Commit
•
41cf22a
1
Parent(s):
c430e63
End of training
Browse files- all_results.json +7 -4
- eval_results.json +6 -0
- runs/Oct06_18-45-10_g3032/events.out.tfevents.1665107227.g3032.570.2 +3 -0
- train_results.json +4 -4
- trainer_state.json +22 -10
all_results.json
CHANGED
|
@@ -1,8 +1,11 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 2.0,
|
| 3 |
-
"
|
| 4 |
-
"
|
|
|
|
|
|
|
|
|
|
| 5 |
"train_samples": 100,
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second":
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 2.0,
|
| 3 |
+
"eval_exact_match": 0.0,
|
| 4 |
+
"eval_f1": 13.633333333333333,
|
| 5 |
+
"eval_samples": 100,
|
| 6 |
+
"train_loss": 0.28480225572219264,
|
| 7 |
+
"train_runtime": 22.8013,
|
| 8 |
"train_samples": 100,
|
| 9 |
+
"train_samples_per_second": 8.771,
|
| 10 |
+
"train_steps_per_second": 1.14
|
| 11 |
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"eval_exact_match": 0.0,
|
| 4 |
+
"eval_f1": 13.633333333333333,
|
| 5 |
+
"eval_samples": 100
|
| 6 |
+
}
|
runs/Oct06_18-45-10_g3032/events.out.tfevents.1665107227.g3032.570.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:38e4976d489defd121c3c2fb9296ff25e3b94943d507399266eaf7a5de352613
|
| 3 |
+
size 188
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 2.0,
|
| 3 |
-
"train_loss": 0.
|
| 4 |
-
"train_runtime":
|
| 5 |
"train_samples": 100,
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second":
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 2.0,
|
| 3 |
+
"train_loss": 0.28480225572219264,
|
| 4 |
+
"train_runtime": 22.8013,
|
| 5 |
"train_samples": 100,
|
| 6 |
+
"train_samples_per_second": 8.771,
|
| 7 |
+
"train_steps_per_second": 1.14
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -2,28 +2,40 @@
|
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
"epoch": 2.0,
|
| 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 |
-
"learning_rate":
|
| 13 |
-
"loss": 0.
|
| 14 |
"step": 10
|
| 15 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
{
|
| 17 |
"epoch": 2.0,
|
| 18 |
-
"step":
|
| 19 |
"total_flos": 60973645824000.0,
|
| 20 |
-
"train_loss": 0.
|
| 21 |
-
"train_runtime":
|
| 22 |
-
"train_samples_per_second":
|
| 23 |
-
"train_steps_per_second":
|
| 24 |
}
|
| 25 |
],
|
| 26 |
-
"max_steps":
|
| 27 |
"num_train_epochs": 2,
|
| 28 |
"total_flos": 60973645824000.0,
|
| 29 |
"trial_name": null,
|
|
|
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
"epoch": 2.0,
|
| 5 |
+
"global_step": 26,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
+
"epoch": 0.77,
|
| 12 |
+
"learning_rate": 1.8461538461538465e-05,
|
| 13 |
+
"loss": 0.5091,
|
| 14 |
"step": 10
|
| 15 |
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.54,
|
| 18 |
+
"learning_rate": 6.923076923076923e-06,
|
| 19 |
+
"loss": 0.1673,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 1.54,
|
| 24 |
+
"eval_exact_match": 0.0,
|
| 25 |
+
"eval_f1": 15.883333333333333,
|
| 26 |
+
"step": 20
|
| 27 |
+
},
|
| 28 |
{
|
| 29 |
"epoch": 2.0,
|
| 30 |
+
"step": 26,
|
| 31 |
"total_flos": 60973645824000.0,
|
| 32 |
+
"train_loss": 0.28480225572219264,
|
| 33 |
+
"train_runtime": 22.8013,
|
| 34 |
+
"train_samples_per_second": 8.771,
|
| 35 |
+
"train_steps_per_second": 1.14
|
| 36 |
}
|
| 37 |
],
|
| 38 |
+
"max_steps": 26,
|
| 39 |
"num_train_epochs": 2,
|
| 40 |
"total_flos": 60973645824000.0,
|
| 41 |
"trial_name": null,
|