Commit
•
cb15024
1
Parent(s):
27ca317
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 +43 -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": 20.0,
|
| 3 |
+
"eval_exact_match": 73.6802270577105,
|
| 4 |
+
"eval_f1": 83.81913172157984,
|
| 5 |
+
"eval_samples": 10790,
|
| 6 |
+
"train_loss": 0.12154395081276118,
|
| 7 |
+
"train_runtime": 262.3624,
|
| 8 |
+
"train_samples": 1024,
|
| 9 |
+
"train_samples_per_second": 78.06,
|
| 10 |
+
"train_steps_per_second": 6.556
|
| 11 |
+
}
|
eval_nbest_predictions.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:41c62aef08bf8f69e0d83cd5da4f847b47690e7c4ca60d1337590ab7ae1644be
|
| 3 |
+
size 49075762
|
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": 20.0,
|
| 3 |
+
"eval_exact_match": 73.6802270577105,
|
| 4 |
+
"eval_f1": 83.81913172157984,
|
| 5 |
+
"eval_samples": 10790
|
| 6 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"train_loss": 0.12154395081276118,
|
| 4 |
+
"train_runtime": 262.3624,
|
| 5 |
+
"train_samples": 1024,
|
| 6 |
+
"train_samples_per_second": 78.06,
|
| 7 |
+
"train_steps_per_second": 6.556
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 20.0,
|
| 5 |
+
"global_step": 1720,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 5.81,
|
| 12 |
+
"learning_rate": 7.881136950904393e-05,
|
| 13 |
+
"loss": 2.578,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 11.63,
|
| 18 |
+
"learning_rate": 4.651162790697675e-05,
|
| 19 |
+
"loss": 0.4809,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 17.44,
|
| 24 |
+
"learning_rate": 1.421188630490956e-05,
|
| 25 |
+
"loss": 0.3023,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 20.0,
|
| 30 |
+
"step": 1720,
|
| 31 |
+
"total_flos": 1.456427177607168e+16,
|
| 32 |
+
"train_loss": 0.12154395081276118,
|
| 33 |
+
"train_runtime": 262.3624,
|
| 34 |
+
"train_samples_per_second": 78.06,
|
| 35 |
+
"train_steps_per_second": 6.556
|
| 36 |
+
}
|
| 37 |
+
],
|
| 38 |
+
"max_steps": 1720,
|
| 39 |
+
"num_train_epochs": 20,
|
| 40 |
+
"total_flos": 1.456427177607168e+16,
|
| 41 |
+
"trial_name": null,
|
| 42 |
+
"trial_params": null
|
| 43 |
+
}
|