681885,
|
| 402 |
+
"learning_rate": 4.675762439807384e-06,
|
| 403 |
+
"loss": 0.3123,
|
| 404 |
+
"step": 550
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 1.0782784517619872,
|
| 408 |
+
"grad_norm": 6.10444974899292,
|
| 409 |
+
"learning_rate": 4.659711075441413e-06,
|
| 410 |
+
"loss": 0.2076,
|
| 411 |
+
"step": 560
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 1.0811669555170422,
|
| 415 |
+
"grad_norm": 9.113558769226074,
|
| 416 |
+
"learning_rate": 4.643659711075442e-06,
|
| 417 |
+
"loss": 0.2545,
|
| 418 |
+
"step": 570
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 1.0834777585210862,
|
| 422 |
+
"eval_accuracy": 0.7811860940695297,
|
| 423 |
+
"eval_loss": 0.4964900314807892,
|
| 424 |
+
"eval_runtime": 66.949,
|
| 425 |
+
"eval_samples_per_second": 7.304,
|
| 426 |
+
"eval_steps_per_second": 0.926,
|
| 427 |
+
"step": 578
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 2.000577700751011,
|
| 431 |
+
"grad_norm": 5.2409467697143555,
|
| 432 |
+
"learning_rate": 4.6276083467094705e-06,
|
| 433 |
+
"loss": 0.1855,
|
| 434 |
+
"step": 580
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 2.003466204506066,
|
| 438 |
+
"grad_norm": 6.332943439483643,
|
| 439 |
+
"learning_rate": 4.6115569823435e-06,
|
| 440 |
+
"loss": 0.1953,
|
| 441 |
+
"step": 590
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 2.006354708261121,
|
| 445 |
+
"grad_norm": 22.365009307861328,
|
| 446 |
+
"learning_rate": 4.595505617977528e-06,
|
| 447 |
+
"loss": 0.3354,
|
| 448 |
+
"step": 600
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 2.009243212016176,
|
| 452 |
+
"grad_norm": 8.605449676513672,
|
| 453 |
+
"learning_rate": 4.579454253611557e-06,
|
| 454 |
+
"loss": 0.2047,
|
| 455 |
+
"step": 610
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 2.0121317157712304,
|
| 459 |
+
"grad_norm": 7.922995090484619,
|
| 460 |
+
"learning_rate": 4.563402889245586e-06,
|
| 461 |
+
"loss": 0.2502,
|
| 462 |
+
"step": 620
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 2.0150202195262854,
|
| 466 |
+
"grad_norm": 10.771293640136719,
|
| 467 |
+
"learning_rate": 4.5473515248796155e-06,
|
| 468 |
+
"loss": 0.1701,
|
| 469 |
+
"step": 630
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 2.0179087232813404,
|
| 473 |
+
"grad_norm": 20.358705520629883,
|
| 474 |
+
"learning_rate": 4.531300160513644e-06,
|
| 475 |
+
"loss": 0.1273,
|
| 476 |
+
"step": 640
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 2.020797227036395,
|
| 480 |
+
"grad_norm": 2.4659533500671387,
|
| 481 |
+
"learning_rate": 4.515248796147673e-06,
|
| 482 |
+
"loss": 0.1772,
|
| 483 |
+
"step": 650
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 2.02368573079145,
|
| 487 |
+
"grad_norm": 10.494536399841309,
|
| 488 |
+
"learning_rate": 4.499197431781702e-06,
|
| 489 |
+
"loss": 0.2002,
|
| 490 |
+
"step": 660
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 2.026574234546505,
|
| 494 |
+
"grad_norm": 16.61016082763672,
|
| 495 |
+
"learning_rate": 4.48314606741573e-06,
|
| 496 |
+
"loss": 0.188,
|
| 497 |
+
"step": 670
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 2.02946273830156,
|
| 501 |
+
"grad_norm": 10.22573471069336,
|
| 502 |
+
"learning_rate": 4.46709470304976e-06,
|
| 503 |
+
"loss": 0.1466,
|
| 504 |
+
"step": 680
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 2.0323512420566145,
|
| 508 |
+
"grad_norm": 10.276712417602539,
|
| 509 |
+
"learning_rate": 4.451043338683789e-06,
|
| 510 |
+
"loss": 0.1377,
|
| 511 |
+
"step": 690
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 2.0352397458116696,
|
| 515 |
+
"grad_norm": 7.458189487457275,
|
| 516 |
+
"learning_rate": 4.4349919743178176e-06,
|
| 517 |
+
"loss": 0.168,
|
| 518 |
+
"step": 700
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 2.0381282495667246,
|
| 522 |
+
"grad_norm": 9.402140617370605,
|
| 523 |
+
"learning_rate": 4.418940609951846e-06,
|
| 524 |
+
"loss": 0.1435,
|
| 525 |
+
"step": 710
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 2.041016753321779,
|
| 529 |
+
"grad_norm": 4.765238285064697,
|
| 530 |
+
"learning_rate": 4.402889245585875e-06,
|
| 531 |
+
"loss": 0.1237,
|
| 532 |
+
"step": 720
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 2.043905257076834,
|
| 536 |
+
"grad_norm": 1.2375091314315796,
|
| 537 |
+
"learning_rate": 4.386837881219904e-06,
|
| 538 |
+
"loss": 0.2354,
|
| 539 |
+
"step": 730
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 2.046793760831889,
|
| 543 |
+
"grad_norm": 12.870935440063477,
|
| 544 |
+
"learning_rate": 4.370786516853933e-06,
|
| 545 |
+
"loss": 0.2488,
|
| 546 |
+
"step": 740
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 2.049682264586944,
|
| 550 |
+
"grad_norm": 6.429897785186768,
|
| 551 |
+
"learning_rate": 4.354735152487962e-06,
|
| 552 |
+
"loss": 0.1568,
|
| 553 |
+
"step": 750
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 2.0525707683419987,
|
| 557 |
+
"grad_norm": 14.20434284210205,
|
| 558 |
+
"learning_rate": 4.33868378812199e-06,
|
| 559 |
+
"loss": 0.1464,
|
| 560 |
+
"step": 760
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 2.0554592720970537,
|
| 564 |
+
"grad_norm": 4.782289028167725,
|
| 565 |
+
"learning_rate": 4.32263242375602e-06,
|
| 566 |
+
"loss": 0.194,
|
| 567 |
+
"step": 770
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 2.0583477758521087,
|
| 571 |
+
"grad_norm": 17.103336334228516,
|
| 572 |
+
"learning_rate": 4.306581059390049e-06,
|
| 573 |
+
"loss": 0.1696,
|
| 574 |
+
"step": 780
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 2.0612362796071633,
|
| 578 |
+
"grad_norm": 0.7173800468444824,
|
| 579 |
+
"learning_rate": 4.290529695024077e-06,
|
| 580 |
+
"loss": 0.1829,
|
| 581 |
+
"step": 790
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 2.0641247833622183,
|
| 585 |
+
"grad_norm": 2.673967123031616,
|
| 586 |
+
"learning_rate": 4.274478330658106e-06,
|
| 587 |
+
"loss": 0.1354,
|
| 588 |
+
"step": 800
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 2.0670132871172733,
|
| 592 |
+
"grad_norm": 13.312447547912598,
|
| 593 |
+
"learning_rate": 4.258426966292135e-06,
|
| 594 |
+
"loss": 0.1753,
|
| 595 |
+
"step": 810
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 2.0699017908723283,
|
| 599 |
+
"grad_norm": 14.13827896118164,
|
| 600 |
+
"learning_rate": 4.242375601926164e-06,
|
| 601 |
+
"loss": 0.1376,
|
| 602 |
+
"step": 820
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 2.072790294627383,
|
| 606 |
+
"grad_norm": 6.9245219230651855,
|
| 607 |
+
"learning_rate": 4.226324237560193e-06,
|
| 608 |
+
"loss": 0.1123,
|
| 609 |
+
"step": 830
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 2.075678798382438,
|
| 613 |
+
"grad_norm": 17.101953506469727,
|
| 614 |
+
"learning_rate": 4.210272873194222e-06,
|
| 615 |
+
"loss": 0.1688,
|
| 616 |
+
"step": 840
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 2.078567302137493,
|
| 620 |
+
"grad_norm": 3.961395502090454,
|
| 621 |
+
"learning_rate": 4.194221508828251e-06,
|
| 622 |
+
"loss": 0.0972,
|
| 623 |
+
"step": 850
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 2.081455805892548,
|
| 627 |
+
"grad_norm": 6.498648166656494,
|
| 628 |
+
"learning_rate": 4.1781701444622794e-06,
|
| 629 |
+
"loss": 0.1261,
|
| 630 |
+
"step": 860
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 2.083477758521086,
|
| 634 |
+
"eval_accuracy": 0.8098159509202454,
|
| 635 |
+
"eval_loss": 0.5260858535766602,
|
| 636 |
+
"eval_runtime": 65.8351,
|
| 637 |
+
"eval_samples_per_second": 7.428,
|
| 638 |
+
"eval_steps_per_second": 0.942,
|
| 639 |
+
"step": 867
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 3.0008665511265167,
|
| 643 |
+
"grad_norm": 1.190217137336731,
|
| 644 |
+
"learning_rate": 4.162118780096309e-06,
|
| 645 |
+
"loss": 0.1403,
|
| 646 |
+
"step": 870
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 3.0037550548815712,
|
| 650 |
+
"grad_norm": 2.1841437816619873,
|
| 651 |
+
"learning_rate": 4.146067415730337e-06,
|
| 652 |
+
"loss": 0.1253,
|
| 653 |
+
"step": 880
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 3.0066435586366262,
|
| 657 |
+
"grad_norm": 29.44947624206543,
|
| 658 |
+
"learning_rate": 4.130016051364366e-06,
|
| 659 |
+
"loss": 0.0811,
|
| 660 |
+
"step": 890
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 3.0095320623916813,
|
| 664 |
+
"grad_norm": 16.02284049987793,
|
| 665 |
+
"learning_rate": 4.113964686998395e-06,
|
| 666 |
+
"loss": 0.1242,
|
| 667 |
+
"step": 900
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 3.012420566146736,
|
| 671 |
+
"grad_norm": 10.445579528808594,
|
| 672 |
+
"learning_rate": 4.0979133226324245e-06,
|
| 673 |
+
"loss": 0.1388,
|
| 674 |
+
"step": 910
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 3.015309069901791,
|
| 678 |
+
"grad_norm": 2.3682429790496826,
|
| 679 |
+
"learning_rate": 4.081861958266453e-06,
|
| 680 |
+
"loss": 0.1039,
|
| 681 |
+
"step": 920
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 3.018197573656846,
|
| 685 |
+
"grad_norm": 0.7850814461708069,
|
| 686 |
+
"learning_rate": 4.0658105939004815e-06,
|
| 687 |
+
"loss": 0.1165,
|
| 688 |
+
"step": 930
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 3.021086077411901,
|
| 692 |
+
"grad_norm": 31.352468490600586,
|
| 693 |
+
"learning_rate": 4.049759229534511e-06,
|
| 694 |
+
"loss": 0.1494,
|
| 695 |
+
"step": 940
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 3.0239745811669554,
|
| 699 |
+
"grad_norm": 0.1588502824306488,
|
| 700 |
+
"learning_rate": 4.033707865168539e-06,
|
| 701 |
+
"loss": 0.0996,
|
| 702 |
+
"step": 950
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 3.0268630849220104,
|
| 706 |
+
"grad_norm": 3.636672019958496,
|
| 707 |
+
"learning_rate": 4.017656500802569e-06,
|
| 708 |
+
"loss": 0.1087,
|
| 709 |
+
"step": 960
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 3.0297515886770654,
|
| 713 |
+
"grad_norm": 24.48581886291504,
|
| 714 |
+
"learning_rate": 4.001605136436598e-06,
|
| 715 |
+
"loss": 0.1439,
|
| 716 |
+
"step": 970
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 3.03264009243212,
|
| 720 |
+
"grad_norm": 0.9635569453239441,
|
| 721 |
+
"learning_rate": 3.9855537720706265e-06,
|
| 722 |
+
"loss": 0.068,
|
| 723 |
+
"step": 980
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 3.035528596187175,
|
| 727 |
+
"grad_norm": 1.4727041721343994,
|
| 728 |
+
"learning_rate": 3.969502407704655e-06,
|
| 729 |
+
"loss": 0.0867,
|
| 730 |
+
"step": 990
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 3.03841709994223,
|
| 734 |
+
"grad_norm": 0.2378067672252655,
|
| 735 |
+
"learning_rate": 3.953451043338684e-06,
|
| 736 |
+
"loss": 0.0891,
|
| 737 |
+
"step": 1000
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 3.041305603697285,
|
| 741 |
+
"grad_norm": 0.4924512505531311,
|
| 742 |
+
"learning_rate": 3.937399678972713e-06,
|
| 743 |
+
"loss": 0.0693,
|
| 744 |
+
"step": 1010
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 3.0441941074523395,
|
| 748 |
+
"grad_norm": 2.5564048290252686,
|
| 749 |
+
"learning_rate": 3.921348314606742e-06,
|
| 750 |
+
"loss": 0.1311,
|
| 751 |
+
"step": 1020
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 3.0470826112073945,
|
| 755 |
+
"grad_norm": 2.72170352935791,
|
| 756 |
+
"learning_rate": 3.905296950240771e-06,
|
| 757 |
+
"loss": 0.0777,
|
| 758 |
+
"step": 1030
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 3.0499711149624495,
|
| 762 |
+
"grad_norm": 0.4120216965675354,
|
| 763 |
+
"learning_rate": 3.8892455858748e-06,
|
| 764 |
+
"loss": 0.1778,
|
| 765 |
+
"step": 1040
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 3.0528596187175046,
|
| 769 |
+
"grad_norm": 16.4429931640625,
|
| 770 |
+
"learning_rate": 3.8731942215088285e-06,
|
| 771 |
+
"loss": 0.0344,
|
| 772 |
+
"step": 1050
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 3.055748122472559,
|
| 776 |
+
"grad_norm": 21.77942657470703,
|
| 777 |
+
"learning_rate": 3.857142857142858e-06,
|
| 778 |
+
"loss": 0.1641,
|
| 779 |
+
"step": 1060
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 3.058636626227614,
|
| 783 |
+
"grad_norm": 4.657069683074951,
|
| 784 |
+
"learning_rate": 3.841091492776886e-06,
|
| 785 |
+
"loss": 0.0319,
|
| 786 |
+
"step": 1070
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 3.061525129982669,
|
| 790 |
+
"grad_norm": 0.2789720892906189,
|
| 791 |
+
"learning_rate": 3.825040128410915e-06,
|
| 792 |
+
"loss": 0.061,
|
| 793 |
+
"step": 1080
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 3.0644136337377237,
|
| 797 |
+
"grad_norm": 0.1231907308101654,
|
| 798 |
+
"learning_rate": 3.808988764044944e-06,
|
| 799 |
+
"loss": 0.1156,
|
| 800 |
+
"step": 1090
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 3.0673021374927787,
|
| 804 |
+
"grad_norm": 17.38383674621582,
|
| 805 |
+
"learning_rate": 3.792937399678973e-06,
|
| 806 |
+
"loss": 0.1351,
|
| 807 |
+
"step": 1100
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 3.0701906412478337,
|
| 811 |
+
"grad_norm": 2.08525013923645,
|
| 812 |
+
"learning_rate": 3.776886035313002e-06,
|
| 813 |
+
"loss": 0.0755,
|
| 814 |
+
"step": 1110
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 3.0730791450028887,
|
| 818 |
+
"grad_norm": 20.763957977294922,
|
| 819 |
+
"learning_rate": 3.7608346709470305e-06,
|
| 820 |
+
"loss": 0.0934,
|
| 821 |
+
"step": 1120
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 3.0759676487579433,
|
| 825 |
+
"grad_norm": 19.472963333129883,
|
| 826 |
+
"learning_rate": 3.7447833065810594e-06,
|
| 827 |
+
"loss": 0.139,
|
| 828 |
+
"step": 1130
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 3.0788561525129983,
|
| 832 |
+
"grad_norm": 2.2785959243774414,
|
| 833 |
+
"learning_rate": 3.7287319422150888e-06,
|
| 834 |
+
"loss": 0.0703,
|
| 835 |
+
"step": 1140
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 3.0817446562680533,
|
| 839 |
+
"grad_norm": 0.3075811564922333,
|
| 840 |
+
"learning_rate": 3.7126805778491177e-06,
|
| 841 |
+
"loss": 0.0753,
|
| 842 |
+
"step": 1150
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 3.083477758521086,
|
| 846 |
+
"eval_accuracy": 0.8159509202453987,
|
| 847 |
+
"eval_loss": 0.625999391078949,
|
| 848 |
+
"eval_runtime": 66.8149,
|
| 849 |
+
"eval_samples_per_second": 7.319,
|
| 850 |
+
"eval_steps_per_second": 0.928,
|
| 851 |
+
"step": 1156
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 4.001155401502022,
|
| 855 |
+
"grad_norm": 2.79459285736084,
|
| 856 |
+
"learning_rate": 3.6966292134831466e-06,
|
| 857 |
+
"loss": 0.0859,
|
| 858 |
+
"step": 1160
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 4.004043905257077,
|
| 862 |
+
"grad_norm": 9.143715858459473,
|
| 863 |
+
"learning_rate": 3.680577849117175e-06,
|
| 864 |
+
"loss": 0.0741,
|
| 865 |
+
"step": 1170
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 4.006932409012132,
|
| 869 |
+
"grad_norm": 7.800527095794678,
|
| 870 |
+
"learning_rate": 3.664526484751204e-06,
|
| 871 |
+
"loss": 0.1363,
|
| 872 |
+
"step": 1180
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 4.009820912767187,
|
| 876 |
+
"grad_norm": 28.958932876586914,
|
| 877 |
+
"learning_rate": 3.648475120385233e-06,
|
| 878 |
+
"loss": 0.0505,
|
| 879 |
+
"step": 1190
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 4.012709416522242,
|
| 883 |
+
"grad_norm": 0.5397215485572815,
|
| 884 |
+
"learning_rate": 3.6324237560192623e-06,
|
| 885 |
+
"loss": 0.0502,
|
| 886 |
+
"step": 1200
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 4.015597920277297,
|
| 890 |
+
"grad_norm": 14.25724983215332,
|
| 891 |
+
"learning_rate": 3.6163723916532904e-06,
|
| 892 |
+
"loss": 0.0464,
|
| 893 |
+
"step": 1210
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 4.018486424032352,
|
| 897 |
+
"grad_norm": 0.7435076832771301,
|
| 898 |
+
"learning_rate": 3.6003210272873197e-06,
|
| 899 |
+
"loss": 0.0605,
|
| 900 |
+
"step": 1220
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 4.021374927787406,
|
| 904 |
+
"grad_norm": 0.11585772037506104,
|
| 905 |
+
"learning_rate": 3.5842696629213486e-06,
|
| 906 |
+
"loss": 0.0408,
|
| 907 |
+
"step": 1230
|
| 908 |
+
},
|
| 909 |
+
{
|
| 910 |
+
"epoch": 4.024263431542461,
|
| 911 |
+
"grad_norm": 2.1825027465820312,
|
| 912 |
+
"learning_rate": 3.5682182985553776e-06,
|
| 913 |
+
"loss": 0.0584,
|
| 914 |
+
"step": 1240
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 4.027151935297516,
|
| 918 |
+
"grad_norm": 0.7946633100509644,
|
| 919 |
+
"learning_rate": 3.5521669341894065e-06,
|
| 920 |
+
"loss": 0.0361,
|
| 921 |
+
"step": 1250
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 4.030040439052571,
|
| 925 |
+
"grad_norm": 0.4123324155807495,
|
| 926 |
+
"learning_rate": 3.536115569823435e-06,
|
| 927 |
+
"loss": 0.1155,
|
| 928 |
+
"step": 1260
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 4.032928942807626,
|
| 932 |
+
"grad_norm": 0.17728902399539948,
|
| 933 |
+
"learning_rate": 3.520064205457464e-06,
|
| 934 |
+
"loss": 0.0038,
|
| 935 |
+
"step": 1270
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 4.035817446562681,
|
| 939 |
+
"grad_norm": 2.5627269744873047,
|
| 940 |
+
"learning_rate": 3.5040128410914932e-06,
|
| 941 |
+
"loss": 0.0489,
|
| 942 |
+
"step": 1280
|
| 943 |
+
},
|
| 944 |
+
{
|
| 945 |
+
"epoch": 4.038705950317736,
|
| 946 |
+
"grad_norm": 2.115309238433838,
|
| 947 |
+
"learning_rate": 3.487961476725522e-06,
|
| 948 |
+
"loss": 0.0572,
|
| 949 |
+
"step": 1290
|
| 950 |
+
},
|
| 951 |
+
{
|
| 952 |
+
"epoch": 4.04159445407279,
|
| 953 |
+
"grad_norm": 0.32022103667259216,
|
| 954 |
+
"learning_rate": 3.471910112359551e-06,
|
| 955 |
+
"loss": 0.067,
|
| 956 |
+
"step": 1300
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 4.044482957827845,
|
| 960 |
+
"grad_norm": 51.26248550415039,
|
| 961 |
+
"learning_rate": 3.4558587479935796e-06,
|
| 962 |
+
"loss": 0.0505,
|
| 963 |
+
"step": 1310
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 4.0473714615829,
|
| 967 |
+
"grad_norm": 3.7673208713531494,
|
| 968 |
+
"learning_rate": 3.4398073836276085e-06,
|
| 969 |
+
"loss": 0.0859,
|
| 970 |
+
"step": 1320
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 4.050259965337955,
|
| 974 |
+
"grad_norm": 47.00321960449219,
|
| 975 |
+
"learning_rate": 3.4237560192616374e-06,
|
| 976 |
+
"loss": 0.0532,
|
| 977 |
+
"step": 1330
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 4.05314846909301,
|
| 981 |
+
"grad_norm": 2.6400699615478516,
|
| 982 |
+
"learning_rate": 3.4077046548956668e-06,
|
| 983 |
+
"loss": 0.0388,
|
| 984 |
+
"step": 1340
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 4.056036972848065,
|
| 988 |
+
"grad_norm": 0.06903611868619919,
|
| 989 |
+
"learning_rate": 3.391653290529695e-06,
|
| 990 |
+
"loss": 0.0154,
|
| 991 |
+
"step": 1350
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 4.05892547660312,
|
| 995 |
+
"grad_norm": 0.4001617431640625,
|
| 996 |
+
"learning_rate": 3.375601926163724e-06,
|
| 997 |
+
"loss": 0.0601,
|
| 998 |
+
"step": 1360
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 4.061813980358174,
|
| 1002 |
+
"grad_norm": 0.8745481967926025,
|
| 1003 |
+
"learning_rate": 3.359550561797753e-06,
|
| 1004 |
+
"loss": 0.0035,
|
| 1005 |
+
"step": 1370
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 4.064702484113229,
|
| 1009 |
+
"grad_norm": 0.3285149931907654,
|
| 1010 |
+
"learning_rate": 3.343499197431782e-06,
|
| 1011 |
+
"loss": 0.0655,
|
| 1012 |
+
"step": 1380
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 4.067590987868284,
|
| 1016 |
+
"grad_norm": 1.2616970539093018,
|
| 1017 |
+
"learning_rate": 3.327447833065811e-06,
|
| 1018 |
+
"loss": 0.0559,
|
| 1019 |
+
"step": 1390
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 4.070479491623339,
|
| 1023 |
+
"grad_norm": 0.5105425715446472,
|
| 1024 |
+
"learning_rate": 3.3113964686998394e-06,
|
| 1025 |
+
"loss": 0.0033,
|
| 1026 |
+
"step": 1400
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 4.073367995378394,
|
| 1030 |
+
"grad_norm": 0.07815102487802505,
|
| 1031 |
+
"learning_rate": 3.2953451043338684e-06,
|
| 1032 |
+
"loss": 0.0535,
|
| 1033 |
+
"step": 1410
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 4.076256499133449,
|
| 1037 |
+
"grad_norm": 50.4415397644043,
|
| 1038 |
+
"learning_rate": 3.2792937399678977e-06,
|
| 1039 |
+
"loss": 0.0305,
|
| 1040 |
+
"step": 1420
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 4.079145002888504,
|
| 1044 |
+
"grad_norm": 0.04866603761911392,
|
| 1045 |
+
"learning_rate": 3.2632423756019266e-06,
|
| 1046 |
+
"loss": 0.0752,
|
| 1047 |
+
"step": 1430
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 4.082033506643558,
|
| 1051 |
+
"grad_norm": 0.6638075113296509,
|
| 1052 |
+
"learning_rate": 3.2471910112359555e-06,
|
| 1053 |
+
"loss": 0.0246,
|
| 1054 |
+
"step": 1440
|
| 1055 |
+
},
|
| 1056 |
+
{
|
| 1057 |
+
"epoch": 4.083477758521086,
|
| 1058 |
+
"eval_accuracy": 0.8159509202453987,
|
| 1059 |
+
"eval_loss": 0.7590932250022888,
|
| 1060 |
+
"eval_runtime": 67.4418,
|
| 1061 |
+
"eval_samples_per_second": 7.251,
|
| 1062 |
+
"eval_steps_per_second": 0.919,
|
| 1063 |
+
"step": 1445
|
| 1064 |
+
},
|
| 1065 |
+
{
|
| 1066 |
+
"epoch": 5.001444251877527,
|
| 1067 |
+
"grad_norm": 0.060185324400663376,
|
| 1068 |
+
"learning_rate": 3.231139646869984e-06,
|
| 1069 |
+
"loss": 0.002,
|
| 1070 |
+
"step": 1450
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 5.004332755632582,
|
| 1074 |
+
"grad_norm": 0.07039889693260193,
|
| 1075 |
+
"learning_rate": 3.215088282504013e-06,
|
| 1076 |
+
"loss": 0.0285,
|
| 1077 |
+
"step": 1460
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 5.007221259387637,
|
| 1081 |
+
"grad_norm": 0.03269031643867493,
|
| 1082 |
+
"learning_rate": 3.199036918138042e-06,
|
| 1083 |
+
"loss": 0.0065,
|
| 1084 |
+
"step": 1470
|
| 1085 |
+
},
|
| 1086 |
+
{
|
| 1087 |
+
"epoch": 5.010109763142692,
|
| 1088 |
+
"grad_norm": 0.32333606481552124,
|
| 1089 |
+
"learning_rate": 3.1829855537720712e-06,
|
| 1090 |
+
"loss": 0.0105,
|
| 1091 |
+
"step": 1480
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 5.012998266897747,
|
| 1095 |
+
"grad_norm": 0.03409011289477348,
|
| 1096 |
+
"learning_rate": 3.1669341894060997e-06,
|
| 1097 |
+
"loss": 0.0347,
|
| 1098 |
+
"step": 1490
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 5.015886770652802,
|
| 1102 |
+
"grad_norm": 0.19116906821727753,
|
| 1103 |
+
"learning_rate": 3.1508828250401286e-06,
|
| 1104 |
+
"loss": 0.0034,
|
| 1105 |
+
"step": 1500
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 5.018775274407857,
|
| 1109 |
+
"grad_norm": 0.25904765725135803,
|
| 1110 |
+
"learning_rate": 3.1348314606741576e-06,
|
| 1111 |
+
"loss": 0.0234,
|
| 1112 |
+
"step": 1510
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 5.021663778162911,
|
| 1116 |
+
"grad_norm": 0.3230428695678711,
|
| 1117 |
+
"learning_rate": 3.1187800963081865e-06,
|
| 1118 |
+
"loss": 0.0316,
|
| 1119 |
+
"step": 1520
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 5.024552281917966,
|
| 1123 |
+
"grad_norm": 0.10437498986721039,
|
| 1124 |
+
"learning_rate": 3.1027287319422154e-06,
|
| 1125 |
+
"loss": 0.004,
|
| 1126 |
+
"step": 1530
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 5.027440785673021,
|
| 1130 |
+
"grad_norm": 0.46833401918411255,
|
| 1131 |
+
"learning_rate": 3.086677367576244e-06,
|
| 1132 |
+
"loss": 0.0075,
|
| 1133 |
+
"step": 1540
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 5.030329289428076,
|
| 1137 |
+
"grad_norm": 0.21706847846508026,
|
| 1138 |
+
"learning_rate": 3.0706260032102732e-06,
|
| 1139 |
+
"loss": 0.012,
|
| 1140 |
+
"step": 1550
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 5.033217793183131,
|
| 1144 |
+
"grad_norm": 3.5541529655456543,
|
| 1145 |
+
"learning_rate": 3.054574638844302e-06,
|
| 1146 |
+
"loss": 0.0654,
|
| 1147 |
+
"step": 1560
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 5.036106296938186,
|
| 1151 |
+
"grad_norm": 35.335044860839844,
|
| 1152 |
+
"learning_rate": 3.038523274478331e-06,
|
| 1153 |
+
"loss": 0.0402,
|
| 1154 |
+
"step": 1570
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 5.038994800693241,
|
| 1158 |
+
"grad_norm": 1.4521031379699707,
|
| 1159 |
+
"learning_rate": 3.02247191011236e-06,
|
| 1160 |
+
"loss": 0.0033,
|
| 1161 |
+
"step": 1580
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 5.041883304448295,
|
| 1165 |
+
"grad_norm": 4.004300594329834,
|
| 1166 |
+
"learning_rate": 3.0064205457463885e-06,
|
| 1167 |
+
"loss": 0.0455,
|
| 1168 |
+
"step": 1590
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 5.04477180820335,
|
| 1172 |
+
"grad_norm": 2.2921578884124756,
|
| 1173 |
+
"learning_rate": 2.9903691813804174e-06,
|
| 1174 |
+
"loss": 0.0058,
|
| 1175 |
+
"step": 1600
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 5.047660311958405,
|
| 1179 |
+
"grad_norm": 0.06124192476272583,
|
| 1180 |
+
"learning_rate": 2.9743178170144463e-06,
|
| 1181 |
+
"loss": 0.0029,
|
| 1182 |
+
"step": 1610
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 5.05054881571346,
|
| 1186 |
+
"grad_norm": 0.20763950049877167,
|
| 1187 |
+
"learning_rate": 2.9582664526484757e-06,
|
| 1188 |
+
"loss": 0.0135,
|
| 1189 |
+
"step": 1620
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 5.053437319468515,
|
| 1193 |
+
"grad_norm": 0.05570823326706886,
|
| 1194 |
+
"learning_rate": 2.942215088282504e-06,
|
| 1195 |
+
"loss": 0.0141,
|
| 1196 |
+
"step": 1630
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 5.05632582322357,
|
| 1200 |
+
"grad_norm": 11.078546524047852,
|
| 1201 |
+
"learning_rate": 2.926163723916533e-06,
|
| 1202 |
+
"loss": 0.0354,
|
| 1203 |
+
"step": 1640
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 5.059214326978625,
|
| 1207 |
+
"grad_norm": 0.05520700663328171,
|
| 1208 |
+
"learning_rate": 2.910112359550562e-06,
|
| 1209 |
+
"loss": 0.0205,
|
| 1210 |
+
"step": 1650
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 5.06210283073368,
|
| 1214 |
+
"grad_norm": 1.370224118232727,
|
| 1215 |
+
"learning_rate": 2.894060995184591e-06,
|
| 1216 |
+
"loss": 0.0302,
|
| 1217 |
+
"step": 1660
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 5.0649913344887345,
|
| 1221 |
+
"grad_norm": 29.20268440246582,
|
| 1222 |
+
"learning_rate": 2.87800963081862e-06,
|
| 1223 |
+
"loss": 0.0856,
|
| 1224 |
+
"step": 1670
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 5.0678798382437895,
|
| 1228 |
+
"grad_norm": 0.0997309535741806,
|
| 1229 |
+
"learning_rate": 2.8619582664526484e-06,
|
| 1230 |
+
"loss": 0.0017,
|
| 1231 |
+
"step": 1680
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 5.0707683419988445,
|
| 1235 |
+
"grad_norm": 0.5986093878746033,
|
| 1236 |
+
"learning_rate": 2.8459069020866777e-06,
|
| 1237 |
+
"loss": 0.0045,
|
| 1238 |
+
"step": 1690
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 5.0736568457538995,
|
| 1242 |
+
"grad_norm": 1.4065715074539185,
|
| 1243 |
+
"learning_rate": 2.8298555377207066e-06,
|
| 1244 |
+
"loss": 0.0227,
|
| 1245 |
+
"step": 1700
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 5.0765453495089545,
|
| 1249 |
+
"grad_norm": 29.846811294555664,
|
| 1250 |
+
"learning_rate": 2.8138041733547356e-06,
|
| 1251 |
+
"loss": 0.127,
|
| 1252 |
+
"step": 1710
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 5.0794338532640095,
|
| 1256 |
+
"grad_norm": 0.12639851868152618,
|
| 1257 |
+
"learning_rate": 2.797752808988764e-06,
|
| 1258 |
+
"loss": 0.0016,
|
| 1259 |
+
"step": 1720
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 5.0823223570190645,
|
| 1263 |
+
"grad_norm": 16.550195693969727,
|
| 1264 |
+
"learning_rate": 2.781701444622793e-06,
|
| 1265 |
+
"loss": 0.0587,
|
| 1266 |
+
"step": 1730
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 5.083477758521086,
|
| 1270 |
+
"eval_accuracy": 0.8220858895705522,
|
| 1271 |
+
"eval_loss": 0.8467618227005005,
|
| 1272 |
+
"eval_runtime": 69.3503,
|
| 1273 |
+
"eval_samples_per_second": 7.051,
|
| 1274 |
+
"eval_steps_per_second": 0.894,
|
| 1275 |
+
"step": 1734
|
| 1276 |
+
},
|
| 1277 |
+
{
|
| 1278 |
+
"epoch": 6.001733102253033,
|
| 1279 |
+
"grad_norm": 0.0677463710308075,
|
| 1280 |
+
"learning_rate": 2.765650080256822e-06,
|
| 1281 |
+
"loss": 0.0073,
|
| 1282 |
+
"step": 1740
|
| 1283 |
+
},
|
| 1284 |
+
{
|
| 1285 |
+
"epoch": 6.0046216060080875,
|
| 1286 |
+
"grad_norm": 0.08975090831518173,
|
| 1287 |
+
"learning_rate": 2.7495987158908512e-06,
|
| 1288 |
+
"loss": 0.0022,
|
| 1289 |
+
"step": 1750
|
| 1290 |
+
},
|
| 1291 |
+
{
|
| 1292 |
+
"epoch": 6.0075101097631425,
|
| 1293 |
+
"grad_norm": 0.31082966923713684,
|
| 1294 |
+
"learning_rate": 2.73354735152488e-06,
|
| 1295 |
+
"loss": 0.0042,
|
| 1296 |
+
"step": 1760
|
| 1297 |
+
},
|
| 1298 |
+
{
|
| 1299 |
+
"epoch": 6.0103986135181975,
|
| 1300 |
+
"grad_norm": 0.11679187417030334,
|
| 1301 |
+
"learning_rate": 2.7174959871589087e-06,
|
| 1302 |
+
"loss": 0.0487,
|
| 1303 |
+
"step": 1770
|
| 1304 |
+
},
|
| 1305 |
+
{
|
| 1306 |
+
"epoch": 6.0132871172732525,
|
| 1307 |
+
"grad_norm": 30.055280685424805,
|
| 1308 |
+
"learning_rate": 2.7014446227929376e-06,
|
| 1309 |
+
"loss": 0.0139,
|
| 1310 |
+
"step": 1780
|
| 1311 |
+
},
|
| 1312 |
+
{
|
| 1313 |
+
"epoch": 6.0161756210283075,
|
| 1314 |
+
"grad_norm": 0.5157354474067688,
|
| 1315 |
+
"learning_rate": 2.6853932584269665e-06,
|
| 1316 |
+
"loss": 0.0094,
|
| 1317 |
+
"step": 1790
|
| 1318 |
+
},
|
| 1319 |
+
{
|
| 1320 |
+
"epoch": 6.0190641247833625,
|
| 1321 |
+
"grad_norm": 0.036292631179094315,
|
| 1322 |
+
"learning_rate": 2.6693418940609954e-06,
|
| 1323 |
+
"loss": 0.0204,
|
| 1324 |
+
"step": 1800
|
| 1325 |
+
},
|
| 1326 |
+
{
|
| 1327 |
+
"epoch": 6.0219526285384175,
|
| 1328 |
+
"grad_norm": 0.013917963020503521,
|
| 1329 |
+
"learning_rate": 2.6532905296950243e-06,
|
| 1330 |
+
"loss": 0.0053,
|
| 1331 |
+
"step": 1810
|
| 1332 |
+
},
|
| 1333 |
+
{
|
| 1334 |
+
"epoch": 6.024841132293472,
|
| 1335 |
+
"grad_norm": 0.21816915273666382,
|
| 1336 |
+
"learning_rate": 2.637239165329053e-06,
|
| 1337 |
+
"loss": 0.0093,
|
| 1338 |
+
"step": 1820
|
| 1339 |
+
},
|
| 1340 |
+
{
|
| 1341 |
+
"epoch": 6.027729636048527,
|
| 1342 |
+
"grad_norm": 0.193815678358078,
|
| 1343 |
+
"learning_rate": 2.621187800963082e-06,
|
| 1344 |
+
"loss": 0.0076,
|
| 1345 |
+
"step": 1830
|
| 1346 |
+
},
|
| 1347 |
+
{
|
| 1348 |
+
"epoch": 6.030618139803582,
|
| 1349 |
+
"grad_norm": 0.46772897243499756,
|
| 1350 |
+
"learning_rate": 2.605136436597111e-06,
|
| 1351 |
+
"loss": 0.0059,
|
| 1352 |
+
"step": 1840
|
| 1353 |
+
},
|
| 1354 |
+
{
|
| 1355 |
+
"epoch": 6.033506643558637,
|
| 1356 |
+
"grad_norm": 0.014806525781750679,
|
| 1357 |
+
"learning_rate": 2.58908507223114e-06,
|
| 1358 |
+
"loss": 0.0081,
|
| 1359 |
+
"step": 1850
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 6.036395147313692,
|
| 1363 |
+
"grad_norm": 0.5249377489089966,
|
| 1364 |
+
"learning_rate": 2.5730337078651685e-06,
|
| 1365 |
+
"loss": 0.0084,
|
| 1366 |
+
"step": 1860
|
| 1367 |
+
},
|
| 1368 |
+
{
|
| 1369 |
+
"epoch": 6.039283651068747,
|
| 1370 |
+
"grad_norm": 0.05226698890328407,
|
| 1371 |
+
"learning_rate": 2.5569823434991974e-06,
|
| 1372 |
+
"loss": 0.0016,
|
| 1373 |
+
"step": 1870
|
| 1374 |
+
},
|
| 1375 |
+
{
|
| 1376 |
+
"epoch": 6.042172154823802,
|
| 1377 |
+
"grad_norm": 0.028807491064071655,
|
| 1378 |
+
"learning_rate": 2.5409309791332264e-06,
|
| 1379 |
+
"loss": 0.0026,
|
| 1380 |
+
"step": 1880
|
| 1381 |
+
},
|
| 1382 |
+
{
|
| 1383 |
+
"epoch": 6.045060658578856,
|
| 1384 |
+
"grad_norm": 0.28243187069892883,
|
| 1385 |
+
"learning_rate": 2.5248796147672557e-06,
|
| 1386 |
+
"loss": 0.001,
|
| 1387 |
+
"step": 1890
|
| 1388 |
+
},
|
| 1389 |
+
{
|
| 1390 |
+
"epoch": 6.047949162333911,
|
| 1391 |
+
"grad_norm": 0.03083970583975315,
|
| 1392 |
+
"learning_rate": 2.5088282504012846e-06,
|
| 1393 |
+
"loss": 0.0015,
|
| 1394 |
+
"step": 1900
|
| 1395 |
+
},
|
| 1396 |
+
{
|
| 1397 |
+
"epoch": 6.050837666088966,
|
| 1398 |
+
"grad_norm": 0.11073260754346848,
|
| 1399 |
+
"learning_rate": 2.492776886035313e-06,
|
| 1400 |
+
"loss": 0.0146,
|
| 1401 |
+
"step": 1910
|
| 1402 |
+
},
|
| 1403 |
+
{
|
| 1404 |
+
"epoch": 6.053726169844021,
|
| 1405 |
+
"grad_norm": 0.07196179777383804,
|
| 1406 |
+
"learning_rate": 2.476725521669342e-06,
|
| 1407 |
+
"loss": 0.0171,
|
| 1408 |
+
"step": 1920
|
| 1409 |
+
},
|
| 1410 |
+
{
|
| 1411 |
+
"epoch": 6.056614673599076,
|
| 1412 |
+
"grad_norm": 0.09667622298002243,
|
| 1413 |
+
"learning_rate": 2.460674157303371e-06,
|
| 1414 |
+
"loss": 0.0023,
|
| 1415 |
+
"step": 1930
|
| 1416 |
+
},
|
| 1417 |
+
{
|
| 1418 |
+
"epoch": 6.059503177354131,
|
| 1419 |
+
"grad_norm": 1.5665602684020996,
|
| 1420 |
+
"learning_rate": 2.4446227929374e-06,
|
| 1421 |
+
"loss": 0.0011,
|
| 1422 |
+
"step": 1940
|
| 1423 |
+
},
|
| 1424 |
+
{
|
| 1425 |
+
"epoch": 6.062391681109186,
|
| 1426 |
+
"grad_norm": 0.15951007604599,
|
| 1427 |
+
"learning_rate": 2.428571428571429e-06,
|
| 1428 |
+
"loss": 0.0126,
|
| 1429 |
+
"step": 1950
|
| 1430 |
+
},
|
| 1431 |
+
{
|
| 1432 |
+
"epoch": 6.06528018486424,
|
| 1433 |
+
"grad_norm": 0.16798914968967438,
|
| 1434 |
+
"learning_rate": 2.4125200642054577e-06,
|
| 1435 |
+
"loss": 0.0042,
|
| 1436 |
+
"step": 1960
|
| 1437 |
+
},
|
| 1438 |
+
{
|
| 1439 |
+
"epoch": 6.068168688619295,
|
| 1440 |
+
"grad_norm": 0.17065782845020294,
|
| 1441 |
+
"learning_rate": 2.3964686998394866e-06,
|
| 1442 |
+
"loss": 0.1316,
|
| 1443 |
+
"step": 1970
|
| 1444 |
+
},
|
| 1445 |
+
{
|
| 1446 |
+
"epoch": 6.07105719237435,
|
| 1447 |
+
"grad_norm": 1.0885783433914185,
|
| 1448 |
+
"learning_rate": 2.3804173354735156e-06,
|
| 1449 |
+
"loss": 0.0021,
|
| 1450 |
+
"step": 1980
|
| 1451 |
+
},
|
| 1452 |
+
{
|
| 1453 |
+
"epoch": 6.073945696129405,
|
| 1454 |
+
"grad_norm": 0.4040501117706299,
|
| 1455 |
+
"learning_rate": 2.364365971107544e-06,
|
| 1456 |
+
"loss": 0.0013,
|
| 1457 |
+
"step": 1990
|
| 1458 |
+
},
|
| 1459 |
+
{
|
| 1460 |
+
"epoch": 6.07683419988446,
|
| 1461 |
+
"grad_norm": 14.820023536682129,
|
| 1462 |
+
"learning_rate": 2.3483146067415734e-06,
|
| 1463 |
+
"loss": 0.0077,
|
| 1464 |
+
"step": 2000
|
| 1465 |
+
},
|
| 1466 |
+
{
|
| 1467 |
+
"epoch": 6.079722703639515,
|
| 1468 |
+
"grad_norm": 0.065485380589962,
|
| 1469 |
+
"learning_rate": 2.3322632423756023e-06,
|
| 1470 |
+
"loss": 0.0047,
|
| 1471 |
+
"step": 2010
|
| 1472 |
+
},
|
| 1473 |
+
{
|
| 1474 |
+
"epoch": 6.08261120739457,
|
| 1475 |
+
"grad_norm": 2.0591225624084473,
|
| 1476 |
+
"learning_rate": 2.316211878009631e-06,
|
| 1477 |
+
"loss": 0.0351,
|
| 1478 |
+
"step": 2020
|
| 1479 |
+
},
|
| 1480 |
+
{
|
| 1481 |
+
"epoch": 6.083477758521086,
|
| 1482 |
+
"eval_accuracy": 0.8179959100204499,
|
| 1483 |
+
"eval_loss": 0.8952175974845886,
|
| 1484 |
+
"eval_runtime": 67.365,
|
| 1485 |
+
"eval_samples_per_second": 7.259,
|
| 1486 |
+
"eval_steps_per_second": 0.92,
|
| 1487 |
+
"step": 2023
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 7.002021952628539,
|
| 1491 |
+
"grad_norm": 0.09516696631908417,
|
| 1492 |
+
"learning_rate": 2.30016051364366e-06,
|
| 1493 |
+
"loss": 0.0007,
|
| 1494 |
+
"step": 2030
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 7.004910456383593,
|
| 1498 |
+
"grad_norm": 0.14757688343524933,
|
| 1499 |
+
"learning_rate": 2.2841091492776887e-06,
|
| 1500 |
+
"loss": 0.0006,
|
| 1501 |
+
"step": 2040
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 7.007798960138648,
|
| 1505 |
+
"grad_norm": 0.19937986135482788,
|
| 1506 |
+
"learning_rate": 2.2680577849117176e-06,
|
| 1507 |
+
"loss": 0.0008,
|
| 1508 |
+
"step": 2050
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 7.010687463893703,
|
| 1512 |
+
"grad_norm": 4.664211750030518,
|
| 1513 |
+
"learning_rate": 2.2520064205457465e-06,
|
| 1514 |
+
"loss": 0.0018,
|
| 1515 |
+
"step": 2060
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 7.013575967648758,
|
| 1519 |
+
"grad_norm": 0.44122084975242615,
|
| 1520 |
+
"learning_rate": 2.2359550561797754e-06,
|
| 1521 |
+
"loss": 0.0025,
|
| 1522 |
+
"step": 2070
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 7.016464471403813,
|
| 1526 |
+
"grad_norm": 0.4168035387992859,
|
| 1527 |
+
"learning_rate": 2.2199036918138043e-06,
|
| 1528 |
+
"loss": 0.0012,
|
| 1529 |
+
"step": 2080
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 7.019352975158868,
|
| 1533 |
+
"grad_norm": 0.30642348527908325,
|
| 1534 |
+
"learning_rate": 2.2038523274478333e-06,
|
| 1535 |
+
"loss": 0.0033,
|
| 1536 |
+
"step": 2090
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 7.022241478913923,
|
| 1540 |
+
"grad_norm": 0.1506723016500473,
|
| 1541 |
+
"learning_rate": 2.187800963081862e-06,
|
| 1542 |
+
"loss": 0.0007,
|
| 1543 |
+
"step": 2100
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 7.025129982668977,
|
| 1547 |
+
"grad_norm": 0.050181757658720016,
|
| 1548 |
+
"learning_rate": 2.171749598715891e-06,
|
| 1549 |
+
"loss": 0.0011,
|
| 1550 |
+
"step": 2110
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 7.028018486424032,
|
| 1554 |
+
"grad_norm": 0.3687441349029541,
|
| 1555 |
+
"learning_rate": 2.15569823434992e-06,
|
| 1556 |
+
"loss": 0.0013,
|
| 1557 |
+
"step": 2120
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 7.030906990179087,
|
| 1561 |
+
"grad_norm": 1.2629284858703613,
|
| 1562 |
+
"learning_rate": 2.1396468699839485e-06,
|
| 1563 |
+
"loss": 0.0031,
|
| 1564 |
+
"step": 2130
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 7.033795493934142,
|
| 1568 |
+
"grad_norm": 0.010518478229641914,
|
| 1569 |
+
"learning_rate": 2.123595505617978e-06,
|
| 1570 |
+
"loss": 0.0133,
|
| 1571 |
+
"step": 2140
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 7.036683997689197,
|
| 1575 |
+
"grad_norm": 0.22406050562858582,
|
| 1576 |
+
"learning_rate": 2.1075441412520064e-06,
|
| 1577 |
+
"loss": 0.0164,
|
| 1578 |
+
"step": 2150
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 7.039572501444252,
|
| 1582 |
+
"grad_norm": 0.6182830333709717,
|
| 1583 |
+
"learning_rate": 2.0914927768860353e-06,
|
| 1584 |
+
"loss": 0.0039,
|
| 1585 |
+
"step": 2160
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 7.042461005199307,
|
| 1589 |
+
"grad_norm": 0.028110405430197716,
|
| 1590 |
+
"learning_rate": 2.0754414125200646e-06,
|
| 1591 |
+
"loss": 0.0314,
|
| 1592 |
+
"step": 2170
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 7.045349508954362,
|
| 1596 |
+
"grad_norm": 0.15830457210540771,
|
| 1597 |
+
"learning_rate": 2.059390048154093e-06,
|
| 1598 |
+
"loss": 0.0021,
|
| 1599 |
+
"step": 2180
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 7.048238012709416,
|
| 1603 |
+
"grad_norm": 0.026566576212644577,
|
| 1604 |
+
"learning_rate": 2.043338683788122e-06,
|
| 1605 |
+
"loss": 0.0079,
|
| 1606 |
+
"step": 2190
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 7.051126516464471,
|
| 1610 |
+
"grad_norm": 0.16128750145435333,
|
| 1611 |
+
"learning_rate": 2.027287319422151e-06,
|
| 1612 |
+
"loss": 0.0036,
|
| 1613 |
+
"step": 2200
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 7.054015020219526,
|
| 1617 |
+
"grad_norm": 0.1151314377784729,
|
| 1618 |
+
"learning_rate": 2.01123595505618e-06,
|
| 1619 |
+
"loss": 0.0009,
|
| 1620 |
+
"step": 2210
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 7.056903523974581,
|
| 1624 |
+
"grad_norm": 5.008311748504639,
|
| 1625 |
+
"learning_rate": 1.995184590690209e-06,
|
| 1626 |
+
"loss": 0.0182,
|
| 1627 |
+
"step": 2220
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 7.059792027729636,
|
| 1631 |
+
"grad_norm": 0.17845681309700012,
|
| 1632 |
+
"learning_rate": 1.9791332263242377e-06,
|
| 1633 |
+
"loss": 0.0007,
|
| 1634 |
+
"step": 2230
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 7.062680531484691,
|
| 1638 |
+
"grad_norm": 0.620922327041626,
|
| 1639 |
+
"learning_rate": 1.9630818619582666e-06,
|
| 1640 |
+
"loss": 0.0013,
|
| 1641 |
+
"step": 2240
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 7.065569035239746,
|
| 1645 |
+
"grad_norm": 0.22967398166656494,
|
| 1646 |
+
"learning_rate": 1.9470304975922956e-06,
|
| 1647 |
+
"loss": 0.0008,
|
| 1648 |
+
"step": 2250
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 7.0684575389948,
|
| 1652 |
+
"grad_norm": 0.4523940682411194,
|
| 1653 |
+
"learning_rate": 1.9309791332263245e-06,
|
| 1654 |
+
"loss": 0.0008,
|
| 1655 |
+
"step": 2260
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 7.071346042749855,
|
| 1659 |
+
"grad_norm": 70.14838409423828,
|
| 1660 |
+
"learning_rate": 1.9149277688603534e-06,
|
| 1661 |
+
"loss": 0.0123,
|
| 1662 |
+
"step": 2270
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 7.07423454650491,
|
| 1666 |
+
"grad_norm": 0.06539999693632126,
|
| 1667 |
+
"learning_rate": 1.8988764044943821e-06,
|
| 1668 |
+
"loss": 0.0014,
|
| 1669 |
+
"step": 2280
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 7.077123050259965,
|
| 1673 |
+
"grad_norm": 0.6128162145614624,
|
| 1674 |
+
"learning_rate": 1.882825040128411e-06,
|
| 1675 |
+
"loss": 0.0924,
|
| 1676 |
+
"step": 2290
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 7.08001155401502,
|
| 1680 |
+
"grad_norm": 0.013330874964594841,
|
| 1681 |
+
"learning_rate": 1.86677367576244e-06,
|
| 1682 |
+
"loss": 0.0005,
|
| 1683 |
+
"step": 2300
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 7.082900057770075,
|
| 1687 |
+
"grad_norm": 0.8353597521781921,
|
| 1688 |
+
"learning_rate": 1.8507223113964689e-06,
|
| 1689 |
+
"loss": 0.001,
|
| 1690 |
+
"step": 2310
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 7.083477758521086,
|
| 1694 |
+
"eval_accuracy": 0.8098159509202454,
|
| 1695 |
+
"eval_loss": 1.0094096660614014,
|
| 1696 |
+
"eval_runtime": 67.7303,
|
| 1697 |
+
"eval_samples_per_second": 7.22,
|
| 1698 |
+
"eval_steps_per_second": 0.915,
|
| 1699 |
+
"step": 2312
|
| 1700 |
+
},
|
| 1701 |
+
{
|
| 1702 |
+
"epoch": 8.002310803004043,
|
| 1703 |
+
"grad_norm": 3.3091068267822266,
|
| 1704 |
+
"learning_rate": 1.8346709470304978e-06,
|
| 1705 |
+
"loss": 0.0028,
|
| 1706 |
+
"step": 2320
|
| 1707 |
+
},
|
| 1708 |
+
{
|
| 1709 |
+
"epoch": 8.0051993067591,
|
| 1710 |
+
"grad_norm": 0.01653185486793518,
|
| 1711 |
+
"learning_rate": 1.8186195826645267e-06,
|
| 1712 |
+
"loss": 0.0006,
|
| 1713 |
+
"step": 2330
|
| 1714 |
+
},
|
| 1715 |
+
{
|
| 1716 |
+
"epoch": 8.008087810514153,
|
| 1717 |
+
"grad_norm": 0.07168268412351608,
|
| 1718 |
+
"learning_rate": 1.8025682182985554e-06,
|
| 1719 |
+
"loss": 0.0015,
|
| 1720 |
+
"step": 2340
|
| 1721 |
+
},
|
| 1722 |
+
{
|
| 1723 |
+
"epoch": 8.01097631426921,
|
| 1724 |
+
"grad_norm": 8.671859741210938,
|
| 1725 |
+
"learning_rate": 1.7865168539325846e-06,
|
| 1726 |
+
"loss": 0.0018,
|
| 1727 |
+
"step": 2350
|
| 1728 |
+
},
|
| 1729 |
+
{
|
| 1730 |
+
"epoch": 8.013864818024263,
|
| 1731 |
+
"grad_norm": 0.32845407724380493,
|
| 1732 |
+
"learning_rate": 1.7704654895666133e-06,
|
| 1733 |
+
"loss": 0.0011,
|
| 1734 |
+
"step": 2360
|
| 1735 |
+
},
|
| 1736 |
+
{
|
| 1737 |
+
"epoch": 8.016753321779317,
|
| 1738 |
+
"grad_norm": 0.029094768688082695,
|
| 1739 |
+
"learning_rate": 1.7544141252006422e-06,
|
| 1740 |
+
"loss": 0.0016,
|
| 1741 |
+
"step": 2370
|
| 1742 |
+
},
|
| 1743 |
+
{
|
| 1744 |
+
"epoch": 8.019641825534373,
|
| 1745 |
+
"grad_norm": 0.28631359338760376,
|
| 1746 |
+
"learning_rate": 1.738362760834671e-06,
|
| 1747 |
+
"loss": 0.0007,
|
| 1748 |
+
"step": 2380
|
| 1749 |
+
},
|
| 1750 |
+
{
|
| 1751 |
+
"epoch": 8.022530329289427,
|
| 1752 |
+
"grad_norm": 0.07883863896131516,
|
| 1753 |
+
"learning_rate": 1.7223113964687e-06,
|
| 1754 |
+
"loss": 0.0008,
|
| 1755 |
+
"step": 2390
|
| 1756 |
+
},
|
| 1757 |
+
{
|
| 1758 |
+
"epoch": 8.025418833044483,
|
| 1759 |
+
"grad_norm": 0.1313171684741974,
|
| 1760 |
+
"learning_rate": 1.706260032102729e-06,
|
| 1761 |
+
"loss": 0.0005,
|
| 1762 |
+
"step": 2400
|
| 1763 |
+
},
|
| 1764 |
+
{
|
| 1765 |
+
"epoch": 8.028307336799537,
|
| 1766 |
+
"grad_norm": 0.00614338181912899,
|
| 1767 |
+
"learning_rate": 1.6902086677367576e-06,
|
| 1768 |
+
"loss": 0.0029,
|
| 1769 |
+
"step": 2410
|
| 1770 |
+
},
|
| 1771 |
+
{
|
| 1772 |
+
"epoch": 8.031195840554593,
|
| 1773 |
+
"grad_norm": 0.008385803550481796,
|
| 1774 |
+
"learning_rate": 1.6741573033707868e-06,
|
| 1775 |
+
"loss": 0.0011,
|
| 1776 |
+
"step": 2420
|
| 1777 |
+
},
|
| 1778 |
+
{
|
| 1779 |
+
"epoch": 8.034084344309647,
|
| 1780 |
+
"grad_norm": 0.07132828235626221,
|
| 1781 |
+
"learning_rate": 1.6581059390048155e-06,
|
| 1782 |
+
"loss": 0.0004,
|
| 1783 |
+
"step": 2430
|
| 1784 |
+
},
|
| 1785 |
+
{
|
| 1786 |
+
"epoch": 8.036972848064703,
|
| 1787 |
+
"grad_norm": 0.018882159143686295,
|
| 1788 |
+
"learning_rate": 1.6420545746388444e-06,
|
| 1789 |
+
"loss": 0.0003,
|
| 1790 |
+
"step": 2440
|
| 1791 |
+
},
|
| 1792 |
+
{
|
| 1793 |
+
"epoch": 8.039861351819757,
|
| 1794 |
+
"grad_norm": 0.9956786036491394,
|
| 1795 |
+
"learning_rate": 1.6260032102728735e-06,
|
| 1796 |
+
"loss": 0.0004,
|
| 1797 |
+
"step": 2450
|
| 1798 |
+
},
|
| 1799 |
+
{
|
| 1800 |
+
"epoch": 8.042749855574812,
|
| 1801 |
+
"grad_norm": 0.03203749656677246,
|
| 1802 |
+
"learning_rate": 1.6099518459069023e-06,
|
| 1803 |
+
"loss": 0.0004,
|
| 1804 |
+
"step": 2460
|
| 1805 |
+
},
|
| 1806 |
+
{
|
| 1807 |
+
"epoch": 8.045638359329867,
|
| 1808 |
+
"grad_norm": 0.016354788094758987,
|
| 1809 |
+
"learning_rate": 1.5939004815409312e-06,
|
| 1810 |
+
"loss": 0.0009,
|
| 1811 |
+
"step": 2470
|
| 1812 |
+
},
|
| 1813 |
+
{
|
| 1814 |
+
"epoch": 8.048526863084922,
|
| 1815 |
+
"grad_norm": 0.06263572722673416,
|
| 1816 |
+
"learning_rate": 1.5778491171749599e-06,
|
| 1817 |
+
"loss": 0.0004,
|
| 1818 |
+
"step": 2480
|
| 1819 |
+
},
|
| 1820 |
+
{
|
| 1821 |
+
"epoch": 8.051415366839977,
|
| 1822 |
+
"grad_norm": 0.39288368821144104,
|
| 1823 |
+
"learning_rate": 1.561797752808989e-06,
|
| 1824 |
+
"loss": 0.0009,
|
| 1825 |
+
"step": 2490
|
| 1826 |
+
},
|
| 1827 |
+
{
|
| 1828 |
+
"epoch": 8.054303870595032,
|
| 1829 |
+
"grad_norm": 0.02906760200858116,
|
| 1830 |
+
"learning_rate": 1.5457463884430177e-06,
|
| 1831 |
+
"loss": 0.0006,
|
| 1832 |
+
"step": 2500
|
| 1833 |
+
},
|
| 1834 |
+
{
|
| 1835 |
+
"epoch": 8.057192374350088,
|
| 1836 |
+
"grad_norm": 0.012857715599238873,
|
| 1837 |
+
"learning_rate": 1.5296950240770466e-06,
|
| 1838 |
+
"loss": 0.0005,
|
| 1839 |
+
"step": 2510
|
| 1840 |
+
},
|
| 1841 |
+
{
|
| 1842 |
+
"epoch": 8.060080878105142,
|
| 1843 |
+
"grad_norm": 0.01696927100419998,
|
| 1844 |
+
"learning_rate": 1.5136436597110758e-06,
|
| 1845 |
+
"loss": 0.0002,
|
| 1846 |
+
"step": 2520
|
| 1847 |
+
},
|
| 1848 |
+
{
|
| 1849 |
+
"epoch": 8.062969381860196,
|
| 1850 |
+
"grad_norm": 0.011458744294941425,
|
| 1851 |
+
"learning_rate": 1.4975922953451045e-06,
|
| 1852 |
+
"loss": 0.0006,
|
| 1853 |
+
"step": 2530
|
| 1854 |
+
},
|
| 1855 |
+
{
|
| 1856 |
+
"epoch": 8.065857885615252,
|
| 1857 |
+
"grad_norm": 0.10132727771997452,
|
| 1858 |
+
"learning_rate": 1.4815409309791334e-06,
|
| 1859 |
+
"loss": 0.0007,
|
| 1860 |
+
"step": 2540
|
| 1861 |
+
},
|
| 1862 |
+
{
|
| 1863 |
+
"epoch": 8.068746389370306,
|
| 1864 |
+
"grad_norm": 0.029605470597743988,
|
| 1865 |
+
"learning_rate": 1.4654895666131621e-06,
|
| 1866 |
+
"loss": 0.0105,
|
| 1867 |
+
"step": 2550
|
| 1868 |
+
},
|
| 1869 |
+
{
|
| 1870 |
+
"epoch": 8.071634893125362,
|
| 1871 |
+
"grad_norm": 0.03353351354598999,
|
| 1872 |
+
"learning_rate": 1.4494382022471912e-06,
|
| 1873 |
+
"loss": 0.0005,
|
| 1874 |
+
"step": 2560
|
| 1875 |
+
},
|
| 1876 |
+
{
|
| 1877 |
+
"epoch": 8.074523396880416,
|
| 1878 |
+
"grad_norm": 0.01684616506099701,
|
| 1879 |
+
"learning_rate": 1.43338683788122e-06,
|
| 1880 |
+
"loss": 0.0011,
|
| 1881 |
+
"step": 2570
|
| 1882 |
+
},
|
| 1883 |
+
{
|
| 1884 |
+
"epoch": 8.077411900635472,
|
| 1885 |
+
"grad_norm": 0.46243542432785034,
|
| 1886 |
+
"learning_rate": 1.4173354735152489e-06,
|
| 1887 |
+
"loss": 0.0007,
|
| 1888 |
+
"step": 2580
|
| 1889 |
+
},
|
| 1890 |
+
{
|
| 1891 |
+
"epoch": 8.080300404390526,
|
| 1892 |
+
"grad_norm": 0.10783965140581131,
|
| 1893 |
+
"learning_rate": 1.401284109149278e-06,
|
| 1894 |
+
"loss": 0.0021,
|
| 1895 |
+
"step": 2590
|
| 1896 |
+
},
|
| 1897 |
+
{
|
| 1898 |
+
"epoch": 8.08318890814558,
|
| 1899 |
+
"grad_norm": 10.902896881103516,
|
| 1900 |
+
"learning_rate": 1.3852327447833067e-06,
|
| 1901 |
+
"loss": 0.0038,
|
| 1902 |
+
"step": 2600
|
| 1903 |
+
},
|
| 1904 |
+
{
|
| 1905 |
+
"epoch": 8.083477758521086,
|
| 1906 |
+
"eval_accuracy": 0.820040899795501,
|
| 1907 |
+
"eval_loss": 1.0583363771438599,
|
| 1908 |
+
"eval_runtime": 70.0171,
|
| 1909 |
+
"eval_samples_per_second": 6.984,
|
| 1910 |
+
"eval_steps_per_second": 0.885,
|
| 1911 |
+
"step": 2601
|
| 1912 |
+
},
|
| 1913 |
+
{
|
| 1914 |
+
"epoch": 9.00259965337955,
|
| 1915 |
+
"grad_norm": 0.00959661416709423,
|
| 1916 |
+
"learning_rate": 1.3691813804173356e-06,
|
| 1917 |
+
"loss": 0.0003,
|
| 1918 |
+
"step": 2610
|
| 1919 |
+
},
|
| 1920 |
+
{
|
| 1921 |
+
"epoch": 9.005488157134604,
|
| 1922 |
+
"grad_norm": 0.0043175676837563515,
|
| 1923 |
+
"learning_rate": 1.3531300160513643e-06,
|
| 1924 |
+
"loss": 0.0003,
|
| 1925 |
+
"step": 2620
|
| 1926 |
+
},
|
| 1927 |
+
{
|
| 1928 |
+
"epoch": 9.00837666088966,
|
| 1929 |
+
"grad_norm": 0.010923999361693859,
|
| 1930 |
+
"learning_rate": 1.3370786516853935e-06,
|
| 1931 |
+
"loss": 0.0003,
|
| 1932 |
+
"step": 2630
|
| 1933 |
+
},
|
| 1934 |
+
{
|
| 1935 |
+
"epoch": 9.011265164644714,
|
| 1936 |
+
"grad_norm": 0.016267606988549232,
|
| 1937 |
+
"learning_rate": 1.3210272873194222e-06,
|
| 1938 |
+
"loss": 0.002,
|
| 1939 |
+
"step": 2640
|
| 1940 |
+
},
|
| 1941 |
+
{
|
| 1942 |
+
"epoch": 9.01415366839977,
|
| 1943 |
+
"grad_norm": 0.011338594369590282,
|
| 1944 |
+
"learning_rate": 1.304975922953451e-06,
|
| 1945 |
+
"loss": 0.0004,
|
| 1946 |
+
"step": 2650
|
| 1947 |
+
},
|
| 1948 |
+
{
|
| 1949 |
+
"epoch": 9.017042172154824,
|
| 1950 |
+
"grad_norm": 2.419212579727173,
|
| 1951 |
+
"learning_rate": 1.2889245585874802e-06,
|
| 1952 |
+
"loss": 0.0007,
|
| 1953 |
+
"step": 2660
|
| 1954 |
+
},
|
| 1955 |
+
{
|
| 1956 |
+
"epoch": 9.019930675909878,
|
| 1957 |
+
"grad_norm": 0.05167938023805618,
|
| 1958 |
+
"learning_rate": 1.272873194221509e-06,
|
| 1959 |
+
"loss": 0.0004,
|
| 1960 |
+
"step": 2670
|
| 1961 |
+
},
|
| 1962 |
+
{
|
| 1963 |
+
"epoch": 9.022819179664934,
|
| 1964 |
+
"grad_norm": 0.010392725467681885,
|
| 1965 |
+
"learning_rate": 1.2568218298555379e-06,
|
| 1966 |
+
"loss": 0.0004,
|
| 1967 |
+
"step": 2680
|
| 1968 |
+
},
|
| 1969 |
+
{
|
| 1970 |
+
"epoch": 9.025707683419988,
|
| 1971 |
+
"grad_norm": 0.09611614793539047,
|
| 1972 |
+
"learning_rate": 1.2407704654895668e-06,
|
| 1973 |
+
"loss": 0.0031,
|
| 1974 |
+
"step": 2690
|
| 1975 |
+
},
|
| 1976 |
+
{
|
| 1977 |
+
"epoch": 9.028596187175044,
|
| 1978 |
+
"grad_norm": 0.0379074327647686,
|
| 1979 |
+
"learning_rate": 1.2247191011235957e-06,
|
| 1980 |
+
"loss": 0.0003,
|
| 1981 |
+
"step": 2700
|
| 1982 |
+
},
|
| 1983 |
+
{
|
| 1984 |
+
"epoch": 9.031484690930098,
|
| 1985 |
+
"grad_norm": 0.2393835335969925,
|
| 1986 |
+
"learning_rate": 1.2086677367576246e-06,
|
| 1987 |
+
"loss": 0.0028,
|
| 1988 |
+
"step": 2710
|
| 1989 |
+
},
|
| 1990 |
+
{
|
| 1991 |
+
"epoch": 9.034373194685154,
|
| 1992 |
+
"grad_norm": 0.19386854767799377,
|
| 1993 |
+
"learning_rate": 1.1926163723916533e-06,
|
| 1994 |
+
"loss": 0.0109,
|
| 1995 |
+
"step": 2720
|
| 1996 |
+
},
|
| 1997 |
+
{
|
| 1998 |
+
"epoch": 9.037261698440208,
|
| 1999 |
+
"grad_norm": 0.014546582475304604,
|
| 2000 |
+
"learning_rate": 1.1765650080256823e-06,
|
| 2001 |
+
"loss": 0.0004,
|
| 2002 |
+
"step": 2730
|
| 2003 |
+
},
|
| 2004 |
+
{
|
| 2005 |
+
"epoch": 9.040150202195262,
|
| 2006 |
+
"grad_norm": 0.018764443695545197,
|
| 2007 |
+
"learning_rate": 1.1605136436597112e-06,
|
| 2008 |
+
"loss": 0.0006,
|
| 2009 |
+
"step": 2740
|
| 2010 |
+
},
|
| 2011 |
+
{
|
| 2012 |
+
"epoch": 9.043038705950318,
|
| 2013 |
+
"grad_norm": 0.0548914410173893,
|
| 2014 |
+
"learning_rate": 1.14446227929374e-06,
|
| 2015 |
+
"loss": 0.0051,
|
| 2016 |
+
"step": 2750
|
| 2017 |
+
},
|
| 2018 |
+
{
|
| 2019 |
+
"epoch": 9.045927209705372,
|
| 2020 |
+
"grad_norm": 0.774179220199585,
|
| 2021 |
+
"learning_rate": 1.1284109149277688e-06,
|
| 2022 |
+
"loss": 0.0005,
|
| 2023 |
+
"step": 2760
|
| 2024 |
+
},
|
| 2025 |
+
{
|
| 2026 |
+
"epoch": 9.048815713460428,
|
| 2027 |
+
"grad_norm": 1.2299340963363647,
|
| 2028 |
+
"learning_rate": 1.112359550561798e-06,
|
| 2029 |
+
"loss": 0.0027,
|
| 2030 |
+
"step": 2770
|
| 2031 |
+
},
|
| 2032 |
+
{
|
| 2033 |
+
"epoch": 9.051704217215482,
|
| 2034 |
+
"grad_norm": 2.421196699142456,
|
| 2035 |
+
"learning_rate": 1.0963081861958269e-06,
|
| 2036 |
+
"loss": 0.0006,
|
| 2037 |
+
"step": 2780
|
| 2038 |
+
},
|
| 2039 |
+
{
|
| 2040 |
+
"epoch": 9.054592720970538,
|
| 2041 |
+
"grad_norm": 0.036972079426050186,
|
| 2042 |
+
"learning_rate": 1.0802568218298556e-06,
|
| 2043 |
+
"loss": 0.0004,
|
| 2044 |
+
"step": 2790
|
| 2045 |
+
},
|
| 2046 |
+
{
|
| 2047 |
+
"epoch": 9.057481224725592,
|
| 2048 |
+
"grad_norm": 1.629666805267334,
|
| 2049 |
+
"learning_rate": 1.0642054574638845e-06,
|
| 2050 |
+
"loss": 0.0026,
|
| 2051 |
+
"step": 2800
|
| 2052 |
+
},
|
| 2053 |
+
{
|
| 2054 |
+
"epoch": 9.060369728480646,
|
| 2055 |
+
"grad_norm": 6.719384670257568,
|
| 2056 |
+
"learning_rate": 1.0481540930979134e-06,
|
| 2057 |
+
"loss": 0.0012,
|
| 2058 |
+
"step": 2810
|
| 2059 |
+
},
|
| 2060 |
+
{
|
| 2061 |
+
"epoch": 9.063258232235702,
|
| 2062 |
+
"grad_norm": 0.04605178162455559,
|
| 2063 |
+
"learning_rate": 1.0321027287319423e-06,
|
| 2064 |
+
"loss": 0.0003,
|
| 2065 |
+
"step": 2820
|
| 2066 |
+
},
|
| 2067 |
+
{
|
| 2068 |
+
"epoch": 9.066146735990756,
|
| 2069 |
+
"grad_norm": 0.9861611723899841,
|
| 2070 |
+
"learning_rate": 1.016051364365971e-06,
|
| 2071 |
+
"loss": 0.0008,
|
| 2072 |
+
"step": 2830
|
| 2073 |
+
},
|
| 2074 |
+
{
|
| 2075 |
+
"epoch": 9.069035239745812,
|
| 2076 |
+
"grad_norm": 0.0451810359954834,
|
| 2077 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 2078 |
+
"loss": 0.001,
|
| 2079 |
+
"step": 2840
|
| 2080 |
+
},
|
| 2081 |
+
{
|
| 2082 |
+
"epoch": 9.071923743500866,
|
| 2083 |
+
"grad_norm": 0.007434166967868805,
|
| 2084 |
+
"learning_rate": 9.83948635634029e-07,
|
| 2085 |
+
"loss": 0.0003,
|
| 2086 |
+
"step": 2850
|
| 2087 |
+
},
|
| 2088 |
+
{
|
| 2089 |
+
"epoch": 9.074812247255922,
|
| 2090 |
+
"grad_norm": 0.00690662395209074,
|
| 2091 |
+
"learning_rate": 9.678972712680578e-07,
|
| 2092 |
+
"loss": 0.0006,
|
| 2093 |
+
"step": 2860
|
| 2094 |
+
},
|
| 2095 |
+
{
|
| 2096 |
+
"epoch": 9.077700751010976,
|
| 2097 |
+
"grad_norm": 0.007874921895563602,
|
| 2098 |
+
"learning_rate": 9.518459069020867e-07,
|
| 2099 |
+
"loss": 0.0005,
|
| 2100 |
+
"step": 2870
|
| 2101 |
+
},
|
| 2102 |
+
{
|
| 2103 |
+
"epoch": 9.080589254766032,
|
| 2104 |
+
"grad_norm": 0.12472189962863922,
|
| 2105 |
+
"learning_rate": 9.357945425361156e-07,
|
| 2106 |
+
"loss": 0.0015,
|
| 2107 |
+
"step": 2880
|
| 2108 |
+
},
|
| 2109 |
+
{
|
| 2110 |
+
"epoch": 9.083477758521086,
|
| 2111 |
+
"grad_norm": 0.38941165804862976,
|
| 2112 |
+
"learning_rate": 9.197431781701445e-07,
|
| 2113 |
+
"loss": 0.0011,
|
| 2114 |
+
"step": 2890
|
| 2115 |
+
},
|
| 2116 |
+
{
|
| 2117 |
+
"epoch": 9.083477758521086,
|
| 2118 |
+
"eval_accuracy": 0.8118609406952966,
|
| 2119 |
+
"eval_loss": 1.0632034540176392,
|
| 2120 |
+
"eval_runtime": 74.4675,
|
| 2121 |
+
"eval_samples_per_second": 6.567,
|
| 2122 |
+
"eval_steps_per_second": 0.833,
|
| 2123 |
+
"step": 2890
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 9.083477758521086,
|
| 2127 |
+
"step": 2890,
|
| 2128 |
+
"total_flos": 2.8784092016797286e+19,
|
| 2129 |
+
"train_loss": 0.13445161678191841,
|
| 2130 |
+
"train_runtime": 7468.4263,
|
| 2131 |
+
"train_samples_per_second": 3.708,
|
| 2132 |
+
"train_steps_per_second": 0.464
|
| 2133 |
+
},
|
| 2134 |
+
{
|
| 2135 |
+
"epoch": 9.083477758521086,
|
| 2136 |
+
"eval_accuracy": 0.8172690763052208,
|
| 2137 |
+
"eval_loss": 0.6521589159965515,
|
| 2138 |
+
"eval_runtime": 71.7298,
|
| 2139 |
+
"eval_samples_per_second": 6.943,
|
| 2140 |
+
"eval_steps_per_second": 0.878,
|
| 2141 |
+
"step": 2890
|
| 2142 |
+
},
|
| 2143 |
+
{
|
| 2144 |
+
"epoch": 9.083477758521086,
|
| 2145 |
+
"eval_accuracy": 0.8172690763052208,
|
| 2146 |
+
"eval_loss": 0.6521589756011963,
|
| 2147 |
+
"eval_runtime": 69.8312,
|
| 2148 |
+
"eval_samples_per_second": 7.131,
|
| 2149 |
+
"eval_steps_per_second": 0.902,
|
| 2150 |
+
"step": 2890
|
| 2151 |
+
},
|
| 2152 |
+
{
|
| 2153 |
+
"epoch": 9.083477758521086,
|
| 2154 |
+
"eval_accuracy": 0.8172690763052208,
|
| 2155 |
+
"eval_loss": 0.6521589159965515,
|
| 2156 |
+
"eval_runtime": 67.9033,
|
| 2157 |
+
"eval_samples_per_second": 7.334,
|
| 2158 |
+
"eval_steps_per_second": 0.928,
|
| 2159 |
+
"step": 2890
|
| 2160 |
+
},
|
| 2161 |
+
{
|
| 2162 |
+
"epoch": 9.083477758521086,
|
| 2163 |
+
"eval_accuracy": 0.8172690763052208,
|
| 2164 |
+
"eval_loss": 0.6521589756011963,
|
| 2165 |
+
"eval_runtime": 71.0552,
|
| 2166 |
+
"eval_samples_per_second": 7.009,
|
| 2167 |
+
"eval_steps_per_second": 0.887,
|
| 2168 |
+
"step": 2890
|
| 2169 |
+
}
|
| 2170 |
+
],
|
| 2171 |
+
"logging_steps": 10,
|
| 2172 |
+
"max_steps": 3462,
|
| 2173 |
+
"num_input_tokens_seen": 0,
|
| 2174 |
+
"num_train_epochs": 9223372036854775807,
|
| 2175 |
+
"save_steps": 500,
|
| 2176 |
+
"stateful_callbacks": {
|
| 2177 |
+
"EarlyStoppingCallback": {
|
| 2178 |
+
"args": {
|
| 2179 |
+
"early_stopping_patience": 4,
|
| 2180 |
+
"early_stopping_threshold": 0.0
|
| 2181 |
+
},
|
| 2182 |
+
"attributes": {
|
| 2183 |
+
"early_stopping_patience_counter": 4
|
| 2184 |
+
}
|
| 2185 |
+
},
|
| 2186 |
+
"TrainerControl": {
|
| 2187 |
+
"args": {
|
| 2188 |
+
"should_epoch_stop": false,
|
| 2189 |
+
"should_evaluate": false,
|
| 2190 |
+
"should_log": false,
|
| 2191 |
+
"should_save": true,
|
| 2192 |
+
"should_training_stop": true
|
| 2193 |
+
},
|
| 2194 |
+
"attributes": {}
|
| 2195 |
+
}
|
| 2196 |
+
},
|
| 2197 |
+
"total_flos": 2.8784092016797286e+19,
|
| 2198 |
+
"train_batch_size": 8,
|
| 2199 |
+
"trial_name": null,
|
| 2200 |
+
"trial_params": null
|
| 2201 |
+
}
|