anas-awadalla
commited on
Commit
•
aa77cb0
1
Parent(s):
833db1e
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_23-13-12_g3010/events.out.tfevents.1664951081.g3010.77440.2 +3 -0
- train_results.json +8 -0
- trainer_state.json +49 -0
all_results.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"eval_exact_match": 27.341532639545886,
|
4 |
+
"eval_f1": 40.85158544214879,
|
5 |
+
"eval_samples": 10793,
|
6 |
+
"train_loss": 2.6702739804290063,
|
7 |
+
"train_runtime": 211.108,
|
8 |
+
"train_samples": 512,
|
9 |
+
"train_samples_per_second": 24.253,
|
10 |
+
"train_steps_per_second": 2.037
|
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 sha256:298920e08a6f3c15a25568e37afb0b6119129236a0c2b1329475efa1246a4392
|
3 |
+
size 50859070
|
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": 27.341532639545886,
|
4 |
+
"eval_f1": 40.85158544214879,
|
5 |
+
"eval_samples": 10793
|
6 |
+
}
|
runs/Oct04_23-13-12_g3010/events.out.tfevents.1664951081.g3010.77440.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e0fa78ad2d3c4852bc561a91921e1016196ae614748017f76f7a2d281f874c29
|
3 |
+
size 191
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"train_loss": 2.6702739804290063,
|
4 |
+
"train_runtime": 211.108,
|
5 |
+
"train_samples": 512,
|
6 |
+
"train_samples_per_second": 24.253,
|
7 |
+
"train_steps_per_second": 2.037
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 10.0,
|
5 |
+
"global_step": 430,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 2.33,
|
12 |
+
"learning_rate": 2.558139534883721e-05,
|
13 |
+
"loss": 4.9684,
|
14 |
+
"step": 100
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 4.65,
|
18 |
+
"learning_rate": 1.7829457364341087e-05,
|
19 |
+
"loss": 2.9975,
|
20 |
+
"step": 200
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 6.98,
|
24 |
+
"learning_rate": 1.0077519379844961e-05,
|
25 |
+
"loss": 1.8901,
|
26 |
+
"step": 300
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 9.3,
|
30 |
+
"learning_rate": 2.325581395348837e-06,
|
31 |
+
"loss": 1.2672,
|
32 |
+
"step": 400
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 10.0,
|
36 |
+
"step": 430,
|
37 |
+
"total_flos": 755694717051456.0,
|
38 |
+
"train_loss": 2.6702739804290063,
|
39 |
+
"train_runtime": 211.108,
|
40 |
+
"train_samples_per_second": 24.253,
|
41 |
+
"train_steps_per_second": 2.037
|
42 |
+
}
|
43 |
+
],
|
44 |
+
"max_steps": 430,
|
45 |
+
"num_train_epochs": 10,
|
46 |
+
"total_flos": 755694717051456.0,
|
47 |
+
"trial_name": null,
|
48 |
+
"trial_params": null
|
49 |
+
}
|