beingbatman
commited on
Commit
•
08f2ba5
1
Parent(s):
6141272
End of training
Browse files- all_results.json +8 -0
- test_results.json +8 -0
- trainer_state.json +1869 -0
all_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 48.02,
|
3 |
+
"eval_accuracy": 0.6507936507936508,
|
4 |
+
"eval_loss": 1.1547214984893799,
|
5 |
+
"eval_runtime": 7.9277,
|
6 |
+
"eval_samples_per_second": 7.947,
|
7 |
+
"eval_steps_per_second": 1.388
|
8 |
+
}
|
test_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 48.02,
|
3 |
+
"eval_accuracy": 0.6507936507936508,
|
4 |
+
"eval_loss": 1.1547214984893799,
|
5 |
+
"eval_runtime": 7.9277,
|
6 |
+
"eval_samples_per_second": 7.947,
|
7 |
+
"eval_steps_per_second": 1.388
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,1869 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.6666666666666666,
|
3 |
+
"best_model_checkpoint": "videomae-base-short-ssv2-finetuned-ct_cpc/checkpoint-47",
|
4 |
+
"epoch": 48.01913043478261,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 2300,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0,
|
13 |
+
"learning_rate": 4.347826086956522e-07,
|
14 |
+
"loss": 2.0243,
|
15 |
+
"step": 10
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.01,
|
19 |
+
"learning_rate": 8.695652173913044e-07,
|
20 |
+
"loss": 1.8063,
|
21 |
+
"step": 20
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.01,
|
25 |
+
"learning_rate": 1.3043478260869566e-06,
|
26 |
+
"loss": 1.6927,
|
27 |
+
"step": 30
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.02,
|
31 |
+
"learning_rate": 1.7391304347826088e-06,
|
32 |
+
"loss": 1.4832,
|
33 |
+
"step": 40
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.02,
|
37 |
+
"eval_accuracy": 0.6666666666666666,
|
38 |
+
"eval_loss": 1.1202621459960938,
|
39 |
+
"eval_runtime": 7.2119,
|
40 |
+
"eval_samples_per_second": 8.32,
|
41 |
+
"eval_steps_per_second": 1.387,
|
42 |
+
"step": 47
|
43 |
+
},
|
44 |
+
{
|
45 |
+
"epoch": 1.0,
|
46 |
+
"learning_rate": 2.173913043478261e-06,
|
47 |
+
"loss": 1.3436,
|
48 |
+
"step": 50
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 1.01,
|
52 |
+
"learning_rate": 2.6086956521739132e-06,
|
53 |
+
"loss": 1.2714,
|
54 |
+
"step": 60
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 1.01,
|
58 |
+
"learning_rate": 3.043478260869566e-06,
|
59 |
+
"loss": 1.1191,
|
60 |
+
"step": 70
|
61 |
+
},
|
62 |
+
{
|
63 |
+
"epoch": 1.01,
|
64 |
+
"learning_rate": 3.4782608695652175e-06,
|
65 |
+
"loss": 0.9807,
|
66 |
+
"step": 80
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 1.02,
|
70 |
+
"learning_rate": 3.91304347826087e-06,
|
71 |
+
"loss": 1.32,
|
72 |
+
"step": 90
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 1.02,
|
76 |
+
"eval_accuracy": 0.6666666666666666,
|
77 |
+
"eval_loss": 1.050528645515442,
|
78 |
+
"eval_runtime": 6.9232,
|
79 |
+
"eval_samples_per_second": 8.667,
|
80 |
+
"eval_steps_per_second": 1.444,
|
81 |
+
"step": 94
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 2.0,
|
85 |
+
"learning_rate": 4.347826086956522e-06,
|
86 |
+
"loss": 1.0838,
|
87 |
+
"step": 100
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 2.01,
|
91 |
+
"learning_rate": 4.782608695652174e-06,
|
92 |
+
"loss": 1.1624,
|
93 |
+
"step": 110
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 2.01,
|
97 |
+
"learning_rate": 5.2173913043478265e-06,
|
98 |
+
"loss": 0.9414,
|
99 |
+
"step": 120
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 2.02,
|
103 |
+
"learning_rate": 5.652173913043479e-06,
|
104 |
+
"loss": 1.2583,
|
105 |
+
"step": 130
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 2.02,
|
109 |
+
"learning_rate": 6.086956521739132e-06,
|
110 |
+
"loss": 1.1539,
|
111 |
+
"step": 140
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 2.02,
|
115 |
+
"eval_accuracy": 0.6666666666666666,
|
116 |
+
"eval_loss": 1.0524587631225586,
|
117 |
+
"eval_runtime": 7.8366,
|
118 |
+
"eval_samples_per_second": 7.656,
|
119 |
+
"eval_steps_per_second": 1.276,
|
120 |
+
"step": 141
|
121 |
+
},
|
122 |
+
{
|
123 |
+
"epoch": 3.0,
|
124 |
+
"learning_rate": 6.521739130434783e-06,
|
125 |
+
"loss": 1.0695,
|
126 |
+
"step": 150
|
127 |
+
},
|
128 |
+
{
|
129 |
+
"epoch": 3.01,
|
130 |
+
"learning_rate": 6.956521739130435e-06,
|
131 |
+
"loss": 0.9282,
|
132 |
+
"step": 160
|
133 |
+
},
|
134 |
+
{
|
135 |
+
"epoch": 3.01,
|
136 |
+
"learning_rate": 7.391304347826087e-06,
|
137 |
+
"loss": 0.9621,
|
138 |
+
"step": 170
|
139 |
+
},
|
140 |
+
{
|
141 |
+
"epoch": 3.02,
|
142 |
+
"learning_rate": 7.82608695652174e-06,
|
143 |
+
"loss": 1.2399,
|
144 |
+
"step": 180
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 3.02,
|
148 |
+
"eval_accuracy": 0.6666666666666666,
|
149 |
+
"eval_loss": 1.0353821516036987,
|
150 |
+
"eval_runtime": 7.1279,
|
151 |
+
"eval_samples_per_second": 8.418,
|
152 |
+
"eval_steps_per_second": 1.403,
|
153 |
+
"step": 188
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 4.0,
|
157 |
+
"learning_rate": 8.260869565217392e-06,
|
158 |
+
"loss": 1.1451,
|
159 |
+
"step": 190
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 4.01,
|
163 |
+
"learning_rate": 8.695652173913044e-06,
|
164 |
+
"loss": 1.1118,
|
165 |
+
"step": 200
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 4.01,
|
169 |
+
"learning_rate": 9.130434782608697e-06,
|
170 |
+
"loss": 1.1014,
|
171 |
+
"step": 210
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 4.01,
|
175 |
+
"learning_rate": 9.565217391304349e-06,
|
176 |
+
"loss": 1.1536,
|
177 |
+
"step": 220
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 4.02,
|
181 |
+
"learning_rate": 1e-05,
|
182 |
+
"loss": 0.9928,
|
183 |
+
"step": 230
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 4.02,
|
187 |
+
"eval_accuracy": 0.6666666666666666,
|
188 |
+
"eval_loss": 1.0516277551651,
|
189 |
+
"eval_runtime": 6.8144,
|
190 |
+
"eval_samples_per_second": 8.805,
|
191 |
+
"eval_steps_per_second": 1.467,
|
192 |
+
"step": 235
|
193 |
+
},
|
194 |
+
{
|
195 |
+
"epoch": 5.0,
|
196 |
+
"learning_rate": 9.95169082125604e-06,
|
197 |
+
"loss": 1.1887,
|
198 |
+
"step": 240
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 5.01,
|
202 |
+
"learning_rate": 9.903381642512077e-06,
|
203 |
+
"loss": 1.176,
|
204 |
+
"step": 250
|
205 |
+
},
|
206 |
+
{
|
207 |
+
"epoch": 5.01,
|
208 |
+
"learning_rate": 9.855072463768118e-06,
|
209 |
+
"loss": 1.0889,
|
210 |
+
"step": 260
|
211 |
+
},
|
212 |
+
{
|
213 |
+
"epoch": 5.02,
|
214 |
+
"learning_rate": 9.806763285024155e-06,
|
215 |
+
"loss": 0.8653,
|
216 |
+
"step": 270
|
217 |
+
},
|
218 |
+
{
|
219 |
+
"epoch": 5.02,
|
220 |
+
"learning_rate": 9.758454106280194e-06,
|
221 |
+
"loss": 1.0054,
|
222 |
+
"step": 280
|
223 |
+
},
|
224 |
+
{
|
225 |
+
"epoch": 5.02,
|
226 |
+
"eval_accuracy": 0.6666666666666666,
|
227 |
+
"eval_loss": 1.0296636819839478,
|
228 |
+
"eval_runtime": 6.8135,
|
229 |
+
"eval_samples_per_second": 8.806,
|
230 |
+
"eval_steps_per_second": 1.468,
|
231 |
+
"step": 282
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"epoch": 6.0,
|
235 |
+
"learning_rate": 9.710144927536233e-06,
|
236 |
+
"loss": 1.1702,
|
237 |
+
"step": 290
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 6.01,
|
241 |
+
"learning_rate": 9.66183574879227e-06,
|
242 |
+
"loss": 1.0608,
|
243 |
+
"step": 300
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 6.01,
|
247 |
+
"learning_rate": 9.61352657004831e-06,
|
248 |
+
"loss": 1.0026,
|
249 |
+
"step": 310
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 6.02,
|
253 |
+
"learning_rate": 9.565217391304349e-06,
|
254 |
+
"loss": 1.1166,
|
255 |
+
"step": 320
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 6.02,
|
259 |
+
"eval_accuracy": 0.6666666666666666,
|
260 |
+
"eval_loss": 1.024717092514038,
|
261 |
+
"eval_runtime": 6.7961,
|
262 |
+
"eval_samples_per_second": 8.829,
|
263 |
+
"eval_steps_per_second": 1.471,
|
264 |
+
"step": 329
|
265 |
+
},
|
266 |
+
{
|
267 |
+
"epoch": 7.0,
|
268 |
+
"learning_rate": 9.516908212560388e-06,
|
269 |
+
"loss": 1.0851,
|
270 |
+
"step": 330
|
271 |
+
},
|
272 |
+
{
|
273 |
+
"epoch": 7.0,
|
274 |
+
"learning_rate": 9.468599033816425e-06,
|
275 |
+
"loss": 0.9748,
|
276 |
+
"step": 340
|
277 |
+
},
|
278 |
+
{
|
279 |
+
"epoch": 7.01,
|
280 |
+
"learning_rate": 9.420289855072464e-06,
|
281 |
+
"loss": 1.0743,
|
282 |
+
"step": 350
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 7.01,
|
286 |
+
"learning_rate": 9.371980676328503e-06,
|
287 |
+
"loss": 0.9153,
|
288 |
+
"step": 360
|
289 |
+
},
|
290 |
+
{
|
291 |
+
"epoch": 7.02,
|
292 |
+
"learning_rate": 9.323671497584542e-06,
|
293 |
+
"loss": 1.2715,
|
294 |
+
"step": 370
|
295 |
+
},
|
296 |
+
{
|
297 |
+
"epoch": 7.02,
|
298 |
+
"eval_accuracy": 0.6666666666666666,
|
299 |
+
"eval_loss": 1.0097945928573608,
|
300 |
+
"eval_runtime": 6.7899,
|
301 |
+
"eval_samples_per_second": 8.837,
|
302 |
+
"eval_steps_per_second": 1.473,
|
303 |
+
"step": 376
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 8.0,
|
307 |
+
"learning_rate": 9.275362318840581e-06,
|
308 |
+
"loss": 0.9517,
|
309 |
+
"step": 380
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 8.01,
|
313 |
+
"learning_rate": 9.227053140096618e-06,
|
314 |
+
"loss": 0.8985,
|
315 |
+
"step": 390
|
316 |
+
},
|
317 |
+
{
|
318 |
+
"epoch": 8.01,
|
319 |
+
"learning_rate": 9.178743961352658e-06,
|
320 |
+
"loss": 1.1341,
|
321 |
+
"step": 400
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 8.01,
|
325 |
+
"learning_rate": 9.130434782608697e-06,
|
326 |
+
"loss": 1.0505,
|
327 |
+
"step": 410
|
328 |
+
},
|
329 |
+
{
|
330 |
+
"epoch": 8.02,
|
331 |
+
"learning_rate": 9.082125603864736e-06,
|
332 |
+
"loss": 1.0317,
|
333 |
+
"step": 420
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"epoch": 8.02,
|
337 |
+
"eval_accuracy": 0.6666666666666666,
|
338 |
+
"eval_loss": 1.040429949760437,
|
339 |
+
"eval_runtime": 6.9971,
|
340 |
+
"eval_samples_per_second": 8.575,
|
341 |
+
"eval_steps_per_second": 1.429,
|
342 |
+
"step": 423
|
343 |
+
},
|
344 |
+
{
|
345 |
+
"epoch": 9.0,
|
346 |
+
"learning_rate": 9.033816425120775e-06,
|
347 |
+
"loss": 1.1947,
|
348 |
+
"step": 430
|
349 |
+
},
|
350 |
+
{
|
351 |
+
"epoch": 9.01,
|
352 |
+
"learning_rate": 8.985507246376812e-06,
|
353 |
+
"loss": 0.9361,
|
354 |
+
"step": 440
|
355 |
+
},
|
356 |
+
{
|
357 |
+
"epoch": 9.01,
|
358 |
+
"learning_rate": 8.937198067632851e-06,
|
359 |
+
"loss": 0.9432,
|
360 |
+
"step": 450
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"epoch": 9.02,
|
364 |
+
"learning_rate": 8.888888888888888e-06,
|
365 |
+
"loss": 1.0958,
|
366 |
+
"step": 460
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 9.02,
|
370 |
+
"learning_rate": 8.840579710144929e-06,
|
371 |
+
"loss": 1.1258,
|
372 |
+
"step": 470
|
373 |
+
},
|
374 |
+
{
|
375 |
+
"epoch": 9.02,
|
376 |
+
"eval_accuracy": 0.6666666666666666,
|
377 |
+
"eval_loss": 1.0053784847259521,
|
378 |
+
"eval_runtime": 7.1441,
|
379 |
+
"eval_samples_per_second": 8.399,
|
380 |
+
"eval_steps_per_second": 1.4,
|
381 |
+
"step": 470
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 10.0,
|
385 |
+
"learning_rate": 8.792270531400966e-06,
|
386 |
+
"loss": 1.0206,
|
387 |
+
"step": 480
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 10.01,
|
391 |
+
"learning_rate": 8.743961352657005e-06,
|
392 |
+
"loss": 1.0568,
|
393 |
+
"step": 490
|
394 |
+
},
|
395 |
+
{
|
396 |
+
"epoch": 10.01,
|
397 |
+
"learning_rate": 8.695652173913044e-06,
|
398 |
+
"loss": 1.1054,
|
399 |
+
"step": 500
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 10.02,
|
403 |
+
"learning_rate": 8.647342995169082e-06,
|
404 |
+
"loss": 0.8991,
|
405 |
+
"step": 510
|
406 |
+
},
|
407 |
+
{
|
408 |
+
"epoch": 10.02,
|
409 |
+
"eval_accuracy": 0.6666666666666666,
|
410 |
+
"eval_loss": 1.0477041006088257,
|
411 |
+
"eval_runtime": 7.2799,
|
412 |
+
"eval_samples_per_second": 8.242,
|
413 |
+
"eval_steps_per_second": 1.374,
|
414 |
+
"step": 517
|
415 |
+
},
|
416 |
+
{
|
417 |
+
"epoch": 11.0,
|
418 |
+
"learning_rate": 8.599033816425122e-06,
|
419 |
+
"loss": 1.167,
|
420 |
+
"step": 520
|
421 |
+
},
|
422 |
+
{
|
423 |
+
"epoch": 11.01,
|
424 |
+
"learning_rate": 8.55072463768116e-06,
|
425 |
+
"loss": 0.9754,
|
426 |
+
"step": 530
|
427 |
+
},
|
428 |
+
{
|
429 |
+
"epoch": 11.01,
|
430 |
+
"learning_rate": 8.502415458937199e-06,
|
431 |
+
"loss": 1.0365,
|
432 |
+
"step": 540
|
433 |
+
},
|
434 |
+
{
|
435 |
+
"epoch": 11.01,
|
436 |
+
"learning_rate": 8.454106280193238e-06,
|
437 |
+
"loss": 0.9409,
|
438 |
+
"step": 550
|
439 |
+
},
|
440 |
+
{
|
441 |
+
"epoch": 11.02,
|
442 |
+
"learning_rate": 8.405797101449275e-06,
|
443 |
+
"loss": 0.8957,
|
444 |
+
"step": 560
|
445 |
+
},
|
446 |
+
{
|
447 |
+
"epoch": 11.02,
|
448 |
+
"eval_accuracy": 0.6666666666666666,
|
449 |
+
"eval_loss": 1.0607702732086182,
|
450 |
+
"eval_runtime": 6.9041,
|
451 |
+
"eval_samples_per_second": 8.69,
|
452 |
+
"eval_steps_per_second": 1.448,
|
453 |
+
"step": 564
|
454 |
+
},
|
455 |
+
{
|
456 |
+
"epoch": 12.0,
|
457 |
+
"learning_rate": 8.357487922705316e-06,
|
458 |
+
"loss": 0.8378,
|
459 |
+
"step": 570
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 12.01,
|
463 |
+
"learning_rate": 8.309178743961353e-06,
|
464 |
+
"loss": 0.8314,
|
465 |
+
"step": 580
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 12.01,
|
469 |
+
"learning_rate": 8.260869565217392e-06,
|
470 |
+
"loss": 1.092,
|
471 |
+
"step": 590
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 12.02,
|
475 |
+
"learning_rate": 8.212560386473431e-06,
|
476 |
+
"loss": 1.0079,
|
477 |
+
"step": 600
|
478 |
+
},
|
479 |
+
{
|
480 |
+
"epoch": 12.02,
|
481 |
+
"learning_rate": 8.164251207729469e-06,
|
482 |
+
"loss": 1.078,
|
483 |
+
"step": 610
|
484 |
+
},
|
485 |
+
{
|
486 |
+
"epoch": 12.02,
|
487 |
+
"eval_accuracy": 0.6666666666666666,
|
488 |
+
"eval_loss": 1.0165636539459229,
|
489 |
+
"eval_runtime": 7.648,
|
490 |
+
"eval_samples_per_second": 7.845,
|
491 |
+
"eval_steps_per_second": 1.308,
|
492 |
+
"step": 611
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 13.0,
|
496 |
+
"learning_rate": 8.115942028985508e-06,
|
497 |
+
"loss": 0.8161,
|
498 |
+
"step": 620
|
499 |
+
},
|
500 |
+
{
|
501 |
+
"epoch": 13.01,
|
502 |
+
"learning_rate": 8.067632850241547e-06,
|
503 |
+
"loss": 1.2458,
|
504 |
+
"step": 630
|
505 |
+
},
|
506 |
+
{
|
507 |
+
"epoch": 13.01,
|
508 |
+
"learning_rate": 8.019323671497586e-06,
|
509 |
+
"loss": 0.9597,
|
510 |
+
"step": 640
|
511 |
+
},
|
512 |
+
{
|
513 |
+
"epoch": 13.02,
|
514 |
+
"learning_rate": 7.971014492753623e-06,
|
515 |
+
"loss": 0.9067,
|
516 |
+
"step": 650
|
517 |
+
},
|
518 |
+
{
|
519 |
+
"epoch": 13.02,
|
520 |
+
"eval_accuracy": 0.6666666666666666,
|
521 |
+
"eval_loss": 1.2110427618026733,
|
522 |
+
"eval_runtime": 7.2284,
|
523 |
+
"eval_samples_per_second": 8.301,
|
524 |
+
"eval_steps_per_second": 1.383,
|
525 |
+
"step": 658
|
526 |
+
},
|
527 |
+
{
|
528 |
+
"epoch": 14.0,
|
529 |
+
"learning_rate": 7.922705314009662e-06,
|
530 |
+
"loss": 0.9322,
|
531 |
+
"step": 660
|
532 |
+
},
|
533 |
+
{
|
534 |
+
"epoch": 14.01,
|
535 |
+
"learning_rate": 7.874396135265701e-06,
|
536 |
+
"loss": 0.993,
|
537 |
+
"step": 670
|
538 |
+
},
|
539 |
+
{
|
540 |
+
"epoch": 14.01,
|
541 |
+
"learning_rate": 7.82608695652174e-06,
|
542 |
+
"loss": 0.7774,
|
543 |
+
"step": 680
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 14.01,
|
547 |
+
"learning_rate": 7.77777777777778e-06,
|
548 |
+
"loss": 0.9399,
|
549 |
+
"step": 690
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 14.02,
|
553 |
+
"learning_rate": 7.729468599033817e-06,
|
554 |
+
"loss": 1.0383,
|
555 |
+
"step": 700
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 14.02,
|
559 |
+
"eval_accuracy": 0.6,
|
560 |
+
"eval_loss": 1.0380301475524902,
|
561 |
+
"eval_runtime": 6.9013,
|
562 |
+
"eval_samples_per_second": 8.694,
|
563 |
+
"eval_steps_per_second": 1.449,
|
564 |
+
"step": 705
|
565 |
+
},
|
566 |
+
{
|
567 |
+
"epoch": 15.0,
|
568 |
+
"learning_rate": 7.681159420289856e-06,
|
569 |
+
"loss": 0.7043,
|
570 |
+
"step": 710
|
571 |
+
},
|
572 |
+
{
|
573 |
+
"epoch": 15.01,
|
574 |
+
"learning_rate": 7.632850241545895e-06,
|
575 |
+
"loss": 1.0185,
|
576 |
+
"step": 720
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 15.01,
|
580 |
+
"learning_rate": 7.584541062801934e-06,
|
581 |
+
"loss": 0.9907,
|
582 |
+
"step": 730
|
583 |
+
},
|
584 |
+
{
|
585 |
+
"epoch": 15.02,
|
586 |
+
"learning_rate": 7.536231884057972e-06,
|
587 |
+
"loss": 0.8602,
|
588 |
+
"step": 740
|
589 |
+
},
|
590 |
+
{
|
591 |
+
"epoch": 15.02,
|
592 |
+
"learning_rate": 7.48792270531401e-06,
|
593 |
+
"loss": 1.2244,
|
594 |
+
"step": 750
|
595 |
+
},
|
596 |
+
{
|
597 |
+
"epoch": 15.02,
|
598 |
+
"eval_accuracy": 0.6666666666666666,
|
599 |
+
"eval_loss": 1.1040699481964111,
|
600 |
+
"eval_runtime": 7.4605,
|
601 |
+
"eval_samples_per_second": 8.042,
|
602 |
+
"eval_steps_per_second": 1.34,
|
603 |
+
"step": 752
|
604 |
+
},
|
605 |
+
{
|
606 |
+
"epoch": 16.0,
|
607 |
+
"learning_rate": 7.439613526570049e-06,
|
608 |
+
"loss": 0.9108,
|
609 |
+
"step": 760
|
610 |
+
},
|
611 |
+
{
|
612 |
+
"epoch": 16.01,
|
613 |
+
"learning_rate": 7.391304347826087e-06,
|
614 |
+
"loss": 0.8811,
|
615 |
+
"step": 770
|
616 |
+
},
|
617 |
+
{
|
618 |
+
"epoch": 16.01,
|
619 |
+
"learning_rate": 7.342995169082127e-06,
|
620 |
+
"loss": 0.8487,
|
621 |
+
"step": 780
|
622 |
+
},
|
623 |
+
{
|
624 |
+
"epoch": 16.02,
|
625 |
+
"learning_rate": 7.294685990338165e-06,
|
626 |
+
"loss": 1.0364,
|
627 |
+
"step": 790
|
628 |
+
},
|
629 |
+
{
|
630 |
+
"epoch": 16.02,
|
631 |
+
"eval_accuracy": 0.6,
|
632 |
+
"eval_loss": 1.0123381614685059,
|
633 |
+
"eval_runtime": 6.8033,
|
634 |
+
"eval_samples_per_second": 8.819,
|
635 |
+
"eval_steps_per_second": 1.47,
|
636 |
+
"step": 799
|
637 |
+
},
|
638 |
+
{
|
639 |
+
"epoch": 17.0,
|
640 |
+
"learning_rate": 7.246376811594203e-06,
|
641 |
+
"loss": 0.8189,
|
642 |
+
"step": 800
|
643 |
+
},
|
644 |
+
{
|
645 |
+
"epoch": 17.0,
|
646 |
+
"learning_rate": 7.1980676328502416e-06,
|
647 |
+
"loss": 0.8733,
|
648 |
+
"step": 810
|
649 |
+
},
|
650 |
+
{
|
651 |
+
"epoch": 17.01,
|
652 |
+
"learning_rate": 7.149758454106281e-06,
|
653 |
+
"loss": 0.6958,
|
654 |
+
"step": 820
|
655 |
+
},
|
656 |
+
{
|
657 |
+
"epoch": 17.01,
|
658 |
+
"learning_rate": 7.10144927536232e-06,
|
659 |
+
"loss": 0.782,
|
660 |
+
"step": 830
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 17.02,
|
664 |
+
"learning_rate": 7.053140096618359e-06,
|
665 |
+
"loss": 0.9662,
|
666 |
+
"step": 840
|
667 |
+
},
|
668 |
+
{
|
669 |
+
"epoch": 17.02,
|
670 |
+
"eval_accuracy": 0.6333333333333333,
|
671 |
+
"eval_loss": 1.1802695989608765,
|
672 |
+
"eval_runtime": 7.2583,
|
673 |
+
"eval_samples_per_second": 8.266,
|
674 |
+
"eval_steps_per_second": 1.378,
|
675 |
+
"step": 846
|
676 |
+
},
|
677 |
+
{
|
678 |
+
"epoch": 18.0,
|
679 |
+
"learning_rate": 7.004830917874397e-06,
|
680 |
+
"loss": 0.9205,
|
681 |
+
"step": 850
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 18.01,
|
685 |
+
"learning_rate": 6.956521739130435e-06,
|
686 |
+
"loss": 0.8999,
|
687 |
+
"step": 860
|
688 |
+
},
|
689 |
+
{
|
690 |
+
"epoch": 18.01,
|
691 |
+
"learning_rate": 6.908212560386473e-06,
|
692 |
+
"loss": 0.6096,
|
693 |
+
"step": 870
|
694 |
+
},
|
695 |
+
{
|
696 |
+
"epoch": 18.01,
|
697 |
+
"learning_rate": 6.859903381642513e-06,
|
698 |
+
"loss": 0.79,
|
699 |
+
"step": 880
|
700 |
+
},
|
701 |
+
{
|
702 |
+
"epoch": 18.02,
|
703 |
+
"learning_rate": 6.811594202898551e-06,
|
704 |
+
"loss": 0.9299,
|
705 |
+
"step": 890
|
706 |
+
},
|
707 |
+
{
|
708 |
+
"epoch": 18.02,
|
709 |
+
"eval_accuracy": 0.6333333333333333,
|
710 |
+
"eval_loss": 1.0910345315933228,
|
711 |
+
"eval_runtime": 6.9398,
|
712 |
+
"eval_samples_per_second": 8.646,
|
713 |
+
"eval_steps_per_second": 1.441,
|
714 |
+
"step": 893
|
715 |
+
},
|
716 |
+
{
|
717 |
+
"epoch": 19.0,
|
718 |
+
"learning_rate": 6.76328502415459e-06,
|
719 |
+
"loss": 0.8715,
|
720 |
+
"step": 900
|
721 |
+
},
|
722 |
+
{
|
723 |
+
"epoch": 19.01,
|
724 |
+
"learning_rate": 6.7149758454106285e-06,
|
725 |
+
"loss": 0.8882,
|
726 |
+
"step": 910
|
727 |
+
},
|
728 |
+
{
|
729 |
+
"epoch": 19.01,
|
730 |
+
"learning_rate": 6.666666666666667e-06,
|
731 |
+
"loss": 0.8562,
|
732 |
+
"step": 920
|
733 |
+
},
|
734 |
+
{
|
735 |
+
"epoch": 19.02,
|
736 |
+
"learning_rate": 6.6183574879227065e-06,
|
737 |
+
"loss": 0.9704,
|
738 |
+
"step": 930
|
739 |
+
},
|
740 |
+
{
|
741 |
+
"epoch": 19.02,
|
742 |
+
"learning_rate": 6.570048309178745e-06,
|
743 |
+
"loss": 0.877,
|
744 |
+
"step": 940
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 19.02,
|
748 |
+
"eval_accuracy": 0.65,
|
749 |
+
"eval_loss": 1.0182613134384155,
|
750 |
+
"eval_runtime": 7.0493,
|
751 |
+
"eval_samples_per_second": 8.511,
|
752 |
+
"eval_steps_per_second": 1.419,
|
753 |
+
"step": 940
|
754 |
+
},
|
755 |
+
{
|
756 |
+
"epoch": 20.0,
|
757 |
+
"learning_rate": 6.521739130434783e-06,
|
758 |
+
"loss": 0.8358,
|
759 |
+
"step": 950
|
760 |
+
},
|
761 |
+
{
|
762 |
+
"epoch": 20.01,
|
763 |
+
"learning_rate": 6.473429951690822e-06,
|
764 |
+
"loss": 0.7785,
|
765 |
+
"step": 960
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 20.01,
|
769 |
+
"learning_rate": 6.42512077294686e-06,
|
770 |
+
"loss": 0.7644,
|
771 |
+
"step": 970
|
772 |
+
},
|
773 |
+
{
|
774 |
+
"epoch": 20.02,
|
775 |
+
"learning_rate": 6.376811594202898e-06,
|
776 |
+
"loss": 0.8649,
|
777 |
+
"step": 980
|
778 |
+
},
|
779 |
+
{
|
780 |
+
"epoch": 20.02,
|
781 |
+
"eval_accuracy": 0.6166666666666667,
|
782 |
+
"eval_loss": 1.1414852142333984,
|
783 |
+
"eval_runtime": 7.0701,
|
784 |
+
"eval_samples_per_second": 8.486,
|
785 |
+
"eval_steps_per_second": 1.414,
|
786 |
+
"step": 987
|
787 |
+
},
|
788 |
+
{
|
789 |
+
"epoch": 21.0,
|
790 |
+
"learning_rate": 6.328502415458938e-06,
|
791 |
+
"loss": 0.8795,
|
792 |
+
"step": 990
|
793 |
+
},
|
794 |
+
{
|
795 |
+
"epoch": 21.01,
|
796 |
+
"learning_rate": 6.280193236714976e-06,
|
797 |
+
"loss": 0.7464,
|
798 |
+
"step": 1000
|
799 |
+
},
|
800 |
+
{
|
801 |
+
"epoch": 21.01,
|
802 |
+
"learning_rate": 6.2318840579710145e-06,
|
803 |
+
"loss": 0.7973,
|
804 |
+
"step": 1010
|
805 |
+
},
|
806 |
+
{
|
807 |
+
"epoch": 21.01,
|
808 |
+
"learning_rate": 6.1835748792270535e-06,
|
809 |
+
"loss": 0.9681,
|
810 |
+
"step": 1020
|
811 |
+
},
|
812 |
+
{
|
813 |
+
"epoch": 21.02,
|
814 |
+
"learning_rate": 6.135265700483092e-06,
|
815 |
+
"loss": 0.8841,
|
816 |
+
"step": 1030
|
817 |
+
},
|
818 |
+
{
|
819 |
+
"epoch": 21.02,
|
820 |
+
"eval_accuracy": 0.6333333333333333,
|
821 |
+
"eval_loss": 1.0975487232208252,
|
822 |
+
"eval_runtime": 7.726,
|
823 |
+
"eval_samples_per_second": 7.766,
|
824 |
+
"eval_steps_per_second": 1.294,
|
825 |
+
"step": 1034
|
826 |
+
},
|
827 |
+
{
|
828 |
+
"epoch": 22.0,
|
829 |
+
"learning_rate": 6.086956521739132e-06,
|
830 |
+
"loss": 0.6596,
|
831 |
+
"step": 1040
|
832 |
+
},
|
833 |
+
{
|
834 |
+
"epoch": 22.01,
|
835 |
+
"learning_rate": 6.03864734299517e-06,
|
836 |
+
"loss": 0.7252,
|
837 |
+
"step": 1050
|
838 |
+
},
|
839 |
+
{
|
840 |
+
"epoch": 22.01,
|
841 |
+
"learning_rate": 5.990338164251208e-06,
|
842 |
+
"loss": 0.7564,
|
843 |
+
"step": 1060
|
844 |
+
},
|
845 |
+
{
|
846 |
+
"epoch": 22.02,
|
847 |
+
"learning_rate": 5.942028985507247e-06,
|
848 |
+
"loss": 0.7406,
|
849 |
+
"step": 1070
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 22.02,
|
853 |
+
"learning_rate": 5.893719806763285e-06,
|
854 |
+
"loss": 0.6276,
|
855 |
+
"step": 1080
|
856 |
+
},
|
857 |
+
{
|
858 |
+
"epoch": 22.02,
|
859 |
+
"eval_accuracy": 0.6,
|
860 |
+
"eval_loss": 1.072813868522644,
|
861 |
+
"eval_runtime": 7.252,
|
862 |
+
"eval_samples_per_second": 8.274,
|
863 |
+
"eval_steps_per_second": 1.379,
|
864 |
+
"step": 1081
|
865 |
+
},
|
866 |
+
{
|
867 |
+
"epoch": 23.0,
|
868 |
+
"learning_rate": 5.845410628019324e-06,
|
869 |
+
"loss": 0.7456,
|
870 |
+
"step": 1090
|
871 |
+
},
|
872 |
+
{
|
873 |
+
"epoch": 23.01,
|
874 |
+
"learning_rate": 5.797101449275363e-06,
|
875 |
+
"loss": 0.5497,
|
876 |
+
"step": 1100
|
877 |
+
},
|
878 |
+
{
|
879 |
+
"epoch": 23.01,
|
880 |
+
"learning_rate": 5.748792270531401e-06,
|
881 |
+
"loss": 0.875,
|
882 |
+
"step": 1110
|
883 |
+
},
|
884 |
+
{
|
885 |
+
"epoch": 23.02,
|
886 |
+
"learning_rate": 5.70048309178744e-06,
|
887 |
+
"loss": 0.7974,
|
888 |
+
"step": 1120
|
889 |
+
},
|
890 |
+
{
|
891 |
+
"epoch": 23.02,
|
892 |
+
"eval_accuracy": 0.5833333333333334,
|
893 |
+
"eval_loss": 1.1675584316253662,
|
894 |
+
"eval_runtime": 6.8242,
|
895 |
+
"eval_samples_per_second": 8.792,
|
896 |
+
"eval_steps_per_second": 1.465,
|
897 |
+
"step": 1128
|
898 |
+
},
|
899 |
+
{
|
900 |
+
"epoch": 24.0,
|
901 |
+
"learning_rate": 5.652173913043479e-06,
|
902 |
+
"loss": 0.8186,
|
903 |
+
"step": 1130
|
904 |
+
},
|
905 |
+
{
|
906 |
+
"epoch": 24.01,
|
907 |
+
"learning_rate": 5.603864734299518e-06,
|
908 |
+
"loss": 0.7628,
|
909 |
+
"step": 1140
|
910 |
+
},
|
911 |
+
{
|
912 |
+
"epoch": 24.01,
|
913 |
+
"learning_rate": 5.555555555555557e-06,
|
914 |
+
"loss": 0.4592,
|
915 |
+
"step": 1150
|
916 |
+
},
|
917 |
+
{
|
918 |
+
"epoch": 24.01,
|
919 |
+
"learning_rate": 5.507246376811595e-06,
|
920 |
+
"loss": 0.6761,
|
921 |
+
"step": 1160
|
922 |
+
},
|
923 |
+
{
|
924 |
+
"epoch": 24.02,
|
925 |
+
"learning_rate": 5.458937198067633e-06,
|
926 |
+
"loss": 0.7381,
|
927 |
+
"step": 1170
|
928 |
+
},
|
929 |
+
{
|
930 |
+
"epoch": 24.02,
|
931 |
+
"eval_accuracy": 0.55,
|
932 |
+
"eval_loss": 1.1623855829238892,
|
933 |
+
"eval_runtime": 6.815,
|
934 |
+
"eval_samples_per_second": 8.804,
|
935 |
+
"eval_steps_per_second": 1.467,
|
936 |
+
"step": 1175
|
937 |
+
},
|
938 |
+
{
|
939 |
+
"epoch": 25.0,
|
940 |
+
"learning_rate": 5.410628019323671e-06,
|
941 |
+
"loss": 0.8723,
|
942 |
+
"step": 1180
|
943 |
+
},
|
944 |
+
{
|
945 |
+
"epoch": 25.01,
|
946 |
+
"learning_rate": 5.362318840579711e-06,
|
947 |
+
"loss": 0.6832,
|
948 |
+
"step": 1190
|
949 |
+
},
|
950 |
+
{
|
951 |
+
"epoch": 25.01,
|
952 |
+
"learning_rate": 5.314009661835749e-06,
|
953 |
+
"loss": 0.7768,
|
954 |
+
"step": 1200
|
955 |
+
},
|
956 |
+
{
|
957 |
+
"epoch": 25.02,
|
958 |
+
"learning_rate": 5.265700483091788e-06,
|
959 |
+
"loss": 0.6568,
|
960 |
+
"step": 1210
|
961 |
+
},
|
962 |
+
{
|
963 |
+
"epoch": 25.02,
|
964 |
+
"learning_rate": 5.2173913043478265e-06,
|
965 |
+
"loss": 0.4807,
|
966 |
+
"step": 1220
|
967 |
+
},
|
968 |
+
{
|
969 |
+
"epoch": 25.02,
|
970 |
+
"eval_accuracy": 0.55,
|
971 |
+
"eval_loss": 1.1929564476013184,
|
972 |
+
"eval_runtime": 6.8394,
|
973 |
+
"eval_samples_per_second": 8.773,
|
974 |
+
"eval_steps_per_second": 1.462,
|
975 |
+
"step": 1222
|
976 |
+
},
|
977 |
+
{
|
978 |
+
"epoch": 26.0,
|
979 |
+
"learning_rate": 5.169082125603865e-06,
|
980 |
+
"loss": 0.7603,
|
981 |
+
"step": 1230
|
982 |
+
},
|
983 |
+
{
|
984 |
+
"epoch": 26.01,
|
985 |
+
"learning_rate": 5.1207729468599045e-06,
|
986 |
+
"loss": 0.647,
|
987 |
+
"step": 1240
|
988 |
+
},
|
989 |
+
{
|
990 |
+
"epoch": 26.01,
|
991 |
+
"learning_rate": 5.072463768115943e-06,
|
992 |
+
"loss": 0.67,
|
993 |
+
"step": 1250
|
994 |
+
},
|
995 |
+
{
|
996 |
+
"epoch": 26.02,
|
997 |
+
"learning_rate": 5.024154589371981e-06,
|
998 |
+
"loss": 0.6812,
|
999 |
+
"step": 1260
|
1000 |
+
},
|
1001 |
+
{
|
1002 |
+
"epoch": 26.02,
|
1003 |
+
"eval_accuracy": 0.6,
|
1004 |
+
"eval_loss": 1.1511147022247314,
|
1005 |
+
"eval_runtime": 7.0933,
|
1006 |
+
"eval_samples_per_second": 8.459,
|
1007 |
+
"eval_steps_per_second": 1.41,
|
1008 |
+
"step": 1269
|
1009 |
+
},
|
1010 |
+
{
|
1011 |
+
"epoch": 27.0,
|
1012 |
+
"learning_rate": 4.97584541062802e-06,
|
1013 |
+
"loss": 0.6945,
|
1014 |
+
"step": 1270
|
1015 |
+
},
|
1016 |
+
{
|
1017 |
+
"epoch": 27.0,
|
1018 |
+
"learning_rate": 4.927536231884059e-06,
|
1019 |
+
"loss": 0.6031,
|
1020 |
+
"step": 1280
|
1021 |
+
},
|
1022 |
+
{
|
1023 |
+
"epoch": 27.01,
|
1024 |
+
"learning_rate": 4.879227053140097e-06,
|
1025 |
+
"loss": 0.659,
|
1026 |
+
"step": 1290
|
1027 |
+
},
|
1028 |
+
{
|
1029 |
+
"epoch": 27.01,
|
1030 |
+
"learning_rate": 4.830917874396135e-06,
|
1031 |
+
"loss": 0.659,
|
1032 |
+
"step": 1300
|
1033 |
+
},
|
1034 |
+
{
|
1035 |
+
"epoch": 27.02,
|
1036 |
+
"learning_rate": 4.782608695652174e-06,
|
1037 |
+
"loss": 0.5802,
|
1038 |
+
"step": 1310
|
1039 |
+
},
|
1040 |
+
{
|
1041 |
+
"epoch": 27.02,
|
1042 |
+
"eval_accuracy": 0.6166666666666667,
|
1043 |
+
"eval_loss": 1.2314832210540771,
|
1044 |
+
"eval_runtime": 7.5214,
|
1045 |
+
"eval_samples_per_second": 7.977,
|
1046 |
+
"eval_steps_per_second": 1.33,
|
1047 |
+
"step": 1316
|
1048 |
+
},
|
1049 |
+
{
|
1050 |
+
"epoch": 28.0,
|
1051 |
+
"learning_rate": 4.7342995169082125e-06,
|
1052 |
+
"loss": 0.5988,
|
1053 |
+
"step": 1320
|
1054 |
+
},
|
1055 |
+
{
|
1056 |
+
"epoch": 28.01,
|
1057 |
+
"learning_rate": 4.6859903381642516e-06,
|
1058 |
+
"loss": 0.6461,
|
1059 |
+
"step": 1330
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 28.01,
|
1063 |
+
"learning_rate": 4.637681159420291e-06,
|
1064 |
+
"loss": 0.729,
|
1065 |
+
"step": 1340
|
1066 |
+
},
|
1067 |
+
{
|
1068 |
+
"epoch": 28.01,
|
1069 |
+
"learning_rate": 4.589371980676329e-06,
|
1070 |
+
"loss": 0.5582,
|
1071 |
+
"step": 1350
|
1072 |
+
},
|
1073 |
+
{
|
1074 |
+
"epoch": 28.02,
|
1075 |
+
"learning_rate": 4.541062801932368e-06,
|
1076 |
+
"loss": 0.5943,
|
1077 |
+
"step": 1360
|
1078 |
+
},
|
1079 |
+
{
|
1080 |
+
"epoch": 28.02,
|
1081 |
+
"eval_accuracy": 0.5666666666666667,
|
1082 |
+
"eval_loss": 1.1640959978103638,
|
1083 |
+
"eval_runtime": 7.4811,
|
1084 |
+
"eval_samples_per_second": 8.02,
|
1085 |
+
"eval_steps_per_second": 1.337,
|
1086 |
+
"step": 1363
|
1087 |
+
},
|
1088 |
+
{
|
1089 |
+
"epoch": 29.0,
|
1090 |
+
"learning_rate": 4.492753623188406e-06,
|
1091 |
+
"loss": 0.4759,
|
1092 |
+
"step": 1370
|
1093 |
+
},
|
1094 |
+
{
|
1095 |
+
"epoch": 29.01,
|
1096 |
+
"learning_rate": 4.444444444444444e-06,
|
1097 |
+
"loss": 0.7748,
|
1098 |
+
"step": 1380
|
1099 |
+
},
|
1100 |
+
{
|
1101 |
+
"epoch": 29.01,
|
1102 |
+
"learning_rate": 4.396135265700483e-06,
|
1103 |
+
"loss": 0.5033,
|
1104 |
+
"step": 1390
|
1105 |
+
},
|
1106 |
+
{
|
1107 |
+
"epoch": 29.02,
|
1108 |
+
"learning_rate": 4.347826086956522e-06,
|
1109 |
+
"loss": 0.8771,
|
1110 |
+
"step": 1400
|
1111 |
+
},
|
1112 |
+
{
|
1113 |
+
"epoch": 29.02,
|
1114 |
+
"learning_rate": 4.299516908212561e-06,
|
1115 |
+
"loss": 0.5416,
|
1116 |
+
"step": 1410
|
1117 |
+
},
|
1118 |
+
{
|
1119 |
+
"epoch": 29.02,
|
1120 |
+
"eval_accuracy": 0.6,
|
1121 |
+
"eval_loss": 1.0962903499603271,
|
1122 |
+
"eval_runtime": 7.0002,
|
1123 |
+
"eval_samples_per_second": 8.571,
|
1124 |
+
"eval_steps_per_second": 1.429,
|
1125 |
+
"step": 1410
|
1126 |
+
},
|
1127 |
+
{
|
1128 |
+
"epoch": 30.0,
|
1129 |
+
"learning_rate": 4.251207729468599e-06,
|
1130 |
+
"loss": 0.6134,
|
1131 |
+
"step": 1420
|
1132 |
+
},
|
1133 |
+
{
|
1134 |
+
"epoch": 30.01,
|
1135 |
+
"learning_rate": 4.202898550724638e-06,
|
1136 |
+
"loss": 0.5366,
|
1137 |
+
"step": 1430
|
1138 |
+
},
|
1139 |
+
{
|
1140 |
+
"epoch": 30.01,
|
1141 |
+
"learning_rate": 4.154589371980677e-06,
|
1142 |
+
"loss": 0.5575,
|
1143 |
+
"step": 1440
|
1144 |
+
},
|
1145 |
+
{
|
1146 |
+
"epoch": 30.02,
|
1147 |
+
"learning_rate": 4.106280193236716e-06,
|
1148 |
+
"loss": 0.6676,
|
1149 |
+
"step": 1450
|
1150 |
+
},
|
1151 |
+
{
|
1152 |
+
"epoch": 30.02,
|
1153 |
+
"eval_accuracy": 0.5666666666666667,
|
1154 |
+
"eval_loss": 1.1130536794662476,
|
1155 |
+
"eval_runtime": 7.3167,
|
1156 |
+
"eval_samples_per_second": 8.2,
|
1157 |
+
"eval_steps_per_second": 1.367,
|
1158 |
+
"step": 1457
|
1159 |
+
},
|
1160 |
+
{
|
1161 |
+
"epoch": 31.0,
|
1162 |
+
"learning_rate": 4.057971014492754e-06,
|
1163 |
+
"loss": 0.5169,
|
1164 |
+
"step": 1460
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"epoch": 31.01,
|
1168 |
+
"learning_rate": 4.009661835748793e-06,
|
1169 |
+
"loss": 0.5593,
|
1170 |
+
"step": 1470
|
1171 |
+
},
|
1172 |
+
{
|
1173 |
+
"epoch": 31.01,
|
1174 |
+
"learning_rate": 3.961352657004831e-06,
|
1175 |
+
"loss": 0.7655,
|
1176 |
+
"step": 1480
|
1177 |
+
},
|
1178 |
+
{
|
1179 |
+
"epoch": 31.01,
|
1180 |
+
"learning_rate": 3.91304347826087e-06,
|
1181 |
+
"loss": 0.6803,
|
1182 |
+
"step": 1490
|
1183 |
+
},
|
1184 |
+
{
|
1185 |
+
"epoch": 31.02,
|
1186 |
+
"learning_rate": 3.864734299516908e-06,
|
1187 |
+
"loss": 0.4085,
|
1188 |
+
"step": 1500
|
1189 |
+
},
|
1190 |
+
{
|
1191 |
+
"epoch": 31.02,
|
1192 |
+
"eval_accuracy": 0.5833333333333334,
|
1193 |
+
"eval_loss": 1.2947934865951538,
|
1194 |
+
"eval_runtime": 6.9055,
|
1195 |
+
"eval_samples_per_second": 8.689,
|
1196 |
+
"eval_steps_per_second": 1.448,
|
1197 |
+
"step": 1504
|
1198 |
+
},
|
1199 |
+
{
|
1200 |
+
"epoch": 32.0,
|
1201 |
+
"learning_rate": 3.816425120772947e-06,
|
1202 |
+
"loss": 0.7962,
|
1203 |
+
"step": 1510
|
1204 |
+
},
|
1205 |
+
{
|
1206 |
+
"epoch": 32.01,
|
1207 |
+
"learning_rate": 3.768115942028986e-06,
|
1208 |
+
"loss": 0.742,
|
1209 |
+
"step": 1520
|
1210 |
+
},
|
1211 |
+
{
|
1212 |
+
"epoch": 32.01,
|
1213 |
+
"learning_rate": 3.7198067632850245e-06,
|
1214 |
+
"loss": 0.4275,
|
1215 |
+
"step": 1530
|
1216 |
+
},
|
1217 |
+
{
|
1218 |
+
"epoch": 32.02,
|
1219 |
+
"learning_rate": 3.6714975845410635e-06,
|
1220 |
+
"loss": 0.6044,
|
1221 |
+
"step": 1540
|
1222 |
+
},
|
1223 |
+
{
|
1224 |
+
"epoch": 32.02,
|
1225 |
+
"learning_rate": 3.6231884057971017e-06,
|
1226 |
+
"loss": 0.4548,
|
1227 |
+
"step": 1550
|
1228 |
+
},
|
1229 |
+
{
|
1230 |
+
"epoch": 32.02,
|
1231 |
+
"eval_accuracy": 0.6333333333333333,
|
1232 |
+
"eval_loss": 1.2788442373275757,
|
1233 |
+
"eval_runtime": 6.7575,
|
1234 |
+
"eval_samples_per_second": 8.879,
|
1235 |
+
"eval_steps_per_second": 1.48,
|
1236 |
+
"step": 1551
|
1237 |
+
},
|
1238 |
+
{
|
1239 |
+
"epoch": 33.0,
|
1240 |
+
"learning_rate": 3.5748792270531403e-06,
|
1241 |
+
"loss": 0.7688,
|
1242 |
+
"step": 1560
|
1243 |
+
},
|
1244 |
+
{
|
1245 |
+
"epoch": 33.01,
|
1246 |
+
"learning_rate": 3.5265700483091793e-06,
|
1247 |
+
"loss": 0.489,
|
1248 |
+
"step": 1570
|
1249 |
+
},
|
1250 |
+
{
|
1251 |
+
"epoch": 33.01,
|
1252 |
+
"learning_rate": 3.4782608695652175e-06,
|
1253 |
+
"loss": 0.545,
|
1254 |
+
"step": 1580
|
1255 |
+
},
|
1256 |
+
{
|
1257 |
+
"epoch": 33.02,
|
1258 |
+
"learning_rate": 3.4299516908212565e-06,
|
1259 |
+
"loss": 0.4351,
|
1260 |
+
"step": 1590
|
1261 |
+
},
|
1262 |
+
{
|
1263 |
+
"epoch": 33.02,
|
1264 |
+
"eval_accuracy": 0.5666666666666667,
|
1265 |
+
"eval_loss": 1.1921883821487427,
|
1266 |
+
"eval_runtime": 6.9013,
|
1267 |
+
"eval_samples_per_second": 8.694,
|
1268 |
+
"eval_steps_per_second": 1.449,
|
1269 |
+
"step": 1598
|
1270 |
+
},
|
1271 |
+
{
|
1272 |
+
"epoch": 34.0,
|
1273 |
+
"learning_rate": 3.381642512077295e-06,
|
1274 |
+
"loss": 0.5118,
|
1275 |
+
"step": 1600
|
1276 |
+
},
|
1277 |
+
{
|
1278 |
+
"epoch": 34.01,
|
1279 |
+
"learning_rate": 3.3333333333333333e-06,
|
1280 |
+
"loss": 0.5212,
|
1281 |
+
"step": 1610
|
1282 |
+
},
|
1283 |
+
{
|
1284 |
+
"epoch": 34.01,
|
1285 |
+
"learning_rate": 3.2850241545893724e-06,
|
1286 |
+
"loss": 0.3797,
|
1287 |
+
"step": 1620
|
1288 |
+
},
|
1289 |
+
{
|
1290 |
+
"epoch": 34.01,
|
1291 |
+
"learning_rate": 3.236714975845411e-06,
|
1292 |
+
"loss": 0.5177,
|
1293 |
+
"step": 1630
|
1294 |
+
},
|
1295 |
+
{
|
1296 |
+
"epoch": 34.02,
|
1297 |
+
"learning_rate": 3.188405797101449e-06,
|
1298 |
+
"loss": 0.5641,
|
1299 |
+
"step": 1640
|
1300 |
+
},
|
1301 |
+
{
|
1302 |
+
"epoch": 34.02,
|
1303 |
+
"eval_accuracy": 0.55,
|
1304 |
+
"eval_loss": 1.267711877822876,
|
1305 |
+
"eval_runtime": 7.3036,
|
1306 |
+
"eval_samples_per_second": 8.215,
|
1307 |
+
"eval_steps_per_second": 1.369,
|
1308 |
+
"step": 1645
|
1309 |
+
},
|
1310 |
+
{
|
1311 |
+
"epoch": 35.0,
|
1312 |
+
"learning_rate": 3.140096618357488e-06,
|
1313 |
+
"loss": 0.3153,
|
1314 |
+
"step": 1650
|
1315 |
+
},
|
1316 |
+
{
|
1317 |
+
"epoch": 35.01,
|
1318 |
+
"learning_rate": 3.0917874396135268e-06,
|
1319 |
+
"loss": 0.4103,
|
1320 |
+
"step": 1660
|
1321 |
+
},
|
1322 |
+
{
|
1323 |
+
"epoch": 35.01,
|
1324 |
+
"learning_rate": 3.043478260869566e-06,
|
1325 |
+
"loss": 0.503,
|
1326 |
+
"step": 1670
|
1327 |
+
},
|
1328 |
+
{
|
1329 |
+
"epoch": 35.02,
|
1330 |
+
"learning_rate": 2.995169082125604e-06,
|
1331 |
+
"loss": 0.5921,
|
1332 |
+
"step": 1680
|
1333 |
+
},
|
1334 |
+
{
|
1335 |
+
"epoch": 35.02,
|
1336 |
+
"learning_rate": 2.9468599033816426e-06,
|
1337 |
+
"loss": 0.4471,
|
1338 |
+
"step": 1690
|
1339 |
+
},
|
1340 |
+
{
|
1341 |
+
"epoch": 35.02,
|
1342 |
+
"eval_accuracy": 0.6166666666666667,
|
1343 |
+
"eval_loss": 1.2765668630599976,
|
1344 |
+
"eval_runtime": 7.0911,
|
1345 |
+
"eval_samples_per_second": 8.461,
|
1346 |
+
"eval_steps_per_second": 1.41,
|
1347 |
+
"step": 1692
|
1348 |
+
},
|
1349 |
+
{
|
1350 |
+
"epoch": 36.0,
|
1351 |
+
"learning_rate": 2.8985507246376816e-06,
|
1352 |
+
"loss": 0.4534,
|
1353 |
+
"step": 1700
|
1354 |
+
},
|
1355 |
+
{
|
1356 |
+
"epoch": 36.01,
|
1357 |
+
"learning_rate": 2.85024154589372e-06,
|
1358 |
+
"loss": 0.4072,
|
1359 |
+
"step": 1710
|
1360 |
+
},
|
1361 |
+
{
|
1362 |
+
"epoch": 36.01,
|
1363 |
+
"learning_rate": 2.801932367149759e-06,
|
1364 |
+
"loss": 0.4057,
|
1365 |
+
"step": 1720
|
1366 |
+
},
|
1367 |
+
{
|
1368 |
+
"epoch": 36.02,
|
1369 |
+
"learning_rate": 2.7536231884057974e-06,
|
1370 |
+
"loss": 0.361,
|
1371 |
+
"step": 1730
|
1372 |
+
},
|
1373 |
+
{
|
1374 |
+
"epoch": 36.02,
|
1375 |
+
"eval_accuracy": 0.55,
|
1376 |
+
"eval_loss": 1.2524678707122803,
|
1377 |
+
"eval_runtime": 7.3291,
|
1378 |
+
"eval_samples_per_second": 8.187,
|
1379 |
+
"eval_steps_per_second": 1.364,
|
1380 |
+
"step": 1739
|
1381 |
+
},
|
1382 |
+
{
|
1383 |
+
"epoch": 37.0,
|
1384 |
+
"learning_rate": 2.7053140096618356e-06,
|
1385 |
+
"loss": 0.5294,
|
1386 |
+
"step": 1740
|
1387 |
+
},
|
1388 |
+
{
|
1389 |
+
"epoch": 37.0,
|
1390 |
+
"learning_rate": 2.6570048309178746e-06,
|
1391 |
+
"loss": 0.4,
|
1392 |
+
"step": 1750
|
1393 |
+
},
|
1394 |
+
{
|
1395 |
+
"epoch": 37.01,
|
1396 |
+
"learning_rate": 2.6086956521739132e-06,
|
1397 |
+
"loss": 0.4891,
|
1398 |
+
"step": 1760
|
1399 |
+
},
|
1400 |
+
{
|
1401 |
+
"epoch": 37.01,
|
1402 |
+
"learning_rate": 2.5603864734299523e-06,
|
1403 |
+
"loss": 0.3458,
|
1404 |
+
"step": 1770
|
1405 |
+
},
|
1406 |
+
{
|
1407 |
+
"epoch": 37.02,
|
1408 |
+
"learning_rate": 2.5120772946859904e-06,
|
1409 |
+
"loss": 0.5668,
|
1410 |
+
"step": 1780
|
1411 |
+
},
|
1412 |
+
{
|
1413 |
+
"epoch": 37.02,
|
1414 |
+
"eval_accuracy": 0.55,
|
1415 |
+
"eval_loss": 1.292838454246521,
|
1416 |
+
"eval_runtime": 7.1147,
|
1417 |
+
"eval_samples_per_second": 8.433,
|
1418 |
+
"eval_steps_per_second": 1.406,
|
1419 |
+
"step": 1786
|
1420 |
+
},
|
1421 |
+
{
|
1422 |
+
"epoch": 38.0,
|
1423 |
+
"learning_rate": 2.4637681159420295e-06,
|
1424 |
+
"loss": 0.4136,
|
1425 |
+
"step": 1790
|
1426 |
+
},
|
1427 |
+
{
|
1428 |
+
"epoch": 38.01,
|
1429 |
+
"learning_rate": 2.4154589371980677e-06,
|
1430 |
+
"loss": 0.6028,
|
1431 |
+
"step": 1800
|
1432 |
+
},
|
1433 |
+
{
|
1434 |
+
"epoch": 38.01,
|
1435 |
+
"learning_rate": 2.3671497584541063e-06,
|
1436 |
+
"loss": 0.4004,
|
1437 |
+
"step": 1810
|
1438 |
+
},
|
1439 |
+
{
|
1440 |
+
"epoch": 38.01,
|
1441 |
+
"learning_rate": 2.3188405797101453e-06,
|
1442 |
+
"loss": 0.4186,
|
1443 |
+
"step": 1820
|
1444 |
+
},
|
1445 |
+
{
|
1446 |
+
"epoch": 38.02,
|
1447 |
+
"learning_rate": 2.270531400966184e-06,
|
1448 |
+
"loss": 0.5262,
|
1449 |
+
"step": 1830
|
1450 |
+
},
|
1451 |
+
{
|
1452 |
+
"epoch": 38.02,
|
1453 |
+
"eval_accuracy": 0.6333333333333333,
|
1454 |
+
"eval_loss": 1.2428669929504395,
|
1455 |
+
"eval_runtime": 7.0978,
|
1456 |
+
"eval_samples_per_second": 8.453,
|
1457 |
+
"eval_steps_per_second": 1.409,
|
1458 |
+
"step": 1833
|
1459 |
+
},
|
1460 |
+
{
|
1461 |
+
"epoch": 39.0,
|
1462 |
+
"learning_rate": 2.222222222222222e-06,
|
1463 |
+
"loss": 0.4642,
|
1464 |
+
"step": 1840
|
1465 |
+
},
|
1466 |
+
{
|
1467 |
+
"epoch": 39.01,
|
1468 |
+
"learning_rate": 2.173913043478261e-06,
|
1469 |
+
"loss": 0.485,
|
1470 |
+
"step": 1850
|
1471 |
+
},
|
1472 |
+
{
|
1473 |
+
"epoch": 39.01,
|
1474 |
+
"learning_rate": 2.1256038647342997e-06,
|
1475 |
+
"loss": 0.3757,
|
1476 |
+
"step": 1860
|
1477 |
+
},
|
1478 |
+
{
|
1479 |
+
"epoch": 39.02,
|
1480 |
+
"learning_rate": 2.0772946859903383e-06,
|
1481 |
+
"loss": 0.5197,
|
1482 |
+
"step": 1870
|
1483 |
+
},
|
1484 |
+
{
|
1485 |
+
"epoch": 39.02,
|
1486 |
+
"learning_rate": 2.028985507246377e-06,
|
1487 |
+
"loss": 0.4901,
|
1488 |
+
"step": 1880
|
1489 |
+
},
|
1490 |
+
{
|
1491 |
+
"epoch": 39.02,
|
1492 |
+
"eval_accuracy": 0.5666666666666667,
|
1493 |
+
"eval_loss": 1.1457266807556152,
|
1494 |
+
"eval_runtime": 7.0788,
|
1495 |
+
"eval_samples_per_second": 8.476,
|
1496 |
+
"eval_steps_per_second": 1.413,
|
1497 |
+
"step": 1880
|
1498 |
+
},
|
1499 |
+
{
|
1500 |
+
"epoch": 40.0,
|
1501 |
+
"learning_rate": 1.9806763285024155e-06,
|
1502 |
+
"loss": 0.432,
|
1503 |
+
"step": 1890
|
1504 |
+
},
|
1505 |
+
{
|
1506 |
+
"epoch": 40.01,
|
1507 |
+
"learning_rate": 1.932367149758454e-06,
|
1508 |
+
"loss": 0.3237,
|
1509 |
+
"step": 1900
|
1510 |
+
},
|
1511 |
+
{
|
1512 |
+
"epoch": 40.01,
|
1513 |
+
"learning_rate": 1.884057971014493e-06,
|
1514 |
+
"loss": 0.3166,
|
1515 |
+
"step": 1910
|
1516 |
+
},
|
1517 |
+
{
|
1518 |
+
"epoch": 40.02,
|
1519 |
+
"learning_rate": 1.8357487922705318e-06,
|
1520 |
+
"loss": 0.481,
|
1521 |
+
"step": 1920
|
1522 |
+
},
|
1523 |
+
{
|
1524 |
+
"epoch": 40.02,
|
1525 |
+
"eval_accuracy": 0.5833333333333334,
|
1526 |
+
"eval_loss": 1.213700771331787,
|
1527 |
+
"eval_runtime": 7.0464,
|
1528 |
+
"eval_samples_per_second": 8.515,
|
1529 |
+
"eval_steps_per_second": 1.419,
|
1530 |
+
"step": 1927
|
1531 |
+
},
|
1532 |
+
{
|
1533 |
+
"epoch": 41.0,
|
1534 |
+
"learning_rate": 1.7874396135265702e-06,
|
1535 |
+
"loss": 0.3313,
|
1536 |
+
"step": 1930
|
1537 |
+
},
|
1538 |
+
{
|
1539 |
+
"epoch": 41.01,
|
1540 |
+
"learning_rate": 1.7391304347826088e-06,
|
1541 |
+
"loss": 0.4095,
|
1542 |
+
"step": 1940
|
1543 |
+
},
|
1544 |
+
{
|
1545 |
+
"epoch": 41.01,
|
1546 |
+
"learning_rate": 1.6908212560386476e-06,
|
1547 |
+
"loss": 0.4013,
|
1548 |
+
"step": 1950
|
1549 |
+
},
|
1550 |
+
{
|
1551 |
+
"epoch": 41.01,
|
1552 |
+
"learning_rate": 1.6425120772946862e-06,
|
1553 |
+
"loss": 0.453,
|
1554 |
+
"step": 1960
|
1555 |
+
},
|
1556 |
+
{
|
1557 |
+
"epoch": 41.02,
|
1558 |
+
"learning_rate": 1.5942028985507246e-06,
|
1559 |
+
"loss": 0.3566,
|
1560 |
+
"step": 1970
|
1561 |
+
},
|
1562 |
+
{
|
1563 |
+
"epoch": 41.02,
|
1564 |
+
"eval_accuracy": 0.6166666666666667,
|
1565 |
+
"eval_loss": 1.1829572916030884,
|
1566 |
+
"eval_runtime": 7.0773,
|
1567 |
+
"eval_samples_per_second": 8.478,
|
1568 |
+
"eval_steps_per_second": 1.413,
|
1569 |
+
"step": 1974
|
1570 |
+
},
|
1571 |
+
{
|
1572 |
+
"epoch": 42.0,
|
1573 |
+
"learning_rate": 1.5458937198067634e-06,
|
1574 |
+
"loss": 0.342,
|
1575 |
+
"step": 1980
|
1576 |
+
},
|
1577 |
+
{
|
1578 |
+
"epoch": 42.01,
|
1579 |
+
"learning_rate": 1.497584541062802e-06,
|
1580 |
+
"loss": 0.2666,
|
1581 |
+
"step": 1990
|
1582 |
+
},
|
1583 |
+
{
|
1584 |
+
"epoch": 42.01,
|
1585 |
+
"learning_rate": 1.4492753623188408e-06,
|
1586 |
+
"loss": 0.4153,
|
1587 |
+
"step": 2000
|
1588 |
+
},
|
1589 |
+
{
|
1590 |
+
"epoch": 42.02,
|
1591 |
+
"learning_rate": 1.4009661835748794e-06,
|
1592 |
+
"loss": 0.3853,
|
1593 |
+
"step": 2010
|
1594 |
+
},
|
1595 |
+
{
|
1596 |
+
"epoch": 42.02,
|
1597 |
+
"learning_rate": 1.3526570048309178e-06,
|
1598 |
+
"loss": 0.5147,
|
1599 |
+
"step": 2020
|
1600 |
+
},
|
1601 |
+
{
|
1602 |
+
"epoch": 42.02,
|
1603 |
+
"eval_accuracy": 0.6,
|
1604 |
+
"eval_loss": 1.1628528833389282,
|
1605 |
+
"eval_runtime": 6.9693,
|
1606 |
+
"eval_samples_per_second": 8.609,
|
1607 |
+
"eval_steps_per_second": 1.435,
|
1608 |
+
"step": 2021
|
1609 |
+
},
|
1610 |
+
{
|
1611 |
+
"epoch": 43.0,
|
1612 |
+
"learning_rate": 1.3043478260869566e-06,
|
1613 |
+
"loss": 0.5075,
|
1614 |
+
"step": 2030
|
1615 |
+
},
|
1616 |
+
{
|
1617 |
+
"epoch": 43.01,
|
1618 |
+
"learning_rate": 1.2560386473429952e-06,
|
1619 |
+
"loss": 0.3599,
|
1620 |
+
"step": 2040
|
1621 |
+
},
|
1622 |
+
{
|
1623 |
+
"epoch": 43.01,
|
1624 |
+
"learning_rate": 1.2077294685990338e-06,
|
1625 |
+
"loss": 0.3602,
|
1626 |
+
"step": 2050
|
1627 |
+
},
|
1628 |
+
{
|
1629 |
+
"epoch": 43.02,
|
1630 |
+
"learning_rate": 1.1594202898550726e-06,
|
1631 |
+
"loss": 0.4013,
|
1632 |
+
"step": 2060
|
1633 |
+
},
|
1634 |
+
{
|
1635 |
+
"epoch": 43.02,
|
1636 |
+
"eval_accuracy": 0.6,
|
1637 |
+
"eval_loss": 1.2734596729278564,
|
1638 |
+
"eval_runtime": 7.5005,
|
1639 |
+
"eval_samples_per_second": 8.0,
|
1640 |
+
"eval_steps_per_second": 1.333,
|
1641 |
+
"step": 2068
|
1642 |
+
},
|
1643 |
+
{
|
1644 |
+
"epoch": 44.0,
|
1645 |
+
"learning_rate": 1.111111111111111e-06,
|
1646 |
+
"loss": 0.1829,
|
1647 |
+
"step": 2070
|
1648 |
+
},
|
1649 |
+
{
|
1650 |
+
"epoch": 44.01,
|
1651 |
+
"learning_rate": 1.0628019323671499e-06,
|
1652 |
+
"loss": 0.3784,
|
1653 |
+
"step": 2080
|
1654 |
+
},
|
1655 |
+
{
|
1656 |
+
"epoch": 44.01,
|
1657 |
+
"learning_rate": 1.0144927536231885e-06,
|
1658 |
+
"loss": 0.3492,
|
1659 |
+
"step": 2090
|
1660 |
+
},
|
1661 |
+
{
|
1662 |
+
"epoch": 44.01,
|
1663 |
+
"learning_rate": 9.66183574879227e-07,
|
1664 |
+
"loss": 0.3413,
|
1665 |
+
"step": 2100
|
1666 |
+
},
|
1667 |
+
{
|
1668 |
+
"epoch": 44.02,
|
1669 |
+
"learning_rate": 9.178743961352659e-07,
|
1670 |
+
"loss": 0.3895,
|
1671 |
+
"step": 2110
|
1672 |
+
},
|
1673 |
+
{
|
1674 |
+
"epoch": 44.02,
|
1675 |
+
"eval_accuracy": 0.6166666666666667,
|
1676 |
+
"eval_loss": 1.275781273841858,
|
1677 |
+
"eval_runtime": 7.0795,
|
1678 |
+
"eval_samples_per_second": 8.475,
|
1679 |
+
"eval_steps_per_second": 1.413,
|
1680 |
+
"step": 2115
|
1681 |
+
},
|
1682 |
+
{
|
1683 |
+
"epoch": 45.0,
|
1684 |
+
"learning_rate": 8.695652173913044e-07,
|
1685 |
+
"loss": 0.2765,
|
1686 |
+
"step": 2120
|
1687 |
+
},
|
1688 |
+
{
|
1689 |
+
"epoch": 45.01,
|
1690 |
+
"learning_rate": 8.212560386473431e-07,
|
1691 |
+
"loss": 0.3307,
|
1692 |
+
"step": 2130
|
1693 |
+
},
|
1694 |
+
{
|
1695 |
+
"epoch": 45.01,
|
1696 |
+
"learning_rate": 7.729468599033817e-07,
|
1697 |
+
"loss": 0.4263,
|
1698 |
+
"step": 2140
|
1699 |
+
},
|
1700 |
+
{
|
1701 |
+
"epoch": 45.02,
|
1702 |
+
"learning_rate": 7.246376811594204e-07,
|
1703 |
+
"loss": 0.2821,
|
1704 |
+
"step": 2150
|
1705 |
+
},
|
1706 |
+
{
|
1707 |
+
"epoch": 45.02,
|
1708 |
+
"learning_rate": 6.763285024154589e-07,
|
1709 |
+
"loss": 0.3727,
|
1710 |
+
"step": 2160
|
1711 |
+
},
|
1712 |
+
{
|
1713 |
+
"epoch": 45.02,
|
1714 |
+
"eval_accuracy": 0.5833333333333334,
|
1715 |
+
"eval_loss": 1.251878023147583,
|
1716 |
+
"eval_runtime": 6.9821,
|
1717 |
+
"eval_samples_per_second": 8.593,
|
1718 |
+
"eval_steps_per_second": 1.432,
|
1719 |
+
"step": 2162
|
1720 |
+
},
|
1721 |
+
{
|
1722 |
+
"epoch": 46.0,
|
1723 |
+
"learning_rate": 6.280193236714976e-07,
|
1724 |
+
"loss": 0.2848,
|
1725 |
+
"step": 2170
|
1726 |
+
},
|
1727 |
+
{
|
1728 |
+
"epoch": 46.01,
|
1729 |
+
"learning_rate": 5.797101449275363e-07,
|
1730 |
+
"loss": 0.3064,
|
1731 |
+
"step": 2180
|
1732 |
+
},
|
1733 |
+
{
|
1734 |
+
"epoch": 46.01,
|
1735 |
+
"learning_rate": 5.314009661835749e-07,
|
1736 |
+
"loss": 0.2802,
|
1737 |
+
"step": 2190
|
1738 |
+
},
|
1739 |
+
{
|
1740 |
+
"epoch": 46.02,
|
1741 |
+
"learning_rate": 4.830917874396135e-07,
|
1742 |
+
"loss": 0.2379,
|
1743 |
+
"step": 2200
|
1744 |
+
},
|
1745 |
+
{
|
1746 |
+
"epoch": 46.02,
|
1747 |
+
"eval_accuracy": 0.5833333333333334,
|
1748 |
+
"eval_loss": 1.2318103313446045,
|
1749 |
+
"eval_runtime": 7.4568,
|
1750 |
+
"eval_samples_per_second": 8.046,
|
1751 |
+
"eval_steps_per_second": 1.341,
|
1752 |
+
"step": 2209
|
1753 |
+
},
|
1754 |
+
{
|
1755 |
+
"epoch": 47.0,
|
1756 |
+
"learning_rate": 4.347826086956522e-07,
|
1757 |
+
"loss": 0.3444,
|
1758 |
+
"step": 2210
|
1759 |
+
},
|
1760 |
+
{
|
1761 |
+
"epoch": 47.0,
|
1762 |
+
"learning_rate": 3.8647342995169085e-07,
|
1763 |
+
"loss": 0.3964,
|
1764 |
+
"step": 2220
|
1765 |
+
},
|
1766 |
+
{
|
1767 |
+
"epoch": 47.01,
|
1768 |
+
"learning_rate": 3.3816425120772945e-07,
|
1769 |
+
"loss": 0.218,
|
1770 |
+
"step": 2230
|
1771 |
+
},
|
1772 |
+
{
|
1773 |
+
"epoch": 47.01,
|
1774 |
+
"learning_rate": 2.8985507246376816e-07,
|
1775 |
+
"loss": 0.4576,
|
1776 |
+
"step": 2240
|
1777 |
+
},
|
1778 |
+
{
|
1779 |
+
"epoch": 47.02,
|
1780 |
+
"learning_rate": 2.4154589371980677e-07,
|
1781 |
+
"loss": 0.2985,
|
1782 |
+
"step": 2250
|
1783 |
+
},
|
1784 |
+
{
|
1785 |
+
"epoch": 47.02,
|
1786 |
+
"eval_accuracy": 0.5833333333333334,
|
1787 |
+
"eval_loss": 1.2594045400619507,
|
1788 |
+
"eval_runtime": 6.9353,
|
1789 |
+
"eval_samples_per_second": 8.651,
|
1790 |
+
"eval_steps_per_second": 1.442,
|
1791 |
+
"step": 2256
|
1792 |
+
},
|
1793 |
+
{
|
1794 |
+
"epoch": 48.0,
|
1795 |
+
"learning_rate": 1.9323671497584542e-07,
|
1796 |
+
"loss": 0.359,
|
1797 |
+
"step": 2260
|
1798 |
+
},
|
1799 |
+
{
|
1800 |
+
"epoch": 48.01,
|
1801 |
+
"learning_rate": 1.4492753623188408e-07,
|
1802 |
+
"loss": 0.3572,
|
1803 |
+
"step": 2270
|
1804 |
+
},
|
1805 |
+
{
|
1806 |
+
"epoch": 48.01,
|
1807 |
+
"learning_rate": 9.661835748792271e-08,
|
1808 |
+
"loss": 0.4208,
|
1809 |
+
"step": 2280
|
1810 |
+
},
|
1811 |
+
{
|
1812 |
+
"epoch": 48.01,
|
1813 |
+
"learning_rate": 4.8309178743961356e-08,
|
1814 |
+
"loss": 0.3265,
|
1815 |
+
"step": 2290
|
1816 |
+
},
|
1817 |
+
{
|
1818 |
+
"epoch": 48.02,
|
1819 |
+
"learning_rate": 0.0,
|
1820 |
+
"loss": 0.2991,
|
1821 |
+
"step": 2300
|
1822 |
+
},
|
1823 |
+
{
|
1824 |
+
"epoch": 48.02,
|
1825 |
+
"eval_accuracy": 0.5833333333333334,
|
1826 |
+
"eval_loss": 1.2510361671447754,
|
1827 |
+
"eval_runtime": 6.9183,
|
1828 |
+
"eval_samples_per_second": 8.673,
|
1829 |
+
"eval_steps_per_second": 1.445,
|
1830 |
+
"step": 2300
|
1831 |
+
},
|
1832 |
+
{
|
1833 |
+
"epoch": 48.02,
|
1834 |
+
"step": 2300,
|
1835 |
+
"total_flos": 1.7136338694977618e+19,
|
1836 |
+
"train_loss": 0.7374556654950847,
|
1837 |
+
"train_runtime": 3025.2001,
|
1838 |
+
"train_samples_per_second": 4.562,
|
1839 |
+
"train_steps_per_second": 0.76
|
1840 |
+
},
|
1841 |
+
{
|
1842 |
+
"epoch": 48.02,
|
1843 |
+
"eval_accuracy": 0.6507936507936508,
|
1844 |
+
"eval_loss": 1.1547213792800903,
|
1845 |
+
"eval_runtime": 9.0552,
|
1846 |
+
"eval_samples_per_second": 6.957,
|
1847 |
+
"eval_steps_per_second": 1.215,
|
1848 |
+
"step": 2300
|
1849 |
+
},
|
1850 |
+
{
|
1851 |
+
"epoch": 48.02,
|
1852 |
+
"eval_accuracy": 0.6507936507936508,
|
1853 |
+
"eval_loss": 1.1547214984893799,
|
1854 |
+
"eval_runtime": 7.9277,
|
1855 |
+
"eval_samples_per_second": 7.947,
|
1856 |
+
"eval_steps_per_second": 1.388,
|
1857 |
+
"step": 2300
|
1858 |
+
}
|
1859 |
+
],
|
1860 |
+
"logging_steps": 10,
|
1861 |
+
"max_steps": 2300,
|
1862 |
+
"num_input_tokens_seen": 0,
|
1863 |
+
"num_train_epochs": 9223372036854775807,
|
1864 |
+
"save_steps": 500,
|
1865 |
+
"total_flos": 1.7136338694977618e+19,
|
1866 |
+
"train_batch_size": 6,
|
1867 |
+
"trial_name": null,
|
1868 |
+
"trial_params": null
|
1869 |
+
}
|