anas-awadalla
commited on
Commit
•
a80ad82
1
Parent(s):
68a1cff
End of training
Browse files- all_results.json +11 -0
- eval_nbest_predictions.json +2 -2
- eval_predictions.json +0 -0
- eval_results.json +6 -0
- runs/Oct04_22-11-07_g3010/events.out.tfevents.1664947231.g3010.87143.2 +3 -0
- train_results.json +8 -0
- trainer_state.json +37 -0
all_results.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"eval_exact_match": 10.832544938505203,
|
4 |
+
"eval_f1": 21.3597069356687,
|
5 |
+
"eval_samples": 10793,
|
6 |
+
"train_loss": 3.405086222561923,
|
7 |
+
"train_runtime": 100.589,
|
8 |
+
"train_samples": 256,
|
9 |
+
"train_samples_per_second": 25.45,
|
10 |
+
"train_steps_per_second": 2.187
|
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 sha256:60a17d4441a8c16f880ed3cbab3e1b4893ca451e63e9374999f07ba868e5a6de
|
3 |
+
size 51852726
|
eval_predictions.json
CHANGED
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": 10.832544938505203,
|
4 |
+
"eval_f1": 21.3597069356687,
|
5 |
+
"eval_samples": 10793
|
6 |
+
}
|
runs/Oct04_22-11-07_g3010/events.out.tfevents.1664947231.g3010.87143.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0603bd77cd49217d56283bea0fcb73cd921145617655507adc96a33d1304b306
|
3 |
+
size 191
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"train_loss": 3.405086222561923,
|
4 |
+
"train_runtime": 100.589,
|
5 |
+
"train_samples": 256,
|
6 |
+
"train_samples_per_second": 25.45,
|
7 |
+
"train_steps_per_second": 2.187
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": 4.55,
|
12 |
+
"learning_rate": 1.8181818181818182e-05,
|
13 |
+
"loss": 4.5806,
|
14 |
+
"step": 100
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 9.09,
|
18 |
+
"learning_rate": 3.0303030303030305e-06,
|
19 |
+
"loss": 2.5073,
|
20 |
+
"step": 200
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 10.0,
|
24 |
+
"step": 220,
|
25 |
+
"total_flos": 396870987244656.0,
|
26 |
+
"train_loss": 3.405086222561923,
|
27 |
+
"train_runtime": 100.589,
|
28 |
+
"train_samples_per_second": 25.45,
|
29 |
+
"train_steps_per_second": 2.187
|
30 |
+
}
|
31 |
+
],
|
32 |
+
"max_steps": 220,
|
33 |
+
"num_train_epochs": 10,
|
34 |
+
"total_flos": 396870987244656.0,
|
35 |
+
"trial_name": null,
|
36 |
+
"trial_params": null
|
37 |
+
}
|