Upload trainer_state.json
Browse files- trainer_state.json +1336 -0
trainer_state.json
ADDED
|
@@ -0,0 +1,1336 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 88.70164904870342,
|
| 3 |
+
"best_model_checkpoint": "output/ft_minilm_roberta_base_tokenizer/checkpoint-55000",
|
| 4 |
+
"epoch": 4.9679342426158435,
|
| 5 |
+
"global_step": 55000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.05,
|
| 12 |
+
"learning_rate": 2.972902176858459e-05,
|
| 13 |
+
"loss": 3.6092,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.05,
|
| 18 |
+
"eval_exact_match": 38.34437086092715,
|
| 19 |
+
"eval_f1": 53.04195171599385,
|
| 20 |
+
"step": 500
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.09,
|
| 24 |
+
"learning_rate": 2.9458043537169182e-05,
|
| 25 |
+
"loss": 2.3309,
|
| 26 |
+
"step": 1000
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.09,
|
| 30 |
+
"eval_exact_match": 57.48344370860927,
|
| 31 |
+
"eval_f1": 69.86399789823338,
|
| 32 |
+
"step": 1000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.14,
|
| 36 |
+
"learning_rate": 2.9187065305753772e-05,
|
| 37 |
+
"loss": 1.869,
|
| 38 |
+
"step": 1500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.14,
|
| 42 |
+
"eval_exact_match": 60.8325449385052,
|
| 43 |
+
"eval_f1": 73.39213373938078,
|
| 44 |
+
"step": 1500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.18,
|
| 48 |
+
"learning_rate": 2.8916087074338363e-05,
|
| 49 |
+
"loss": 1.714,
|
| 50 |
+
"step": 2000
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.18,
|
| 54 |
+
"eval_exact_match": 67.55912961210974,
|
| 55 |
+
"eval_f1": 78.46892865109527,
|
| 56 |
+
"step": 2000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.23,
|
| 60 |
+
"learning_rate": 2.864510884292295e-05,
|
| 61 |
+
"loss": 1.596,
|
| 62 |
+
"step": 2500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.23,
|
| 66 |
+
"eval_exact_match": 69.00662251655629,
|
| 67 |
+
"eval_f1": 79.38516098327496,
|
| 68 |
+
"step": 2500
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.27,
|
| 72 |
+
"learning_rate": 2.8374130611507544e-05,
|
| 73 |
+
"loss": 1.4757,
|
| 74 |
+
"step": 3000
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.27,
|
| 78 |
+
"eval_exact_match": 70.37842951750237,
|
| 79 |
+
"eval_f1": 80.6431787888757,
|
| 80 |
+
"step": 3000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.32,
|
| 84 |
+
"learning_rate": 2.8103152380092135e-05,
|
| 85 |
+
"loss": 1.4583,
|
| 86 |
+
"step": 3500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.32,
|
| 90 |
+
"eval_exact_match": 70.35004730368969,
|
| 91 |
+
"eval_f1": 80.79000685737387,
|
| 92 |
+
"step": 3500
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.36,
|
| 96 |
+
"learning_rate": 2.783217414867672e-05,
|
| 97 |
+
"loss": 1.409,
|
| 98 |
+
"step": 4000
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.36,
|
| 102 |
+
"eval_exact_match": 72.25165562913908,
|
| 103 |
+
"eval_f1": 81.90341789407236,
|
| 104 |
+
"step": 4000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.41,
|
| 108 |
+
"learning_rate": 2.7561195917261312e-05,
|
| 109 |
+
"loss": 1.3424,
|
| 110 |
+
"step": 4500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.41,
|
| 114 |
+
"eval_exact_match": 72.48817407757805,
|
| 115 |
+
"eval_f1": 82.40953492685638,
|
| 116 |
+
"step": 4500
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.45,
|
| 120 |
+
"learning_rate": 2.7290217685845906e-05,
|
| 121 |
+
"loss": 1.35,
|
| 122 |
+
"step": 5000
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.45,
|
| 126 |
+
"eval_exact_match": 73.56669820245979,
|
| 127 |
+
"eval_f1": 83.04642576372542,
|
| 128 |
+
"step": 5000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.5,
|
| 132 |
+
"learning_rate": 2.7019239454430493e-05,
|
| 133 |
+
"loss": 1.3199,
|
| 134 |
+
"step": 5500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.5,
|
| 138 |
+
"eval_exact_match": 73.97350993377484,
|
| 139 |
+
"eval_f1": 83.20596198058827,
|
| 140 |
+
"step": 5500
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.54,
|
| 144 |
+
"learning_rate": 2.6748261223015084e-05,
|
| 145 |
+
"loss": 1.2529,
|
| 146 |
+
"step": 6000
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.54,
|
| 150 |
+
"eval_exact_match": 74.53169347209082,
|
| 151 |
+
"eval_f1": 83.5595619348799,
|
| 152 |
+
"step": 6000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.59,
|
| 156 |
+
"learning_rate": 2.6477282991599678e-05,
|
| 157 |
+
"loss": 1.2637,
|
| 158 |
+
"step": 6500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.59,
|
| 162 |
+
"eval_exact_match": 75.10879848628193,
|
| 163 |
+
"eval_f1": 84.03364368528639,
|
| 164 |
+
"step": 6500
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.63,
|
| 168 |
+
"learning_rate": 2.6206304760184265e-05,
|
| 169 |
+
"loss": 1.2265,
|
| 170 |
+
"step": 7000
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.63,
|
| 174 |
+
"eval_exact_match": 74.9763481551561,
|
| 175 |
+
"eval_f1": 84.28762156566786,
|
| 176 |
+
"step": 7000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.68,
|
| 180 |
+
"learning_rate": 2.5935326528768855e-05,
|
| 181 |
+
"loss": 1.2274,
|
| 182 |
+
"step": 7500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.68,
|
| 186 |
+
"eval_exact_match": 74.78713339640493,
|
| 187 |
+
"eval_f1": 84.24767651424737,
|
| 188 |
+
"step": 7500
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.72,
|
| 192 |
+
"learning_rate": 2.5664348297353446e-05,
|
| 193 |
+
"loss": 1.2305,
|
| 194 |
+
"step": 8000
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.72,
|
| 198 |
+
"eval_exact_match": 75.47776726584674,
|
| 199 |
+
"eval_f1": 84.74489870588677,
|
| 200 |
+
"step": 8000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.77,
|
| 204 |
+
"learning_rate": 2.539337006593804e-05,
|
| 205 |
+
"loss": 1.2175,
|
| 206 |
+
"step": 8500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.77,
|
| 210 |
+
"eval_exact_match": 76.7833491012299,
|
| 211 |
+
"eval_f1": 85.271914926584,
|
| 212 |
+
"step": 8500
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.81,
|
| 216 |
+
"learning_rate": 2.5122391834522627e-05,
|
| 217 |
+
"loss": 1.182,
|
| 218 |
+
"step": 9000
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.81,
|
| 222 |
+
"eval_exact_match": 76.45222327341533,
|
| 223 |
+
"eval_f1": 85.33283456122666,
|
| 224 |
+
"step": 9000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.86,
|
| 228 |
+
"learning_rate": 2.4851413603107218e-05,
|
| 229 |
+
"loss": 1.1853,
|
| 230 |
+
"step": 9500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.86,
|
| 234 |
+
"eval_exact_match": 76.96310312204352,
|
| 235 |
+
"eval_f1": 85.2924473992702,
|
| 236 |
+
"step": 9500
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.9,
|
| 240 |
+
"learning_rate": 2.4580435371691808e-05,
|
| 241 |
+
"loss": 1.1664,
|
| 242 |
+
"step": 10000
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.9,
|
| 246 |
+
"eval_exact_match": 76.04541154210028,
|
| 247 |
+
"eval_f1": 85.02171266178281,
|
| 248 |
+
"step": 10000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.95,
|
| 252 |
+
"learning_rate": 2.43094571402764e-05,
|
| 253 |
+
"loss": 1.1932,
|
| 254 |
+
"step": 10500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.95,
|
| 258 |
+
"eval_exact_match": 75.78051087984863,
|
| 259 |
+
"eval_f1": 85.14984769166524,
|
| 260 |
+
"step": 10500
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.99,
|
| 264 |
+
"learning_rate": 2.403847890886099e-05,
|
| 265 |
+
"loss": 1.1671,
|
| 266 |
+
"step": 11000
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.99,
|
| 270 |
+
"eval_exact_match": 77.6158940397351,
|
| 271 |
+
"eval_f1": 85.8681189259958,
|
| 272 |
+
"step": 11000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 1.04,
|
| 276 |
+
"learning_rate": 2.376750067744558e-05,
|
| 277 |
+
"loss": 1.028,
|
| 278 |
+
"step": 11500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 1.04,
|
| 282 |
+
"eval_exact_match": 77.33207190160833,
|
| 283 |
+
"eval_f1": 86.13476093529944,
|
| 284 |
+
"step": 11500
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 1.08,
|
| 288 |
+
"learning_rate": 2.349652244603017e-05,
|
| 289 |
+
"loss": 1.0269,
|
| 290 |
+
"step": 12000
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.08,
|
| 294 |
+
"eval_exact_match": 77.31315042573321,
|
| 295 |
+
"eval_f1": 85.78642346203148,
|
| 296 |
+
"step": 12000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 1.13,
|
| 300 |
+
"learning_rate": 2.322554421461476e-05,
|
| 301 |
+
"loss": 1.0276,
|
| 302 |
+
"step": 12500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 1.13,
|
| 306 |
+
"eval_exact_match": 77.62535477767265,
|
| 307 |
+
"eval_f1": 86.04542466345086,
|
| 308 |
+
"step": 12500
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 1.17,
|
| 312 |
+
"learning_rate": 2.295456598319935e-05,
|
| 313 |
+
"loss": 1.0251,
|
| 314 |
+
"step": 13000
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 1.17,
|
| 318 |
+
"eval_exact_match": 77.96594134342479,
|
| 319 |
+
"eval_f1": 86.0039567640003,
|
| 320 |
+
"step": 13000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 1.22,
|
| 324 |
+
"learning_rate": 2.268358775178394e-05,
|
| 325 |
+
"loss": 1.0153,
|
| 326 |
+
"step": 13500
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 1.22,
|
| 330 |
+
"eval_exact_match": 77.918637653737,
|
| 331 |
+
"eval_f1": 85.94724245197462,
|
| 332 |
+
"step": 13500
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.26,
|
| 336 |
+
"learning_rate": 2.2412609520368532e-05,
|
| 337 |
+
"loss": 1.0273,
|
| 338 |
+
"step": 14000
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.26,
|
| 342 |
+
"eval_exact_match": 77.88079470198676,
|
| 343 |
+
"eval_f1": 86.43469515459539,
|
| 344 |
+
"step": 14000
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 1.31,
|
| 348 |
+
"learning_rate": 2.2141631288953123e-05,
|
| 349 |
+
"loss": 1.0184,
|
| 350 |
+
"step": 14500
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 1.31,
|
| 354 |
+
"eval_exact_match": 78.30652790917692,
|
| 355 |
+
"eval_f1": 86.49960884571237,
|
| 356 |
+
"step": 14500
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 1.35,
|
| 360 |
+
"learning_rate": 2.187065305753771e-05,
|
| 361 |
+
"loss": 1.0129,
|
| 362 |
+
"step": 15000
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 1.35,
|
| 366 |
+
"eval_exact_match": 77.84295175023652,
|
| 367 |
+
"eval_f1": 86.34551242938619,
|
| 368 |
+
"step": 15000
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 1.4,
|
| 372 |
+
"learning_rate": 2.15996748261223e-05,
|
| 373 |
+
"loss": 1.0298,
|
| 374 |
+
"step": 15500
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.4,
|
| 378 |
+
"eval_exact_match": 78.36329233680227,
|
| 379 |
+
"eval_f1": 86.62513916601708,
|
| 380 |
+
"step": 15500
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 1.45,
|
| 384 |
+
"learning_rate": 2.1328696594706894e-05,
|
| 385 |
+
"loss": 0.9999,
|
| 386 |
+
"step": 16000
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 1.45,
|
| 390 |
+
"eval_exact_match": 78.59981078524125,
|
| 391 |
+
"eval_f1": 86.75304072732975,
|
| 392 |
+
"step": 16000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 1.49,
|
| 396 |
+
"learning_rate": 2.105771836329148e-05,
|
| 397 |
+
"loss": 0.957,
|
| 398 |
+
"step": 16500
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 1.49,
|
| 402 |
+
"eval_exact_match": 78.69441816461683,
|
| 403 |
+
"eval_f1": 86.9310767775865,
|
| 404 |
+
"step": 16500
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 1.54,
|
| 408 |
+
"learning_rate": 2.0786740131876072e-05,
|
| 409 |
+
"loss": 1.0023,
|
| 410 |
+
"step": 17000
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 1.54,
|
| 414 |
+
"eval_exact_match": 78.80794701986756,
|
| 415 |
+
"eval_f1": 87.1131371682942,
|
| 416 |
+
"step": 17000
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 1.58,
|
| 420 |
+
"learning_rate": 2.0515761900460666e-05,
|
| 421 |
+
"loss": 0.999,
|
| 422 |
+
"step": 17500
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 1.58,
|
| 426 |
+
"eval_exact_match": 78.69441816461683,
|
| 427 |
+
"eval_f1": 86.85637778000766,
|
| 428 |
+
"step": 17500
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 1.63,
|
| 432 |
+
"learning_rate": 2.0244783669045253e-05,
|
| 433 |
+
"loss": 1.0011,
|
| 434 |
+
"step": 18000
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 1.63,
|
| 438 |
+
"eval_exact_match": 79.120151371807,
|
| 439 |
+
"eval_f1": 87.31859279800312,
|
| 440 |
+
"step": 18000
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 1.67,
|
| 444 |
+
"learning_rate": 1.9973805437629844e-05,
|
| 445 |
+
"loss": 1.0053,
|
| 446 |
+
"step": 18500
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 1.67,
|
| 450 |
+
"eval_exact_match": 79.29990539262063,
|
| 451 |
+
"eval_f1": 87.20927813197312,
|
| 452 |
+
"step": 18500
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 1.72,
|
| 456 |
+
"learning_rate": 1.9702827206214434e-05,
|
| 457 |
+
"loss": 0.9997,
|
| 458 |
+
"step": 19000
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.72,
|
| 462 |
+
"eval_exact_match": 79.0728476821192,
|
| 463 |
+
"eval_f1": 87.14281225266565,
|
| 464 |
+
"step": 19000
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 1.76,
|
| 468 |
+
"learning_rate": 1.9431848974799025e-05,
|
| 469 |
+
"loss": 0.9993,
|
| 470 |
+
"step": 19500
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 1.76,
|
| 474 |
+
"eval_exact_match": 78.77010406811732,
|
| 475 |
+
"eval_f1": 86.96515368656466,
|
| 476 |
+
"step": 19500
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 1.81,
|
| 480 |
+
"learning_rate": 1.9160870743383615e-05,
|
| 481 |
+
"loss": 0.9712,
|
| 482 |
+
"step": 20000
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 1.81,
|
| 486 |
+
"eval_exact_match": 78.86471144749291,
|
| 487 |
+
"eval_f1": 87.139815910334,
|
| 488 |
+
"step": 20000
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 1.85,
|
| 492 |
+
"learning_rate": 1.8889892511968206e-05,
|
| 493 |
+
"loss": 0.9586,
|
| 494 |
+
"step": 20500
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 1.85,
|
| 498 |
+
"eval_exact_match": 79.60264900662251,
|
| 499 |
+
"eval_f1": 87.67189897254278,
|
| 500 |
+
"step": 20500
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 1.9,
|
| 504 |
+
"learning_rate": 1.8618914280552793e-05,
|
| 505 |
+
"loss": 0.9855,
|
| 506 |
+
"step": 21000
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 1.9,
|
| 510 |
+
"eval_exact_match": 79.29044465468307,
|
| 511 |
+
"eval_f1": 87.35142110336871,
|
| 512 |
+
"step": 21000
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 1.94,
|
| 516 |
+
"learning_rate": 1.8347936049137387e-05,
|
| 517 |
+
"loss": 0.9577,
|
| 518 |
+
"step": 21500
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 1.94,
|
| 522 |
+
"eval_exact_match": 79.71617786187322,
|
| 523 |
+
"eval_f1": 87.58757029471191,
|
| 524 |
+
"step": 21500
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 1.99,
|
| 528 |
+
"learning_rate": 1.8076957817721978e-05,
|
| 529 |
+
"loss": 0.9764,
|
| 530 |
+
"step": 22000
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 1.99,
|
| 534 |
+
"eval_exact_match": 79.45127719962157,
|
| 535 |
+
"eval_f1": 87.47183032338337,
|
| 536 |
+
"step": 22000
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 2.03,
|
| 540 |
+
"learning_rate": 1.7805979586306565e-05,
|
| 541 |
+
"loss": 0.8665,
|
| 542 |
+
"step": 22500
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 2.03,
|
| 546 |
+
"eval_exact_match": 79.66887417218543,
|
| 547 |
+
"eval_f1": 87.64021806679038,
|
| 548 |
+
"step": 22500
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 2.08,
|
| 552 |
+
"learning_rate": 1.753500135489116e-05,
|
| 553 |
+
"loss": 0.8516,
|
| 554 |
+
"step": 23000
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 2.08,
|
| 558 |
+
"eval_exact_match": 79.66887417218543,
|
| 559 |
+
"eval_f1": 87.7551254398469,
|
| 560 |
+
"step": 23000
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 2.12,
|
| 564 |
+
"learning_rate": 1.726402312347575e-05,
|
| 565 |
+
"loss": 0.8475,
|
| 566 |
+
"step": 23500
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 2.12,
|
| 570 |
+
"eval_exact_match": 79.2336802270577,
|
| 571 |
+
"eval_f1": 87.42734800717938,
|
| 572 |
+
"step": 23500
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 2.17,
|
| 576 |
+
"learning_rate": 1.699304489206034e-05,
|
| 577 |
+
"loss": 0.8682,
|
| 578 |
+
"step": 24000
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 2.17,
|
| 582 |
+
"eval_exact_match": 79.85808893093662,
|
| 583 |
+
"eval_f1": 87.76673576734072,
|
| 584 |
+
"step": 24000
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 2.21,
|
| 588 |
+
"learning_rate": 1.6722066660644927e-05,
|
| 589 |
+
"loss": 0.885,
|
| 590 |
+
"step": 24500
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 2.21,
|
| 594 |
+
"eval_exact_match": 79.52696310312204,
|
| 595 |
+
"eval_f1": 87.60864611417429,
|
| 596 |
+
"step": 24500
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 2.26,
|
| 600 |
+
"learning_rate": 1.645108842922952e-05,
|
| 601 |
+
"loss": 0.8821,
|
| 602 |
+
"step": 25000
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 2.26,
|
| 606 |
+
"eval_exact_match": 79.99053926206244,
|
| 607 |
+
"eval_f1": 87.83466920921494,
|
| 608 |
+
"step": 25000
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 2.3,
|
| 612 |
+
"learning_rate": 1.618011019781411e-05,
|
| 613 |
+
"loss": 0.8379,
|
| 614 |
+
"step": 25500
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 2.3,
|
| 618 |
+
"eval_exact_match": 79.68779564806054,
|
| 619 |
+
"eval_f1": 87.65155459405366,
|
| 620 |
+
"step": 25500
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 2.35,
|
| 624 |
+
"learning_rate": 1.59091319663987e-05,
|
| 625 |
+
"loss": 0.8406,
|
| 626 |
+
"step": 26000
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 2.35,
|
| 630 |
+
"eval_exact_match": 79.71617786187322,
|
| 631 |
+
"eval_f1": 87.80269063903106,
|
| 632 |
+
"step": 26000
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 2.39,
|
| 636 |
+
"learning_rate": 1.563815373498329e-05,
|
| 637 |
+
"loss": 0.8817,
|
| 638 |
+
"step": 26500
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 2.39,
|
| 642 |
+
"eval_exact_match": 79.76348155156103,
|
| 643 |
+
"eval_f1": 87.6863825089024,
|
| 644 |
+
"step": 26500
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 2.44,
|
| 648 |
+
"learning_rate": 1.5367175503567883e-05,
|
| 649 |
+
"loss": 0.8487,
|
| 650 |
+
"step": 27000
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 2.44,
|
| 654 |
+
"eval_exact_match": 79.87701040681173,
|
| 655 |
+
"eval_f1": 87.85589778459244,
|
| 656 |
+
"step": 27000
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 2.48,
|
| 660 |
+
"learning_rate": 1.509619727215247e-05,
|
| 661 |
+
"loss": 0.8474,
|
| 662 |
+
"step": 27500
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 2.48,
|
| 666 |
+
"eval_exact_match": 80.13245033112582,
|
| 667 |
+
"eval_f1": 87.88619033429767,
|
| 668 |
+
"step": 27500
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 2.53,
|
| 672 |
+
"learning_rate": 1.482521904073706e-05,
|
| 673 |
+
"loss": 0.844,
|
| 674 |
+
"step": 28000
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 2.53,
|
| 678 |
+
"eval_exact_match": 80.22705771050141,
|
| 679 |
+
"eval_f1": 87.94538843278356,
|
| 680 |
+
"step": 28000
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 2.57,
|
| 684 |
+
"learning_rate": 1.4554240809321651e-05,
|
| 685 |
+
"loss": 0.8165,
|
| 686 |
+
"step": 28500
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 2.57,
|
| 690 |
+
"eval_exact_match": 80.1135288552507,
|
| 691 |
+
"eval_f1": 87.94195235666041,
|
| 692 |
+
"step": 28500
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 2.62,
|
| 696 |
+
"learning_rate": 1.4283262577906243e-05,
|
| 697 |
+
"loss": 0.8857,
|
| 698 |
+
"step": 29000
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 2.62,
|
| 702 |
+
"eval_exact_match": 80.3027436140019,
|
| 703 |
+
"eval_f1": 88.06711014071337,
|
| 704 |
+
"step": 29000
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 2.66,
|
| 708 |
+
"learning_rate": 1.4012284346490832e-05,
|
| 709 |
+
"loss": 0.8881,
|
| 710 |
+
"step": 29500
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 2.66,
|
| 714 |
+
"eval_exact_match": 79.46073793755913,
|
| 715 |
+
"eval_f1": 87.63361243864426,
|
| 716 |
+
"step": 29500
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 2.71,
|
| 720 |
+
"learning_rate": 1.3741306115075423e-05,
|
| 721 |
+
"loss": 0.8478,
|
| 722 |
+
"step": 30000
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 2.71,
|
| 726 |
+
"eval_exact_match": 80.24597918637653,
|
| 727 |
+
"eval_f1": 88.16985739641302,
|
| 728 |
+
"step": 30000
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 2.75,
|
| 732 |
+
"learning_rate": 1.3470327883660013e-05,
|
| 733 |
+
"loss": 0.8322,
|
| 734 |
+
"step": 30500
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 2.75,
|
| 738 |
+
"eval_exact_match": 80.13245033112582,
|
| 739 |
+
"eval_f1": 87.86660396184342,
|
| 740 |
+
"step": 30500
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 2.8,
|
| 744 |
+
"learning_rate": 1.3199349652244604e-05,
|
| 745 |
+
"loss": 0.8407,
|
| 746 |
+
"step": 31000
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 2.8,
|
| 750 |
+
"eval_exact_match": 80.07568590350047,
|
| 751 |
+
"eval_f1": 87.92805047246172,
|
| 752 |
+
"step": 31000
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 2.85,
|
| 756 |
+
"learning_rate": 1.2928371420829193e-05,
|
| 757 |
+
"loss": 0.8427,
|
| 758 |
+
"step": 31500
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 2.85,
|
| 762 |
+
"eval_exact_match": 80.17975402081362,
|
| 763 |
+
"eval_f1": 88.0783939864499,
|
| 764 |
+
"step": 31500
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 2.89,
|
| 768 |
+
"learning_rate": 1.2657393189413785e-05,
|
| 769 |
+
"loss": 0.8334,
|
| 770 |
+
"step": 32000
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 2.89,
|
| 774 |
+
"eval_exact_match": 80.19867549668874,
|
| 775 |
+
"eval_f1": 88.06310378279342,
|
| 776 |
+
"step": 32000
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 2.94,
|
| 780 |
+
"learning_rate": 1.2386414957998374e-05,
|
| 781 |
+
"loss": 0.8234,
|
| 782 |
+
"step": 32500
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 2.94,
|
| 786 |
+
"eval_exact_match": 80.22705771050141,
|
| 787 |
+
"eval_f1": 88.08144574072385,
|
| 788 |
+
"step": 32500
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 2.98,
|
| 792 |
+
"learning_rate": 1.2115436726582964e-05,
|
| 793 |
+
"loss": 0.8344,
|
| 794 |
+
"step": 33000
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 2.98,
|
| 798 |
+
"eval_exact_match": 80.66225165562913,
|
| 799 |
+
"eval_f1": 88.25754342761562,
|
| 800 |
+
"step": 33000
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 3.03,
|
| 804 |
+
"learning_rate": 1.1844458495167555e-05,
|
| 805 |
+
"loss": 0.7908,
|
| 806 |
+
"step": 33500
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 3.03,
|
| 810 |
+
"eval_exact_match": 80.3027436140019,
|
| 811 |
+
"eval_f1": 88.2107177195419,
|
| 812 |
+
"step": 33500
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 3.07,
|
| 816 |
+
"learning_rate": 1.1573480263752145e-05,
|
| 817 |
+
"loss": 0.7268,
|
| 818 |
+
"step": 34000
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 3.07,
|
| 822 |
+
"eval_exact_match": 80.47303689687796,
|
| 823 |
+
"eval_f1": 88.33146167313825,
|
| 824 |
+
"step": 34000
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 3.12,
|
| 828 |
+
"learning_rate": 1.1302502032336736e-05,
|
| 829 |
+
"loss": 0.7416,
|
| 830 |
+
"step": 34500
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 3.12,
|
| 834 |
+
"eval_exact_match": 80.33112582781457,
|
| 835 |
+
"eval_f1": 88.20770283656012,
|
| 836 |
+
"step": 34500
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 3.16,
|
| 840 |
+
"learning_rate": 1.1031523800921326e-05,
|
| 841 |
+
"loss": 0.7289,
|
| 842 |
+
"step": 35000
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 3.16,
|
| 846 |
+
"eval_exact_match": 80.27436140018922,
|
| 847 |
+
"eval_f1": 88.08675881507963,
|
| 848 |
+
"step": 35000
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 3.21,
|
| 852 |
+
"learning_rate": 1.0760545569505917e-05,
|
| 853 |
+
"loss": 0.7338,
|
| 854 |
+
"step": 35500
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 3.21,
|
| 858 |
+
"eval_exact_match": 80.32166508987702,
|
| 859 |
+
"eval_f1": 88.24483276676646,
|
| 860 |
+
"step": 35500
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 3.25,
|
| 864 |
+
"learning_rate": 1.0489567338090507e-05,
|
| 865 |
+
"loss": 0.7992,
|
| 866 |
+
"step": 36000
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 3.25,
|
| 870 |
+
"eval_exact_match": 80.48249763481552,
|
| 871 |
+
"eval_f1": 88.24667332064766,
|
| 872 |
+
"step": 36000
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 3.3,
|
| 876 |
+
"learning_rate": 1.0218589106675098e-05,
|
| 877 |
+
"loss": 0.7497,
|
| 878 |
+
"step": 36500
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 3.3,
|
| 882 |
+
"eval_exact_match": 80.0,
|
| 883 |
+
"eval_f1": 87.95371777369881,
|
| 884 |
+
"step": 36500
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 3.34,
|
| 888 |
+
"learning_rate": 9.947610875259687e-06,
|
| 889 |
+
"loss": 0.7389,
|
| 890 |
+
"step": 37000
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 3.34,
|
| 894 |
+
"eval_exact_match": 80.45411542100284,
|
| 895 |
+
"eval_f1": 88.24729821889156,
|
| 896 |
+
"step": 37000
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 3.39,
|
| 900 |
+
"learning_rate": 9.676632643844279e-06,
|
| 901 |
+
"loss": 0.748,
|
| 902 |
+
"step": 37500
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 3.39,
|
| 906 |
+
"eval_exact_match": 80.49195837275307,
|
| 907 |
+
"eval_f1": 88.27202955999378,
|
| 908 |
+
"step": 37500
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 3.43,
|
| 912 |
+
"learning_rate": 9.405654412428868e-06,
|
| 913 |
+
"loss": 0.7528,
|
| 914 |
+
"step": 38000
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 3.43,
|
| 918 |
+
"eval_exact_match": 80.59602649006622,
|
| 919 |
+
"eval_f1": 88.27897205791908,
|
| 920 |
+
"step": 38000
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 3.48,
|
| 924 |
+
"learning_rate": 9.134676181013458e-06,
|
| 925 |
+
"loss": 0.7544,
|
| 926 |
+
"step": 38500
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 3.48,
|
| 930 |
+
"eval_exact_match": 80.71901608325449,
|
| 931 |
+
"eval_f1": 88.29085294791585,
|
| 932 |
+
"step": 38500
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 3.52,
|
| 936 |
+
"learning_rate": 8.863697949598049e-06,
|
| 937 |
+
"loss": 0.7185,
|
| 938 |
+
"step": 39000
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 3.52,
|
| 942 |
+
"eval_exact_match": 80.77578051087986,
|
| 943 |
+
"eval_f1": 88.45178084091113,
|
| 944 |
+
"step": 39000
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 3.57,
|
| 948 |
+
"learning_rate": 8.59271971818264e-06,
|
| 949 |
+
"loss": 0.711,
|
| 950 |
+
"step": 39500
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 3.57,
|
| 954 |
+
"eval_exact_match": 80.54872280037843,
|
| 955 |
+
"eval_f1": 88.23006827695103,
|
| 956 |
+
"step": 39500
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 3.61,
|
| 960 |
+
"learning_rate": 8.32174148676723e-06,
|
| 961 |
+
"loss": 0.7767,
|
| 962 |
+
"step": 40000
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 3.61,
|
| 966 |
+
"eval_exact_match": 80.51087984862819,
|
| 967 |
+
"eval_f1": 88.21518807166053,
|
| 968 |
+
"step": 40000
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 3.66,
|
| 972 |
+
"learning_rate": 8.05076325535182e-06,
|
| 973 |
+
"loss": 0.7299,
|
| 974 |
+
"step": 40500
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 3.66,
|
| 978 |
+
"eval_exact_match": 80.42573320719016,
|
| 979 |
+
"eval_f1": 88.14657248237756,
|
| 980 |
+
"step": 40500
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 3.7,
|
| 984 |
+
"learning_rate": 7.779785023936411e-06,
|
| 985 |
+
"loss": 0.7443,
|
| 986 |
+
"step": 41000
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 3.7,
|
| 990 |
+
"eval_exact_match": 80.45411542100284,
|
| 991 |
+
"eval_f1": 88.25882487493044,
|
| 992 |
+
"step": 41000
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 3.75,
|
| 996 |
+
"learning_rate": 7.508806792521e-06,
|
| 997 |
+
"loss": 0.7672,
|
| 998 |
+
"step": 41500
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 3.75,
|
| 1002 |
+
"eval_exact_match": 80.79470198675497,
|
| 1003 |
+
"eval_f1": 88.35767687765708,
|
| 1004 |
+
"step": 41500
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 3.79,
|
| 1008 |
+
"learning_rate": 7.237828561105591e-06,
|
| 1009 |
+
"loss": 0.7466,
|
| 1010 |
+
"step": 42000
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 3.79,
|
| 1014 |
+
"eval_exact_match": 80.81362346263009,
|
| 1015 |
+
"eval_f1": 88.49878983679895,
|
| 1016 |
+
"step": 42000
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 3.84,
|
| 1020 |
+
"learning_rate": 6.966850329690182e-06,
|
| 1021 |
+
"loss": 0.7294,
|
| 1022 |
+
"step": 42500
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 3.84,
|
| 1026 |
+
"eval_exact_match": 80.66225165562913,
|
| 1027 |
+
"eval_f1": 88.4219719582272,
|
| 1028 |
+
"step": 42500
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 3.88,
|
| 1032 |
+
"learning_rate": 6.695872098274772e-06,
|
| 1033 |
+
"loss": 0.7554,
|
| 1034 |
+
"step": 43000
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 3.88,
|
| 1038 |
+
"eval_exact_match": 80.80416272469253,
|
| 1039 |
+
"eval_f1": 88.36066468276921,
|
| 1040 |
+
"step": 43000
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 3.93,
|
| 1044 |
+
"learning_rate": 6.424893866859363e-06,
|
| 1045 |
+
"loss": 0.761,
|
| 1046 |
+
"step": 43500
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 3.93,
|
| 1050 |
+
"eval_exact_match": 80.63386944181646,
|
| 1051 |
+
"eval_f1": 88.41315914502825,
|
| 1052 |
+
"step": 43500
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 3.97,
|
| 1056 |
+
"learning_rate": 6.1539156354439526e-06,
|
| 1057 |
+
"loss": 0.7363,
|
| 1058 |
+
"step": 44000
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 3.97,
|
| 1062 |
+
"eval_exact_match": 80.65279091769158,
|
| 1063 |
+
"eval_f1": 88.34571302471203,
|
| 1064 |
+
"step": 44000
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 4.02,
|
| 1068 |
+
"learning_rate": 5.882937404028543e-06,
|
| 1069 |
+
"loss": 0.7057,
|
| 1070 |
+
"step": 44500
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 4.02,
|
| 1074 |
+
"eval_exact_match": 80.91769157994324,
|
| 1075 |
+
"eval_f1": 88.47587754641178,
|
| 1076 |
+
"step": 44500
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 4.06,
|
| 1080 |
+
"learning_rate": 5.611959172613134e-06,
|
| 1081 |
+
"loss": 0.6499,
|
| 1082 |
+
"step": 45000
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 4.06,
|
| 1086 |
+
"eval_exact_match": 80.9271523178808,
|
| 1087 |
+
"eval_f1": 88.48670524401668,
|
| 1088 |
+
"step": 45000
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 4.11,
|
| 1092 |
+
"learning_rate": 5.340980941197724e-06,
|
| 1093 |
+
"loss": 0.6538,
|
| 1094 |
+
"step": 45500
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 4.11,
|
| 1098 |
+
"eval_exact_match": 80.89877010406812,
|
| 1099 |
+
"eval_f1": 88.44196466728391,
|
| 1100 |
+
"step": 45500
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 4.15,
|
| 1104 |
+
"learning_rate": 5.070002709782314e-06,
|
| 1105 |
+
"loss": 0.6996,
|
| 1106 |
+
"step": 46000
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 4.15,
|
| 1110 |
+
"eval_exact_match": 80.98391674550615,
|
| 1111 |
+
"eval_f1": 88.49930789298939,
|
| 1112 |
+
"step": 46000
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 4.2,
|
| 1116 |
+
"learning_rate": 4.799024478366904e-06,
|
| 1117 |
+
"loss": 0.6394,
|
| 1118 |
+
"step": 46500
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 4.2,
|
| 1122 |
+
"eval_exact_match": 80.6244087038789,
|
| 1123 |
+
"eval_f1": 88.34556116700644,
|
| 1124 |
+
"step": 46500
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 4.25,
|
| 1128 |
+
"learning_rate": 4.528046246951495e-06,
|
| 1129 |
+
"loss": 0.6721,
|
| 1130 |
+
"step": 47000
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 4.25,
|
| 1134 |
+
"eval_exact_match": 80.83254493850521,
|
| 1135 |
+
"eval_f1": 88.44910098996408,
|
| 1136 |
+
"step": 47000
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 4.29,
|
| 1140 |
+
"learning_rate": 4.257068015536085e-06,
|
| 1141 |
+
"loss": 0.6854,
|
| 1142 |
+
"step": 47500
|
| 1143 |
+
},
|
| 1144 |
+
{
|
| 1145 |
+
"epoch": 4.29,
|
| 1146 |
+
"eval_exact_match": 80.86092715231788,
|
| 1147 |
+
"eval_f1": 88.53212448905681,
|
| 1148 |
+
"step": 47500
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 4.34,
|
| 1152 |
+
"learning_rate": 3.986089784120676e-06,
|
| 1153 |
+
"loss": 0.6761,
|
| 1154 |
+
"step": 48000
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 4.34,
|
| 1158 |
+
"eval_exact_match": 80.6717123935667,
|
| 1159 |
+
"eval_f1": 88.4448096587991,
|
| 1160 |
+
"step": 48000
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 4.38,
|
| 1164 |
+
"learning_rate": 3.715111552705266e-06,
|
| 1165 |
+
"loss": 0.6943,
|
| 1166 |
+
"step": 48500
|
| 1167 |
+
},
|
| 1168 |
+
{
|
| 1169 |
+
"epoch": 4.38,
|
| 1170 |
+
"eval_exact_match": 80.52980132450331,
|
| 1171 |
+
"eval_f1": 88.33280893923866,
|
| 1172 |
+
"step": 48500
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 4.43,
|
| 1176 |
+
"learning_rate": 3.444133321289856e-06,
|
| 1177 |
+
"loss": 0.6655,
|
| 1178 |
+
"step": 49000
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 4.43,
|
| 1182 |
+
"eval_exact_match": 80.93661305581836,
|
| 1183 |
+
"eval_f1": 88.56888817902892,
|
| 1184 |
+
"step": 49000
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 4.47,
|
| 1188 |
+
"learning_rate": 3.173155089874447e-06,
|
| 1189 |
+
"loss": 0.7029,
|
| 1190 |
+
"step": 49500
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"epoch": 4.47,
|
| 1194 |
+
"eval_exact_match": 80.84200567644277,
|
| 1195 |
+
"eval_f1": 88.51593698418615,
|
| 1196 |
+
"step": 49500
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 4.52,
|
| 1200 |
+
"learning_rate": 2.9021768584590373e-06,
|
| 1201 |
+
"loss": 0.6648,
|
| 1202 |
+
"step": 50000
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 4.52,
|
| 1206 |
+
"eval_exact_match": 80.83254493850521,
|
| 1207 |
+
"eval_f1": 88.61534249704374,
|
| 1208 |
+
"step": 50000
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 4.56,
|
| 1212 |
+
"learning_rate": 2.6311986270436274e-06,
|
| 1213 |
+
"loss": 0.6901,
|
| 1214 |
+
"step": 50500
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 4.56,
|
| 1218 |
+
"eval_exact_match": 80.94607379375591,
|
| 1219 |
+
"eval_f1": 88.66269781300855,
|
| 1220 |
+
"step": 50500
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 4.61,
|
| 1224 |
+
"learning_rate": 2.360220395628218e-06,
|
| 1225 |
+
"loss": 0.6784,
|
| 1226 |
+
"step": 51000
|
| 1227 |
+
},
|
| 1228 |
+
{
|
| 1229 |
+
"epoch": 4.61,
|
| 1230 |
+
"eval_exact_match": 80.879848628193,
|
| 1231 |
+
"eval_f1": 88.58225782143238,
|
| 1232 |
+
"step": 51000
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 4.65,
|
| 1236 |
+
"learning_rate": 2.089242164212808e-06,
|
| 1237 |
+
"loss": 0.6543,
|
| 1238 |
+
"step": 51500
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 4.65,
|
| 1242 |
+
"eval_exact_match": 80.99337748344371,
|
| 1243 |
+
"eval_f1": 88.67206922431193,
|
| 1244 |
+
"step": 51500
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 4.7,
|
| 1248 |
+
"learning_rate": 1.8182639327973986e-06,
|
| 1249 |
+
"loss": 0.6419,
|
| 1250 |
+
"step": 52000
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 4.7,
|
| 1254 |
+
"eval_exact_match": 80.97445600756859,
|
| 1255 |
+
"eval_f1": 88.6884615459273,
|
| 1256 |
+
"step": 52000
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 4.74,
|
| 1260 |
+
"learning_rate": 1.5472857013819889e-06,
|
| 1261 |
+
"loss": 0.6617,
|
| 1262 |
+
"step": 52500
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 4.74,
|
| 1266 |
+
"eval_exact_match": 80.85146641438033,
|
| 1267 |
+
"eval_f1": 88.58266438928703,
|
| 1268 |
+
"step": 52500
|
| 1269 |
+
},
|
| 1270 |
+
{
|
| 1271 |
+
"epoch": 4.79,
|
| 1272 |
+
"learning_rate": 1.2763074699665794e-06,
|
| 1273 |
+
"loss": 0.7022,
|
| 1274 |
+
"step": 53000
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 4.79,
|
| 1278 |
+
"eval_exact_match": 80.89877010406812,
|
| 1279 |
+
"eval_f1": 88.62217290793005,
|
| 1280 |
+
"step": 53000
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 4.83,
|
| 1284 |
+
"learning_rate": 1.0053292385511697e-06,
|
| 1285 |
+
"loss": 0.662,
|
| 1286 |
+
"step": 53500
|
| 1287 |
+
},
|
| 1288 |
+
{
|
| 1289 |
+
"epoch": 4.83,
|
| 1290 |
+
"eval_exact_match": 80.96499526963103,
|
| 1291 |
+
"eval_f1": 88.5709480325892,
|
| 1292 |
+
"step": 53500
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"epoch": 4.88,
|
| 1296 |
+
"learning_rate": 7.343510071357602e-07,
|
| 1297 |
+
"loss": 0.6708,
|
| 1298 |
+
"step": 54000
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 4.88,
|
| 1302 |
+
"eval_exact_match": 80.83254493850521,
|
| 1303 |
+
"eval_f1": 88.61340923000925,
|
| 1304 |
+
"step": 54000
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 4.92,
|
| 1308 |
+
"learning_rate": 4.6337277572035044e-07,
|
| 1309 |
+
"loss": 0.6504,
|
| 1310 |
+
"step": 54500
|
| 1311 |
+
},
|
| 1312 |
+
{
|
| 1313 |
+
"epoch": 4.92,
|
| 1314 |
+
"eval_exact_match": 81.01229895931883,
|
| 1315 |
+
"eval_f1": 88.68117331158336,
|
| 1316 |
+
"step": 54500
|
| 1317 |
+
},
|
| 1318 |
+
{
|
| 1319 |
+
"epoch": 4.97,
|
| 1320 |
+
"learning_rate": 1.9239454430494084e-07,
|
| 1321 |
+
"loss": 0.6681,
|
| 1322 |
+
"step": 55000
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 4.97,
|
| 1326 |
+
"eval_exact_match": 81.03122043519394,
|
| 1327 |
+
"eval_f1": 88.70164904870342,
|
| 1328 |
+
"step": 55000
|
| 1329 |
+
}
|
| 1330 |
+
],
|
| 1331 |
+
"max_steps": 55355,
|
| 1332 |
+
"num_train_epochs": 5,
|
| 1333 |
+
"total_flos": 1.079484291072e+16,
|
| 1334 |
+
"trial_name": null,
|
| 1335 |
+
"trial_params": null
|
| 1336 |
+
}
|