End of training
Browse files- README.md +21 -3
- all_results.json +6 -6
- eval_results.json +3 -3
- logs/events.out.tfevents.1677749304.serv-3317.65033.5 +3 -0
- train_results.json +3 -3
- trainer_state.json +24 -24
README.md
CHANGED
@@ -1,12 +1,30 @@
|
|
1 |
---
|
|
|
|
|
2 |
tags:
|
3 |
- generated_from_trainer
|
|
|
|
|
4 |
metrics:
|
5 |
- accuracy
|
6 |
- f1
|
7 |
model-index:
|
8 |
- name: hBERTv2_data_aug_mrpc
|
9 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
10 |
---
|
11 |
|
12 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -14,9 +32,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
14 |
|
15 |
# hBERTv2_data_aug_mrpc
|
16 |
|
17 |
-
This model is a fine-tuned version of [gokuls/bert_12_layer_model_v2](https://huggingface.co/gokuls/bert_12_layer_model_v2) on
|
18 |
It achieves the following results on the evaluation set:
|
19 |
-
- Loss: 0.
|
20 |
- Accuracy: 0.6838
|
21 |
- F1: 0.8122
|
22 |
- Combined Score: 0.7480
|
|
|
1 |
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- glue
|
8 |
metrics:
|
9 |
- accuracy
|
10 |
- f1
|
11 |
model-index:
|
12 |
- name: hBERTv2_data_aug_mrpc
|
13 |
+
results:
|
14 |
+
- task:
|
15 |
+
name: Text Classification
|
16 |
+
type: text-classification
|
17 |
+
dataset:
|
18 |
+
name: GLUE MRPC
|
19 |
+
type: glue
|
20 |
+
args: mrpc
|
21 |
+
metrics:
|
22 |
+
- name: Accuracy
|
23 |
+
type: accuracy
|
24 |
+
value: 0.6838235294117647
|
25 |
+
- name: F1
|
26 |
+
type: f1
|
27 |
+
value: 0.8122270742358079
|
28 |
---
|
29 |
|
30 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
32 |
|
33 |
# hBERTv2_data_aug_mrpc
|
34 |
|
35 |
+
This model is a fine-tuned version of [gokuls/bert_12_layer_model_v2](https://huggingface.co/gokuls/bert_12_layer_model_v2) on the GLUE MRPC dataset.
|
36 |
It achieves the following results on the evaluation set:
|
37 |
+
- Loss: 0.6240
|
38 |
- Accuracy: 0.6838
|
39 |
- F1: 0.8122
|
40 |
- Combined Score: 0.7480
|
all_results.json
CHANGED
@@ -4,13 +4,13 @@
|
|
4 |
"eval_combined_score": 0.7480253018237863,
|
5 |
"eval_f1": 0.8122270742358079,
|
6 |
"eval_loss": 0.6239516139030457,
|
7 |
-
"eval_runtime": 0.
|
8 |
"eval_samples": 408,
|
9 |
-
"eval_samples_per_second":
|
10 |
-
"eval_steps_per_second": 4.
|
11 |
"train_loss": 0.6304825585368076,
|
12 |
-
"train_runtime":
|
13 |
"train_samples": 250736,
|
14 |
-
"train_samples_per_second":
|
15 |
-
"train_steps_per_second": 8.
|
16 |
}
|
|
|
4 |
"eval_combined_score": 0.7480253018237863,
|
5 |
"eval_f1": 0.8122270742358079,
|
6 |
"eval_loss": 0.6239516139030457,
|
7 |
+
"eval_runtime": 0.4873,
|
8 |
"eval_samples": 408,
|
9 |
+
"eval_samples_per_second": 837.231,
|
10 |
+
"eval_steps_per_second": 4.104,
|
11 |
"train_loss": 0.6304825585368076,
|
12 |
+
"train_runtime": 6112.7657,
|
13 |
"train_samples": 250736,
|
14 |
+
"train_samples_per_second": 2050.921,
|
15 |
+
"train_steps_per_second": 8.016
|
16 |
}
|
eval_results.json
CHANGED
@@ -4,8 +4,8 @@
|
|
4 |
"eval_combined_score": 0.7480253018237863,
|
5 |
"eval_f1": 0.8122270742358079,
|
6 |
"eval_loss": 0.6239516139030457,
|
7 |
-
"eval_runtime": 0.
|
8 |
"eval_samples": 408,
|
9 |
-
"eval_samples_per_second":
|
10 |
-
"eval_steps_per_second": 4.
|
11 |
}
|
|
|
4 |
"eval_combined_score": 0.7480253018237863,
|
5 |
"eval_f1": 0.8122270742358079,
|
6 |
"eval_loss": 0.6239516139030457,
|
7 |
+
"eval_runtime": 0.4873,
|
8 |
"eval_samples": 408,
|
9 |
+
"eval_samples_per_second": 837.231,
|
10 |
+
"eval_steps_per_second": 4.104
|
11 |
}
|
logs/events.out.tfevents.1677749304.serv-3317.65033.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:70bf5d804c4e3b85adfcaafca019c400c74dccab4e6ffda8c616e09aa3e89dbe
|
3 |
+
size 467
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 7.0,
|
3 |
"train_loss": 0.6304825585368076,
|
4 |
-
"train_runtime":
|
5 |
"train_samples": 250736,
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second": 8.
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 7.0,
|
3 |
"train_loss": 0.6304825585368076,
|
4 |
+
"train_runtime": 6112.7657,
|
5 |
"train_samples": 250736,
|
6 |
+
"train_samples_per_second": 2050.921,
|
7 |
+
"train_steps_per_second": 8.016
|
8 |
}
|
trainer_state.json
CHANGED
@@ -19,9 +19,9 @@
|
|
19 |
"eval_combined_score": 0.7480253018237863,
|
20 |
"eval_f1": 0.8122270742358079,
|
21 |
"eval_loss": 0.6244884133338928,
|
22 |
-
"eval_runtime": 0.
|
23 |
-
"eval_samples_per_second":
|
24 |
-
"eval_steps_per_second": 4.
|
25 |
"step": 980
|
26 |
},
|
27 |
{
|
@@ -36,9 +36,9 @@
|
|
36 |
"eval_combined_score": 0.7480253018237863,
|
37 |
"eval_f1": 0.8122270742358079,
|
38 |
"eval_loss": 0.6239516139030457,
|
39 |
-
"eval_runtime": 0.
|
40 |
-
"eval_samples_per_second":
|
41 |
-
"eval_steps_per_second": 4.
|
42 |
"step": 1960
|
43 |
},
|
44 |
{
|
@@ -53,9 +53,9 @@
|
|
53 |
"eval_combined_score": 0.7480253018237863,
|
54 |
"eval_f1": 0.8122270742358079,
|
55 |
"eval_loss": 0.6259029507637024,
|
56 |
-
"eval_runtime": 0.
|
57 |
-
"eval_samples_per_second": 834.
|
58 |
-
"eval_steps_per_second": 4.
|
59 |
"step": 2940
|
60 |
},
|
61 |
{
|
@@ -70,9 +70,9 @@
|
|
70 |
"eval_combined_score": 0.7480253018237863,
|
71 |
"eval_f1": 0.8122270742358079,
|
72 |
"eval_loss": 0.6251693964004517,
|
73 |
-
"eval_runtime": 0.
|
74 |
-
"eval_samples_per_second":
|
75 |
-
"eval_steps_per_second": 4.
|
76 |
"step": 3920
|
77 |
},
|
78 |
{
|
@@ -87,9 +87,9 @@
|
|
87 |
"eval_combined_score": 0.7480253018237863,
|
88 |
"eval_f1": 0.8122270742358079,
|
89 |
"eval_loss": 0.6241449117660522,
|
90 |
-
"eval_runtime": 0.
|
91 |
-
"eval_samples_per_second":
|
92 |
-
"eval_steps_per_second": 4.
|
93 |
"step": 4900
|
94 |
},
|
95 |
{
|
@@ -104,9 +104,9 @@
|
|
104 |
"eval_combined_score": 0.7480253018237863,
|
105 |
"eval_f1": 0.8122270742358079,
|
106 |
"eval_loss": 0.6241024136543274,
|
107 |
-
"eval_runtime": 0.
|
108 |
-
"eval_samples_per_second":
|
109 |
-
"eval_steps_per_second": 4.
|
110 |
"step": 5880
|
111 |
},
|
112 |
{
|
@@ -121,9 +121,9 @@
|
|
121 |
"eval_combined_score": 0.7480253018237863,
|
122 |
"eval_f1": 0.8122270742358079,
|
123 |
"eval_loss": 0.6241885423660278,
|
124 |
-
"eval_runtime": 0.
|
125 |
-
"eval_samples_per_second":
|
126 |
-
"eval_steps_per_second": 4.
|
127 |
"step": 6860
|
128 |
},
|
129 |
{
|
@@ -131,9 +131,9 @@
|
|
131 |
"step": 6860,
|
132 |
"total_flos": 2.1861021041400218e+17,
|
133 |
"train_loss": 0.6304825585368076,
|
134 |
-
"train_runtime":
|
135 |
-
"train_samples_per_second":
|
136 |
-
"train_steps_per_second": 8.
|
137 |
}
|
138 |
],
|
139 |
"max_steps": 49000,
|
|
|
19 |
"eval_combined_score": 0.7480253018237863,
|
20 |
"eval_f1": 0.8122270742358079,
|
21 |
"eval_loss": 0.6244884133338928,
|
22 |
+
"eval_runtime": 0.489,
|
23 |
+
"eval_samples_per_second": 834.271,
|
24 |
+
"eval_steps_per_second": 4.09,
|
25 |
"step": 980
|
26 |
},
|
27 |
{
|
|
|
36 |
"eval_combined_score": 0.7480253018237863,
|
37 |
"eval_f1": 0.8122270742358079,
|
38 |
"eval_loss": 0.6239516139030457,
|
39 |
+
"eval_runtime": 0.4884,
|
40 |
+
"eval_samples_per_second": 835.412,
|
41 |
+
"eval_steps_per_second": 4.095,
|
42 |
"step": 1960
|
43 |
},
|
44 |
{
|
|
|
53 |
"eval_combined_score": 0.7480253018237863,
|
54 |
"eval_f1": 0.8122270742358079,
|
55 |
"eval_loss": 0.6259029507637024,
|
56 |
+
"eval_runtime": 0.489,
|
57 |
+
"eval_samples_per_second": 834.359,
|
58 |
+
"eval_steps_per_second": 4.09,
|
59 |
"step": 2940
|
60 |
},
|
61 |
{
|
|
|
70 |
"eval_combined_score": 0.7480253018237863,
|
71 |
"eval_f1": 0.8122270742358079,
|
72 |
"eval_loss": 0.6251693964004517,
|
73 |
+
"eval_runtime": 0.4902,
|
74 |
+
"eval_samples_per_second": 832.302,
|
75 |
+
"eval_steps_per_second": 4.08,
|
76 |
"step": 3920
|
77 |
},
|
78 |
{
|
|
|
87 |
"eval_combined_score": 0.7480253018237863,
|
88 |
"eval_f1": 0.8122270742358079,
|
89 |
"eval_loss": 0.6241449117660522,
|
90 |
+
"eval_runtime": 0.4885,
|
91 |
+
"eval_samples_per_second": 835.178,
|
92 |
+
"eval_steps_per_second": 4.094,
|
93 |
"step": 4900
|
94 |
},
|
95 |
{
|
|
|
104 |
"eval_combined_score": 0.7480253018237863,
|
105 |
"eval_f1": 0.8122270742358079,
|
106 |
"eval_loss": 0.6241024136543274,
|
107 |
+
"eval_runtime": 0.4883,
|
108 |
+
"eval_samples_per_second": 835.632,
|
109 |
+
"eval_steps_per_second": 4.096,
|
110 |
"step": 5880
|
111 |
},
|
112 |
{
|
|
|
121 |
"eval_combined_score": 0.7480253018237863,
|
122 |
"eval_f1": 0.8122270742358079,
|
123 |
"eval_loss": 0.6241885423660278,
|
124 |
+
"eval_runtime": 0.4876,
|
125 |
+
"eval_samples_per_second": 836.76,
|
126 |
+
"eval_steps_per_second": 4.102,
|
127 |
"step": 6860
|
128 |
},
|
129 |
{
|
|
|
131 |
"step": 6860,
|
132 |
"total_flos": 2.1861021041400218e+17,
|
133 |
"train_loss": 0.6304825585368076,
|
134 |
+
"train_runtime": 6112.7657,
|
135 |
+
"train_samples_per_second": 2050.921,
|
136 |
+
"train_steps_per_second": 8.016
|
137 |
}
|
138 |
],
|
139 |
"max_steps": 49000,
|