haibotamiu
commited on
Commit
•
d283211
1
Parent(s):
ab5e273
End of training
Browse files- README.md +4 -1
- all_results.json +7 -7
- args.bin +1 -1
- eval_nbest_predictions.json +2 -2
- eval_predictions.json +0 -0
- eval_results.json +3 -3
- train_results.json +5 -5
- trainer_state.json +36 -18
README.md
CHANGED
@@ -2,7 +2,10 @@
|
|
2 |
license: apache-2.0
|
3 |
base_model: distilbert-base-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 [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the
|
17 |
|
18 |
## Model description
|
19 |
|
|
|
2 |
license: apache-2.0
|
3 |
base_model: distilbert-base-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 [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the squad dataset.
|
20 |
|
21 |
## Model description
|
22 |
|
all_results.json
CHANGED
@@ -1,11 +1,11 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
"eval_samples": 5000,
|
4 |
-
"exact_match": 57.
|
5 |
-
"f1":
|
6 |
-
"train_loss": 0.
|
7 |
-
"train_runtime":
|
8 |
"train_samples": 5000,
|
9 |
-
"train_samples_per_second":
|
10 |
-
"train_steps_per_second": 6.
|
11 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 20.0,
|
3 |
"eval_samples": 5000,
|
4 |
+
"exact_match": 57.7,
|
5 |
+
"f1": 67.32789188139478,
|
6 |
+
"train_loss": 0.3331835723606644,
|
7 |
+
"train_runtime": 459.4653,
|
8 |
"train_samples": 5000,
|
9 |
+
"train_samples_per_second": 217.644,
|
10 |
+
"train_steps_per_second": 6.834
|
11 |
}
|
args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5588
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:19fcedcf799fe5c8a5554bae0d95655190c81d2a729e89a6ace2293869ce7b49
|
3 |
size 5588
|
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 sha256:44c78f55fa51175ec7393b9b2e06c58fc1f4e109fdee310cf1d8f4b1f94dd962
|
3 |
+
size 23011821
|
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": 5000,
|
4 |
-
"exact_match": 57.
|
5 |
-
"f1":
|
6 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 20.0,
|
3 |
"eval_samples": 5000,
|
4 |
+
"exact_match": 57.7,
|
5 |
+
"f1": 67.32789188139478
|
6 |
}
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"train_loss": 0.
|
4 |
-
"train_runtime":
|
5 |
"train_samples": 5000,
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second": 6.
|
8 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 20.0,
|
3 |
+
"train_loss": 0.3331835723606644,
|
4 |
+
"train_runtime": 459.4653,
|
5 |
"train_samples": 5000,
|
6 |
+
"train_samples_per_second": 217.644,
|
7 |
+
"train_steps_per_second": 6.834
|
8 |
}
|
trainer_state.json
CHANGED
@@ -1,46 +1,64 @@
|
|
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": 3.18,
|
13 |
-
"learning_rate":
|
14 |
-
"loss": 1.
|
15 |
"step": 500
|
16 |
},
|
17 |
{
|
18 |
"epoch": 6.37,
|
19 |
-
"learning_rate":
|
20 |
-
"loss": 0.
|
21 |
"step": 1000
|
22 |
},
|
23 |
{
|
24 |
"epoch": 9.55,
|
25 |
-
"learning_rate": 2.
|
26 |
-
"loss": 0.
|
27 |
"step": 1500
|
28 |
},
|
29 |
{
|
30 |
-
"epoch":
|
31 |
-
"
|
32 |
-
"
|
33 |
-
"
|
34 |
-
|
35 |
-
|
36 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
37 |
}
|
38 |
],
|
39 |
"logging_steps": 500,
|
40 |
-
"max_steps":
|
41 |
-
"num_train_epochs":
|
42 |
"save_steps": 500,
|
43 |
-
"total_flos":
|
44 |
"trial_name": null,
|
45 |
"trial_params": null
|
46 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 20.0,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 3140,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 3.18,
|
13 |
+
"learning_rate": 4.2038216560509556e-05,
|
14 |
+
"loss": 1.5882,
|
15 |
"step": 500
|
16 |
},
|
17 |
{
|
18 |
"epoch": 6.37,
|
19 |
+
"learning_rate": 3.407643312101911e-05,
|
20 |
+
"loss": 0.2947,
|
21 |
"step": 1000
|
22 |
},
|
23 |
{
|
24 |
"epoch": 9.55,
|
25 |
+
"learning_rate": 2.6114649681528662e-05,
|
26 |
+
"loss": 0.112,
|
27 |
"step": 1500
|
28 |
},
|
29 |
{
|
30 |
+
"epoch": 12.74,
|
31 |
+
"learning_rate": 1.8152866242038215e-05,
|
32 |
+
"loss": 0.0539,
|
33 |
+
"step": 2000
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 15.92,
|
37 |
+
"learning_rate": 1.0191082802547772e-05,
|
38 |
+
"loss": 0.0277,
|
39 |
+
"step": 2500
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 19.11,
|
43 |
+
"learning_rate": 2.229299363057325e-06,
|
44 |
+
"loss": 0.0134,
|
45 |
+
"step": 3000
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 20.0,
|
49 |
+
"step": 3140,
|
50 |
+
"total_flos": 9798982502400000.0,
|
51 |
+
"train_loss": 0.3331835723606644,
|
52 |
+
"train_runtime": 459.4653,
|
53 |
+
"train_samples_per_second": 217.644,
|
54 |
+
"train_steps_per_second": 6.834
|
55 |
}
|
56 |
],
|
57 |
"logging_steps": 500,
|
58 |
+
"max_steps": 3140,
|
59 |
+
"num_train_epochs": 20,
|
60 |
"save_steps": 500,
|
61 |
+
"total_flos": 9798982502400000.0,
|
62 |
"trial_name": null,
|
63 |
"trial_params": null
|
64 |
}
|