anas-awadalla
commited on
Commit
•
23f58c4
1
Parent(s):
4a8d959
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 +31 -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": 77.68211920529801,
|
4 |
+
"eval_f1": 86.51792551155518,
|
5 |
+
"eval_samples": 10829,
|
6 |
+
"train_loss": 0.458767032623291,
|
7 |
+
"train_runtime": 808.9499,
|
8 |
+
"train_samples": 1024,
|
9 |
+
"train_samples_per_second": 12.658,
|
10 |
+
"train_steps_per_second": 1.063
|
11 |
+
}
|
eval_nbest_predictions.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aabba8bcfbdb0cc8582205538c7ce6e4557fe05921488dc6420869009c39e0bd
|
3 |
+
size 49294877
|
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": 77.68211920529801,
|
4 |
+
"eval_f1": 86.51792551155518,
|
5 |
+
"eval_samples": 10829
|
6 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"train_loss": 0.458767032623291,
|
4 |
+
"train_runtime": 808.9499,
|
5 |
+
"train_samples": 1024,
|
6 |
+
"train_samples_per_second": 12.658,
|
7 |
+
"train_steps_per_second": 1.063
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 10.0,
|
5 |
+
"global_step": 860,
|
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": 1.3953488372093024e-05,
|
13 |
+
"loss": 0.7424,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 10.0,
|
18 |
+
"step": 860,
|
19 |
+
"total_flos": 7281145314017280.0,
|
20 |
+
"train_loss": 0.458767032623291,
|
21 |
+
"train_runtime": 808.9499,
|
22 |
+
"train_samples_per_second": 12.658,
|
23 |
+
"train_steps_per_second": 1.063
|
24 |
+
}
|
25 |
+
],
|
26 |
+
"max_steps": 860,
|
27 |
+
"num_train_epochs": 10,
|
28 |
+
"total_flos": 7281145314017280.0,
|
29 |
+
"trial_name": null,
|
30 |
+
"trial_params": null
|
31 |
+
}
|