anas-awadalla
commited on
Commit
•
c701df6
1
Parent(s):
89beb04
End of training
Browse files- all_results.json +7 -7
- eval_nbest_predictions.json +2 -2
- eval_predictions.json +0 -0
- eval_results.json +3 -3
- train_results.json +5 -5
- trainer_state.json +12 -12
all_results.json
CHANGED
@@ -1,11 +1,11 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"eval_exact_match":
|
4 |
-
"eval_f1":
|
5 |
"eval_samples": 10790,
|
6 |
-
"train_loss":
|
7 |
-
"train_runtime":
|
8 |
"train_samples": 32,
|
9 |
-
"train_samples_per_second":
|
10 |
-
"train_steps_per_second":
|
11 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 75.0,
|
3 |
+
"eval_exact_match": 1.2771996215704824,
|
4 |
+
"eval_f1": 8.727663530677017,
|
5 |
"eval_samples": 10790,
|
6 |
+
"train_loss": 4.511438802083333,
|
7 |
+
"train_runtime": 36.3443,
|
8 |
"train_samples": 32,
|
9 |
+
"train_samples_per_second": 264.14,
|
10 |
+
"train_steps_per_second": 2.064
|
11 |
}
|
eval_nbest_predictions.json
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d32a6a443d4ae3ecb8b3a98992411a5cf9771d968e7c7f9173f05402b9922840
|
3 |
+
size 53893265
|
eval_predictions.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
eval_results.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"eval_exact_match":
|
4 |
-
"eval_f1":
|
5 |
"eval_samples": 10790
|
6 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 75.0,
|
3 |
+
"eval_exact_match": 1.2771996215704824,
|
4 |
+
"eval_f1": 8.727663530677017,
|
5 |
"eval_samples": 10790
|
6 |
}
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"train_loss":
|
4 |
-
"train_runtime":
|
5 |
"train_samples": 32,
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second":
|
8 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 75.0,
|
3 |
+
"train_loss": 4.511438802083333,
|
4 |
+
"train_runtime": 36.3443,
|
5 |
"train_samples": 32,
|
6 |
+
"train_samples_per_second": 264.14,
|
7 |
+
"train_steps_per_second": 2.064
|
8 |
}
|
trainer_state.json
CHANGED
@@ -1,25 +1,25 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
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 |
-
"step":
|
13 |
-
"total_flos":
|
14 |
-
"train_loss":
|
15 |
-
"train_runtime":
|
16 |
-
"train_samples_per_second":
|
17 |
-
"train_steps_per_second":
|
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": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 75.0,
|
5 |
+
"global_step": 75,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
9 |
"log_history": [
|
10 |
{
|
11 |
+
"epoch": 75.0,
|
12 |
+
"step": 75,
|
13 |
+
"total_flos": 1706750612865024.0,
|
14 |
+
"train_loss": 4.511438802083333,
|
15 |
+
"train_runtime": 36.3443,
|
16 |
+
"train_samples_per_second": 264.14,
|
17 |
+
"train_steps_per_second": 2.064
|
18 |
}
|
19 |
],
|
20 |
+
"max_steps": 75,
|
21 |
+
"num_train_epochs": 75,
|
22 |
+
"total_flos": 1706750612865024.0,
|
23 |
"trial_name": null,
|
24 |
"trial_params": null
|
25 |
}
|