Commit
•
d101760
1
Parent(s):
b3006e5
End of training
Browse files- .gitattributes +1 -0
- all_results.json +11 -0
- eval_nbest_predictions.json +3 -0
- eval_predictions.json +0 -0
- eval_results.json +6 -0
- train_results.json +8 -0
- trainer_state.json +25 -0
.gitattributes
CHANGED
|
@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 26 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
| 27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 26 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
| 27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
+
eval_nbest_predictions.json filter=lfs diff=lfs merge=lfs -text
|
all_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_exact_match": 74.59791863765373,
|
| 4 |
+
"eval_f1": 84.39624966061163,
|
| 5 |
+
"eval_samples": 10829,
|
| 6 |
+
"train_loss": 0.6062377236106179,
|
| 7 |
+
"train_runtime": 198.279,
|
| 8 |
+
"train_samples": 256,
|
| 9 |
+
"train_samples_per_second": 12.911,
|
| 10 |
+
"train_steps_per_second": 1.11
|
| 11 |
+
}
|
eval_nbest_predictions.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fb166db3e8ea5398a40503cfd53ef934d33177bd4b1f74c4329d6c30410e0b53
|
| 3 |
+
size 48690424
|
eval_predictions.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
eval_results.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_exact_match": 74.59791863765373,
|
| 4 |
+
"eval_f1": 84.39624966061163,
|
| 5 |
+
"eval_samples": 10829
|
| 6 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"train_loss": 0.6062377236106179,
|
| 4 |
+
"train_runtime": 198.279,
|
| 5 |
+
"train_samples": 256,
|
| 6 |
+
"train_samples_per_second": 12.911,
|
| 7 |
+
"train_steps_per_second": 1.11
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"global_step": 220,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 10.0,
|
| 12 |
+
"step": 220,
|
| 13 |
+
"total_flos": 1820286328504320.0,
|
| 14 |
+
"train_loss": 0.6062377236106179,
|
| 15 |
+
"train_runtime": 198.279,
|
| 16 |
+
"train_samples_per_second": 12.911,
|
| 17 |
+
"train_steps_per_second": 1.11
|
| 18 |
+
}
|
| 19 |
+
],
|
| 20 |
+
"max_steps": 220,
|
| 21 |
+
"num_train_epochs": 10,
|
| 22 |
+
"total_flos": 1820286328504320.0,
|
| 23 |
+
"trial_name": null,
|
| 24 |
+
"trial_params": null
|
| 25 |
+
}
|