haibotamiu
commited on
Commit
•
698711a
1
Parent(s):
3673da8
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 +78 -24
README.md
CHANGED
@@ -2,7 +2,10 @@
|
|
2 |
license: apache-2.0
|
3 |
base_model: bert-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 [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the
|
17 |
|
18 |
## Model description
|
19 |
|
|
|
2 |
license: apache-2.0
|
3 |
base_model: bert-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 [bert-base-uncased](https://huggingface.co/bert-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":
|
5 |
-
"f1":
|
6 |
-
"train_loss": 0.
|
7 |
-
"train_runtime":
|
8 |
"train_samples": 5000,
|
9 |
-
"train_samples_per_second":
|
10 |
-
"train_steps_per_second": 3.
|
11 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 50.0,
|
3 |
"eval_samples": 5000,
|
4 |
+
"exact_match": 34.92,
|
5 |
+
"f1": 47.79389306204009,
|
6 |
+
"train_loss": 0.4468785848435323,
|
7 |
+
"train_runtime": 2136.4763,
|
8 |
"train_samples": 5000,
|
9 |
+
"train_samples_per_second": 117.015,
|
10 |
+
"train_steps_per_second": 3.674
|
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 sha256:95bdff34edcf1b619422dd081958b538f4912da5430f12817e638bacd4ac122c
|
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 sha256:4a994ec4ce88bef3058d6401482c9e7ebc3b7bf5a0f22ee54e47429201c59ebd
|
3 |
+
size 23040916
|
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":
|
5 |
-
"f1":
|
6 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 50.0,
|
3 |
"eval_samples": 5000,
|
4 |
+
"exact_match": 34.92,
|
5 |
+
"f1": 47.79389306204009
|
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": 3.
|
8 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 50.0,
|
3 |
+
"train_loss": 0.4468785848435323,
|
4 |
+
"train_runtime": 2136.4763,
|
5 |
"train_samples": 5000,
|
6 |
+
"train_samples_per_second": 117.015,
|
7 |
+
"train_steps_per_second": 3.674
|
8 |
}
|
trainer_state.json
CHANGED
@@ -1,64 +1,118 @@
|
|
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": 4.
|
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":
|
26 |
-
"loss": 0.
|
27 |
"step": 1500
|
28 |
},
|
29 |
{
|
30 |
"epoch": 12.74,
|
31 |
-
"learning_rate":
|
32 |
-
"loss": 0.
|
33 |
"step": 2000
|
34 |
},
|
35 |
{
|
36 |
"epoch": 15.92,
|
37 |
-
"learning_rate":
|
38 |
-
"loss": 0.
|
39 |
"step": 2500
|
40 |
},
|
41 |
{
|
42 |
"epoch": 19.11,
|
43 |
-
"learning_rate":
|
44 |
-
"loss": 0.
|
45 |
"step": 3000
|
46 |
},
|
47 |
{
|
48 |
-
"epoch":
|
49 |
-
"
|
50 |
-
"
|
51 |
-
"
|
52 |
-
|
53 |
-
|
54 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
55 |
}
|
56 |
],
|
57 |
"logging_steps": 500,
|
58 |
-
"max_steps":
|
59 |
-
"num_train_epochs":
|
60 |
"save_steps": 500,
|
61 |
-
"total_flos":
|
62 |
"trial_name": null,
|
63 |
"trial_params": null
|
64 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 50.0,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 7850,
|
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": 4.681528662420383e-05,
|
14 |
+
"loss": 1.2838,
|
15 |
"step": 500
|
16 |
},
|
17 |
{
|
18 |
"epoch": 6.37,
|
19 |
+
"learning_rate": 4.3630573248407646e-05,
|
20 |
+
"loss": 0.2252,
|
21 |
"step": 1000
|
22 |
},
|
23 |
{
|
24 |
"epoch": 9.55,
|
25 |
+
"learning_rate": 4.044585987261147e-05,
|
26 |
+
"loss": 0.1119,
|
27 |
"step": 1500
|
28 |
},
|
29 |
{
|
30 |
"epoch": 12.74,
|
31 |
+
"learning_rate": 3.7261146496815283e-05,
|
32 |
+
"loss": 0.066,
|
33 |
"step": 2000
|
34 |
},
|
35 |
{
|
36 |
"epoch": 15.92,
|
37 |
+
"learning_rate": 3.407643312101911e-05,
|
38 |
+
"loss": 0.0493,
|
39 |
"step": 2500
|
40 |
},
|
41 |
{
|
42 |
"epoch": 19.11,
|
43 |
+
"learning_rate": 3.089171974522293e-05,
|
44 |
+
"loss": 0.041,
|
45 |
"step": 3000
|
46 |
},
|
47 |
{
|
48 |
+
"epoch": 22.29,
|
49 |
+
"learning_rate": 2.7707006369426753e-05,
|
50 |
+
"loss": 0.0492,
|
51 |
+
"step": 3500
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 25.48,
|
55 |
+
"learning_rate": 2.4522292993630575e-05,
|
56 |
+
"loss": 0.0654,
|
57 |
+
"step": 4000
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 28.66,
|
61 |
+
"learning_rate": 2.1337579617834397e-05,
|
62 |
+
"loss": 0.0816,
|
63 |
+
"step": 4500
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 31.85,
|
67 |
+
"learning_rate": 1.8152866242038215e-05,
|
68 |
+
"loss": 0.1484,
|
69 |
+
"step": 5000
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 35.03,
|
73 |
+
"learning_rate": 1.4968152866242039e-05,
|
74 |
+
"loss": 0.3258,
|
75 |
+
"step": 5500
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 38.22,
|
79 |
+
"learning_rate": 1.178343949044586e-05,
|
80 |
+
"loss": 0.6468,
|
81 |
+
"step": 6000
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 41.4,
|
85 |
+
"learning_rate": 8.598726114649681e-06,
|
86 |
+
"loss": 0.7716,
|
87 |
+
"step": 6500
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 44.59,
|
91 |
+
"learning_rate": 5.414012738853504e-06,
|
92 |
+
"loss": 1.0718,
|
93 |
+
"step": 7000
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 47.77,
|
97 |
+
"learning_rate": 2.229299363057325e-06,
|
98 |
+
"loss": 1.2439,
|
99 |
+
"step": 7500
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 50.0,
|
103 |
+
"step": 7850,
|
104 |
+
"total_flos": 4.8993141888e+16,
|
105 |
+
"train_loss": 0.4468785848435323,
|
106 |
+
"train_runtime": 2136.4763,
|
107 |
+
"train_samples_per_second": 117.015,
|
108 |
+
"train_steps_per_second": 3.674
|
109 |
}
|
110 |
],
|
111 |
"logging_steps": 500,
|
112 |
+
"max_steps": 7850,
|
113 |
+
"num_train_epochs": 50,
|
114 |
"save_steps": 500,
|
115 |
+
"total_flos": 4.8993141888e+16,
|
116 |
"trial_name": null,
|
117 |
"trial_params": null
|
118 |
}
|