End of training
Browse files- all_results.json +8 -0
- test_results.json +8 -0
- trainer_state.json +2260 -0
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 49.0004,
|
| 3 |
+
"eval_accuracy": 0.5753424657534246,
|
| 4 |
+
"eval_loss": 2.5945777893066406,
|
| 5 |
+
"eval_runtime": 14.1475,
|
| 6 |
+
"eval_samples_per_second": 5.16,
|
| 7 |
+
"eval_steps_per_second": 1.343
|
| 8 |
+
}
|
test_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 49.0004,
|
| 3 |
+
"eval_accuracy": 0.5753424657534246,
|
| 4 |
+
"eval_loss": 2.5945777893066406,
|
| 5 |
+
"eval_runtime": 14.1475,
|
| 6 |
+
"eval_samples_per_second": 5.16,
|
| 7 |
+
"eval_steps_per_second": 1.343
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2260 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.825,
|
| 3 |
+
"best_model_checkpoint": "MAE-CT-CPC-Dicotomized-v8-n0-m1/checkpoint-1020",
|
| 4 |
+
"epoch": 49.0004,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 2500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.004,
|
| 13 |
+
"grad_norm": 3.163785934448242,
|
| 14 |
+
"learning_rate": 4.0000000000000003e-07,
|
| 15 |
+
"loss": 0.6803,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.008,
|
| 20 |
+
"grad_norm": 1.8414620161056519,
|
| 21 |
+
"learning_rate": 8.000000000000001e-07,
|
| 22 |
+
"loss": 0.6811,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.012,
|
| 27 |
+
"grad_norm": 2.732853412628174,
|
| 28 |
+
"learning_rate": 1.2000000000000002e-06,
|
| 29 |
+
"loss": 0.6724,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.016,
|
| 34 |
+
"grad_norm": 2.302961826324463,
|
| 35 |
+
"learning_rate": 1.6000000000000001e-06,
|
| 36 |
+
"loss": 0.6625,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.02,
|
| 41 |
+
"grad_norm": 2.289227247238159,
|
| 42 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 43 |
+
"loss": 0.6826,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.0204,
|
| 48 |
+
"eval_accuracy": 0.7625,
|
| 49 |
+
"eval_loss": 0.6156964302062988,
|
| 50 |
+
"eval_runtime": 16.4829,
|
| 51 |
+
"eval_samples_per_second": 4.854,
|
| 52 |
+
"eval_steps_per_second": 1.213,
|
| 53 |
+
"step": 51
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 1.0036,
|
| 57 |
+
"grad_norm": 2.539074420928955,
|
| 58 |
+
"learning_rate": 2.4000000000000003e-06,
|
| 59 |
+
"loss": 0.653,
|
| 60 |
+
"step": 60
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 1.0076,
|
| 64 |
+
"grad_norm": 4.338445663452148,
|
| 65 |
+
"learning_rate": 2.8000000000000003e-06,
|
| 66 |
+
"loss": 0.6605,
|
| 67 |
+
"step": 70
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 1.0116,
|
| 71 |
+
"grad_norm": 4.448472023010254,
|
| 72 |
+
"learning_rate": 3.2000000000000003e-06,
|
| 73 |
+
"loss": 0.6647,
|
| 74 |
+
"step": 80
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.0156,
|
| 78 |
+
"grad_norm": 8.590893745422363,
|
| 79 |
+
"learning_rate": 3.6000000000000003e-06,
|
| 80 |
+
"loss": 0.665,
|
| 81 |
+
"step": 90
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 1.0196,
|
| 85 |
+
"grad_norm": 4.512553691864014,
|
| 86 |
+
"learning_rate": 4.000000000000001e-06,
|
| 87 |
+
"loss": 0.6549,
|
| 88 |
+
"step": 100
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 1.0204,
|
| 92 |
+
"eval_accuracy": 0.7625,
|
| 93 |
+
"eval_loss": 0.5930413603782654,
|
| 94 |
+
"eval_runtime": 15.1042,
|
| 95 |
+
"eval_samples_per_second": 5.297,
|
| 96 |
+
"eval_steps_per_second": 1.324,
|
| 97 |
+
"step": 102
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 2.0032,
|
| 101 |
+
"grad_norm": 9.520898818969727,
|
| 102 |
+
"learning_rate": 4.4e-06,
|
| 103 |
+
"loss": 0.6033,
|
| 104 |
+
"step": 110
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 2.0072,
|
| 108 |
+
"grad_norm": 7.96126651763916,
|
| 109 |
+
"learning_rate": 4.800000000000001e-06,
|
| 110 |
+
"loss": 0.5796,
|
| 111 |
+
"step": 120
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 2.0112,
|
| 115 |
+
"grad_norm": 10.471980094909668,
|
| 116 |
+
"learning_rate": 5.2e-06,
|
| 117 |
+
"loss": 0.6731,
|
| 118 |
+
"step": 130
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 2.0152,
|
| 122 |
+
"grad_norm": 17.355741500854492,
|
| 123 |
+
"learning_rate": 5.600000000000001e-06,
|
| 124 |
+
"loss": 0.6853,
|
| 125 |
+
"step": 140
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 2.0192,
|
| 129 |
+
"grad_norm": 7.118047714233398,
|
| 130 |
+
"learning_rate": 6e-06,
|
| 131 |
+
"loss": 0.6486,
|
| 132 |
+
"step": 150
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 2.0204,
|
| 136 |
+
"eval_accuracy": 0.5125,
|
| 137 |
+
"eval_loss": 0.6796671152114868,
|
| 138 |
+
"eval_runtime": 15.1483,
|
| 139 |
+
"eval_samples_per_second": 5.281,
|
| 140 |
+
"eval_steps_per_second": 1.32,
|
| 141 |
+
"step": 153
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 3.0028,
|
| 145 |
+
"grad_norm": 9.448248863220215,
|
| 146 |
+
"learning_rate": 6.4000000000000006e-06,
|
| 147 |
+
"loss": 0.627,
|
| 148 |
+
"step": 160
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 3.0068,
|
| 152 |
+
"grad_norm": 10.044306755065918,
|
| 153 |
+
"learning_rate": 6.800000000000001e-06,
|
| 154 |
+
"loss": 0.5988,
|
| 155 |
+
"step": 170
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 3.0108,
|
| 159 |
+
"grad_norm": 11.673822402954102,
|
| 160 |
+
"learning_rate": 7.2000000000000005e-06,
|
| 161 |
+
"loss": 0.5388,
|
| 162 |
+
"step": 180
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 3.0148,
|
| 166 |
+
"grad_norm": 13.179671287536621,
|
| 167 |
+
"learning_rate": 7.600000000000001e-06,
|
| 168 |
+
"loss": 0.4922,
|
| 169 |
+
"step": 190
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 3.0188,
|
| 173 |
+
"grad_norm": 17.30994987487793,
|
| 174 |
+
"learning_rate": 8.000000000000001e-06,
|
| 175 |
+
"loss": 0.5595,
|
| 176 |
+
"step": 200
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 3.0204,
|
| 180 |
+
"eval_accuracy": 0.6625,
|
| 181 |
+
"eval_loss": 0.49017828702926636,
|
| 182 |
+
"eval_runtime": 14.3197,
|
| 183 |
+
"eval_samples_per_second": 5.587,
|
| 184 |
+
"eval_steps_per_second": 1.397,
|
| 185 |
+
"step": 204
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 4.0024,
|
| 189 |
+
"grad_norm": 12.384488105773926,
|
| 190 |
+
"learning_rate": 8.400000000000001e-06,
|
| 191 |
+
"loss": 0.5512,
|
| 192 |
+
"step": 210
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 4.0064,
|
| 196 |
+
"grad_norm": 16.830211639404297,
|
| 197 |
+
"learning_rate": 8.8e-06,
|
| 198 |
+
"loss": 0.5532,
|
| 199 |
+
"step": 220
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 4.0104,
|
| 203 |
+
"grad_norm": 25.703161239624023,
|
| 204 |
+
"learning_rate": 9.200000000000002e-06,
|
| 205 |
+
"loss": 0.4503,
|
| 206 |
+
"step": 230
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 4.0144,
|
| 210 |
+
"grad_norm": 31.191774368286133,
|
| 211 |
+
"learning_rate": 9.600000000000001e-06,
|
| 212 |
+
"loss": 0.4281,
|
| 213 |
+
"step": 240
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 4.0184,
|
| 217 |
+
"grad_norm": 7.301267147064209,
|
| 218 |
+
"learning_rate": 1e-05,
|
| 219 |
+
"loss": 0.5586,
|
| 220 |
+
"step": 250
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 4.0204,
|
| 224 |
+
"eval_accuracy": 0.475,
|
| 225 |
+
"eval_loss": 0.8194777369499207,
|
| 226 |
+
"eval_runtime": 15.5636,
|
| 227 |
+
"eval_samples_per_second": 5.14,
|
| 228 |
+
"eval_steps_per_second": 1.285,
|
| 229 |
+
"step": 255
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 5.002,
|
| 233 |
+
"grad_norm": 6.1059746742248535,
|
| 234 |
+
"learning_rate": 9.955555555555556e-06,
|
| 235 |
+
"loss": 0.4667,
|
| 236 |
+
"step": 260
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 5.006,
|
| 240 |
+
"grad_norm": 11.250345230102539,
|
| 241 |
+
"learning_rate": 9.911111111111113e-06,
|
| 242 |
+
"loss": 0.3866,
|
| 243 |
+
"step": 270
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 5.01,
|
| 247 |
+
"grad_norm": 11.811776161193848,
|
| 248 |
+
"learning_rate": 9.866666666666668e-06,
|
| 249 |
+
"loss": 0.3093,
|
| 250 |
+
"step": 280
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 5.014,
|
| 254 |
+
"grad_norm": 2.898249387741089,
|
| 255 |
+
"learning_rate": 9.822222222222223e-06,
|
| 256 |
+
"loss": 0.4655,
|
| 257 |
+
"step": 290
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 5.018,
|
| 261 |
+
"grad_norm": 39.88842010498047,
|
| 262 |
+
"learning_rate": 9.777777777777779e-06,
|
| 263 |
+
"loss": 0.4565,
|
| 264 |
+
"step": 300
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 5.0204,
|
| 268 |
+
"eval_accuracy": 0.75,
|
| 269 |
+
"eval_loss": 0.5872394442558289,
|
| 270 |
+
"eval_runtime": 15.5445,
|
| 271 |
+
"eval_samples_per_second": 5.147,
|
| 272 |
+
"eval_steps_per_second": 1.287,
|
| 273 |
+
"step": 306
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 6.0016,
|
| 277 |
+
"grad_norm": 18.96799659729004,
|
| 278 |
+
"learning_rate": 9.733333333333334e-06,
|
| 279 |
+
"loss": 0.6334,
|
| 280 |
+
"step": 310
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 6.0056,
|
| 284 |
+
"grad_norm": 26.40775489807129,
|
| 285 |
+
"learning_rate": 9.688888888888889e-06,
|
| 286 |
+
"loss": 0.5505,
|
| 287 |
+
"step": 320
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 6.0096,
|
| 291 |
+
"grad_norm": 23.987438201904297,
|
| 292 |
+
"learning_rate": 9.644444444444444e-06,
|
| 293 |
+
"loss": 0.4702,
|
| 294 |
+
"step": 330
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 6.0136,
|
| 298 |
+
"grad_norm": 11.874549865722656,
|
| 299 |
+
"learning_rate": 9.600000000000001e-06,
|
| 300 |
+
"loss": 0.5567,
|
| 301 |
+
"step": 340
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 6.0176,
|
| 305 |
+
"grad_norm": 1.870789647102356,
|
| 306 |
+
"learning_rate": 9.555555555555556e-06,
|
| 307 |
+
"loss": 0.3697,
|
| 308 |
+
"step": 350
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 6.0204,
|
| 312 |
+
"eval_accuracy": 0.775,
|
| 313 |
+
"eval_loss": 0.5016795992851257,
|
| 314 |
+
"eval_runtime": 15.1939,
|
| 315 |
+
"eval_samples_per_second": 5.265,
|
| 316 |
+
"eval_steps_per_second": 1.316,
|
| 317 |
+
"step": 357
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 7.0012,
|
| 321 |
+
"grad_norm": 1.9288091659545898,
|
| 322 |
+
"learning_rate": 9.511111111111112e-06,
|
| 323 |
+
"loss": 0.3384,
|
| 324 |
+
"step": 360
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 7.0052,
|
| 328 |
+
"grad_norm": 47.43910598754883,
|
| 329 |
+
"learning_rate": 9.466666666666667e-06,
|
| 330 |
+
"loss": 0.4776,
|
| 331 |
+
"step": 370
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 7.0092,
|
| 335 |
+
"grad_norm": 24.75432586669922,
|
| 336 |
+
"learning_rate": 9.422222222222222e-06,
|
| 337 |
+
"loss": 0.3272,
|
| 338 |
+
"step": 380
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 7.0132,
|
| 342 |
+
"grad_norm": 6.029924392700195,
|
| 343 |
+
"learning_rate": 9.377777777777779e-06,
|
| 344 |
+
"loss": 0.6358,
|
| 345 |
+
"step": 390
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 7.0172,
|
| 349 |
+
"grad_norm": 36.66233825683594,
|
| 350 |
+
"learning_rate": 9.333333333333334e-06,
|
| 351 |
+
"loss": 0.6201,
|
| 352 |
+
"step": 400
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 7.0204,
|
| 356 |
+
"eval_accuracy": 0.7,
|
| 357 |
+
"eval_loss": 0.6555034518241882,
|
| 358 |
+
"eval_runtime": 15.1733,
|
| 359 |
+
"eval_samples_per_second": 5.272,
|
| 360 |
+
"eval_steps_per_second": 1.318,
|
| 361 |
+
"step": 408
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 8.0008,
|
| 365 |
+
"grad_norm": 13.244248390197754,
|
| 366 |
+
"learning_rate": 9.28888888888889e-06,
|
| 367 |
+
"loss": 0.2307,
|
| 368 |
+
"step": 410
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 8.0048,
|
| 372 |
+
"grad_norm": 0.1510910540819168,
|
| 373 |
+
"learning_rate": 9.244444444444445e-06,
|
| 374 |
+
"loss": 0.2198,
|
| 375 |
+
"step": 420
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 8.0088,
|
| 379 |
+
"grad_norm": 48.222145080566406,
|
| 380 |
+
"learning_rate": 9.200000000000002e-06,
|
| 381 |
+
"loss": 0.1961,
|
| 382 |
+
"step": 430
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 8.0128,
|
| 386 |
+
"grad_norm": 12.182064056396484,
|
| 387 |
+
"learning_rate": 9.155555555555557e-06,
|
| 388 |
+
"loss": 0.4113,
|
| 389 |
+
"step": 440
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 8.0168,
|
| 393 |
+
"grad_norm": 90.49524688720703,
|
| 394 |
+
"learning_rate": 9.111111111111112e-06,
|
| 395 |
+
"loss": 0.4333,
|
| 396 |
+
"step": 450
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 8.0204,
|
| 400 |
+
"eval_accuracy": 0.6125,
|
| 401 |
+
"eval_loss": 1.2277292013168335,
|
| 402 |
+
"eval_runtime": 15.8873,
|
| 403 |
+
"eval_samples_per_second": 5.035,
|
| 404 |
+
"eval_steps_per_second": 1.259,
|
| 405 |
+
"step": 459
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 9.0004,
|
| 409 |
+
"grad_norm": 8.979384422302246,
|
| 410 |
+
"learning_rate": 9.066666666666667e-06,
|
| 411 |
+
"loss": 0.2832,
|
| 412 |
+
"step": 460
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 9.0044,
|
| 416 |
+
"grad_norm": 124.57083892822266,
|
| 417 |
+
"learning_rate": 9.022222222222223e-06,
|
| 418 |
+
"loss": 0.4698,
|
| 419 |
+
"step": 470
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 9.0084,
|
| 423 |
+
"grad_norm": 1.4499937295913696,
|
| 424 |
+
"learning_rate": 8.977777777777778e-06,
|
| 425 |
+
"loss": 0.622,
|
| 426 |
+
"step": 480
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 9.0124,
|
| 430 |
+
"grad_norm": 204.4443359375,
|
| 431 |
+
"learning_rate": 8.933333333333333e-06,
|
| 432 |
+
"loss": 0.4289,
|
| 433 |
+
"step": 490
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 9.0164,
|
| 437 |
+
"grad_norm": 13.056779861450195,
|
| 438 |
+
"learning_rate": 8.888888888888888e-06,
|
| 439 |
+
"loss": 0.3958,
|
| 440 |
+
"step": 500
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 9.0204,
|
| 444 |
+
"grad_norm": 3.7403643131256104,
|
| 445 |
+
"learning_rate": 8.844444444444445e-06,
|
| 446 |
+
"loss": 0.2148,
|
| 447 |
+
"step": 510
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 9.0204,
|
| 451 |
+
"eval_accuracy": 0.7625,
|
| 452 |
+
"eval_loss": 0.8114517331123352,
|
| 453 |
+
"eval_runtime": 14.7863,
|
| 454 |
+
"eval_samples_per_second": 5.41,
|
| 455 |
+
"eval_steps_per_second": 1.353,
|
| 456 |
+
"step": 510
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 10.004,
|
| 460 |
+
"grad_norm": 0.3079785704612732,
|
| 461 |
+
"learning_rate": 8.8e-06,
|
| 462 |
+
"loss": 0.4126,
|
| 463 |
+
"step": 520
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 10.008,
|
| 467 |
+
"grad_norm": 10.519120216369629,
|
| 468 |
+
"learning_rate": 8.755555555555556e-06,
|
| 469 |
+
"loss": 0.2208,
|
| 470 |
+
"step": 530
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 10.012,
|
| 474 |
+
"grad_norm": 37.70737075805664,
|
| 475 |
+
"learning_rate": 8.711111111111111e-06,
|
| 476 |
+
"loss": 0.4088,
|
| 477 |
+
"step": 540
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 10.016,
|
| 481 |
+
"grad_norm": 27.64992332458496,
|
| 482 |
+
"learning_rate": 8.666666666666668e-06,
|
| 483 |
+
"loss": 0.6548,
|
| 484 |
+
"step": 550
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 10.02,
|
| 488 |
+
"grad_norm": 1.9343359470367432,
|
| 489 |
+
"learning_rate": 8.622222222222223e-06,
|
| 490 |
+
"loss": 0.9458,
|
| 491 |
+
"step": 560
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 10.0204,
|
| 495 |
+
"eval_accuracy": 0.6625,
|
| 496 |
+
"eval_loss": 0.9872623682022095,
|
| 497 |
+
"eval_runtime": 14.8048,
|
| 498 |
+
"eval_samples_per_second": 5.404,
|
| 499 |
+
"eval_steps_per_second": 1.351,
|
| 500 |
+
"step": 561
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 11.0036,
|
| 504 |
+
"grad_norm": 127.26286315917969,
|
| 505 |
+
"learning_rate": 8.577777777777778e-06,
|
| 506 |
+
"loss": 0.4077,
|
| 507 |
+
"step": 570
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 11.0076,
|
| 511 |
+
"grad_norm": 48.36285400390625,
|
| 512 |
+
"learning_rate": 8.533333333333335e-06,
|
| 513 |
+
"loss": 0.315,
|
| 514 |
+
"step": 580
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 11.0116,
|
| 518 |
+
"grad_norm": 1.3444968461990356,
|
| 519 |
+
"learning_rate": 8.48888888888889e-06,
|
| 520 |
+
"loss": 0.3529,
|
| 521 |
+
"step": 590
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 11.0156,
|
| 525 |
+
"grad_norm": 1.425925374031067,
|
| 526 |
+
"learning_rate": 8.444444444444446e-06,
|
| 527 |
+
"loss": 0.2537,
|
| 528 |
+
"step": 600
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 11.0196,
|
| 532 |
+
"grad_norm": 0.11205915361642838,
|
| 533 |
+
"learning_rate": 8.400000000000001e-06,
|
| 534 |
+
"loss": 0.0651,
|
| 535 |
+
"step": 610
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 11.0204,
|
| 539 |
+
"eval_accuracy": 0.7625,
|
| 540 |
+
"eval_loss": 1.0840221643447876,
|
| 541 |
+
"eval_runtime": 16.1692,
|
| 542 |
+
"eval_samples_per_second": 4.948,
|
| 543 |
+
"eval_steps_per_second": 1.237,
|
| 544 |
+
"step": 612
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 12.0032,
|
| 548 |
+
"grad_norm": 1.6690884828567505,
|
| 549 |
+
"learning_rate": 8.355555555555556e-06,
|
| 550 |
+
"loss": 0.0219,
|
| 551 |
+
"step": 620
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 12.0072,
|
| 555 |
+
"grad_norm": 0.04994206875562668,
|
| 556 |
+
"learning_rate": 8.311111111111111e-06,
|
| 557 |
+
"loss": 0.3325,
|
| 558 |
+
"step": 630
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 12.0112,
|
| 562 |
+
"grad_norm": 1.1334573030471802,
|
| 563 |
+
"learning_rate": 8.266666666666667e-06,
|
| 564 |
+
"loss": 0.1766,
|
| 565 |
+
"step": 640
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 12.0152,
|
| 569 |
+
"grad_norm": 84.09977722167969,
|
| 570 |
+
"learning_rate": 8.222222222222222e-06,
|
| 571 |
+
"loss": 0.3474,
|
| 572 |
+
"step": 650
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 12.0192,
|
| 576 |
+
"grad_norm": 0.11686452478170395,
|
| 577 |
+
"learning_rate": 8.177777777777779e-06,
|
| 578 |
+
"loss": 0.5756,
|
| 579 |
+
"step": 660
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 12.0204,
|
| 583 |
+
"eval_accuracy": 0.8,
|
| 584 |
+
"eval_loss": 1.0489223003387451,
|
| 585 |
+
"eval_runtime": 14.837,
|
| 586 |
+
"eval_samples_per_second": 5.392,
|
| 587 |
+
"eval_steps_per_second": 1.348,
|
| 588 |
+
"step": 663
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 13.0028,
|
| 592 |
+
"grad_norm": 0.4879148304462433,
|
| 593 |
+
"learning_rate": 8.133333333333334e-06,
|
| 594 |
+
"loss": 0.1627,
|
| 595 |
+
"step": 670
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 13.0068,
|
| 599 |
+
"grad_norm": 10.051454544067383,
|
| 600 |
+
"learning_rate": 8.08888888888889e-06,
|
| 601 |
+
"loss": 0.1414,
|
| 602 |
+
"step": 680
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 13.0108,
|
| 606 |
+
"grad_norm": 317.5495910644531,
|
| 607 |
+
"learning_rate": 8.044444444444444e-06,
|
| 608 |
+
"loss": 0.4045,
|
| 609 |
+
"step": 690
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 13.0148,
|
| 613 |
+
"grad_norm": 12.827858924865723,
|
| 614 |
+
"learning_rate": 8.000000000000001e-06,
|
| 615 |
+
"loss": 0.2213,
|
| 616 |
+
"step": 700
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 13.0188,
|
| 620 |
+
"grad_norm": 7.5428338050842285,
|
| 621 |
+
"learning_rate": 7.955555555555557e-06,
|
| 622 |
+
"loss": 0.354,
|
| 623 |
+
"step": 710
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 13.0204,
|
| 627 |
+
"eval_accuracy": 0.7875,
|
| 628 |
+
"eval_loss": 1.1601030826568604,
|
| 629 |
+
"eval_runtime": 14.793,
|
| 630 |
+
"eval_samples_per_second": 5.408,
|
| 631 |
+
"eval_steps_per_second": 1.352,
|
| 632 |
+
"step": 714
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 14.0024,
|
| 636 |
+
"grad_norm": 1.0718170404434204,
|
| 637 |
+
"learning_rate": 7.911111111111112e-06,
|
| 638 |
+
"loss": 0.1341,
|
| 639 |
+
"step": 720
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 14.0064,
|
| 643 |
+
"grad_norm": 204.27011108398438,
|
| 644 |
+
"learning_rate": 7.866666666666667e-06,
|
| 645 |
+
"loss": 0.2009,
|
| 646 |
+
"step": 730
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 14.0104,
|
| 650 |
+
"grad_norm": 623.6522827148438,
|
| 651 |
+
"learning_rate": 7.822222222222224e-06,
|
| 652 |
+
"loss": 0.2302,
|
| 653 |
+
"step": 740
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 14.0144,
|
| 657 |
+
"grad_norm": 53.07473373413086,
|
| 658 |
+
"learning_rate": 7.77777777777778e-06,
|
| 659 |
+
"loss": 0.4521,
|
| 660 |
+
"step": 750
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 14.0184,
|
| 664 |
+
"grad_norm": 0.032519057393074036,
|
| 665 |
+
"learning_rate": 7.733333333333334e-06,
|
| 666 |
+
"loss": 0.2888,
|
| 667 |
+
"step": 760
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 14.0204,
|
| 671 |
+
"eval_accuracy": 0.625,
|
| 672 |
+
"eval_loss": 1.8143768310546875,
|
| 673 |
+
"eval_runtime": 15.8798,
|
| 674 |
+
"eval_samples_per_second": 5.038,
|
| 675 |
+
"eval_steps_per_second": 1.259,
|
| 676 |
+
"step": 765
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 15.002,
|
| 680 |
+
"grad_norm": 457.6705322265625,
|
| 681 |
+
"learning_rate": 7.68888888888889e-06,
|
| 682 |
+
"loss": 0.2657,
|
| 683 |
+
"step": 770
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 15.006,
|
| 687 |
+
"grad_norm": 431.8014221191406,
|
| 688 |
+
"learning_rate": 7.644444444444445e-06,
|
| 689 |
+
"loss": 0.0887,
|
| 690 |
+
"step": 780
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 15.01,
|
| 694 |
+
"grad_norm": 0.013111516833305359,
|
| 695 |
+
"learning_rate": 7.600000000000001e-06,
|
| 696 |
+
"loss": 0.0183,
|
| 697 |
+
"step": 790
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 15.014,
|
| 701 |
+
"grad_norm": 0.08553914725780487,
|
| 702 |
+
"learning_rate": 7.555555555555556e-06,
|
| 703 |
+
"loss": 0.0991,
|
| 704 |
+
"step": 800
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 15.018,
|
| 708 |
+
"grad_norm": 0.11689701676368713,
|
| 709 |
+
"learning_rate": 7.511111111111111e-06,
|
| 710 |
+
"loss": 0.2449,
|
| 711 |
+
"step": 810
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 15.0204,
|
| 715 |
+
"eval_accuracy": 0.7125,
|
| 716 |
+
"eval_loss": 1.3988301753997803,
|
| 717 |
+
"eval_runtime": 14.9719,
|
| 718 |
+
"eval_samples_per_second": 5.343,
|
| 719 |
+
"eval_steps_per_second": 1.336,
|
| 720 |
+
"step": 816
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 16.0016,
|
| 724 |
+
"grad_norm": 0.12991830706596375,
|
| 725 |
+
"learning_rate": 7.4666666666666675e-06,
|
| 726 |
+
"loss": 0.009,
|
| 727 |
+
"step": 820
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 16.0056,
|
| 731 |
+
"grad_norm": 185.4541015625,
|
| 732 |
+
"learning_rate": 7.422222222222223e-06,
|
| 733 |
+
"loss": 0.2772,
|
| 734 |
+
"step": 830
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 16.0096,
|
| 738 |
+
"grad_norm": 0.7622888088226318,
|
| 739 |
+
"learning_rate": 7.377777777777778e-06,
|
| 740 |
+
"loss": 0.1701,
|
| 741 |
+
"step": 840
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 16.0136,
|
| 745 |
+
"grad_norm": 0.5893406867980957,
|
| 746 |
+
"learning_rate": 7.333333333333333e-06,
|
| 747 |
+
"loss": 0.1631,
|
| 748 |
+
"step": 850
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 16.0176,
|
| 752 |
+
"grad_norm": 0.7813571691513062,
|
| 753 |
+
"learning_rate": 7.28888888888889e-06,
|
| 754 |
+
"loss": 0.1326,
|
| 755 |
+
"step": 860
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 16.0204,
|
| 759 |
+
"eval_accuracy": 0.7125,
|
| 760 |
+
"eval_loss": 1.715152382850647,
|
| 761 |
+
"eval_runtime": 15.1438,
|
| 762 |
+
"eval_samples_per_second": 5.283,
|
| 763 |
+
"eval_steps_per_second": 1.321,
|
| 764 |
+
"step": 867
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 17.0012,
|
| 768 |
+
"grad_norm": 0.07987383008003235,
|
| 769 |
+
"learning_rate": 7.244444444444445e-06,
|
| 770 |
+
"loss": 0.0021,
|
| 771 |
+
"step": 870
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 17.0052,
|
| 775 |
+
"grad_norm": 17.579423904418945,
|
| 776 |
+
"learning_rate": 7.2000000000000005e-06,
|
| 777 |
+
"loss": 0.2835,
|
| 778 |
+
"step": 880
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 17.0092,
|
| 782 |
+
"grad_norm": 0.05407591536641121,
|
| 783 |
+
"learning_rate": 7.155555555555556e-06,
|
| 784 |
+
"loss": 0.0557,
|
| 785 |
+
"step": 890
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 17.0132,
|
| 789 |
+
"grad_norm": 129.4159393310547,
|
| 790 |
+
"learning_rate": 7.111111111111112e-06,
|
| 791 |
+
"loss": 0.147,
|
| 792 |
+
"step": 900
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 17.0172,
|
| 796 |
+
"grad_norm": 0.6726216673851013,
|
| 797 |
+
"learning_rate": 7.066666666666667e-06,
|
| 798 |
+
"loss": 0.0018,
|
| 799 |
+
"step": 910
|
| 800 |
+
},
|
| 801 |
+
{
|
| 802 |
+
"epoch": 17.0204,
|
| 803 |
+
"eval_accuracy": 0.6375,
|
| 804 |
+
"eval_loss": 2.1475367546081543,
|
| 805 |
+
"eval_runtime": 15.0746,
|
| 806 |
+
"eval_samples_per_second": 5.307,
|
| 807 |
+
"eval_steps_per_second": 1.327,
|
| 808 |
+
"step": 918
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 18.0008,
|
| 812 |
+
"grad_norm": 0.06342015415430069,
|
| 813 |
+
"learning_rate": 7.022222222222222e-06,
|
| 814 |
+
"loss": 0.2025,
|
| 815 |
+
"step": 920
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 18.0048,
|
| 819 |
+
"grad_norm": 0.03912360593676567,
|
| 820 |
+
"learning_rate": 6.977777777777779e-06,
|
| 821 |
+
"loss": 0.0017,
|
| 822 |
+
"step": 930
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 18.0088,
|
| 826 |
+
"grad_norm": 0.015669086948037148,
|
| 827 |
+
"learning_rate": 6.9333333333333344e-06,
|
| 828 |
+
"loss": 0.1518,
|
| 829 |
+
"step": 940
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 18.0128,
|
| 833 |
+
"grad_norm": 0.03878331929445267,
|
| 834 |
+
"learning_rate": 6.88888888888889e-06,
|
| 835 |
+
"loss": 0.6683,
|
| 836 |
+
"step": 950
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 18.0168,
|
| 840 |
+
"grad_norm": 0.009163687005639076,
|
| 841 |
+
"learning_rate": 6.844444444444445e-06,
|
| 842 |
+
"loss": 0.3631,
|
| 843 |
+
"step": 960
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 18.0204,
|
| 847 |
+
"eval_accuracy": 0.65,
|
| 848 |
+
"eval_loss": 1.8957328796386719,
|
| 849 |
+
"eval_runtime": 14.5069,
|
| 850 |
+
"eval_samples_per_second": 5.515,
|
| 851 |
+
"eval_steps_per_second": 1.379,
|
| 852 |
+
"step": 969
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 19.0004,
|
| 856 |
+
"grad_norm": 0.030928779393434525,
|
| 857 |
+
"learning_rate": 6.800000000000001e-06,
|
| 858 |
+
"loss": 0.1663,
|
| 859 |
+
"step": 970
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 19.0044,
|
| 863 |
+
"grad_norm": 0.8263186812400818,
|
| 864 |
+
"learning_rate": 6.755555555555556e-06,
|
| 865 |
+
"loss": 0.2357,
|
| 866 |
+
"step": 980
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 19.0084,
|
| 870 |
+
"grad_norm": 0.09255637228488922,
|
| 871 |
+
"learning_rate": 6.711111111111111e-06,
|
| 872 |
+
"loss": 0.0141,
|
| 873 |
+
"step": 990
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 19.0124,
|
| 877 |
+
"grad_norm": 0.10079475492238998,
|
| 878 |
+
"learning_rate": 6.666666666666667e-06,
|
| 879 |
+
"loss": 0.001,
|
| 880 |
+
"step": 1000
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 19.0164,
|
| 884 |
+
"grad_norm": 0.1445166915655136,
|
| 885 |
+
"learning_rate": 6.6222222222222236e-06,
|
| 886 |
+
"loss": 0.1313,
|
| 887 |
+
"step": 1010
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 19.0204,
|
| 891 |
+
"grad_norm": 0.0298333577811718,
|
| 892 |
+
"learning_rate": 6.577777777777779e-06,
|
| 893 |
+
"loss": 0.1252,
|
| 894 |
+
"step": 1020
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 19.0204,
|
| 898 |
+
"eval_accuracy": 0.825,
|
| 899 |
+
"eval_loss": 1.124619960784912,
|
| 900 |
+
"eval_runtime": 14.4479,
|
| 901 |
+
"eval_samples_per_second": 5.537,
|
| 902 |
+
"eval_steps_per_second": 1.384,
|
| 903 |
+
"step": 1020
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 20.004,
|
| 907 |
+
"grad_norm": 0.19592173397541046,
|
| 908 |
+
"learning_rate": 6.533333333333334e-06,
|
| 909 |
+
"loss": 0.0141,
|
| 910 |
+
"step": 1030
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 20.008,
|
| 914 |
+
"grad_norm": 42.12409591674805,
|
| 915 |
+
"learning_rate": 6.488888888888889e-06,
|
| 916 |
+
"loss": 0.1769,
|
| 917 |
+
"step": 1040
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 20.012,
|
| 921 |
+
"grad_norm": 482.6688537597656,
|
| 922 |
+
"learning_rate": 6.444444444444445e-06,
|
| 923 |
+
"loss": 0.1202,
|
| 924 |
+
"step": 1050
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 20.016,
|
| 928 |
+
"grad_norm": 0.5874069333076477,
|
| 929 |
+
"learning_rate": 6.4000000000000006e-06,
|
| 930 |
+
"loss": 0.0007,
|
| 931 |
+
"step": 1060
|
| 932 |
+
},
|
| 933 |
+
{
|
| 934 |
+
"epoch": 20.02,
|
| 935 |
+
"grad_norm": 0.018259378150105476,
|
| 936 |
+
"learning_rate": 6.355555555555556e-06,
|
| 937 |
+
"loss": 0.0943,
|
| 938 |
+
"step": 1070
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 20.0204,
|
| 942 |
+
"eval_accuracy": 0.6625,
|
| 943 |
+
"eval_loss": 1.9498172998428345,
|
| 944 |
+
"eval_runtime": 14.4129,
|
| 945 |
+
"eval_samples_per_second": 5.551,
|
| 946 |
+
"eval_steps_per_second": 1.388,
|
| 947 |
+
"step": 1071
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 21.0036,
|
| 951 |
+
"grad_norm": 0.00311831571161747,
|
| 952 |
+
"learning_rate": 6.311111111111111e-06,
|
| 953 |
+
"loss": 0.2018,
|
| 954 |
+
"step": 1080
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 21.0076,
|
| 958 |
+
"grad_norm": 7.55759859085083,
|
| 959 |
+
"learning_rate": 6.266666666666668e-06,
|
| 960 |
+
"loss": 0.333,
|
| 961 |
+
"step": 1090
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 21.0116,
|
| 965 |
+
"grad_norm": 0.13464294373989105,
|
| 966 |
+
"learning_rate": 6.222222222222223e-06,
|
| 967 |
+
"loss": 0.2933,
|
| 968 |
+
"step": 1100
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 21.0156,
|
| 972 |
+
"grad_norm": 0.013299187645316124,
|
| 973 |
+
"learning_rate": 6.177777777777778e-06,
|
| 974 |
+
"loss": 0.0908,
|
| 975 |
+
"step": 1110
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 21.0196,
|
| 979 |
+
"grad_norm": 28.606412887573242,
|
| 980 |
+
"learning_rate": 6.133333333333334e-06,
|
| 981 |
+
"loss": 0.3488,
|
| 982 |
+
"step": 1120
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 21.0204,
|
| 986 |
+
"eval_accuracy": 0.7875,
|
| 987 |
+
"eval_loss": 1.3456709384918213,
|
| 988 |
+
"eval_runtime": 15.9369,
|
| 989 |
+
"eval_samples_per_second": 5.02,
|
| 990 |
+
"eval_steps_per_second": 1.255,
|
| 991 |
+
"step": 1122
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 22.0032,
|
| 995 |
+
"grad_norm": 2.039261817932129,
|
| 996 |
+
"learning_rate": 6.08888888888889e-06,
|
| 997 |
+
"loss": 0.2154,
|
| 998 |
+
"step": 1130
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 22.0072,
|
| 1002 |
+
"grad_norm": 6.409753799438477,
|
| 1003 |
+
"learning_rate": 6.044444444444445e-06,
|
| 1004 |
+
"loss": 0.0051,
|
| 1005 |
+
"step": 1140
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 22.0112,
|
| 1009 |
+
"grad_norm": 0.010469136759638786,
|
| 1010 |
+
"learning_rate": 6e-06,
|
| 1011 |
+
"loss": 0.1893,
|
| 1012 |
+
"step": 1150
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 22.0152,
|
| 1016 |
+
"grad_norm": 0.022801605984568596,
|
| 1017 |
+
"learning_rate": 5.955555555555555e-06,
|
| 1018 |
+
"loss": 0.0428,
|
| 1019 |
+
"step": 1160
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 22.0192,
|
| 1023 |
+
"grad_norm": 0.014003835618495941,
|
| 1024 |
+
"learning_rate": 5.911111111111112e-06,
|
| 1025 |
+
"loss": 0.0008,
|
| 1026 |
+
"step": 1170
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 22.0204,
|
| 1030 |
+
"eval_accuracy": 0.7125,
|
| 1031 |
+
"eval_loss": 1.7872467041015625,
|
| 1032 |
+
"eval_runtime": 14.9328,
|
| 1033 |
+
"eval_samples_per_second": 5.357,
|
| 1034 |
+
"eval_steps_per_second": 1.339,
|
| 1035 |
+
"step": 1173
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 23.0028,
|
| 1039 |
+
"grad_norm": 336.1969299316406,
|
| 1040 |
+
"learning_rate": 5.8666666666666675e-06,
|
| 1041 |
+
"loss": 0.5488,
|
| 1042 |
+
"step": 1180
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 23.0068,
|
| 1046 |
+
"grad_norm": 0.009750437922775745,
|
| 1047 |
+
"learning_rate": 5.822222222222223e-06,
|
| 1048 |
+
"loss": 0.3029,
|
| 1049 |
+
"step": 1190
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 23.0108,
|
| 1053 |
+
"grad_norm": 0.15668730437755585,
|
| 1054 |
+
"learning_rate": 5.777777777777778e-06,
|
| 1055 |
+
"loss": 0.6396,
|
| 1056 |
+
"step": 1200
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 23.0148,
|
| 1060 |
+
"grad_norm": 0.019450828433036804,
|
| 1061 |
+
"learning_rate": 5.733333333333334e-06,
|
| 1062 |
+
"loss": 0.0974,
|
| 1063 |
+
"step": 1210
|
| 1064 |
+
},
|
| 1065 |
+
{
|
| 1066 |
+
"epoch": 23.0188,
|
| 1067 |
+
"grad_norm": 6.186660289764404,
|
| 1068 |
+
"learning_rate": 5.688888888888889e-06,
|
| 1069 |
+
"loss": 0.009,
|
| 1070 |
+
"step": 1220
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 23.0204,
|
| 1074 |
+
"eval_accuracy": 0.75,
|
| 1075 |
+
"eval_loss": 1.5437147617340088,
|
| 1076 |
+
"eval_runtime": 14.8598,
|
| 1077 |
+
"eval_samples_per_second": 5.384,
|
| 1078 |
+
"eval_steps_per_second": 1.346,
|
| 1079 |
+
"step": 1224
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 24.0024,
|
| 1083 |
+
"grad_norm": 0.012686701491475105,
|
| 1084 |
+
"learning_rate": 5.6444444444444445e-06,
|
| 1085 |
+
"loss": 0.0007,
|
| 1086 |
+
"step": 1230
|
| 1087 |
+
},
|
| 1088 |
+
{
|
| 1089 |
+
"epoch": 24.0064,
|
| 1090 |
+
"grad_norm": 0.008507036603987217,
|
| 1091 |
+
"learning_rate": 5.600000000000001e-06,
|
| 1092 |
+
"loss": 0.0796,
|
| 1093 |
+
"step": 1240
|
| 1094 |
+
},
|
| 1095 |
+
{
|
| 1096 |
+
"epoch": 24.0104,
|
| 1097 |
+
"grad_norm": 0.05275079980492592,
|
| 1098 |
+
"learning_rate": 5.555555555555557e-06,
|
| 1099 |
+
"loss": 0.0045,
|
| 1100 |
+
"step": 1250
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 24.0144,
|
| 1104 |
+
"grad_norm": 0.020087506622076035,
|
| 1105 |
+
"learning_rate": 5.511111111111112e-06,
|
| 1106 |
+
"loss": 0.0007,
|
| 1107 |
+
"step": 1260
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 24.0184,
|
| 1111 |
+
"grad_norm": 0.0037845964543521404,
|
| 1112 |
+
"learning_rate": 5.466666666666667e-06,
|
| 1113 |
+
"loss": 0.0274,
|
| 1114 |
+
"step": 1270
|
| 1115 |
+
},
|
| 1116 |
+
{
|
| 1117 |
+
"epoch": 24.0204,
|
| 1118 |
+
"eval_accuracy": 0.6875,
|
| 1119 |
+
"eval_loss": 1.9865350723266602,
|
| 1120 |
+
"eval_runtime": 15.8645,
|
| 1121 |
+
"eval_samples_per_second": 5.043,
|
| 1122 |
+
"eval_steps_per_second": 1.261,
|
| 1123 |
+
"step": 1275
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 25.002,
|
| 1127 |
+
"grad_norm": 0.008797760121524334,
|
| 1128 |
+
"learning_rate": 5.422222222222223e-06,
|
| 1129 |
+
"loss": 0.1231,
|
| 1130 |
+
"step": 1280
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 25.006,
|
| 1134 |
+
"grad_norm": 0.012985019944608212,
|
| 1135 |
+
"learning_rate": 5.3777777777777784e-06,
|
| 1136 |
+
"loss": 0.0003,
|
| 1137 |
+
"step": 1290
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 25.01,
|
| 1141 |
+
"grad_norm": 0.02057729661464691,
|
| 1142 |
+
"learning_rate": 5.333333333333334e-06,
|
| 1143 |
+
"loss": 0.058,
|
| 1144 |
+
"step": 1300
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 25.014,
|
| 1148 |
+
"grad_norm": 1.6732549667358398,
|
| 1149 |
+
"learning_rate": 5.288888888888889e-06,
|
| 1150 |
+
"loss": 0.002,
|
| 1151 |
+
"step": 1310
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 25.018,
|
| 1155 |
+
"grad_norm": 0.006808862090110779,
|
| 1156 |
+
"learning_rate": 5.244444444444445e-06,
|
| 1157 |
+
"loss": 0.0004,
|
| 1158 |
+
"step": 1320
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 25.0204,
|
| 1162 |
+
"eval_accuracy": 0.7625,
|
| 1163 |
+
"eval_loss": 1.5100300312042236,
|
| 1164 |
+
"eval_runtime": 15.0066,
|
| 1165 |
+
"eval_samples_per_second": 5.331,
|
| 1166 |
+
"eval_steps_per_second": 1.333,
|
| 1167 |
+
"step": 1326
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 26.0016,
|
| 1171 |
+
"grad_norm": 0.011416507884860039,
|
| 1172 |
+
"learning_rate": 5.2e-06,
|
| 1173 |
+
"loss": 0.0003,
|
| 1174 |
+
"step": 1330
|
| 1175 |
+
},
|
| 1176 |
+
{
|
| 1177 |
+
"epoch": 26.0056,
|
| 1178 |
+
"grad_norm": 0.006314845755696297,
|
| 1179 |
+
"learning_rate": 5.155555555555556e-06,
|
| 1180 |
+
"loss": 0.0236,
|
| 1181 |
+
"step": 1340
|
| 1182 |
+
},
|
| 1183 |
+
{
|
| 1184 |
+
"epoch": 26.0096,
|
| 1185 |
+
"grad_norm": 1.8917161226272583,
|
| 1186 |
+
"learning_rate": 5.1111111111111115e-06,
|
| 1187 |
+
"loss": 0.0011,
|
| 1188 |
+
"step": 1350
|
| 1189 |
+
},
|
| 1190 |
+
{
|
| 1191 |
+
"epoch": 26.0136,
|
| 1192 |
+
"grad_norm": 0.015401429496705532,
|
| 1193 |
+
"learning_rate": 5.0666666666666676e-06,
|
| 1194 |
+
"loss": 0.0003,
|
| 1195 |
+
"step": 1360
|
| 1196 |
+
},
|
| 1197 |
+
{
|
| 1198 |
+
"epoch": 26.0176,
|
| 1199 |
+
"grad_norm": 0.2598150372505188,
|
| 1200 |
+
"learning_rate": 5.022222222222223e-06,
|
| 1201 |
+
"loss": 0.1007,
|
| 1202 |
+
"step": 1370
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 26.0204,
|
| 1206 |
+
"eval_accuracy": 0.6875,
|
| 1207 |
+
"eval_loss": 1.959010124206543,
|
| 1208 |
+
"eval_runtime": 15.1089,
|
| 1209 |
+
"eval_samples_per_second": 5.295,
|
| 1210 |
+
"eval_steps_per_second": 1.324,
|
| 1211 |
+
"step": 1377
|
| 1212 |
+
},
|
| 1213 |
+
{
|
| 1214 |
+
"epoch": 27.0012,
|
| 1215 |
+
"grad_norm": 0.025213167071342468,
|
| 1216 |
+
"learning_rate": 4.977777777777778e-06,
|
| 1217 |
+
"loss": 0.0352,
|
| 1218 |
+
"step": 1380
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 27.0052,
|
| 1222 |
+
"grad_norm": 0.17898155748844147,
|
| 1223 |
+
"learning_rate": 4.933333333333334e-06,
|
| 1224 |
+
"loss": 0.0003,
|
| 1225 |
+
"step": 1390
|
| 1226 |
+
},
|
| 1227 |
+
{
|
| 1228 |
+
"epoch": 27.0092,
|
| 1229 |
+
"grad_norm": 0.011180482804775238,
|
| 1230 |
+
"learning_rate": 4.888888888888889e-06,
|
| 1231 |
+
"loss": 0.3099,
|
| 1232 |
+
"step": 1400
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 27.0132,
|
| 1236 |
+
"grad_norm": 0.003275972092524171,
|
| 1237 |
+
"learning_rate": 4.8444444444444446e-06,
|
| 1238 |
+
"loss": 0.0006,
|
| 1239 |
+
"step": 1410
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 27.0172,
|
| 1243 |
+
"grad_norm": 0.10510570555925369,
|
| 1244 |
+
"learning_rate": 4.800000000000001e-06,
|
| 1245 |
+
"loss": 0.0006,
|
| 1246 |
+
"step": 1420
|
| 1247 |
+
},
|
| 1248 |
+
{
|
| 1249 |
+
"epoch": 27.0204,
|
| 1250 |
+
"eval_accuracy": 0.7125,
|
| 1251 |
+
"eval_loss": 1.8345705270767212,
|
| 1252 |
+
"eval_runtime": 15.6323,
|
| 1253 |
+
"eval_samples_per_second": 5.118,
|
| 1254 |
+
"eval_steps_per_second": 1.279,
|
| 1255 |
+
"step": 1428
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 28.0008,
|
| 1259 |
+
"grad_norm": 0.00974931288510561,
|
| 1260 |
+
"learning_rate": 4.755555555555556e-06,
|
| 1261 |
+
"loss": 0.0003,
|
| 1262 |
+
"step": 1430
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 28.0048,
|
| 1266 |
+
"grad_norm": 0.01707894168794155,
|
| 1267 |
+
"learning_rate": 4.711111111111111e-06,
|
| 1268 |
+
"loss": 0.0002,
|
| 1269 |
+
"step": 1440
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 28.0088,
|
| 1273 |
+
"grad_norm": 0.007560590747743845,
|
| 1274 |
+
"learning_rate": 4.666666666666667e-06,
|
| 1275 |
+
"loss": 0.0004,
|
| 1276 |
+
"step": 1450
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 28.0128,
|
| 1280 |
+
"grad_norm": 66.74208068847656,
|
| 1281 |
+
"learning_rate": 4.622222222222222e-06,
|
| 1282 |
+
"loss": 0.1921,
|
| 1283 |
+
"step": 1460
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 28.0168,
|
| 1287 |
+
"grad_norm": 0.0025084693916141987,
|
| 1288 |
+
"learning_rate": 4.5777777777777785e-06,
|
| 1289 |
+
"loss": 0.0006,
|
| 1290 |
+
"step": 1470
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 28.0204,
|
| 1294 |
+
"eval_accuracy": 0.825,
|
| 1295 |
+
"eval_loss": 1.4668537378311157,
|
| 1296 |
+
"eval_runtime": 14.5998,
|
| 1297 |
+
"eval_samples_per_second": 5.48,
|
| 1298 |
+
"eval_steps_per_second": 1.37,
|
| 1299 |
+
"step": 1479
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 29.0004,
|
| 1303 |
+
"grad_norm": 0.3155474364757538,
|
| 1304 |
+
"learning_rate": 4.533333333333334e-06,
|
| 1305 |
+
"loss": 0.0002,
|
| 1306 |
+
"step": 1480
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 29.0044,
|
| 1310 |
+
"grad_norm": 0.024095896631479263,
|
| 1311 |
+
"learning_rate": 4.488888888888889e-06,
|
| 1312 |
+
"loss": 0.0011,
|
| 1313 |
+
"step": 1490
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 29.0084,
|
| 1317 |
+
"grad_norm": 0.00578249292448163,
|
| 1318 |
+
"learning_rate": 4.444444444444444e-06,
|
| 1319 |
+
"loss": 0.0002,
|
| 1320 |
+
"step": 1500
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 29.0124,
|
| 1324 |
+
"grad_norm": 0.009000943042337894,
|
| 1325 |
+
"learning_rate": 4.4e-06,
|
| 1326 |
+
"loss": 0.0008,
|
| 1327 |
+
"step": 1510
|
| 1328 |
+
},
|
| 1329 |
+
{
|
| 1330 |
+
"epoch": 29.0164,
|
| 1331 |
+
"grad_norm": 0.3360608220100403,
|
| 1332 |
+
"learning_rate": 4.3555555555555555e-06,
|
| 1333 |
+
"loss": 0.0004,
|
| 1334 |
+
"step": 1520
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 29.0204,
|
| 1338 |
+
"grad_norm": 0.007300488650798798,
|
| 1339 |
+
"learning_rate": 4.3111111111111115e-06,
|
| 1340 |
+
"loss": 0.0001,
|
| 1341 |
+
"step": 1530
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"epoch": 29.0204,
|
| 1345 |
+
"eval_accuracy": 0.7875,
|
| 1346 |
+
"eval_loss": 1.5396068096160889,
|
| 1347 |
+
"eval_runtime": 14.8018,
|
| 1348 |
+
"eval_samples_per_second": 5.405,
|
| 1349 |
+
"eval_steps_per_second": 1.351,
|
| 1350 |
+
"step": 1530
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 30.004,
|
| 1354 |
+
"grad_norm": 0.0051333606243133545,
|
| 1355 |
+
"learning_rate": 4.266666666666668e-06,
|
| 1356 |
+
"loss": 0.0002,
|
| 1357 |
+
"step": 1540
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 30.008,
|
| 1361 |
+
"grad_norm": 0.006649728864431381,
|
| 1362 |
+
"learning_rate": 4.222222222222223e-06,
|
| 1363 |
+
"loss": 0.0002,
|
| 1364 |
+
"step": 1550
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 30.012,
|
| 1368 |
+
"grad_norm": 0.004679904319345951,
|
| 1369 |
+
"learning_rate": 4.177777777777778e-06,
|
| 1370 |
+
"loss": 0.0002,
|
| 1371 |
+
"step": 1560
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 30.016,
|
| 1375 |
+
"grad_norm": 220.38076782226562,
|
| 1376 |
+
"learning_rate": 4.133333333333333e-06,
|
| 1377 |
+
"loss": 0.0777,
|
| 1378 |
+
"step": 1570
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 30.02,
|
| 1382 |
+
"grad_norm": 0.004013615660369396,
|
| 1383 |
+
"learning_rate": 4.088888888888889e-06,
|
| 1384 |
+
"loss": 0.0002,
|
| 1385 |
+
"step": 1580
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 30.0204,
|
| 1389 |
+
"eval_accuracy": 0.7875,
|
| 1390 |
+
"eval_loss": 1.571619987487793,
|
| 1391 |
+
"eval_runtime": 14.813,
|
| 1392 |
+
"eval_samples_per_second": 5.401,
|
| 1393 |
+
"eval_steps_per_second": 1.35,
|
| 1394 |
+
"step": 1581
|
| 1395 |
+
},
|
| 1396 |
+
{
|
| 1397 |
+
"epoch": 31.0036,
|
| 1398 |
+
"grad_norm": 0.049216415733098984,
|
| 1399 |
+
"learning_rate": 4.044444444444445e-06,
|
| 1400 |
+
"loss": 0.0002,
|
| 1401 |
+
"step": 1590
|
| 1402 |
+
},
|
| 1403 |
+
{
|
| 1404 |
+
"epoch": 31.0076,
|
| 1405 |
+
"grad_norm": 0.01534576527774334,
|
| 1406 |
+
"learning_rate": 4.000000000000001e-06,
|
| 1407 |
+
"loss": 0.0001,
|
| 1408 |
+
"step": 1600
|
| 1409 |
+
},
|
| 1410 |
+
{
|
| 1411 |
+
"epoch": 31.0116,
|
| 1412 |
+
"grad_norm": 0.002917769132182002,
|
| 1413 |
+
"learning_rate": 3.955555555555556e-06,
|
| 1414 |
+
"loss": 0.0002,
|
| 1415 |
+
"step": 1610
|
| 1416 |
+
},
|
| 1417 |
+
{
|
| 1418 |
+
"epoch": 31.0156,
|
| 1419 |
+
"grad_norm": 0.002222651382908225,
|
| 1420 |
+
"learning_rate": 3.911111111111112e-06,
|
| 1421 |
+
"loss": 0.0002,
|
| 1422 |
+
"step": 1620
|
| 1423 |
+
},
|
| 1424 |
+
{
|
| 1425 |
+
"epoch": 31.0196,
|
| 1426 |
+
"grad_norm": 0.008118602447211742,
|
| 1427 |
+
"learning_rate": 3.866666666666667e-06,
|
| 1428 |
+
"loss": 0.0001,
|
| 1429 |
+
"step": 1630
|
| 1430 |
+
},
|
| 1431 |
+
{
|
| 1432 |
+
"epoch": 31.0204,
|
| 1433 |
+
"eval_accuracy": 0.7625,
|
| 1434 |
+
"eval_loss": 1.6614097356796265,
|
| 1435 |
+
"eval_runtime": 14.4379,
|
| 1436 |
+
"eval_samples_per_second": 5.541,
|
| 1437 |
+
"eval_steps_per_second": 1.385,
|
| 1438 |
+
"step": 1632
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 32.0032,
|
| 1442 |
+
"grad_norm": 0.004146672319620848,
|
| 1443 |
+
"learning_rate": 3.8222222222222224e-06,
|
| 1444 |
+
"loss": 0.0001,
|
| 1445 |
+
"step": 1640
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 32.0072,
|
| 1449 |
+
"grad_norm": 0.0034797696862369776,
|
| 1450 |
+
"learning_rate": 3.777777777777778e-06,
|
| 1451 |
+
"loss": 0.0001,
|
| 1452 |
+
"step": 1650
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 32.0112,
|
| 1456 |
+
"grad_norm": 0.0042143468745052814,
|
| 1457 |
+
"learning_rate": 3.7333333333333337e-06,
|
| 1458 |
+
"loss": 0.0001,
|
| 1459 |
+
"step": 1660
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 32.0152,
|
| 1463 |
+
"grad_norm": 0.054984163492918015,
|
| 1464 |
+
"learning_rate": 3.688888888888889e-06,
|
| 1465 |
+
"loss": 0.0001,
|
| 1466 |
+
"step": 1670
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 32.0192,
|
| 1470 |
+
"grad_norm": 0.004838942550122738,
|
| 1471 |
+
"learning_rate": 3.644444444444445e-06,
|
| 1472 |
+
"loss": 0.0002,
|
| 1473 |
+
"step": 1680
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 32.0204,
|
| 1477 |
+
"eval_accuracy": 0.7625,
|
| 1478 |
+
"eval_loss": 1.6355606317520142,
|
| 1479 |
+
"eval_runtime": 15.4442,
|
| 1480 |
+
"eval_samples_per_second": 5.18,
|
| 1481 |
+
"eval_steps_per_second": 1.295,
|
| 1482 |
+
"step": 1683
|
| 1483 |
+
},
|
| 1484 |
+
{
|
| 1485 |
+
"epoch": 33.0028,
|
| 1486 |
+
"grad_norm": 0.3461035192012787,
|
| 1487 |
+
"learning_rate": 3.6000000000000003e-06,
|
| 1488 |
+
"loss": 0.0001,
|
| 1489 |
+
"step": 1690
|
| 1490 |
+
},
|
| 1491 |
+
{
|
| 1492 |
+
"epoch": 33.0068,
|
| 1493 |
+
"grad_norm": 0.002831398043781519,
|
| 1494 |
+
"learning_rate": 3.555555555555556e-06,
|
| 1495 |
+
"loss": 0.0001,
|
| 1496 |
+
"step": 1700
|
| 1497 |
+
},
|
| 1498 |
+
{
|
| 1499 |
+
"epoch": 33.0108,
|
| 1500 |
+
"grad_norm": 0.06873564422130585,
|
| 1501 |
+
"learning_rate": 3.511111111111111e-06,
|
| 1502 |
+
"loss": 0.0001,
|
| 1503 |
+
"step": 1710
|
| 1504 |
+
},
|
| 1505 |
+
{
|
| 1506 |
+
"epoch": 33.0148,
|
| 1507 |
+
"grad_norm": 0.006833823397755623,
|
| 1508 |
+
"learning_rate": 3.4666666666666672e-06,
|
| 1509 |
+
"loss": 0.0002,
|
| 1510 |
+
"step": 1720
|
| 1511 |
+
},
|
| 1512 |
+
{
|
| 1513 |
+
"epoch": 33.0188,
|
| 1514 |
+
"grad_norm": 0.004828931763768196,
|
| 1515 |
+
"learning_rate": 3.4222222222222224e-06,
|
| 1516 |
+
"loss": 0.0001,
|
| 1517 |
+
"step": 1730
|
| 1518 |
+
},
|
| 1519 |
+
{
|
| 1520 |
+
"epoch": 33.0204,
|
| 1521 |
+
"eval_accuracy": 0.8,
|
| 1522 |
+
"eval_loss": 1.5730502605438232,
|
| 1523 |
+
"eval_runtime": 14.4769,
|
| 1524 |
+
"eval_samples_per_second": 5.526,
|
| 1525 |
+
"eval_steps_per_second": 1.382,
|
| 1526 |
+
"step": 1734
|
| 1527 |
+
},
|
| 1528 |
+
{
|
| 1529 |
+
"epoch": 34.0024,
|
| 1530 |
+
"grad_norm": 0.02358504943549633,
|
| 1531 |
+
"learning_rate": 3.377777777777778e-06,
|
| 1532 |
+
"loss": 0.0003,
|
| 1533 |
+
"step": 1740
|
| 1534 |
+
},
|
| 1535 |
+
{
|
| 1536 |
+
"epoch": 34.0064,
|
| 1537 |
+
"grad_norm": 0.0021904546301811934,
|
| 1538 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 1539 |
+
"loss": 0.0237,
|
| 1540 |
+
"step": 1750
|
| 1541 |
+
},
|
| 1542 |
+
{
|
| 1543 |
+
"epoch": 34.0104,
|
| 1544 |
+
"grad_norm": 0.004002240486443043,
|
| 1545 |
+
"learning_rate": 3.2888888888888894e-06,
|
| 1546 |
+
"loss": 0.0002,
|
| 1547 |
+
"step": 1760
|
| 1548 |
+
},
|
| 1549 |
+
{
|
| 1550 |
+
"epoch": 34.0144,
|
| 1551 |
+
"grad_norm": 0.00806827750056982,
|
| 1552 |
+
"learning_rate": 3.2444444444444446e-06,
|
| 1553 |
+
"loss": 0.0001,
|
| 1554 |
+
"step": 1770
|
| 1555 |
+
},
|
| 1556 |
+
{
|
| 1557 |
+
"epoch": 34.0184,
|
| 1558 |
+
"grad_norm": 0.004369418602436781,
|
| 1559 |
+
"learning_rate": 3.2000000000000003e-06,
|
| 1560 |
+
"loss": 0.0001,
|
| 1561 |
+
"step": 1780
|
| 1562 |
+
},
|
| 1563 |
+
{
|
| 1564 |
+
"epoch": 34.0204,
|
| 1565 |
+
"eval_accuracy": 0.725,
|
| 1566 |
+
"eval_loss": 2.0019965171813965,
|
| 1567 |
+
"eval_runtime": 14.7093,
|
| 1568 |
+
"eval_samples_per_second": 5.439,
|
| 1569 |
+
"eval_steps_per_second": 1.36,
|
| 1570 |
+
"step": 1785
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 35.002,
|
| 1574 |
+
"grad_norm": 0.004029570147395134,
|
| 1575 |
+
"learning_rate": 3.1555555555555555e-06,
|
| 1576 |
+
"loss": 0.0001,
|
| 1577 |
+
"step": 1790
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 35.006,
|
| 1581 |
+
"grad_norm": 0.0854596495628357,
|
| 1582 |
+
"learning_rate": 3.1111111111111116e-06,
|
| 1583 |
+
"loss": 0.0001,
|
| 1584 |
+
"step": 1800
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 35.01,
|
| 1588 |
+
"grad_norm": 0.00881748553365469,
|
| 1589 |
+
"learning_rate": 3.066666666666667e-06,
|
| 1590 |
+
"loss": 0.0001,
|
| 1591 |
+
"step": 1810
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 35.014,
|
| 1595 |
+
"grad_norm": 0.007664634846150875,
|
| 1596 |
+
"learning_rate": 3.0222222222222225e-06,
|
| 1597 |
+
"loss": 0.0001,
|
| 1598 |
+
"step": 1820
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 35.018,
|
| 1602 |
+
"grad_norm": 0.004043503198772669,
|
| 1603 |
+
"learning_rate": 2.9777777777777777e-06,
|
| 1604 |
+
"loss": 0.0001,
|
| 1605 |
+
"step": 1830
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 35.0204,
|
| 1609 |
+
"eval_accuracy": 0.75,
|
| 1610 |
+
"eval_loss": 1.888606071472168,
|
| 1611 |
+
"eval_runtime": 16.1561,
|
| 1612 |
+
"eval_samples_per_second": 4.952,
|
| 1613 |
+
"eval_steps_per_second": 1.238,
|
| 1614 |
+
"step": 1836
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 36.0016,
|
| 1618 |
+
"grad_norm": 0.027049187570810318,
|
| 1619 |
+
"learning_rate": 2.9333333333333338e-06,
|
| 1620 |
+
"loss": 0.0001,
|
| 1621 |
+
"step": 1840
|
| 1622 |
+
},
|
| 1623 |
+
{
|
| 1624 |
+
"epoch": 36.0056,
|
| 1625 |
+
"grad_norm": 0.011712036095559597,
|
| 1626 |
+
"learning_rate": 2.888888888888889e-06,
|
| 1627 |
+
"loss": 0.0001,
|
| 1628 |
+
"step": 1850
|
| 1629 |
+
},
|
| 1630 |
+
{
|
| 1631 |
+
"epoch": 36.0096,
|
| 1632 |
+
"grad_norm": 0.0028739357367157936,
|
| 1633 |
+
"learning_rate": 2.8444444444444446e-06,
|
| 1634 |
+
"loss": 0.0001,
|
| 1635 |
+
"step": 1860
|
| 1636 |
+
},
|
| 1637 |
+
{
|
| 1638 |
+
"epoch": 36.0136,
|
| 1639 |
+
"grad_norm": 0.0029218129348009825,
|
| 1640 |
+
"learning_rate": 2.8000000000000003e-06,
|
| 1641 |
+
"loss": 0.0001,
|
| 1642 |
+
"step": 1870
|
| 1643 |
+
},
|
| 1644 |
+
{
|
| 1645 |
+
"epoch": 36.0176,
|
| 1646 |
+
"grad_norm": 0.002428996842354536,
|
| 1647 |
+
"learning_rate": 2.755555555555556e-06,
|
| 1648 |
+
"loss": 0.0001,
|
| 1649 |
+
"step": 1880
|
| 1650 |
+
},
|
| 1651 |
+
{
|
| 1652 |
+
"epoch": 36.0204,
|
| 1653 |
+
"eval_accuracy": 0.75,
|
| 1654 |
+
"eval_loss": 1.8363139629364014,
|
| 1655 |
+
"eval_runtime": 14.1077,
|
| 1656 |
+
"eval_samples_per_second": 5.671,
|
| 1657 |
+
"eval_steps_per_second": 1.418,
|
| 1658 |
+
"step": 1887
|
| 1659 |
+
},
|
| 1660 |
+
{
|
| 1661 |
+
"epoch": 37.0012,
|
| 1662 |
+
"grad_norm": 0.001762293977662921,
|
| 1663 |
+
"learning_rate": 2.7111111111111116e-06,
|
| 1664 |
+
"loss": 0.0001,
|
| 1665 |
+
"step": 1890
|
| 1666 |
+
},
|
| 1667 |
+
{
|
| 1668 |
+
"epoch": 37.0052,
|
| 1669 |
+
"grad_norm": 0.010973138734698296,
|
| 1670 |
+
"learning_rate": 2.666666666666667e-06,
|
| 1671 |
+
"loss": 0.0001,
|
| 1672 |
+
"step": 1900
|
| 1673 |
+
},
|
| 1674 |
+
{
|
| 1675 |
+
"epoch": 37.0092,
|
| 1676 |
+
"grad_norm": 0.007034891285002232,
|
| 1677 |
+
"learning_rate": 2.6222222222222225e-06,
|
| 1678 |
+
"loss": 0.0001,
|
| 1679 |
+
"step": 1910
|
| 1680 |
+
},
|
| 1681 |
+
{
|
| 1682 |
+
"epoch": 37.0132,
|
| 1683 |
+
"grad_norm": 0.04831545799970627,
|
| 1684 |
+
"learning_rate": 2.577777777777778e-06,
|
| 1685 |
+
"loss": 0.0001,
|
| 1686 |
+
"step": 1920
|
| 1687 |
+
},
|
| 1688 |
+
{
|
| 1689 |
+
"epoch": 37.0172,
|
| 1690 |
+
"grad_norm": 0.003924284130334854,
|
| 1691 |
+
"learning_rate": 2.5333333333333338e-06,
|
| 1692 |
+
"loss": 0.0001,
|
| 1693 |
+
"step": 1930
|
| 1694 |
+
},
|
| 1695 |
+
{
|
| 1696 |
+
"epoch": 37.0204,
|
| 1697 |
+
"eval_accuracy": 0.7625,
|
| 1698 |
+
"eval_loss": 1.6848043203353882,
|
| 1699 |
+
"eval_runtime": 14.1172,
|
| 1700 |
+
"eval_samples_per_second": 5.667,
|
| 1701 |
+
"eval_steps_per_second": 1.417,
|
| 1702 |
+
"step": 1938
|
| 1703 |
+
},
|
| 1704 |
+
{
|
| 1705 |
+
"epoch": 38.0008,
|
| 1706 |
+
"grad_norm": 0.003881203942000866,
|
| 1707 |
+
"learning_rate": 2.488888888888889e-06,
|
| 1708 |
+
"loss": 0.0001,
|
| 1709 |
+
"step": 1940
|
| 1710 |
+
},
|
| 1711 |
+
{
|
| 1712 |
+
"epoch": 38.0048,
|
| 1713 |
+
"grad_norm": 0.002467320766299963,
|
| 1714 |
+
"learning_rate": 2.4444444444444447e-06,
|
| 1715 |
+
"loss": 0.0001,
|
| 1716 |
+
"step": 1950
|
| 1717 |
+
},
|
| 1718 |
+
{
|
| 1719 |
+
"epoch": 38.0088,
|
| 1720 |
+
"grad_norm": 0.004267244599759579,
|
| 1721 |
+
"learning_rate": 2.4000000000000003e-06,
|
| 1722 |
+
"loss": 0.0001,
|
| 1723 |
+
"step": 1960
|
| 1724 |
+
},
|
| 1725 |
+
{
|
| 1726 |
+
"epoch": 38.0128,
|
| 1727 |
+
"grad_norm": 0.003334041452035308,
|
| 1728 |
+
"learning_rate": 2.3555555555555555e-06,
|
| 1729 |
+
"loss": 0.1433,
|
| 1730 |
+
"step": 1970
|
| 1731 |
+
},
|
| 1732 |
+
{
|
| 1733 |
+
"epoch": 38.0168,
|
| 1734 |
+
"grad_norm": 0.0034292838536202908,
|
| 1735 |
+
"learning_rate": 2.311111111111111e-06,
|
| 1736 |
+
"loss": 0.0001,
|
| 1737 |
+
"step": 1980
|
| 1738 |
+
},
|
| 1739 |
+
{
|
| 1740 |
+
"epoch": 38.0204,
|
| 1741 |
+
"eval_accuracy": 0.75,
|
| 1742 |
+
"eval_loss": 1.7187621593475342,
|
| 1743 |
+
"eval_runtime": 14.1135,
|
| 1744 |
+
"eval_samples_per_second": 5.668,
|
| 1745 |
+
"eval_steps_per_second": 1.417,
|
| 1746 |
+
"step": 1989
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 39.0004,
|
| 1750 |
+
"grad_norm": 0.002690413035452366,
|
| 1751 |
+
"learning_rate": 2.266666666666667e-06,
|
| 1752 |
+
"loss": 0.0142,
|
| 1753 |
+
"step": 1990
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 39.0044,
|
| 1757 |
+
"grad_norm": 0.003135059028863907,
|
| 1758 |
+
"learning_rate": 2.222222222222222e-06,
|
| 1759 |
+
"loss": 0.0001,
|
| 1760 |
+
"step": 2000
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 39.0084,
|
| 1764 |
+
"grad_norm": 0.003898640163242817,
|
| 1765 |
+
"learning_rate": 2.1777777777777777e-06,
|
| 1766 |
+
"loss": 0.0001,
|
| 1767 |
+
"step": 2010
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 39.0124,
|
| 1771 |
+
"grad_norm": 0.0050819204188883305,
|
| 1772 |
+
"learning_rate": 2.133333333333334e-06,
|
| 1773 |
+
"loss": 0.0001,
|
| 1774 |
+
"step": 2020
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 39.0164,
|
| 1778 |
+
"grad_norm": 0.0032317114528268576,
|
| 1779 |
+
"learning_rate": 2.088888888888889e-06,
|
| 1780 |
+
"loss": 0.0412,
|
| 1781 |
+
"step": 2030
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 39.0204,
|
| 1785 |
+
"grad_norm": 0.00116757582873106,
|
| 1786 |
+
"learning_rate": 2.0444444444444447e-06,
|
| 1787 |
+
"loss": 0.0001,
|
| 1788 |
+
"step": 2040
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 39.0204,
|
| 1792 |
+
"eval_accuracy": 0.8,
|
| 1793 |
+
"eval_loss": 1.5820459127426147,
|
| 1794 |
+
"eval_runtime": 15.2596,
|
| 1795 |
+
"eval_samples_per_second": 5.243,
|
| 1796 |
+
"eval_steps_per_second": 1.311,
|
| 1797 |
+
"step": 2040
|
| 1798 |
+
},
|
| 1799 |
+
{
|
| 1800 |
+
"epoch": 40.004,
|
| 1801 |
+
"grad_norm": 0.00318012572824955,
|
| 1802 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 1803 |
+
"loss": 0.0001,
|
| 1804 |
+
"step": 2050
|
| 1805 |
+
},
|
| 1806 |
+
{
|
| 1807 |
+
"epoch": 40.008,
|
| 1808 |
+
"grad_norm": 0.0023195173125714064,
|
| 1809 |
+
"learning_rate": 1.955555555555556e-06,
|
| 1810 |
+
"loss": 0.0008,
|
| 1811 |
+
"step": 2060
|
| 1812 |
+
},
|
| 1813 |
+
{
|
| 1814 |
+
"epoch": 40.012,
|
| 1815 |
+
"grad_norm": 0.002880761167034507,
|
| 1816 |
+
"learning_rate": 1.9111111111111112e-06,
|
| 1817 |
+
"loss": 0.0001,
|
| 1818 |
+
"step": 2070
|
| 1819 |
+
},
|
| 1820 |
+
{
|
| 1821 |
+
"epoch": 40.016,
|
| 1822 |
+
"grad_norm": 88.72091674804688,
|
| 1823 |
+
"learning_rate": 1.8666666666666669e-06,
|
| 1824 |
+
"loss": 0.0023,
|
| 1825 |
+
"step": 2080
|
| 1826 |
+
},
|
| 1827 |
+
{
|
| 1828 |
+
"epoch": 40.02,
|
| 1829 |
+
"grad_norm": 0.0025204592384397984,
|
| 1830 |
+
"learning_rate": 1.8222222222222225e-06,
|
| 1831 |
+
"loss": 0.0001,
|
| 1832 |
+
"step": 2090
|
| 1833 |
+
},
|
| 1834 |
+
{
|
| 1835 |
+
"epoch": 40.0204,
|
| 1836 |
+
"eval_accuracy": 0.7875,
|
| 1837 |
+
"eval_loss": 1.6061248779296875,
|
| 1838 |
+
"eval_runtime": 14.5072,
|
| 1839 |
+
"eval_samples_per_second": 5.515,
|
| 1840 |
+
"eval_steps_per_second": 1.379,
|
| 1841 |
+
"step": 2091
|
| 1842 |
+
},
|
| 1843 |
+
{
|
| 1844 |
+
"epoch": 41.0036,
|
| 1845 |
+
"grad_norm": 0.0022217093501240015,
|
| 1846 |
+
"learning_rate": 1.777777777777778e-06,
|
| 1847 |
+
"loss": 0.167,
|
| 1848 |
+
"step": 2100
|
| 1849 |
+
},
|
| 1850 |
+
{
|
| 1851 |
+
"epoch": 41.0076,
|
| 1852 |
+
"grad_norm": 0.0016050190897658467,
|
| 1853 |
+
"learning_rate": 1.7333333333333336e-06,
|
| 1854 |
+
"loss": 0.0001,
|
| 1855 |
+
"step": 2110
|
| 1856 |
+
},
|
| 1857 |
+
{
|
| 1858 |
+
"epoch": 41.0116,
|
| 1859 |
+
"grad_norm": 0.0031738209072500467,
|
| 1860 |
+
"learning_rate": 1.688888888888889e-06,
|
| 1861 |
+
"loss": 0.0001,
|
| 1862 |
+
"step": 2120
|
| 1863 |
+
},
|
| 1864 |
+
{
|
| 1865 |
+
"epoch": 41.0156,
|
| 1866 |
+
"grad_norm": 0.0036317266058176756,
|
| 1867 |
+
"learning_rate": 1.6444444444444447e-06,
|
| 1868 |
+
"loss": 0.0001,
|
| 1869 |
+
"step": 2130
|
| 1870 |
+
},
|
| 1871 |
+
{
|
| 1872 |
+
"epoch": 41.0196,
|
| 1873 |
+
"grad_norm": 0.002648336812853813,
|
| 1874 |
+
"learning_rate": 1.6000000000000001e-06,
|
| 1875 |
+
"loss": 0.0001,
|
| 1876 |
+
"step": 2140
|
| 1877 |
+
},
|
| 1878 |
+
{
|
| 1879 |
+
"epoch": 41.0204,
|
| 1880 |
+
"eval_accuracy": 0.7,
|
| 1881 |
+
"eval_loss": 2.2816524505615234,
|
| 1882 |
+
"eval_runtime": 14.2804,
|
| 1883 |
+
"eval_samples_per_second": 5.602,
|
| 1884 |
+
"eval_steps_per_second": 1.401,
|
| 1885 |
+
"step": 2142
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 42.0032,
|
| 1889 |
+
"grad_norm": 0.0022142785601317883,
|
| 1890 |
+
"learning_rate": 1.5555555555555558e-06,
|
| 1891 |
+
"loss": 0.0001,
|
| 1892 |
+
"step": 2150
|
| 1893 |
+
},
|
| 1894 |
+
{
|
| 1895 |
+
"epoch": 42.0072,
|
| 1896 |
+
"grad_norm": 0.006730781402438879,
|
| 1897 |
+
"learning_rate": 1.5111111111111112e-06,
|
| 1898 |
+
"loss": 0.0001,
|
| 1899 |
+
"step": 2160
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 42.0112,
|
| 1903 |
+
"grad_norm": 0.0027248021215200424,
|
| 1904 |
+
"learning_rate": 1.4666666666666669e-06,
|
| 1905 |
+
"loss": 0.0001,
|
| 1906 |
+
"step": 2170
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 42.0152,
|
| 1910 |
+
"grad_norm": 0.0026180455461144447,
|
| 1911 |
+
"learning_rate": 1.4222222222222223e-06,
|
| 1912 |
+
"loss": 0.0001,
|
| 1913 |
+
"step": 2180
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 42.0192,
|
| 1917 |
+
"grad_norm": 0.0017348204273730516,
|
| 1918 |
+
"learning_rate": 1.377777777777778e-06,
|
| 1919 |
+
"loss": 0.0001,
|
| 1920 |
+
"step": 2190
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 42.0204,
|
| 1924 |
+
"eval_accuracy": 0.725,
|
| 1925 |
+
"eval_loss": 2.101508617401123,
|
| 1926 |
+
"eval_runtime": 15.3729,
|
| 1927 |
+
"eval_samples_per_second": 5.204,
|
| 1928 |
+
"eval_steps_per_second": 1.301,
|
| 1929 |
+
"step": 2193
|
| 1930 |
+
},
|
| 1931 |
+
{
|
| 1932 |
+
"epoch": 43.0028,
|
| 1933 |
+
"grad_norm": 0.0021387911401689053,
|
| 1934 |
+
"learning_rate": 1.3333333333333334e-06,
|
| 1935 |
+
"loss": 0.0001,
|
| 1936 |
+
"step": 2200
|
| 1937 |
+
},
|
| 1938 |
+
{
|
| 1939 |
+
"epoch": 43.0068,
|
| 1940 |
+
"grad_norm": 0.0030123190954327583,
|
| 1941 |
+
"learning_rate": 1.288888888888889e-06,
|
| 1942 |
+
"loss": 0.0001,
|
| 1943 |
+
"step": 2210
|
| 1944 |
+
},
|
| 1945 |
+
{
|
| 1946 |
+
"epoch": 43.0108,
|
| 1947 |
+
"grad_norm": 0.0043581160716712475,
|
| 1948 |
+
"learning_rate": 1.2444444444444445e-06,
|
| 1949 |
+
"loss": 0.0001,
|
| 1950 |
+
"step": 2220
|
| 1951 |
+
},
|
| 1952 |
+
{
|
| 1953 |
+
"epoch": 43.0148,
|
| 1954 |
+
"grad_norm": 0.0023331050761044025,
|
| 1955 |
+
"learning_rate": 1.2000000000000002e-06,
|
| 1956 |
+
"loss": 0.0001,
|
| 1957 |
+
"step": 2230
|
| 1958 |
+
},
|
| 1959 |
+
{
|
| 1960 |
+
"epoch": 43.0188,
|
| 1961 |
+
"grad_norm": 0.0014669563388451934,
|
| 1962 |
+
"learning_rate": 1.1555555555555556e-06,
|
| 1963 |
+
"loss": 0.0001,
|
| 1964 |
+
"step": 2240
|
| 1965 |
+
},
|
| 1966 |
+
{
|
| 1967 |
+
"epoch": 43.0204,
|
| 1968 |
+
"eval_accuracy": 0.775,
|
| 1969 |
+
"eval_loss": 1.6356258392333984,
|
| 1970 |
+
"eval_runtime": 14.3954,
|
| 1971 |
+
"eval_samples_per_second": 5.557,
|
| 1972 |
+
"eval_steps_per_second": 1.389,
|
| 1973 |
+
"step": 2244
|
| 1974 |
+
},
|
| 1975 |
+
{
|
| 1976 |
+
"epoch": 44.0024,
|
| 1977 |
+
"grad_norm": 0.0022818814031779766,
|
| 1978 |
+
"learning_rate": 1.111111111111111e-06,
|
| 1979 |
+
"loss": 0.2123,
|
| 1980 |
+
"step": 2250
|
| 1981 |
+
},
|
| 1982 |
+
{
|
| 1983 |
+
"epoch": 44.0064,
|
| 1984 |
+
"grad_norm": 0.004321521148085594,
|
| 1985 |
+
"learning_rate": 1.066666666666667e-06,
|
| 1986 |
+
"loss": 0.0001,
|
| 1987 |
+
"step": 2260
|
| 1988 |
+
},
|
| 1989 |
+
{
|
| 1990 |
+
"epoch": 44.0104,
|
| 1991 |
+
"grad_norm": 0.002616771264001727,
|
| 1992 |
+
"learning_rate": 1.0222222222222223e-06,
|
| 1993 |
+
"loss": 0.0001,
|
| 1994 |
+
"step": 2270
|
| 1995 |
+
},
|
| 1996 |
+
{
|
| 1997 |
+
"epoch": 44.0144,
|
| 1998 |
+
"grad_norm": 0.008771556429564953,
|
| 1999 |
+
"learning_rate": 9.77777777777778e-07,
|
| 2000 |
+
"loss": 0.0001,
|
| 2001 |
+
"step": 2280
|
| 2002 |
+
},
|
| 2003 |
+
{
|
| 2004 |
+
"epoch": 44.0184,
|
| 2005 |
+
"grad_norm": 0.007163883652538061,
|
| 2006 |
+
"learning_rate": 9.333333333333334e-07,
|
| 2007 |
+
"loss": 0.0001,
|
| 2008 |
+
"step": 2290
|
| 2009 |
+
},
|
| 2010 |
+
{
|
| 2011 |
+
"epoch": 44.0204,
|
| 2012 |
+
"eval_accuracy": 0.8125,
|
| 2013 |
+
"eval_loss": 1.5849277973175049,
|
| 2014 |
+
"eval_runtime": 14.7946,
|
| 2015 |
+
"eval_samples_per_second": 5.407,
|
| 2016 |
+
"eval_steps_per_second": 1.352,
|
| 2017 |
+
"step": 2295
|
| 2018 |
+
},
|
| 2019 |
+
{
|
| 2020 |
+
"epoch": 45.002,
|
| 2021 |
+
"grad_norm": 0.001609973143786192,
|
| 2022 |
+
"learning_rate": 8.88888888888889e-07,
|
| 2023 |
+
"loss": 0.0001,
|
| 2024 |
+
"step": 2300
|
| 2025 |
+
},
|
| 2026 |
+
{
|
| 2027 |
+
"epoch": 45.006,
|
| 2028 |
+
"grad_norm": 0.0015221175272017717,
|
| 2029 |
+
"learning_rate": 8.444444444444445e-07,
|
| 2030 |
+
"loss": 0.0001,
|
| 2031 |
+
"step": 2310
|
| 2032 |
+
},
|
| 2033 |
+
{
|
| 2034 |
+
"epoch": 45.01,
|
| 2035 |
+
"grad_norm": 0.00561766279861331,
|
| 2036 |
+
"learning_rate": 8.000000000000001e-07,
|
| 2037 |
+
"loss": 0.0002,
|
| 2038 |
+
"step": 2320
|
| 2039 |
+
},
|
| 2040 |
+
{
|
| 2041 |
+
"epoch": 45.014,
|
| 2042 |
+
"grad_norm": 0.005561948753893375,
|
| 2043 |
+
"learning_rate": 7.555555555555556e-07,
|
| 2044 |
+
"loss": 0.0001,
|
| 2045 |
+
"step": 2330
|
| 2046 |
+
},
|
| 2047 |
+
{
|
| 2048 |
+
"epoch": 45.018,
|
| 2049 |
+
"grad_norm": 0.0020426807459443808,
|
| 2050 |
+
"learning_rate": 7.111111111111112e-07,
|
| 2051 |
+
"loss": 0.0001,
|
| 2052 |
+
"step": 2340
|
| 2053 |
+
},
|
| 2054 |
+
{
|
| 2055 |
+
"epoch": 45.0204,
|
| 2056 |
+
"eval_accuracy": 0.775,
|
| 2057 |
+
"eval_loss": 1.6463369131088257,
|
| 2058 |
+
"eval_runtime": 15.349,
|
| 2059 |
+
"eval_samples_per_second": 5.212,
|
| 2060 |
+
"eval_steps_per_second": 1.303,
|
| 2061 |
+
"step": 2346
|
| 2062 |
+
},
|
| 2063 |
+
{
|
| 2064 |
+
"epoch": 46.0016,
|
| 2065 |
+
"grad_norm": 0.011843581683933735,
|
| 2066 |
+
"learning_rate": 6.666666666666667e-07,
|
| 2067 |
+
"loss": 0.0001,
|
| 2068 |
+
"step": 2350
|
| 2069 |
+
},
|
| 2070 |
+
{
|
| 2071 |
+
"epoch": 46.0056,
|
| 2072 |
+
"grad_norm": 0.003159413579851389,
|
| 2073 |
+
"learning_rate": 6.222222222222223e-07,
|
| 2074 |
+
"loss": 0.0001,
|
| 2075 |
+
"step": 2360
|
| 2076 |
+
},
|
| 2077 |
+
{
|
| 2078 |
+
"epoch": 46.0096,
|
| 2079 |
+
"grad_norm": 0.021830186247825623,
|
| 2080 |
+
"learning_rate": 5.777777777777778e-07,
|
| 2081 |
+
"loss": 0.0001,
|
| 2082 |
+
"step": 2370
|
| 2083 |
+
},
|
| 2084 |
+
{
|
| 2085 |
+
"epoch": 46.0136,
|
| 2086 |
+
"grad_norm": 0.0015857354737818241,
|
| 2087 |
+
"learning_rate": 5.333333333333335e-07,
|
| 2088 |
+
"loss": 0.0001,
|
| 2089 |
+
"step": 2380
|
| 2090 |
+
},
|
| 2091 |
+
{
|
| 2092 |
+
"epoch": 46.0176,
|
| 2093 |
+
"grad_norm": 0.0021360372193157673,
|
| 2094 |
+
"learning_rate": 4.88888888888889e-07,
|
| 2095 |
+
"loss": 0.0001,
|
| 2096 |
+
"step": 2390
|
| 2097 |
+
},
|
| 2098 |
+
{
|
| 2099 |
+
"epoch": 46.0204,
|
| 2100 |
+
"eval_accuracy": 0.775,
|
| 2101 |
+
"eval_loss": 1.664137601852417,
|
| 2102 |
+
"eval_runtime": 14.3393,
|
| 2103 |
+
"eval_samples_per_second": 5.579,
|
| 2104 |
+
"eval_steps_per_second": 1.395,
|
| 2105 |
+
"step": 2397
|
| 2106 |
+
},
|
| 2107 |
+
{
|
| 2108 |
+
"epoch": 47.0012,
|
| 2109 |
+
"grad_norm": 7.805647850036621,
|
| 2110 |
+
"learning_rate": 4.444444444444445e-07,
|
| 2111 |
+
"loss": 0.0007,
|
| 2112 |
+
"step": 2400
|
| 2113 |
+
},
|
| 2114 |
+
{
|
| 2115 |
+
"epoch": 47.0052,
|
| 2116 |
+
"grad_norm": 0.002305046422407031,
|
| 2117 |
+
"learning_rate": 4.0000000000000003e-07,
|
| 2118 |
+
"loss": 0.0001,
|
| 2119 |
+
"step": 2410
|
| 2120 |
+
},
|
| 2121 |
+
{
|
| 2122 |
+
"epoch": 47.0092,
|
| 2123 |
+
"grad_norm": 0.0024446428287774324,
|
| 2124 |
+
"learning_rate": 3.555555555555556e-07,
|
| 2125 |
+
"loss": 0.0001,
|
| 2126 |
+
"step": 2420
|
| 2127 |
+
},
|
| 2128 |
+
{
|
| 2129 |
+
"epoch": 47.0132,
|
| 2130 |
+
"grad_norm": 0.0018226341344416142,
|
| 2131 |
+
"learning_rate": 3.111111111111111e-07,
|
| 2132 |
+
"loss": 0.0001,
|
| 2133 |
+
"step": 2430
|
| 2134 |
+
},
|
| 2135 |
+
{
|
| 2136 |
+
"epoch": 47.0172,
|
| 2137 |
+
"grad_norm": 0.0018344988347962499,
|
| 2138 |
+
"learning_rate": 2.666666666666667e-07,
|
| 2139 |
+
"loss": 0.0001,
|
| 2140 |
+
"step": 2440
|
| 2141 |
+
},
|
| 2142 |
+
{
|
| 2143 |
+
"epoch": 47.0204,
|
| 2144 |
+
"eval_accuracy": 0.7875,
|
| 2145 |
+
"eval_loss": 1.612348198890686,
|
| 2146 |
+
"eval_runtime": 14.4481,
|
| 2147 |
+
"eval_samples_per_second": 5.537,
|
| 2148 |
+
"eval_steps_per_second": 1.384,
|
| 2149 |
+
"step": 2448
|
| 2150 |
+
},
|
| 2151 |
+
{
|
| 2152 |
+
"epoch": 48.0008,
|
| 2153 |
+
"grad_norm": 0.0016147164860740304,
|
| 2154 |
+
"learning_rate": 2.2222222222222224e-07,
|
| 2155 |
+
"loss": 0.0001,
|
| 2156 |
+
"step": 2450
|
| 2157 |
+
},
|
| 2158 |
+
{
|
| 2159 |
+
"epoch": 48.0048,
|
| 2160 |
+
"grad_norm": 0.0015180219197645783,
|
| 2161 |
+
"learning_rate": 1.777777777777778e-07,
|
| 2162 |
+
"loss": 0.0001,
|
| 2163 |
+
"step": 2460
|
| 2164 |
+
},
|
| 2165 |
+
{
|
| 2166 |
+
"epoch": 48.0088,
|
| 2167 |
+
"grad_norm": 0.0027082718443125486,
|
| 2168 |
+
"learning_rate": 1.3333333333333336e-07,
|
| 2169 |
+
"loss": 0.0001,
|
| 2170 |
+
"step": 2470
|
| 2171 |
+
},
|
| 2172 |
+
{
|
| 2173 |
+
"epoch": 48.0128,
|
| 2174 |
+
"grad_norm": 0.0015189133118838072,
|
| 2175 |
+
"learning_rate": 8.88888888888889e-08,
|
| 2176 |
+
"loss": 0.0001,
|
| 2177 |
+
"step": 2480
|
| 2178 |
+
},
|
| 2179 |
+
{
|
| 2180 |
+
"epoch": 48.0168,
|
| 2181 |
+
"grad_norm": 0.0014700506580993533,
|
| 2182 |
+
"learning_rate": 4.444444444444445e-08,
|
| 2183 |
+
"loss": 0.0001,
|
| 2184 |
+
"step": 2490
|
| 2185 |
+
},
|
| 2186 |
+
{
|
| 2187 |
+
"epoch": 48.0204,
|
| 2188 |
+
"eval_accuracy": 0.7875,
|
| 2189 |
+
"eval_loss": 1.6145384311676025,
|
| 2190 |
+
"eval_runtime": 14.6364,
|
| 2191 |
+
"eval_samples_per_second": 5.466,
|
| 2192 |
+
"eval_steps_per_second": 1.366,
|
| 2193 |
+
"step": 2499
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 49.0004,
|
| 2197 |
+
"grad_norm": 0.005640446674078703,
|
| 2198 |
+
"learning_rate": 0.0,
|
| 2199 |
+
"loss": 0.0001,
|
| 2200 |
+
"step": 2500
|
| 2201 |
+
},
|
| 2202 |
+
{
|
| 2203 |
+
"epoch": 49.0004,
|
| 2204 |
+
"eval_accuracy": 0.7875,
|
| 2205 |
+
"eval_loss": 1.6145387887954712,
|
| 2206 |
+
"eval_runtime": 15.4845,
|
| 2207 |
+
"eval_samples_per_second": 5.166,
|
| 2208 |
+
"eval_steps_per_second": 1.292,
|
| 2209 |
+
"step": 2500
|
| 2210 |
+
},
|
| 2211 |
+
{
|
| 2212 |
+
"epoch": 49.0004,
|
| 2213 |
+
"step": 2500,
|
| 2214 |
+
"total_flos": 4.34799425740686e+19,
|
| 2215 |
+
"train_loss": 0.1747144501608098,
|
| 2216 |
+
"train_runtime": 4798.9949,
|
| 2217 |
+
"train_samples_per_second": 2.084,
|
| 2218 |
+
"train_steps_per_second": 0.521
|
| 2219 |
+
},
|
| 2220 |
+
{
|
| 2221 |
+
"epoch": 49.0004,
|
| 2222 |
+
"eval_accuracy": 0.5753424657534246,
|
| 2223 |
+
"eval_loss": 2.5945777893066406,
|
| 2224 |
+
"eval_runtime": 15.5022,
|
| 2225 |
+
"eval_samples_per_second": 4.709,
|
| 2226 |
+
"eval_steps_per_second": 1.226,
|
| 2227 |
+
"step": 2500
|
| 2228 |
+
},
|
| 2229 |
+
{
|
| 2230 |
+
"epoch": 49.0004,
|
| 2231 |
+
"eval_accuracy": 0.5753424657534246,
|
| 2232 |
+
"eval_loss": 2.5945777893066406,
|
| 2233 |
+
"eval_runtime": 14.1475,
|
| 2234 |
+
"eval_samples_per_second": 5.16,
|
| 2235 |
+
"eval_steps_per_second": 1.343,
|
| 2236 |
+
"step": 2500
|
| 2237 |
+
}
|
| 2238 |
+
],
|
| 2239 |
+
"logging_steps": 10,
|
| 2240 |
+
"max_steps": 2500,
|
| 2241 |
+
"num_input_tokens_seen": 0,
|
| 2242 |
+
"num_train_epochs": 9223372036854775807,
|
| 2243 |
+
"save_steps": 500,
|
| 2244 |
+
"stateful_callbacks": {
|
| 2245 |
+
"TrainerControl": {
|
| 2246 |
+
"args": {
|
| 2247 |
+
"should_epoch_stop": false,
|
| 2248 |
+
"should_evaluate": false,
|
| 2249 |
+
"should_log": false,
|
| 2250 |
+
"should_save": true,
|
| 2251 |
+
"should_training_stop": true
|
| 2252 |
+
},
|
| 2253 |
+
"attributes": {}
|
| 2254 |
+
}
|
| 2255 |
+
},
|
| 2256 |
+
"total_flos": 4.34799425740686e+19,
|
| 2257 |
+
"train_batch_size": 4,
|
| 2258 |
+
"trial_name": null,
|
| 2259 |
+
"trial_params": null
|
| 2260 |
+
}
|