Commit
•
121551f
1
Parent(s):
14385b5
End of training
Browse files- all_results.json +9 -5
- eval_results.json +7 -0
- runs/Jul14_16-14-45_flyswot-vm/events.out.tfevents.1657900440.flyswot-vm.185404.2 +3 -0
- train_results.json +5 -5
- trainer_state.json +1932 -14
all_results.json
CHANGED
|
@@ -1,7 +1,11 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"
|
| 4 |
-
"
|
| 5 |
-
"
|
| 6 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
}
|
| 1 |
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_loss": 2.5792043209075928,
|
| 4 |
+
"eval_runtime": 211.7413,
|
| 5 |
+
"eval_samples_per_second": 461.535,
|
| 6 |
+
"eval_steps_per_second": 1.804,
|
| 7 |
+
"train_loss": 2.026226943438967,
|
| 8 |
+
"train_runtime": 84552.1773,
|
| 9 |
+
"train_samples_per_second": 104.022,
|
| 10 |
+
"train_steps_per_second": 0.813
|
| 11 |
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_loss": 2.5792043209075928,
|
| 4 |
+
"eval_runtime": 211.7413,
|
| 5 |
+
"eval_samples_per_second": 461.535,
|
| 6 |
+
"eval_steps_per_second": 1.804
|
| 7 |
+
}
|
runs/Jul14_16-14-45_flyswot-vm/events.out.tfevents.1657900440.flyswot-vm.185404.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e137bdf2c06e4f69f16c1b361b54e3d38b9f7c7bbec6a0286e25d1951a32046e
|
| 3 |
+
size 316
|
train_results.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"train_loss": 2.
|
| 4 |
-
"train_runtime":
|
| 5 |
-
"train_samples_per_second":
|
| 6 |
-
"train_steps_per_second": 0.
|
| 7 |
}
|
| 1 |
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"train_loss": 2.026226943438967,
|
| 4 |
+
"train_runtime": 84552.1773,
|
| 5 |
+
"train_samples_per_second": 104.022,
|
| 6 |
+
"train_steps_per_second": 0.813
|
| 7 |
}
|
trainer_state.json
CHANGED
|
@@ -1,25 +1,1943 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric":
|
| 3 |
-
"best_model_checkpoint":
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
-
"epoch":
|
| 12 |
-
"
|
| 13 |
-
"
|
| 14 |
-
"
|
| 15 |
-
|
| 16 |
-
|
| 17 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
}
|
| 19 |
],
|
| 20 |
-
"max_steps":
|
| 21 |
-
"num_train_epochs":
|
| 22 |
-
"total_flos":
|
| 23 |
"trial_name": null,
|
| 24 |
"trial_params": null
|
| 25 |
}
|
| 1 |
{
|
| 2 |
+
"best_metric": 2.5792043209075928,
|
| 3 |
+
"best_model_checkpoint": "./clip-roberta-finetuned/checkpoint-48000",
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"global_step": 68710,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
+
"epoch": 0.07,
|
| 12 |
+
"learning_rate": 4.963760733517683e-05,
|
| 13 |
+
"loss": 2.9841,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.07,
|
| 18 |
+
"eval_loss": 3.411221504211426,
|
| 19 |
+
"eval_runtime": 218.2214,
|
| 20 |
+
"eval_samples_per_second": 447.83,
|
| 21 |
+
"eval_steps_per_second": 1.751,
|
| 22 |
+
"step": 500
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"epoch": 0.15,
|
| 26 |
+
"learning_rate": 4.927521467035366e-05,
|
| 27 |
+
"loss": 2.72,
|
| 28 |
+
"step": 1000
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 0.15,
|
| 32 |
+
"eval_loss": 3.3430113792419434,
|
| 33 |
+
"eval_runtime": 214.9656,
|
| 34 |
+
"eval_samples_per_second": 454.612,
|
| 35 |
+
"eval_steps_per_second": 1.777,
|
| 36 |
+
"step": 1000
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 0.22,
|
| 40 |
+
"learning_rate": 4.891209430941639e-05,
|
| 41 |
+
"loss": 2.6319,
|
| 42 |
+
"step": 1500
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.22,
|
| 46 |
+
"eval_loss": 3.2295451164245605,
|
| 47 |
+
"eval_runtime": 250.7246,
|
| 48 |
+
"eval_samples_per_second": 389.774,
|
| 49 |
+
"eval_steps_per_second": 1.524,
|
| 50 |
+
"step": 1500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.29,
|
| 54 |
+
"learning_rate": 4.854824625236501e-05,
|
| 55 |
+
"loss": 2.5781,
|
| 56 |
+
"step": 2000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.29,
|
| 60 |
+
"eval_loss": 3.1644504070281982,
|
| 61 |
+
"eval_runtime": 249.2113,
|
| 62 |
+
"eval_samples_per_second": 392.141,
|
| 63 |
+
"eval_steps_per_second": 1.533,
|
| 64 |
+
"step": 2000
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.36,
|
| 68 |
+
"learning_rate": 4.818439819531364e-05,
|
| 69 |
+
"loss": 2.5339,
|
| 70 |
+
"step": 2500
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 0.36,
|
| 74 |
+
"eval_loss": 3.1226284503936768,
|
| 75 |
+
"eval_runtime": 249.7319,
|
| 76 |
+
"eval_samples_per_second": 391.324,
|
| 77 |
+
"eval_steps_per_second": 1.53,
|
| 78 |
+
"step": 2500
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 0.44,
|
| 82 |
+
"learning_rate": 4.782055013826226e-05,
|
| 83 |
+
"loss": 2.503,
|
| 84 |
+
"step": 3000
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.44,
|
| 88 |
+
"eval_loss": 3.0856029987335205,
|
| 89 |
+
"eval_runtime": 260.6356,
|
| 90 |
+
"eval_samples_per_second": 374.953,
|
| 91 |
+
"eval_steps_per_second": 1.466,
|
| 92 |
+
"step": 3000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.51,
|
| 96 |
+
"learning_rate": 4.745670208121089e-05,
|
| 97 |
+
"loss": 2.4581,
|
| 98 |
+
"step": 3500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.51,
|
| 102 |
+
"eval_loss": 3.063863515853882,
|
| 103 |
+
"eval_runtime": 246.5877,
|
| 104 |
+
"eval_samples_per_second": 396.313,
|
| 105 |
+
"eval_steps_per_second": 1.549,
|
| 106 |
+
"step": 3500
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.58,
|
| 110 |
+
"learning_rate": 4.709285402415951e-05,
|
| 111 |
+
"loss": 2.4494,
|
| 112 |
+
"step": 4000
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 0.58,
|
| 116 |
+
"eval_loss": 3.0415244102478027,
|
| 117 |
+
"eval_runtime": 244.6941,
|
| 118 |
+
"eval_samples_per_second": 399.38,
|
| 119 |
+
"eval_steps_per_second": 1.561,
|
| 120 |
+
"step": 4000
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.65,
|
| 124 |
+
"learning_rate": 4.6729005967108134e-05,
|
| 125 |
+
"loss": 2.4275,
|
| 126 |
+
"step": 4500
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 0.65,
|
| 130 |
+
"eval_loss": 3.0244903564453125,
|
| 131 |
+
"eval_runtime": 210.3742,
|
| 132 |
+
"eval_samples_per_second": 464.534,
|
| 133 |
+
"eval_steps_per_second": 1.816,
|
| 134 |
+
"step": 4500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.73,
|
| 138 |
+
"learning_rate": 4.636515791005676e-05,
|
| 139 |
+
"loss": 2.3909,
|
| 140 |
+
"step": 5000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.73,
|
| 144 |
+
"eval_loss": 2.999117851257324,
|
| 145 |
+
"eval_runtime": 210.4024,
|
| 146 |
+
"eval_samples_per_second": 464.472,
|
| 147 |
+
"eval_steps_per_second": 1.816,
|
| 148 |
+
"step": 5000
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 0.8,
|
| 152 |
+
"learning_rate": 4.6001309853005384e-05,
|
| 153 |
+
"loss": 2.3902,
|
| 154 |
+
"step": 5500
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.8,
|
| 158 |
+
"eval_loss": 2.9931323528289795,
|
| 159 |
+
"eval_runtime": 208.7009,
|
| 160 |
+
"eval_samples_per_second": 468.259,
|
| 161 |
+
"eval_steps_per_second": 1.83,
|
| 162 |
+
"step": 5500
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.87,
|
| 166 |
+
"learning_rate": 4.563746179595401e-05,
|
| 167 |
+
"loss": 2.3741,
|
| 168 |
+
"step": 6000
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 0.87,
|
| 172 |
+
"eval_loss": 2.9612369537353516,
|
| 173 |
+
"eval_runtime": 212.7001,
|
| 174 |
+
"eval_samples_per_second": 459.454,
|
| 175 |
+
"eval_steps_per_second": 1.796,
|
| 176 |
+
"step": 6000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.95,
|
| 180 |
+
"learning_rate": 4.5273613738902634e-05,
|
| 181 |
+
"loss": 2.3536,
|
| 182 |
+
"step": 6500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.95,
|
| 186 |
+
"eval_loss": 2.9508631229400635,
|
| 187 |
+
"eval_runtime": 210.803,
|
| 188 |
+
"eval_samples_per_second": 463.589,
|
| 189 |
+
"eval_steps_per_second": 1.812,
|
| 190 |
+
"step": 6500
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 1.02,
|
| 194 |
+
"learning_rate": 4.490976568185126e-05,
|
| 195 |
+
"loss": 2.3392,
|
| 196 |
+
"step": 7000
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 1.02,
|
| 200 |
+
"eval_loss": 2.9288971424102783,
|
| 201 |
+
"eval_runtime": 210.6758,
|
| 202 |
+
"eval_samples_per_second": 463.869,
|
| 203 |
+
"eval_steps_per_second": 1.813,
|
| 204 |
+
"step": 7000
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 1.09,
|
| 208 |
+
"learning_rate": 4.454591762479989e-05,
|
| 209 |
+
"loss": 2.3083,
|
| 210 |
+
"step": 7500
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 1.09,
|
| 214 |
+
"eval_loss": 2.9214062690734863,
|
| 215 |
+
"eval_runtime": 211.6271,
|
| 216 |
+
"eval_samples_per_second": 461.784,
|
| 217 |
+
"eval_steps_per_second": 1.805,
|
| 218 |
+
"step": 7500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 1.16,
|
| 222 |
+
"learning_rate": 4.418206956774851e-05,
|
| 223 |
+
"loss": 2.3094,
|
| 224 |
+
"step": 8000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 1.16,
|
| 228 |
+
"eval_loss": 2.915283441543579,
|
| 229 |
+
"eval_runtime": 210.1146,
|
| 230 |
+
"eval_samples_per_second": 465.108,
|
| 231 |
+
"eval_steps_per_second": 1.818,
|
| 232 |
+
"step": 8000
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 1.24,
|
| 236 |
+
"learning_rate": 4.3818221510697134e-05,
|
| 237 |
+
"loss": 2.2864,
|
| 238 |
+
"step": 8500
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 1.24,
|
| 242 |
+
"eval_loss": 2.903420925140381,
|
| 243 |
+
"eval_runtime": 214.0395,
|
| 244 |
+
"eval_samples_per_second": 456.579,
|
| 245 |
+
"eval_steps_per_second": 1.785,
|
| 246 |
+
"step": 8500
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 1.31,
|
| 250 |
+
"learning_rate": 4.3454373453645755e-05,
|
| 251 |
+
"loss": 2.2893,
|
| 252 |
+
"step": 9000
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 1.31,
|
| 256 |
+
"eval_loss": 2.8963093757629395,
|
| 257 |
+
"eval_runtime": 218.4194,
|
| 258 |
+
"eval_samples_per_second": 447.424,
|
| 259 |
+
"eval_steps_per_second": 1.749,
|
| 260 |
+
"step": 9000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 1.38,
|
| 264 |
+
"learning_rate": 4.3090525396594384e-05,
|
| 265 |
+
"loss": 2.2697,
|
| 266 |
+
"step": 9500
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 1.38,
|
| 270 |
+
"eval_loss": 2.884676456451416,
|
| 271 |
+
"eval_runtime": 207.7625,
|
| 272 |
+
"eval_samples_per_second": 470.374,
|
| 273 |
+
"eval_steps_per_second": 1.839,
|
| 274 |
+
"step": 9500
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 1.46,
|
| 278 |
+
"learning_rate": 4.2726677339543005e-05,
|
| 279 |
+
"loss": 2.2762,
|
| 280 |
+
"step": 10000
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 1.46,
|
| 284 |
+
"eval_loss": 2.866511106491089,
|
| 285 |
+
"eval_runtime": 207.4714,
|
| 286 |
+
"eval_samples_per_second": 471.034,
|
| 287 |
+
"eval_steps_per_second": 1.841,
|
| 288 |
+
"step": 10000
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 1.53,
|
| 292 |
+
"learning_rate": 4.2363556978605734e-05,
|
| 293 |
+
"loss": 2.2667,
|
| 294 |
+
"step": 10500
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 1.53,
|
| 298 |
+
"eval_loss": 2.853637456893921,
|
| 299 |
+
"eval_runtime": 209.4841,
|
| 300 |
+
"eval_samples_per_second": 466.508,
|
| 301 |
+
"eval_steps_per_second": 1.824,
|
| 302 |
+
"step": 10500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 1.6,
|
| 306 |
+
"learning_rate": 4.1999708921554356e-05,
|
| 307 |
+
"loss": 2.2548,
|
| 308 |
+
"step": 11000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 1.6,
|
| 312 |
+
"eval_loss": 2.8472321033477783,
|
| 313 |
+
"eval_runtime": 207.7935,
|
| 314 |
+
"eval_samples_per_second": 470.303,
|
| 315 |
+
"eval_steps_per_second": 1.838,
|
| 316 |
+
"step": 11000
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 1.67,
|
| 320 |
+
"learning_rate": 4.1635860864502984e-05,
|
| 321 |
+
"loss": 2.238,
|
| 322 |
+
"step": 11500
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 1.67,
|
| 326 |
+
"eval_loss": 2.849086284637451,
|
| 327 |
+
"eval_runtime": 207.5183,
|
| 328 |
+
"eval_samples_per_second": 470.927,
|
| 329 |
+
"eval_steps_per_second": 1.841,
|
| 330 |
+
"step": 11500
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 1.75,
|
| 334 |
+
"learning_rate": 4.127201280745161e-05,
|
| 335 |
+
"loss": 2.2423,
|
| 336 |
+
"step": 12000
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 1.75,
|
| 340 |
+
"eval_loss": 2.825746774673462,
|
| 341 |
+
"eval_runtime": 218.1498,
|
| 342 |
+
"eval_samples_per_second": 447.977,
|
| 343 |
+
"eval_steps_per_second": 1.751,
|
| 344 |
+
"step": 12000
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 1.82,
|
| 348 |
+
"learning_rate": 4.0908164750400234e-05,
|
| 349 |
+
"loss": 2.2406,
|
| 350 |
+
"step": 12500
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 1.82,
|
| 354 |
+
"eval_loss": 2.82869029045105,
|
| 355 |
+
"eval_runtime": 208.9781,
|
| 356 |
+
"eval_samples_per_second": 467.637,
|
| 357 |
+
"eval_steps_per_second": 1.828,
|
| 358 |
+
"step": 12500
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 1.89,
|
| 362 |
+
"learning_rate": 4.054431669334886e-05,
|
| 363 |
+
"loss": 2.2248,
|
| 364 |
+
"step": 13000
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 1.89,
|
| 368 |
+
"eval_loss": 2.81931734085083,
|
| 369 |
+
"eval_runtime": 210.3496,
|
| 370 |
+
"eval_samples_per_second": 464.588,
|
| 371 |
+
"eval_steps_per_second": 1.816,
|
| 372 |
+
"step": 13000
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 1.96,
|
| 376 |
+
"learning_rate": 4.0181196332411585e-05,
|
| 377 |
+
"loss": 2.223,
|
| 378 |
+
"step": 13500
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 1.96,
|
| 382 |
+
"eval_loss": 2.810143232345581,
|
| 383 |
+
"eval_runtime": 211.5447,
|
| 384 |
+
"eval_samples_per_second": 461.964,
|
| 385 |
+
"eval_steps_per_second": 1.806,
|
| 386 |
+
"step": 13500
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 2.04,
|
| 390 |
+
"learning_rate": 3.981734827536021e-05,
|
| 391 |
+
"loss": 2.1995,
|
| 392 |
+
"step": 14000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 2.04,
|
| 396 |
+
"eval_loss": 2.802741527557373,
|
| 397 |
+
"eval_runtime": 210.9696,
|
| 398 |
+
"eval_samples_per_second": 463.223,
|
| 399 |
+
"eval_steps_per_second": 1.811,
|
| 400 |
+
"step": 14000
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 2.11,
|
| 404 |
+
"learning_rate": 3.9453500218308835e-05,
|
| 405 |
+
"loss": 2.1834,
|
| 406 |
+
"step": 14500
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 2.11,
|
| 410 |
+
"eval_loss": 2.787959098815918,
|
| 411 |
+
"eval_runtime": 207.5007,
|
| 412 |
+
"eval_samples_per_second": 470.967,
|
| 413 |
+
"eval_steps_per_second": 1.841,
|
| 414 |
+
"step": 14500
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 2.18,
|
| 418 |
+
"learning_rate": 3.908965216125746e-05,
|
| 419 |
+
"loss": 2.1723,
|
| 420 |
+
"step": 15000
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 2.18,
|
| 424 |
+
"eval_loss": 2.778273582458496,
|
| 425 |
+
"eval_runtime": 217.4843,
|
| 426 |
+
"eval_samples_per_second": 449.347,
|
| 427 |
+
"eval_steps_per_second": 1.756,
|
| 428 |
+
"step": 15000
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 2.26,
|
| 432 |
+
"learning_rate": 3.8725804104206085e-05,
|
| 433 |
+
"loss": 2.1651,
|
| 434 |
+
"step": 15500
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 2.26,
|
| 438 |
+
"eval_loss": 2.773916721343994,
|
| 439 |
+
"eval_runtime": 211.3325,
|
| 440 |
+
"eval_samples_per_second": 462.428,
|
| 441 |
+
"eval_steps_per_second": 1.808,
|
| 442 |
+
"step": 15500
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 2.33,
|
| 446 |
+
"learning_rate": 3.836195604715471e-05,
|
| 447 |
+
"loss": 2.1575,
|
| 448 |
+
"step": 16000
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 2.33,
|
| 452 |
+
"eval_loss": 2.782458543777466,
|
| 453 |
+
"eval_runtime": 214.023,
|
| 454 |
+
"eval_samples_per_second": 456.615,
|
| 455 |
+
"eval_steps_per_second": 1.785,
|
| 456 |
+
"step": 16000
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 2.4,
|
| 460 |
+
"learning_rate": 3.7998107990103335e-05,
|
| 461 |
+
"loss": 2.1598,
|
| 462 |
+
"step": 16500
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 2.4,
|
| 466 |
+
"eval_loss": 2.7659904956817627,
|
| 467 |
+
"eval_runtime": 211.2594,
|
| 468 |
+
"eval_samples_per_second": 462.588,
|
| 469 |
+
"eval_steps_per_second": 1.808,
|
| 470 |
+
"step": 16500
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 2.47,
|
| 474 |
+
"learning_rate": 3.7634259933051956e-05,
|
| 475 |
+
"loss": 2.1667,
|
| 476 |
+
"step": 17000
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 2.47,
|
| 480 |
+
"eval_loss": 2.75777530670166,
|
| 481 |
+
"eval_runtime": 209.9442,
|
| 482 |
+
"eval_samples_per_second": 465.486,
|
| 483 |
+
"eval_steps_per_second": 1.82,
|
| 484 |
+
"step": 17000
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 2.55,
|
| 488 |
+
"learning_rate": 3.7271139572114685e-05,
|
| 489 |
+
"loss": 2.1565,
|
| 490 |
+
"step": 17500
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 2.55,
|
| 494 |
+
"eval_loss": 2.757976770401001,
|
| 495 |
+
"eval_runtime": 211.0178,
|
| 496 |
+
"eval_samples_per_second": 463.117,
|
| 497 |
+
"eval_steps_per_second": 1.81,
|
| 498 |
+
"step": 17500
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 2.62,
|
| 502 |
+
"learning_rate": 3.6907291515063314e-05,
|
| 503 |
+
"loss": 2.1558,
|
| 504 |
+
"step": 18000
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 2.62,
|
| 508 |
+
"eval_loss": 2.7561423778533936,
|
| 509 |
+
"eval_runtime": 210.4961,
|
| 510 |
+
"eval_samples_per_second": 464.265,
|
| 511 |
+
"eval_steps_per_second": 1.815,
|
| 512 |
+
"step": 18000
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 2.69,
|
| 516 |
+
"learning_rate": 3.6543443458011935e-05,
|
| 517 |
+
"loss": 2.1642,
|
| 518 |
+
"step": 18500
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 2.69,
|
| 522 |
+
"eval_loss": 2.751215934753418,
|
| 523 |
+
"eval_runtime": 210.4158,
|
| 524 |
+
"eval_samples_per_second": 464.442,
|
| 525 |
+
"eval_steps_per_second": 1.815,
|
| 526 |
+
"step": 18500
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 2.77,
|
| 530 |
+
"learning_rate": 3.617959540096056e-05,
|
| 531 |
+
"loss": 2.1374,
|
| 532 |
+
"step": 19000
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 2.77,
|
| 536 |
+
"eval_loss": 2.736060619354248,
|
| 537 |
+
"eval_runtime": 214.104,
|
| 538 |
+
"eval_samples_per_second": 456.442,
|
| 539 |
+
"eval_steps_per_second": 1.784,
|
| 540 |
+
"step": 19000
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 2.84,
|
| 544 |
+
"learning_rate": 3.5815747343909185e-05,
|
| 545 |
+
"loss": 2.1402,
|
| 546 |
+
"step": 19500
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 2.84,
|
| 550 |
+
"eval_loss": 2.7384564876556396,
|
| 551 |
+
"eval_runtime": 210.1981,
|
| 552 |
+
"eval_samples_per_second": 464.923,
|
| 553 |
+
"eval_steps_per_second": 1.817,
|
| 554 |
+
"step": 19500
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 2.91,
|
| 558 |
+
"learning_rate": 3.545189928685781e-05,
|
| 559 |
+
"loss": 2.1326,
|
| 560 |
+
"step": 20000
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 2.91,
|
| 564 |
+
"eval_loss": 2.723484516143799,
|
| 565 |
+
"eval_runtime": 210.8719,
|
| 566 |
+
"eval_samples_per_second": 463.438,
|
| 567 |
+
"eval_steps_per_second": 1.812,
|
| 568 |
+
"step": 20000
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 2.98,
|
| 572 |
+
"learning_rate": 3.5088051229806435e-05,
|
| 573 |
+
"loss": 2.1272,
|
| 574 |
+
"step": 20500
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 2.98,
|
| 578 |
+
"eval_loss": 2.7183401584625244,
|
| 579 |
+
"eval_runtime": 239.7397,
|
| 580 |
+
"eval_samples_per_second": 407.634,
|
| 581 |
+
"eval_steps_per_second": 1.593,
|
| 582 |
+
"step": 20500
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 3.06,
|
| 586 |
+
"learning_rate": 3.4724203172755057e-05,
|
| 587 |
+
"loss": 2.0954,
|
| 588 |
+
"step": 21000
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 3.06,
|
| 592 |
+
"eval_loss": 2.7156314849853516,
|
| 593 |
+
"eval_runtime": 211.1012,
|
| 594 |
+
"eval_samples_per_second": 462.934,
|
| 595 |
+
"eval_steps_per_second": 1.81,
|
| 596 |
+
"step": 21000
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 3.13,
|
| 600 |
+
"learning_rate": 3.4360355115703685e-05,
|
| 601 |
+
"loss": 2.0842,
|
| 602 |
+
"step": 21500
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 3.13,
|
| 606 |
+
"eval_loss": 2.7065327167510986,
|
| 607 |
+
"eval_runtime": 210.8515,
|
| 608 |
+
"eval_samples_per_second": 463.483,
|
| 609 |
+
"eval_steps_per_second": 1.812,
|
| 610 |
+
"step": 21500
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 3.2,
|
| 614 |
+
"learning_rate": 3.399650705865231e-05,
|
| 615 |
+
"loss": 2.0859,
|
| 616 |
+
"step": 22000
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 3.2,
|
| 620 |
+
"eval_loss": 2.7088747024536133,
|
| 621 |
+
"eval_runtime": 215.2076,
|
| 622 |
+
"eval_samples_per_second": 454.101,
|
| 623 |
+
"eval_steps_per_second": 1.775,
|
| 624 |
+
"step": 22000
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 3.27,
|
| 628 |
+
"learning_rate": 3.3632659001600935e-05,
|
| 629 |
+
"loss": 2.0856,
|
| 630 |
+
"step": 22500
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 3.27,
|
| 634 |
+
"eval_loss": 2.6962101459503174,
|
| 635 |
+
"eval_runtime": 210.6214,
|
| 636 |
+
"eval_samples_per_second": 463.989,
|
| 637 |
+
"eval_steps_per_second": 1.814,
|
| 638 |
+
"step": 22500
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 3.35,
|
| 642 |
+
"learning_rate": 3.3268810944549556e-05,
|
| 643 |
+
"loss": 2.0775,
|
| 644 |
+
"step": 23000
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 3.35,
|
| 648 |
+
"eval_loss": 2.693091630935669,
|
| 649 |
+
"eval_runtime": 210.6882,
|
| 650 |
+
"eval_samples_per_second": 463.842,
|
| 651 |
+
"eval_steps_per_second": 1.813,
|
| 652 |
+
"step": 23000
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 3.42,
|
| 656 |
+
"learning_rate": 3.2905690583612286e-05,
|
| 657 |
+
"loss": 2.0821,
|
| 658 |
+
"step": 23500
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 3.42,
|
| 662 |
+
"eval_loss": 2.693345069885254,
|
| 663 |
+
"eval_runtime": 217.6654,
|
| 664 |
+
"eval_samples_per_second": 448.973,
|
| 665 |
+
"eval_steps_per_second": 1.755,
|
| 666 |
+
"step": 23500
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 3.49,
|
| 670 |
+
"learning_rate": 3.2541842526560914e-05,
|
| 671 |
+
"loss": 2.0706,
|
| 672 |
+
"step": 24000
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 3.49,
|
| 676 |
+
"eval_loss": 2.70108699798584,
|
| 677 |
+
"eval_runtime": 210.1763,
|
| 678 |
+
"eval_samples_per_second": 464.971,
|
| 679 |
+
"eval_steps_per_second": 1.818,
|
| 680 |
+
"step": 24000
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 3.57,
|
| 684 |
+
"learning_rate": 3.2177994469509535e-05,
|
| 685 |
+
"loss": 2.0689,
|
| 686 |
+
"step": 24500
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 3.57,
|
| 690 |
+
"eval_loss": 2.7009191513061523,
|
| 691 |
+
"eval_runtime": 207.9861,
|
| 692 |
+
"eval_samples_per_second": 469.868,
|
| 693 |
+
"eval_steps_per_second": 1.837,
|
| 694 |
+
"step": 24500
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 3.64,
|
| 698 |
+
"learning_rate": 3.181414641245816e-05,
|
| 699 |
+
"loss": 2.0807,
|
| 700 |
+
"step": 25000
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 3.64,
|
| 704 |
+
"eval_loss": 2.682542324066162,
|
| 705 |
+
"eval_runtime": 214.5749,
|
| 706 |
+
"eval_samples_per_second": 455.44,
|
| 707 |
+
"eval_steps_per_second": 1.78,
|
| 708 |
+
"step": 25000
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 3.71,
|
| 712 |
+
"learning_rate": 3.1450298355406785e-05,
|
| 713 |
+
"loss": 2.0639,
|
| 714 |
+
"step": 25500
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 3.71,
|
| 718 |
+
"eval_loss": 2.674436330795288,
|
| 719 |
+
"eval_runtime": 245.508,
|
| 720 |
+
"eval_samples_per_second": 398.056,
|
| 721 |
+
"eval_steps_per_second": 1.556,
|
| 722 |
+
"step": 25500
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 3.78,
|
| 726 |
+
"learning_rate": 3.108645029835541e-05,
|
| 727 |
+
"loss": 2.0742,
|
| 728 |
+
"step": 26000
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 3.78,
|
| 732 |
+
"eval_loss": 2.677746295928955,
|
| 733 |
+
"eval_runtime": 245.3374,
|
| 734 |
+
"eval_samples_per_second": 398.333,
|
| 735 |
+
"eval_steps_per_second": 1.557,
|
| 736 |
+
"step": 26000
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 3.86,
|
| 740 |
+
"learning_rate": 3.0722602241304035e-05,
|
| 741 |
+
"loss": 2.0789,
|
| 742 |
+
"step": 26500
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 3.86,
|
| 746 |
+
"eval_loss": 2.6688921451568604,
|
| 747 |
+
"eval_runtime": 246.4423,
|
| 748 |
+
"eval_samples_per_second": 396.547,
|
| 749 |
+
"eval_steps_per_second": 1.55,
|
| 750 |
+
"step": 26500
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 3.93,
|
| 754 |
+
"learning_rate": 3.0359481880366758e-05,
|
| 755 |
+
"loss": 2.0594,
|
| 756 |
+
"step": 27000
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 3.93,
|
| 760 |
+
"eval_loss": 2.6566038131713867,
|
| 761 |
+
"eval_runtime": 252.2995,
|
| 762 |
+
"eval_samples_per_second": 387.341,
|
| 763 |
+
"eval_steps_per_second": 1.514,
|
| 764 |
+
"step": 27000
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 4.0,
|
| 768 |
+
"learning_rate": 2.9995633823315383e-05,
|
| 769 |
+
"loss": 2.056,
|
| 770 |
+
"step": 27500
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 4.0,
|
| 774 |
+
"eval_loss": 2.667599678039551,
|
| 775 |
+
"eval_runtime": 245.2202,
|
| 776 |
+
"eval_samples_per_second": 398.523,
|
| 777 |
+
"eval_steps_per_second": 1.558,
|
| 778 |
+
"step": 27500
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 4.08,
|
| 782 |
+
"learning_rate": 2.9631785766264007e-05,
|
| 783 |
+
"loss": 2.0223,
|
| 784 |
+
"step": 28000
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 4.08,
|
| 788 |
+
"eval_loss": 2.6711361408233643,
|
| 789 |
+
"eval_runtime": 245.2433,
|
| 790 |
+
"eval_samples_per_second": 398.486,
|
| 791 |
+
"eval_steps_per_second": 1.558,
|
| 792 |
+
"step": 28000
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 4.15,
|
| 796 |
+
"learning_rate": 2.9267937709212632e-05,
|
| 797 |
+
"loss": 2.0185,
|
| 798 |
+
"step": 28500
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 4.15,
|
| 802 |
+
"eval_loss": 2.65678071975708,
|
| 803 |
+
"eval_runtime": 208.848,
|
| 804 |
+
"eval_samples_per_second": 467.929,
|
| 805 |
+
"eval_steps_per_second": 1.829,
|
| 806 |
+
"step": 28500
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 4.22,
|
| 810 |
+
"learning_rate": 2.890408965216126e-05,
|
| 811 |
+
"loss": 2.018,
|
| 812 |
+
"step": 29000
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 4.22,
|
| 816 |
+
"eval_loss": 2.656717538833618,
|
| 817 |
+
"eval_runtime": 209.2801,
|
| 818 |
+
"eval_samples_per_second": 466.963,
|
| 819 |
+
"eval_steps_per_second": 1.825,
|
| 820 |
+
"step": 29000
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 4.29,
|
| 824 |
+
"learning_rate": 2.8540241595109886e-05,
|
| 825 |
+
"loss": 2.0036,
|
| 826 |
+
"step": 29500
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 4.29,
|
| 830 |
+
"eval_loss": 2.6545379161834717,
|
| 831 |
+
"eval_runtime": 210.0273,
|
| 832 |
+
"eval_samples_per_second": 465.301,
|
| 833 |
+
"eval_steps_per_second": 1.819,
|
| 834 |
+
"step": 29500
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 4.37,
|
| 838 |
+
"learning_rate": 2.817639353805851e-05,
|
| 839 |
+
"loss": 2.0238,
|
| 840 |
+
"step": 30000
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 4.37,
|
| 844 |
+
"eval_loss": 2.6558964252471924,
|
| 845 |
+
"eval_runtime": 211.3486,
|
| 846 |
+
"eval_samples_per_second": 462.392,
|
| 847 |
+
"eval_steps_per_second": 1.807,
|
| 848 |
+
"step": 30000
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 4.44,
|
| 852 |
+
"learning_rate": 2.781472856934944e-05,
|
| 853 |
+
"loss": 2.0091,
|
| 854 |
+
"step": 30500
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 4.44,
|
| 858 |
+
"eval_loss": 2.6450281143188477,
|
| 859 |
+
"eval_runtime": 208.486,
|
| 860 |
+
"eval_samples_per_second": 468.741,
|
| 861 |
+
"eval_steps_per_second": 1.832,
|
| 862 |
+
"step": 30500
|
| 863 |
+
},
|
| 864 |
+
{
|
| 865 |
+
"epoch": 4.51,
|
| 866 |
+
"learning_rate": 2.7450880512298066e-05,
|
| 867 |
+
"loss": 2.0096,
|
| 868 |
+
"step": 31000
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 4.51,
|
| 872 |
+
"eval_loss": 2.6388843059539795,
|
| 873 |
+
"eval_runtime": 210.8413,
|
| 874 |
+
"eval_samples_per_second": 463.505,
|
| 875 |
+
"eval_steps_per_second": 1.812,
|
| 876 |
+
"step": 31000
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 4.58,
|
| 880 |
+
"learning_rate": 2.708703245524669e-05,
|
| 881 |
+
"loss": 2.0083,
|
| 882 |
+
"step": 31500
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 4.58,
|
| 886 |
+
"eval_loss": 2.6401255130767822,
|
| 887 |
+
"eval_runtime": 213.1597,
|
| 888 |
+
"eval_samples_per_second": 458.464,
|
| 889 |
+
"eval_steps_per_second": 1.792,
|
| 890 |
+
"step": 31500
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 4.66,
|
| 894 |
+
"learning_rate": 2.6723184398195316e-05,
|
| 895 |
+
"loss": 2.0012,
|
| 896 |
+
"step": 32000
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 4.66,
|
| 900 |
+
"eval_loss": 2.639948844909668,
|
| 901 |
+
"eval_runtime": 234.1271,
|
| 902 |
+
"eval_samples_per_second": 417.406,
|
| 903 |
+
"eval_steps_per_second": 1.632,
|
| 904 |
+
"step": 32000
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 4.73,
|
| 908 |
+
"learning_rate": 2.635933634114394e-05,
|
| 909 |
+
"loss": 2.0166,
|
| 910 |
+
"step": 32500
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 4.73,
|
| 914 |
+
"eval_loss": 2.628899097442627,
|
| 915 |
+
"eval_runtime": 242.1039,
|
| 916 |
+
"eval_samples_per_second": 403.653,
|
| 917 |
+
"eval_steps_per_second": 1.578,
|
| 918 |
+
"step": 32500
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 4.8,
|
| 922 |
+
"learning_rate": 2.5995488284092563e-05,
|
| 923 |
+
"loss": 1.9963,
|
| 924 |
+
"step": 33000
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 4.8,
|
| 928 |
+
"eval_loss": 2.634817361831665,
|
| 929 |
+
"eval_runtime": 275.7387,
|
| 930 |
+
"eval_samples_per_second": 354.415,
|
| 931 |
+
"eval_steps_per_second": 1.385,
|
| 932 |
+
"step": 33000
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 4.88,
|
| 936 |
+
"learning_rate": 2.5631640227041188e-05,
|
| 937 |
+
"loss": 1.9943,
|
| 938 |
+
"step": 33500
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 4.88,
|
| 942 |
+
"eval_loss": 2.6239511966705322,
|
| 943 |
+
"eval_runtime": 223.4038,
|
| 944 |
+
"eval_samples_per_second": 437.441,
|
| 945 |
+
"eval_steps_per_second": 1.71,
|
| 946 |
+
"step": 33500
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 4.95,
|
| 950 |
+
"learning_rate": 2.5267792169989813e-05,
|
| 951 |
+
"loss": 2.0099,
|
| 952 |
+
"step": 34000
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"epoch": 4.95,
|
| 956 |
+
"eval_loss": 2.618997812271118,
|
| 957 |
+
"eval_runtime": 215.7939,
|
| 958 |
+
"eval_samples_per_second": 452.867,
|
| 959 |
+
"eval_steps_per_second": 1.77,
|
| 960 |
+
"step": 34000
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 5.02,
|
| 964 |
+
"learning_rate": 2.4903944112938438e-05,
|
| 965 |
+
"loss": 1.9895,
|
| 966 |
+
"step": 34500
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"epoch": 5.02,
|
| 970 |
+
"eval_loss": 2.630808115005493,
|
| 971 |
+
"eval_runtime": 235.2775,
|
| 972 |
+
"eval_samples_per_second": 415.365,
|
| 973 |
+
"eval_steps_per_second": 1.624,
|
| 974 |
+
"step": 34500
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 5.09,
|
| 978 |
+
"learning_rate": 2.4540096055887063e-05,
|
| 979 |
+
"loss": 1.9581,
|
| 980 |
+
"step": 35000
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 5.09,
|
| 984 |
+
"eval_loss": 2.638457775115967,
|
| 985 |
+
"eval_runtime": 232.5729,
|
| 986 |
+
"eval_samples_per_second": 420.195,
|
| 987 |
+
"eval_steps_per_second": 1.642,
|
| 988 |
+
"step": 35000
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 5.17,
|
| 992 |
+
"learning_rate": 2.4176247998835687e-05,
|
| 993 |
+
"loss": 1.9502,
|
| 994 |
+
"step": 35500
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"epoch": 5.17,
|
| 998 |
+
"eval_loss": 2.6236515045166016,
|
| 999 |
+
"eval_runtime": 233.0168,
|
| 1000 |
+
"eval_samples_per_second": 419.395,
|
| 1001 |
+
"eval_steps_per_second": 1.639,
|
| 1002 |
+
"step": 35500
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 5.24,
|
| 1006 |
+
"learning_rate": 2.3812399941784312e-05,
|
| 1007 |
+
"loss": 1.9485,
|
| 1008 |
+
"step": 36000
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 5.24,
|
| 1012 |
+
"eval_loss": 2.624785900115967,
|
| 1013 |
+
"eval_runtime": 246.6057,
|
| 1014 |
+
"eval_samples_per_second": 396.284,
|
| 1015 |
+
"eval_steps_per_second": 1.549,
|
| 1016 |
+
"step": 36000
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 5.31,
|
| 1020 |
+
"learning_rate": 2.3448551884732937e-05,
|
| 1021 |
+
"loss": 1.9643,
|
| 1022 |
+
"step": 36500
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 5.31,
|
| 1026 |
+
"eval_loss": 2.627931833267212,
|
| 1027 |
+
"eval_runtime": 212.8412,
|
| 1028 |
+
"eval_samples_per_second": 459.15,
|
| 1029 |
+
"eval_steps_per_second": 1.795,
|
| 1030 |
+
"step": 36500
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"epoch": 5.38,
|
| 1034 |
+
"learning_rate": 2.3084703827681562e-05,
|
| 1035 |
+
"loss": 1.9535,
|
| 1036 |
+
"step": 37000
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 5.38,
|
| 1040 |
+
"eval_loss": 2.6185333728790283,
|
| 1041 |
+
"eval_runtime": 210.7296,
|
| 1042 |
+
"eval_samples_per_second": 463.751,
|
| 1043 |
+
"eval_steps_per_second": 1.813,
|
| 1044 |
+
"step": 37000
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 5.46,
|
| 1048 |
+
"learning_rate": 2.2720855770630187e-05,
|
| 1049 |
+
"loss": 1.9575,
|
| 1050 |
+
"step": 37500
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 5.46,
|
| 1054 |
+
"eval_loss": 2.614642381668091,
|
| 1055 |
+
"eval_runtime": 211.3001,
|
| 1056 |
+
"eval_samples_per_second": 462.499,
|
| 1057 |
+
"eval_steps_per_second": 1.808,
|
| 1058 |
+
"step": 37500
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 5.53,
|
| 1062 |
+
"learning_rate": 2.235700771357881e-05,
|
| 1063 |
+
"loss": 1.9475,
|
| 1064 |
+
"step": 38000
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 5.53,
|
| 1068 |
+
"eval_loss": 2.6092729568481445,
|
| 1069 |
+
"eval_runtime": 212.2513,
|
| 1070 |
+
"eval_samples_per_second": 460.426,
|
| 1071 |
+
"eval_steps_per_second": 1.8,
|
| 1072 |
+
"step": 38000
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 5.6,
|
| 1076 |
+
"learning_rate": 2.1993159656527434e-05,
|
| 1077 |
+
"loss": 1.9434,
|
| 1078 |
+
"step": 38500
|
| 1079 |
+
},
|
| 1080 |
+
{
|
| 1081 |
+
"epoch": 5.6,
|
| 1082 |
+
"eval_loss": 2.60904598236084,
|
| 1083 |
+
"eval_runtime": 209.1736,
|
| 1084 |
+
"eval_samples_per_second": 467.2,
|
| 1085 |
+
"eval_steps_per_second": 1.826,
|
| 1086 |
+
"step": 38500
|
| 1087 |
+
},
|
| 1088 |
+
{
|
| 1089 |
+
"epoch": 5.68,
|
| 1090 |
+
"learning_rate": 2.1630039295590163e-05,
|
| 1091 |
+
"loss": 1.954,
|
| 1092 |
+
"step": 39000
|
| 1093 |
+
},
|
| 1094 |
+
{
|
| 1095 |
+
"epoch": 5.68,
|
| 1096 |
+
"eval_loss": 2.60274338722229,
|
| 1097 |
+
"eval_runtime": 223.8437,
|
| 1098 |
+
"eval_samples_per_second": 436.581,
|
| 1099 |
+
"eval_steps_per_second": 1.707,
|
| 1100 |
+
"step": 39000
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 5.75,
|
| 1104 |
+
"learning_rate": 2.1266191238538788e-05,
|
| 1105 |
+
"loss": 1.9509,
|
| 1106 |
+
"step": 39500
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 5.75,
|
| 1110 |
+
"eval_loss": 2.6107161045074463,
|
| 1111 |
+
"eval_runtime": 213.2878,
|
| 1112 |
+
"eval_samples_per_second": 458.188,
|
| 1113 |
+
"eval_steps_per_second": 1.791,
|
| 1114 |
+
"step": 39500
|
| 1115 |
+
},
|
| 1116 |
+
{
|
| 1117 |
+
"epoch": 5.82,
|
| 1118 |
+
"learning_rate": 2.0902343181487413e-05,
|
| 1119 |
+
"loss": 1.9454,
|
| 1120 |
+
"step": 40000
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"epoch": 5.82,
|
| 1124 |
+
"eval_loss": 2.59796142578125,
|
| 1125 |
+
"eval_runtime": 214.4371,
|
| 1126 |
+
"eval_samples_per_second": 455.733,
|
| 1127 |
+
"eval_steps_per_second": 1.781,
|
| 1128 |
+
"step": 40000
|
| 1129 |
+
},
|
| 1130 |
+
{
|
| 1131 |
+
"epoch": 5.89,
|
| 1132 |
+
"learning_rate": 2.053922282055014e-05,
|
| 1133 |
+
"loss": 1.9479,
|
| 1134 |
+
"step": 40500
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 5.89,
|
| 1138 |
+
"eval_loss": 2.6016438007354736,
|
| 1139 |
+
"eval_runtime": 218.6403,
|
| 1140 |
+
"eval_samples_per_second": 446.972,
|
| 1141 |
+
"eval_steps_per_second": 1.747,
|
| 1142 |
+
"step": 40500
|
| 1143 |
+
},
|
| 1144 |
+
{
|
| 1145 |
+
"epoch": 5.97,
|
| 1146 |
+
"learning_rate": 2.0175374763498764e-05,
|
| 1147 |
+
"loss": 1.9539,
|
| 1148 |
+
"step": 41000
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 5.97,
|
| 1152 |
+
"eval_loss": 2.5970652103424072,
|
| 1153 |
+
"eval_runtime": 214.0818,
|
| 1154 |
+
"eval_samples_per_second": 456.489,
|
| 1155 |
+
"eval_steps_per_second": 1.784,
|
| 1156 |
+
"step": 41000
|
| 1157 |
+
},
|
| 1158 |
+
{
|
| 1159 |
+
"epoch": 6.04,
|
| 1160 |
+
"learning_rate": 1.981152670644739e-05,
|
| 1161 |
+
"loss": 1.9119,
|
| 1162 |
+
"step": 41500
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 6.04,
|
| 1166 |
+
"eval_loss": 2.622750759124756,
|
| 1167 |
+
"eval_runtime": 211.471,
|
| 1168 |
+
"eval_samples_per_second": 462.125,
|
| 1169 |
+
"eval_steps_per_second": 1.806,
|
| 1170 |
+
"step": 41500
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 6.11,
|
| 1174 |
+
"learning_rate": 1.9447678649396013e-05,
|
| 1175 |
+
"loss": 1.8974,
|
| 1176 |
+
"step": 42000
|
| 1177 |
+
},
|
| 1178 |
+
{
|
| 1179 |
+
"epoch": 6.11,
|
| 1180 |
+
"eval_loss": 2.6169052124023438,
|
| 1181 |
+
"eval_runtime": 221.6976,
|
| 1182 |
+
"eval_samples_per_second": 440.808,
|
| 1183 |
+
"eval_steps_per_second": 1.723,
|
| 1184 |
+
"step": 42000
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 6.19,
|
| 1188 |
+
"learning_rate": 1.908383059234464e-05,
|
| 1189 |
+
"loss": 1.9038,
|
| 1190 |
+
"step": 42500
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"epoch": 6.19,
|
| 1194 |
+
"eval_loss": 2.6027112007141113,
|
| 1195 |
+
"eval_runtime": 212.7185,
|
| 1196 |
+
"eval_samples_per_second": 459.415,
|
| 1197 |
+
"eval_steps_per_second": 1.796,
|
| 1198 |
+
"step": 42500
|
| 1199 |
+
},
|
| 1200 |
+
{
|
| 1201 |
+
"epoch": 6.26,
|
| 1202 |
+
"learning_rate": 1.8719982535293263e-05,
|
| 1203 |
+
"loss": 1.9008,
|
| 1204 |
+
"step": 43000
|
| 1205 |
+
},
|
| 1206 |
+
{
|
| 1207 |
+
"epoch": 6.26,
|
| 1208 |
+
"eval_loss": 2.602651357650757,
|
| 1209 |
+
"eval_runtime": 212.6929,
|
| 1210 |
+
"eval_samples_per_second": 459.47,
|
| 1211 |
+
"eval_steps_per_second": 1.796,
|
| 1212 |
+
"step": 43000
|
| 1213 |
+
},
|
| 1214 |
+
{
|
| 1215 |
+
"epoch": 6.33,
|
| 1216 |
+
"learning_rate": 1.8356134478241888e-05,
|
| 1217 |
+
"loss": 1.9142,
|
| 1218 |
+
"step": 43500
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 6.33,
|
| 1222 |
+
"eval_loss": 2.6011383533477783,
|
| 1223 |
+
"eval_runtime": 217.9682,
|
| 1224 |
+
"eval_samples_per_second": 448.35,
|
| 1225 |
+
"eval_steps_per_second": 1.753,
|
| 1226 |
+
"step": 43500
|
| 1227 |
+
},
|
| 1228 |
+
{
|
| 1229 |
+
"epoch": 6.4,
|
| 1230 |
+
"learning_rate": 1.7992286421190513e-05,
|
| 1231 |
+
"loss": 1.8783,
|
| 1232 |
+
"step": 44000
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 6.4,
|
| 1236 |
+
"eval_loss": 2.595999002456665,
|
| 1237 |
+
"eval_runtime": 216.5321,
|
| 1238 |
+
"eval_samples_per_second": 451.323,
|
| 1239 |
+
"eval_steps_per_second": 1.764,
|
| 1240 |
+
"step": 44000
|
| 1241 |
+
},
|
| 1242 |
+
{
|
| 1243 |
+
"epoch": 6.48,
|
| 1244 |
+
"learning_rate": 1.7628438364139135e-05,
|
| 1245 |
+
"loss": 1.8896,
|
| 1246 |
+
"step": 44500
|
| 1247 |
+
},
|
| 1248 |
+
{
|
| 1249 |
+
"epoch": 6.48,
|
| 1250 |
+
"eval_loss": 2.6111366748809814,
|
| 1251 |
+
"eval_runtime": 209.5809,
|
| 1252 |
+
"eval_samples_per_second": 466.293,
|
| 1253 |
+
"eval_steps_per_second": 1.823,
|
| 1254 |
+
"step": 44500
|
| 1255 |
+
},
|
| 1256 |
+
{
|
| 1257 |
+
"epoch": 6.55,
|
| 1258 |
+
"learning_rate": 1.7265318003201864e-05,
|
| 1259 |
+
"loss": 1.8975,
|
| 1260 |
+
"step": 45000
|
| 1261 |
+
},
|
| 1262 |
+
{
|
| 1263 |
+
"epoch": 6.55,
|
| 1264 |
+
"eval_loss": 2.588871955871582,
|
| 1265 |
+
"eval_runtime": 215.4187,
|
| 1266 |
+
"eval_samples_per_second": 453.656,
|
| 1267 |
+
"eval_steps_per_second": 1.773,
|
| 1268 |
+
"step": 45000
|
| 1269 |
+
},
|
| 1270 |
+
{
|
| 1271 |
+
"epoch": 6.62,
|
| 1272 |
+
"learning_rate": 1.690146994615049e-05,
|
| 1273 |
+
"loss": 1.9048,
|
| 1274 |
+
"step": 45500
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 6.62,
|
| 1278 |
+
"eval_loss": 2.600691556930542,
|
| 1279 |
+
"eval_runtime": 225.7312,
|
| 1280 |
+
"eval_samples_per_second": 432.931,
|
| 1281 |
+
"eval_steps_per_second": 1.692,
|
| 1282 |
+
"step": 45500
|
| 1283 |
+
},
|
| 1284 |
+
{
|
| 1285 |
+
"epoch": 6.69,
|
| 1286 |
+
"learning_rate": 1.6537621889099114e-05,
|
| 1287 |
+
"loss": 1.9049,
|
| 1288 |
+
"step": 46000
|
| 1289 |
+
},
|
| 1290 |
+
{
|
| 1291 |
+
"epoch": 6.69,
|
| 1292 |
+
"eval_loss": 2.5971837043762207,
|
| 1293 |
+
"eval_runtime": 213.1258,
|
| 1294 |
+
"eval_samples_per_second": 458.537,
|
| 1295 |
+
"eval_steps_per_second": 1.792,
|
| 1296 |
+
"step": 46000
|
| 1297 |
+
},
|
| 1298 |
+
{
|
| 1299 |
+
"epoch": 6.77,
|
| 1300 |
+
"learning_rate": 1.6173773832047735e-05,
|
| 1301 |
+
"loss": 1.8969,
|
| 1302 |
+
"step": 46500
|
| 1303 |
+
},
|
| 1304 |
+
{
|
| 1305 |
+
"epoch": 6.77,
|
| 1306 |
+
"eval_loss": 2.605257987976074,
|
| 1307 |
+
"eval_runtime": 212.2604,
|
| 1308 |
+
"eval_samples_per_second": 460.406,
|
| 1309 |
+
"eval_steps_per_second": 1.8,
|
| 1310 |
+
"step": 46500
|
| 1311 |
+
},
|
| 1312 |
+
{
|
| 1313 |
+
"epoch": 6.84,
|
| 1314 |
+
"learning_rate": 1.580992577499636e-05,
|
| 1315 |
+
"loss": 1.9105,
|
| 1316 |
+
"step": 47000
|
| 1317 |
+
},
|
| 1318 |
+
{
|
| 1319 |
+
"epoch": 6.84,
|
| 1320 |
+
"eval_loss": 2.589334726333618,
|
| 1321 |
+
"eval_runtime": 211.6138,
|
| 1322 |
+
"eval_samples_per_second": 461.813,
|
| 1323 |
+
"eval_steps_per_second": 1.805,
|
| 1324 |
+
"step": 47000
|
| 1325 |
+
},
|
| 1326 |
+
{
|
| 1327 |
+
"epoch": 6.91,
|
| 1328 |
+
"learning_rate": 1.544680541405909e-05,
|
| 1329 |
+
"loss": 1.8921,
|
| 1330 |
+
"step": 47500
|
| 1331 |
+
},
|
| 1332 |
+
{
|
| 1333 |
+
"epoch": 6.91,
|
| 1334 |
+
"eval_loss": 2.5882816314697266,
|
| 1335 |
+
"eval_runtime": 211.2215,
|
| 1336 |
+
"eval_samples_per_second": 462.671,
|
| 1337 |
+
"eval_steps_per_second": 1.809,
|
| 1338 |
+
"step": 47500
|
| 1339 |
+
},
|
| 1340 |
+
{
|
| 1341 |
+
"epoch": 6.99,
|
| 1342 |
+
"learning_rate": 1.5083685053121819e-05,
|
| 1343 |
+
"loss": 1.8918,
|
| 1344 |
+
"step": 48000
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 6.99,
|
| 1348 |
+
"eval_loss": 2.5792043209075928,
|
| 1349 |
+
"eval_runtime": 211.5529,
|
| 1350 |
+
"eval_samples_per_second": 461.946,
|
| 1351 |
+
"eval_steps_per_second": 1.806,
|
| 1352 |
+
"step": 48000
|
| 1353 |
+
},
|
| 1354 |
+
{
|
| 1355 |
+
"epoch": 7.06,
|
| 1356 |
+
"learning_rate": 1.471983699607044e-05,
|
| 1357 |
+
"loss": 1.8671,
|
| 1358 |
+
"step": 48500
|
| 1359 |
+
},
|
| 1360 |
+
{
|
| 1361 |
+
"epoch": 7.06,
|
| 1362 |
+
"eval_loss": 2.604069232940674,
|
| 1363 |
+
"eval_runtime": 212.2008,
|
| 1364 |
+
"eval_samples_per_second": 460.536,
|
| 1365 |
+
"eval_steps_per_second": 1.8,
|
| 1366 |
+
"step": 48500
|
| 1367 |
+
},
|
| 1368 |
+
{
|
| 1369 |
+
"epoch": 7.13,
|
| 1370 |
+
"learning_rate": 1.4355988939019067e-05,
|
| 1371 |
+
"loss": 1.8551,
|
| 1372 |
+
"step": 49000
|
| 1373 |
+
},
|
| 1374 |
+
{
|
| 1375 |
+
"epoch": 7.13,
|
| 1376 |
+
"eval_loss": 2.6070237159729004,
|
| 1377 |
+
"eval_runtime": 220.205,
|
| 1378 |
+
"eval_samples_per_second": 443.795,
|
| 1379 |
+
"eval_steps_per_second": 1.735,
|
| 1380 |
+
"step": 49000
|
| 1381 |
+
},
|
| 1382 |
+
{
|
| 1383 |
+
"epoch": 7.2,
|
| 1384 |
+
"learning_rate": 1.3992140881967692e-05,
|
| 1385 |
+
"loss": 1.8555,
|
| 1386 |
+
"step": 49500
|
| 1387 |
+
},
|
| 1388 |
+
{
|
| 1389 |
+
"epoch": 7.2,
|
| 1390 |
+
"eval_loss": 2.614821434020996,
|
| 1391 |
+
"eval_runtime": 263.5514,
|
| 1392 |
+
"eval_samples_per_second": 370.804,
|
| 1393 |
+
"eval_steps_per_second": 1.449,
|
| 1394 |
+
"step": 49500
|
| 1395 |
+
},
|
| 1396 |
+
{
|
| 1397 |
+
"epoch": 7.28,
|
| 1398 |
+
"learning_rate": 1.3628292824916317e-05,
|
| 1399 |
+
"loss": 1.8543,
|
| 1400 |
+
"step": 50000
|
| 1401 |
+
},
|
| 1402 |
+
{
|
| 1403 |
+
"epoch": 7.28,
|
| 1404 |
+
"eval_loss": 2.607656955718994,
|
| 1405 |
+
"eval_runtime": 264.5295,
|
| 1406 |
+
"eval_samples_per_second": 369.433,
|
| 1407 |
+
"eval_steps_per_second": 1.444,
|
| 1408 |
+
"step": 50000
|
| 1409 |
+
},
|
| 1410 |
+
{
|
| 1411 |
+
"epoch": 7.35,
|
| 1412 |
+
"learning_rate": 1.326444476786494e-05,
|
| 1413 |
+
"loss": 1.8485,
|
| 1414 |
+
"step": 50500
|
| 1415 |
+
},
|
| 1416 |
+
{
|
| 1417 |
+
"epoch": 7.35,
|
| 1418 |
+
"eval_loss": 2.613083839416504,
|
| 1419 |
+
"eval_runtime": 263.0661,
|
| 1420 |
+
"eval_samples_per_second": 371.488,
|
| 1421 |
+
"eval_steps_per_second": 1.452,
|
| 1422 |
+
"step": 50500
|
| 1423 |
+
},
|
| 1424 |
+
{
|
| 1425 |
+
"epoch": 7.42,
|
| 1426 |
+
"learning_rate": 1.2900596710813565e-05,
|
| 1427 |
+
"loss": 1.8474,
|
| 1428 |
+
"step": 51000
|
| 1429 |
+
},
|
| 1430 |
+
{
|
| 1431 |
+
"epoch": 7.42,
|
| 1432 |
+
"eval_loss": 2.603851079940796,
|
| 1433 |
+
"eval_runtime": 285.6161,
|
| 1434 |
+
"eval_samples_per_second": 342.159,
|
| 1435 |
+
"eval_steps_per_second": 1.337,
|
| 1436 |
+
"step": 51000
|
| 1437 |
+
},
|
| 1438 |
+
{
|
| 1439 |
+
"epoch": 7.5,
|
| 1440 |
+
"learning_rate": 1.253674865376219e-05,
|
| 1441 |
+
"loss": 1.8474,
|
| 1442 |
+
"step": 51500
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 7.5,
|
| 1446 |
+
"eval_loss": 2.5973451137542725,
|
| 1447 |
+
"eval_runtime": 273.9949,
|
| 1448 |
+
"eval_samples_per_second": 356.671,
|
| 1449 |
+
"eval_steps_per_second": 1.394,
|
| 1450 |
+
"step": 51500
|
| 1451 |
+
},
|
| 1452 |
+
{
|
| 1453 |
+
"epoch": 7.57,
|
| 1454 |
+
"learning_rate": 1.2172900596710813e-05,
|
| 1455 |
+
"loss": 1.8442,
|
| 1456 |
+
"step": 52000
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 7.57,
|
| 1460 |
+
"eval_loss": 2.5946028232574463,
|
| 1461 |
+
"eval_runtime": 244.7175,
|
| 1462 |
+
"eval_samples_per_second": 399.342,
|
| 1463 |
+
"eval_steps_per_second": 1.561,
|
| 1464 |
+
"step": 52000
|
| 1465 |
+
},
|
| 1466 |
+
{
|
| 1467 |
+
"epoch": 7.64,
|
| 1468 |
+
"learning_rate": 1.1809780235773542e-05,
|
| 1469 |
+
"loss": 1.8329,
|
| 1470 |
+
"step": 52500
|
| 1471 |
+
},
|
| 1472 |
+
{
|
| 1473 |
+
"epoch": 7.64,
|
| 1474 |
+
"eval_loss": 2.606858253479004,
|
| 1475 |
+
"eval_runtime": 275.6967,
|
| 1476 |
+
"eval_samples_per_second": 354.469,
|
| 1477 |
+
"eval_steps_per_second": 1.386,
|
| 1478 |
+
"step": 52500
|
| 1479 |
+
},
|
| 1480 |
+
{
|
| 1481 |
+
"epoch": 7.71,
|
| 1482 |
+
"learning_rate": 1.1445932178722165e-05,
|
| 1483 |
+
"loss": 1.8551,
|
| 1484 |
+
"step": 53000
|
| 1485 |
+
},
|
| 1486 |
+
{
|
| 1487 |
+
"epoch": 7.71,
|
| 1488 |
+
"eval_loss": 2.592348337173462,
|
| 1489 |
+
"eval_runtime": 253.7347,
|
| 1490 |
+
"eval_samples_per_second": 385.15,
|
| 1491 |
+
"eval_steps_per_second": 1.506,
|
| 1492 |
+
"step": 53000
|
| 1493 |
+
},
|
| 1494 |
+
{
|
| 1495 |
+
"epoch": 7.79,
|
| 1496 |
+
"learning_rate": 1.108208412167079e-05,
|
| 1497 |
+
"loss": 1.8433,
|
| 1498 |
+
"step": 53500
|
| 1499 |
+
},
|
| 1500 |
+
{
|
| 1501 |
+
"epoch": 7.79,
|
| 1502 |
+
"eval_loss": 2.592151641845703,
|
| 1503 |
+
"eval_runtime": 250.8033,
|
| 1504 |
+
"eval_samples_per_second": 389.652,
|
| 1505 |
+
"eval_steps_per_second": 1.523,
|
| 1506 |
+
"step": 53500
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"epoch": 7.86,
|
| 1510 |
+
"learning_rate": 1.0718236064619415e-05,
|
| 1511 |
+
"loss": 1.851,
|
| 1512 |
+
"step": 54000
|
| 1513 |
+
},
|
| 1514 |
+
{
|
| 1515 |
+
"epoch": 7.86,
|
| 1516 |
+
"eval_loss": 2.5993497371673584,
|
| 1517 |
+
"eval_runtime": 244.9443,
|
| 1518 |
+
"eval_samples_per_second": 398.972,
|
| 1519 |
+
"eval_steps_per_second": 1.56,
|
| 1520 |
+
"step": 54000
|
| 1521 |
+
},
|
| 1522 |
+
{
|
| 1523 |
+
"epoch": 7.93,
|
| 1524 |
+
"learning_rate": 1.035438800756804e-05,
|
| 1525 |
+
"loss": 1.8313,
|
| 1526 |
+
"step": 54500
|
| 1527 |
+
},
|
| 1528 |
+
{
|
| 1529 |
+
"epoch": 7.93,
|
| 1530 |
+
"eval_loss": 2.59601092338562,
|
| 1531 |
+
"eval_runtime": 247.9824,
|
| 1532 |
+
"eval_samples_per_second": 394.084,
|
| 1533 |
+
"eval_steps_per_second": 1.54,
|
| 1534 |
+
"step": 54500
|
| 1535 |
+
},
|
| 1536 |
+
{
|
| 1537 |
+
"epoch": 8.0,
|
| 1538 |
+
"learning_rate": 9.991267646630768e-06,
|
| 1539 |
+
"loss": 1.8298,
|
| 1540 |
+
"step": 55000
|
| 1541 |
+
},
|
| 1542 |
+
{
|
| 1543 |
+
"epoch": 8.0,
|
| 1544 |
+
"eval_loss": 2.6058406829833984,
|
| 1545 |
+
"eval_runtime": 248.1822,
|
| 1546 |
+
"eval_samples_per_second": 393.767,
|
| 1547 |
+
"eval_steps_per_second": 1.539,
|
| 1548 |
+
"step": 55000
|
| 1549 |
+
},
|
| 1550 |
+
{
|
| 1551 |
+
"epoch": 8.08,
|
| 1552 |
+
"learning_rate": 9.628147285693495e-06,
|
| 1553 |
+
"loss": 1.8159,
|
| 1554 |
+
"step": 55500
|
| 1555 |
+
},
|
| 1556 |
+
{
|
| 1557 |
+
"epoch": 8.08,
|
| 1558 |
+
"eval_loss": 2.6286239624023438,
|
| 1559 |
+
"eval_runtime": 249.0138,
|
| 1560 |
+
"eval_samples_per_second": 392.452,
|
| 1561 |
+
"eval_steps_per_second": 1.534,
|
| 1562 |
+
"step": 55500
|
| 1563 |
+
},
|
| 1564 |
+
{
|
| 1565 |
+
"epoch": 8.15,
|
| 1566 |
+
"learning_rate": 9.264299228642118e-06,
|
| 1567 |
+
"loss": 1.817,
|
| 1568 |
+
"step": 56000
|
| 1569 |
+
},
|
| 1570 |
+
{
|
| 1571 |
+
"epoch": 8.15,
|
| 1572 |
+
"eval_loss": 2.634847402572632,
|
| 1573 |
+
"eval_runtime": 257.4805,
|
| 1574 |
+
"eval_samples_per_second": 379.547,
|
| 1575 |
+
"eval_steps_per_second": 1.484,
|
| 1576 |
+
"step": 56000
|
| 1577 |
+
},
|
| 1578 |
+
{
|
| 1579 |
+
"epoch": 8.22,
|
| 1580 |
+
"learning_rate": 8.900451171590745e-06,
|
| 1581 |
+
"loss": 1.8066,
|
| 1582 |
+
"step": 56500
|
| 1583 |
+
},
|
| 1584 |
+
{
|
| 1585 |
+
"epoch": 8.22,
|
| 1586 |
+
"eval_loss": 2.6410584449768066,
|
| 1587 |
+
"eval_runtime": 307.9556,
|
| 1588 |
+
"eval_samples_per_second": 317.338,
|
| 1589 |
+
"eval_steps_per_second": 1.24,
|
| 1590 |
+
"step": 56500
|
| 1591 |
+
},
|
| 1592 |
+
{
|
| 1593 |
+
"epoch": 8.3,
|
| 1594 |
+
"learning_rate": 8.536603114539368e-06,
|
| 1595 |
+
"loss": 1.7935,
|
| 1596 |
+
"step": 57000
|
| 1597 |
+
},
|
| 1598 |
+
{
|
| 1599 |
+
"epoch": 8.3,
|
| 1600 |
+
"eval_loss": 2.633836269378662,
|
| 1601 |
+
"eval_runtime": 253.2423,
|
| 1602 |
+
"eval_samples_per_second": 385.899,
|
| 1603 |
+
"eval_steps_per_second": 1.508,
|
| 1604 |
+
"step": 57000
|
| 1605 |
+
},
|
| 1606 |
+
{
|
| 1607 |
+
"epoch": 8.37,
|
| 1608 |
+
"learning_rate": 8.172755057487993e-06,
|
| 1609 |
+
"loss": 1.809,
|
| 1610 |
+
"step": 57500
|
| 1611 |
+
},
|
| 1612 |
+
{
|
| 1613 |
+
"epoch": 8.37,
|
| 1614 |
+
"eval_loss": 2.629018783569336,
|
| 1615 |
+
"eval_runtime": 250.9739,
|
| 1616 |
+
"eval_samples_per_second": 389.387,
|
| 1617 |
+
"eval_steps_per_second": 1.522,
|
| 1618 |
+
"step": 57500
|
| 1619 |
+
},
|
| 1620 |
+
{
|
| 1621 |
+
"epoch": 8.44,
|
| 1622 |
+
"learning_rate": 7.808907000436618e-06,
|
| 1623 |
+
"loss": 1.812,
|
| 1624 |
+
"step": 58000
|
| 1625 |
+
},
|
| 1626 |
+
{
|
| 1627 |
+
"epoch": 8.44,
|
| 1628 |
+
"eval_loss": 2.6257762908935547,
|
| 1629 |
+
"eval_runtime": 253.0757,
|
| 1630 |
+
"eval_samples_per_second": 386.153,
|
| 1631 |
+
"eval_steps_per_second": 1.509,
|
| 1632 |
+
"step": 58000
|
| 1633 |
+
},
|
| 1634 |
+
{
|
| 1635 |
+
"epoch": 8.51,
|
| 1636 |
+
"learning_rate": 7.445058943385242e-06,
|
| 1637 |
+
"loss": 1.79,
|
| 1638 |
+
"step": 58500
|
| 1639 |
+
},
|
| 1640 |
+
{
|
| 1641 |
+
"epoch": 8.51,
|
| 1642 |
+
"eval_loss": 2.6320676803588867,
|
| 1643 |
+
"eval_runtime": 250.9004,
|
| 1644 |
+
"eval_samples_per_second": 389.501,
|
| 1645 |
+
"eval_steps_per_second": 1.523,
|
| 1646 |
+
"step": 58500
|
| 1647 |
+
},
|
| 1648 |
+
{
|
| 1649 |
+
"epoch": 8.59,
|
| 1650 |
+
"learning_rate": 7.0812108863338665e-06,
|
| 1651 |
+
"loss": 1.8046,
|
| 1652 |
+
"step": 59000
|
| 1653 |
+
},
|
| 1654 |
+
{
|
| 1655 |
+
"epoch": 8.59,
|
| 1656 |
+
"eval_loss": 2.6290555000305176,
|
| 1657 |
+
"eval_runtime": 248.8573,
|
| 1658 |
+
"eval_samples_per_second": 392.699,
|
| 1659 |
+
"eval_steps_per_second": 1.535,
|
| 1660 |
+
"step": 59000
|
| 1661 |
+
},
|
| 1662 |
+
{
|
| 1663 |
+
"epoch": 8.66,
|
| 1664 |
+
"learning_rate": 6.718090525396595e-06,
|
| 1665 |
+
"loss": 1.7975,
|
| 1666 |
+
"step": 59500
|
| 1667 |
+
},
|
| 1668 |
+
{
|
| 1669 |
+
"epoch": 8.66,
|
| 1670 |
+
"eval_loss": 2.6282989978790283,
|
| 1671 |
+
"eval_runtime": 245.3595,
|
| 1672 |
+
"eval_samples_per_second": 398.297,
|
| 1673 |
+
"eval_steps_per_second": 1.557,
|
| 1674 |
+
"step": 59500
|
| 1675 |
+
},
|
| 1676 |
+
{
|
| 1677 |
+
"epoch": 8.73,
|
| 1678 |
+
"learning_rate": 6.354970164459321e-06,
|
| 1679 |
+
"loss": 1.7968,
|
| 1680 |
+
"step": 60000
|
| 1681 |
+
},
|
| 1682 |
+
{
|
| 1683 |
+
"epoch": 8.73,
|
| 1684 |
+
"eval_loss": 2.628397226333618,
|
| 1685 |
+
"eval_runtime": 253.0259,
|
| 1686 |
+
"eval_samples_per_second": 386.229,
|
| 1687 |
+
"eval_steps_per_second": 1.51,
|
| 1688 |
+
"step": 60000
|
| 1689 |
+
},
|
| 1690 |
+
{
|
| 1691 |
+
"epoch": 8.81,
|
| 1692 |
+
"learning_rate": 5.991122107407947e-06,
|
| 1693 |
+
"loss": 1.7779,
|
| 1694 |
+
"step": 60500
|
| 1695 |
+
},
|
| 1696 |
+
{
|
| 1697 |
+
"epoch": 8.81,
|
| 1698 |
+
"eval_loss": 2.625650405883789,
|
| 1699 |
+
"eval_runtime": 247.6056,
|
| 1700 |
+
"eval_samples_per_second": 394.684,
|
| 1701 |
+
"eval_steps_per_second": 1.543,
|
| 1702 |
+
"step": 60500
|
| 1703 |
+
},
|
| 1704 |
+
{
|
| 1705 |
+
"epoch": 8.88,
|
| 1706 |
+
"learning_rate": 5.627274050356571e-06,
|
| 1707 |
+
"loss": 1.7664,
|
| 1708 |
+
"step": 61000
|
| 1709 |
+
},
|
| 1710 |
+
{
|
| 1711 |
+
"epoch": 8.88,
|
| 1712 |
+
"eval_loss": 2.623215675354004,
|
| 1713 |
+
"eval_runtime": 268.5188,
|
| 1714 |
+
"eval_samples_per_second": 363.945,
|
| 1715 |
+
"eval_steps_per_second": 1.423,
|
| 1716 |
+
"step": 61000
|
| 1717 |
+
},
|
| 1718 |
+
{
|
| 1719 |
+
"epoch": 8.95,
|
| 1720 |
+
"learning_rate": 5.263425993305196e-06,
|
| 1721 |
+
"loss": 1.792,
|
| 1722 |
+
"step": 61500
|
| 1723 |
+
},
|
| 1724 |
+
{
|
| 1725 |
+
"epoch": 8.95,
|
| 1726 |
+
"eval_loss": 2.63053297996521,
|
| 1727 |
+
"eval_runtime": 248.0445,
|
| 1728 |
+
"eval_samples_per_second": 393.986,
|
| 1729 |
+
"eval_steps_per_second": 1.54,
|
| 1730 |
+
"step": 61500
|
| 1731 |
+
},
|
| 1732 |
+
{
|
| 1733 |
+
"epoch": 9.02,
|
| 1734 |
+
"learning_rate": 4.89957793625382e-06,
|
| 1735 |
+
"loss": 1.7725,
|
| 1736 |
+
"step": 62000
|
| 1737 |
+
},
|
| 1738 |
+
{
|
| 1739 |
+
"epoch": 9.02,
|
| 1740 |
+
"eval_loss": 2.6525118350982666,
|
| 1741 |
+
"eval_runtime": 247.425,
|
| 1742 |
+
"eval_samples_per_second": 394.972,
|
| 1743 |
+
"eval_steps_per_second": 1.544,
|
| 1744 |
+
"step": 62000
|
| 1745 |
+
},
|
| 1746 |
+
{
|
| 1747 |
+
"epoch": 9.1,
|
| 1748 |
+
"learning_rate": 4.535729879202445e-06,
|
| 1749 |
+
"loss": 1.7563,
|
| 1750 |
+
"step": 62500
|
| 1751 |
+
},
|
| 1752 |
+
{
|
| 1753 |
+
"epoch": 9.1,
|
| 1754 |
+
"eval_loss": 2.679419755935669,
|
| 1755 |
+
"eval_runtime": 249.9688,
|
| 1756 |
+
"eval_samples_per_second": 390.953,
|
| 1757 |
+
"eval_steps_per_second": 1.528,
|
| 1758 |
+
"step": 62500
|
| 1759 |
+
},
|
| 1760 |
+
{
|
| 1761 |
+
"epoch": 9.17,
|
| 1762 |
+
"learning_rate": 4.17188182215107e-06,
|
| 1763 |
+
"loss": 1.7606,
|
| 1764 |
+
"step": 63000
|
| 1765 |
+
},
|
| 1766 |
+
{
|
| 1767 |
+
"epoch": 9.17,
|
| 1768 |
+
"eval_loss": 2.6783671379089355,
|
| 1769 |
+
"eval_runtime": 248.5877,
|
| 1770 |
+
"eval_samples_per_second": 393.125,
|
| 1771 |
+
"eval_steps_per_second": 1.537,
|
| 1772 |
+
"step": 63000
|
| 1773 |
+
},
|
| 1774 |
+
{
|
| 1775 |
+
"epoch": 9.24,
|
| 1776 |
+
"learning_rate": 3.8080337650996943e-06,
|
| 1777 |
+
"loss": 1.7666,
|
| 1778 |
+
"step": 63500
|
| 1779 |
+
},
|
| 1780 |
+
{
|
| 1781 |
+
"epoch": 9.24,
|
| 1782 |
+
"eval_loss": 2.679766893386841,
|
| 1783 |
+
"eval_runtime": 253.2315,
|
| 1784 |
+
"eval_samples_per_second": 385.916,
|
| 1785 |
+
"eval_steps_per_second": 1.509,
|
| 1786 |
+
"step": 63500
|
| 1787 |
+
},
|
| 1788 |
+
{
|
| 1789 |
+
"epoch": 9.31,
|
| 1790 |
+
"learning_rate": 3.4449134041624217e-06,
|
| 1791 |
+
"loss": 1.7551,
|
| 1792 |
+
"step": 64000
|
| 1793 |
+
},
|
| 1794 |
+
{
|
| 1795 |
+
"epoch": 9.31,
|
| 1796 |
+
"eval_loss": 2.6813337802886963,
|
| 1797 |
+
"eval_runtime": 248.5037,
|
| 1798 |
+
"eval_samples_per_second": 393.258,
|
| 1799 |
+
"eval_steps_per_second": 1.537,
|
| 1800 |
+
"step": 64000
|
| 1801 |
+
},
|
| 1802 |
+
{
|
| 1803 |
+
"epoch": 9.39,
|
| 1804 |
+
"learning_rate": 3.0810653471110467e-06,
|
| 1805 |
+
"loss": 1.7578,
|
| 1806 |
+
"step": 64500
|
| 1807 |
+
},
|
| 1808 |
+
{
|
| 1809 |
+
"epoch": 9.39,
|
| 1810 |
+
"eval_loss": 2.683032751083374,
|
| 1811 |
+
"eval_runtime": 245.3373,
|
| 1812 |
+
"eval_samples_per_second": 398.333,
|
| 1813 |
+
"eval_steps_per_second": 1.557,
|
| 1814 |
+
"step": 64500
|
| 1815 |
+
},
|
| 1816 |
+
{
|
| 1817 |
+
"epoch": 9.46,
|
| 1818 |
+
"learning_rate": 2.717217290059671e-06,
|
| 1819 |
+
"loss": 1.7483,
|
| 1820 |
+
"step": 65000
|
| 1821 |
+
},
|
| 1822 |
+
{
|
| 1823 |
+
"epoch": 9.46,
|
| 1824 |
+
"eval_loss": 2.6832828521728516,
|
| 1825 |
+
"eval_runtime": 266.4744,
|
| 1826 |
+
"eval_samples_per_second": 366.737,
|
| 1827 |
+
"eval_steps_per_second": 1.434,
|
| 1828 |
+
"step": 65000
|
| 1829 |
+
},
|
| 1830 |
+
{
|
| 1831 |
+
"epoch": 9.53,
|
| 1832 |
+
"learning_rate": 2.3533692330082957e-06,
|
| 1833 |
+
"loss": 1.7431,
|
| 1834 |
+
"step": 65500
|
| 1835 |
+
},
|
| 1836 |
+
{
|
| 1837 |
+
"epoch": 9.53,
|
| 1838 |
+
"eval_loss": 2.6883933544158936,
|
| 1839 |
+
"eval_runtime": 256.629,
|
| 1840 |
+
"eval_samples_per_second": 380.807,
|
| 1841 |
+
"eval_steps_per_second": 1.489,
|
| 1842 |
+
"step": 65500
|
| 1843 |
+
},
|
| 1844 |
+
{
|
| 1845 |
+
"epoch": 9.61,
|
| 1846 |
+
"learning_rate": 1.9895211759569207e-06,
|
| 1847 |
+
"loss": 1.743,
|
| 1848 |
+
"step": 66000
|
| 1849 |
+
},
|
| 1850 |
+
{
|
| 1851 |
+
"epoch": 9.61,
|
| 1852 |
+
"eval_loss": 2.6931965351104736,
|
| 1853 |
+
"eval_runtime": 260.7406,
|
| 1854 |
+
"eval_samples_per_second": 374.802,
|
| 1855 |
+
"eval_steps_per_second": 1.465,
|
| 1856 |
+
"step": 66000
|
| 1857 |
+
},
|
| 1858 |
+
{
|
| 1859 |
+
"epoch": 9.68,
|
| 1860 |
+
"learning_rate": 1.6264008150196477e-06,
|
| 1861 |
+
"loss": 1.7395,
|
| 1862 |
+
"step": 66500
|
| 1863 |
+
},
|
| 1864 |
+
{
|
| 1865 |
+
"epoch": 9.68,
|
| 1866 |
+
"eval_loss": 2.6927101612091064,
|
| 1867 |
+
"eval_runtime": 254.3781,
|
| 1868 |
+
"eval_samples_per_second": 384.176,
|
| 1869 |
+
"eval_steps_per_second": 1.502,
|
| 1870 |
+
"step": 66500
|
| 1871 |
+
},
|
| 1872 |
+
{
|
| 1873 |
+
"epoch": 9.75,
|
| 1874 |
+
"learning_rate": 1.2625527579682726e-06,
|
| 1875 |
+
"loss": 1.7473,
|
| 1876 |
+
"step": 67000
|
| 1877 |
+
},
|
| 1878 |
+
{
|
| 1879 |
+
"epoch": 9.75,
|
| 1880 |
+
"eval_loss": 2.6903834342956543,
|
| 1881 |
+
"eval_runtime": 221.4662,
|
| 1882 |
+
"eval_samples_per_second": 441.268,
|
| 1883 |
+
"eval_steps_per_second": 1.725,
|
| 1884 |
+
"step": 67000
|
| 1885 |
+
},
|
| 1886 |
+
{
|
| 1887 |
+
"epoch": 9.82,
|
| 1888 |
+
"learning_rate": 8.987047009168971e-07,
|
| 1889 |
+
"loss": 1.7413,
|
| 1890 |
+
"step": 67500
|
| 1891 |
+
},
|
| 1892 |
+
{
|
| 1893 |
+
"epoch": 9.82,
|
| 1894 |
+
"eval_loss": 2.6892080307006836,
|
| 1895 |
+
"eval_runtime": 233.1215,
|
| 1896 |
+
"eval_samples_per_second": 419.206,
|
| 1897 |
+
"eval_steps_per_second": 1.639,
|
| 1898 |
+
"step": 67500
|
| 1899 |
+
},
|
| 1900 |
+
{
|
| 1901 |
+
"epoch": 9.9,
|
| 1902 |
+
"learning_rate": 5.348566438655218e-07,
|
| 1903 |
+
"loss": 1.7437,
|
| 1904 |
+
"step": 68000
|
| 1905 |
+
},
|
| 1906 |
+
{
|
| 1907 |
+
"epoch": 9.9,
|
| 1908 |
+
"eval_loss": 2.6897966861724854,
|
| 1909 |
+
"eval_runtime": 217.2083,
|
| 1910 |
+
"eval_samples_per_second": 449.918,
|
| 1911 |
+
"eval_steps_per_second": 1.759,
|
| 1912 |
+
"step": 68000
|
| 1913 |
+
},
|
| 1914 |
+
{
|
| 1915 |
+
"epoch": 9.97,
|
| 1916 |
+
"learning_rate": 1.7173628292824918e-07,
|
| 1917 |
+
"loss": 1.7546,
|
| 1918 |
+
"step": 68500
|
| 1919 |
+
},
|
| 1920 |
+
{
|
| 1921 |
+
"epoch": 9.97,
|
| 1922 |
+
"eval_loss": 2.689425468444824,
|
| 1923 |
+
"eval_runtime": 214.7197,
|
| 1924 |
+
"eval_samples_per_second": 455.133,
|
| 1925 |
+
"eval_steps_per_second": 1.779,
|
| 1926 |
+
"step": 68500
|
| 1927 |
+
},
|
| 1928 |
+
{
|
| 1929 |
+
"epoch": 10.0,
|
| 1930 |
+
"step": 68710,
|
| 1931 |
+
"total_flos": 1.1742684555264e+18,
|
| 1932 |
+
"train_loss": 2.026226943438967,
|
| 1933 |
+
"train_runtime": 84552.1773,
|
| 1934 |
+
"train_samples_per_second": 104.022,
|
| 1935 |
+
"train_steps_per_second": 0.813
|
| 1936 |
}
|
| 1937 |
],
|
| 1938 |
+
"max_steps": 68710,
|
| 1939 |
+
"num_train_epochs": 10,
|
| 1940 |
+
"total_flos": 1.1742684555264e+18,
|
| 1941 |
"trial_name": null,
|
| 1942 |
"trial_params": null
|
| 1943 |
}
|