haibotamiu
commited on
Commit
•
16929c2
1
Parent(s):
be53342
End of training
Browse files- README.md +4 -1
- all_results.json +6 -6
- args.bin +1 -1
- eval_nbest_predictions.json +2 -2
- eval_predictions.json +0 -0
- eval_results.json +3 -3
- train_results.json +4 -4
- trainer_state.json +27 -15
README.md
CHANGED
@@ -2,7 +2,10 @@
|
|
2 |
license: apache-2.0
|
3 |
base_model: bert-large-uncased
|
4 |
tags:
|
|
|
5 |
- generated_from_trainer
|
|
|
|
|
6 |
model-index:
|
7 |
- name: out
|
8 |
results: []
|
@@ -13,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
13 |
|
14 |
# out
|
15 |
|
16 |
-
This model is a fine-tuned version of [bert-large-uncased](https://huggingface.co/bert-large-uncased) on the
|
17 |
|
18 |
## Model description
|
19 |
|
|
|
2 |
license: apache-2.0
|
3 |
base_model: bert-large-uncased
|
4 |
tags:
|
5 |
+
- question-answering
|
6 |
- generated_from_trainer
|
7 |
+
datasets:
|
8 |
+
- squad
|
9 |
model-index:
|
10 |
- name: out
|
11 |
results: []
|
|
|
16 |
|
17 |
# out
|
18 |
|
19 |
+
This model is a fine-tuned version of [bert-large-uncased](https://huggingface.co/bert-large-uncased) on the squad dataset.
|
20 |
|
21 |
## Model description
|
22 |
|
all_results.json
CHANGED
@@ -1,11 +1,11 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
"eval_samples": 3000,
|
4 |
-
"exact_match": 68.
|
5 |
-
"f1": 77.
|
6 |
-
"train_loss": 0.
|
7 |
-
"train_runtime":
|
8 |
"train_samples": 3000,
|
9 |
-
"train_samples_per_second": 63.
|
10 |
"train_steps_per_second": 0.505
|
11 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 100.0,
|
3 |
"eval_samples": 3000,
|
4 |
+
"exact_match": 68.86666666666666,
|
5 |
+
"f1": 77.76425661888325,
|
6 |
+
"train_loss": 0.09819502154986064,
|
7 |
+
"train_runtime": 4749.1078,
|
8 |
"train_samples": 3000,
|
9 |
+
"train_samples_per_second": 63.17,
|
10 |
"train_steps_per_second": 0.505
|
11 |
}
|
args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5652
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:77d11f566704b8ea970a8b9270c4a9beee63dee776334b5e5fc069c5088dbf0c
|
3 |
size 5652
|
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 sha256:0a5bfba2d642d62d6d3840b324816dc1169c1ca3f0e889b0b8dc530396b98917
|
3 |
+
size 13896163
|
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_samples": 3000,
|
4 |
-
"exact_match": 68.
|
5 |
-
"f1": 77.
|
6 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 100.0,
|
3 |
"eval_samples": 3000,
|
4 |
+
"exact_match": 68.86666666666666,
|
5 |
+
"f1": 77.76425661888325
|
6 |
}
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"train_loss": 0.
|
4 |
-
"train_runtime":
|
5 |
"train_samples": 3000,
|
6 |
-
"train_samples_per_second": 63.
|
7 |
"train_steps_per_second": 0.505
|
8 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 100.0,
|
3 |
+
"train_loss": 0.09819502154986064,
|
4 |
+
"train_runtime": 4749.1078,
|
5 |
"train_samples": 3000,
|
6 |
+
"train_samples_per_second": 63.17,
|
7 |
"train_steps_per_second": 0.505
|
8 |
}
|
trainer_state.json
CHANGED
@@ -1,40 +1,52 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 20.83,
|
13 |
-
"learning_rate":
|
14 |
-
"loss": 0.
|
15 |
"step": 500
|
16 |
},
|
17 |
{
|
18 |
"epoch": 41.67,
|
19 |
-
"learning_rate":
|
20 |
-
"loss": 0.
|
21 |
"step": 1000
|
22 |
},
|
23 |
{
|
24 |
-
"epoch":
|
25 |
-
"
|
26 |
-
"
|
27 |
-
"
|
28 |
-
|
29 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
30 |
"train_steps_per_second": 0.505
|
31 |
}
|
32 |
],
|
33 |
"logging_steps": 500,
|
34 |
-
"max_steps":
|
35 |
-
"num_train_epochs":
|
36 |
"save_steps": 500,
|
37 |
-
"total_flos":
|
38 |
"trial_name": null,
|
39 |
"trial_params": null
|
40 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 100.0,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 2400,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 20.83,
|
13 |
+
"learning_rate": 3.958333333333333e-05,
|
14 |
+
"loss": 0.4465,
|
15 |
"step": 500
|
16 |
},
|
17 |
{
|
18 |
"epoch": 41.67,
|
19 |
+
"learning_rate": 2.916666666666667e-05,
|
20 |
+
"loss": 0.0159,
|
21 |
"step": 1000
|
22 |
},
|
23 |
{
|
24 |
+
"epoch": 62.5,
|
25 |
+
"learning_rate": 1.8750000000000002e-05,
|
26 |
+
"loss": 0.005,
|
27 |
+
"step": 1500
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 83.33,
|
31 |
+
"learning_rate": 8.333333333333334e-06,
|
32 |
+
"loss": 0.0025,
|
33 |
+
"step": 2000
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 100.0,
|
37 |
+
"step": 2400,
|
38 |
+
"total_flos": 2.089590732288e+17,
|
39 |
+
"train_loss": 0.09819502154986064,
|
40 |
+
"train_runtime": 4749.1078,
|
41 |
+
"train_samples_per_second": 63.17,
|
42 |
"train_steps_per_second": 0.505
|
43 |
}
|
44 |
],
|
45 |
"logging_steps": 500,
|
46 |
+
"max_steps": 2400,
|
47 |
+
"num_train_epochs": 100,
|
48 |
"save_steps": 500,
|
49 |
+
"total_flos": 2.089590732288e+17,
|
50 |
"trial_name": null,
|
51 |
"trial_params": null
|
52 |
}
|