End of training
Browse files- README.md +10 -8
- all_results.json +7 -7
- eval_results.json +3 -3
- logs/events.out.tfevents.1677737995.serv-9223.249682.5 +3 -0
- train_results.json +4 -4
- trainer_state.json +40 -40
README.md
CHANGED
@@ -1,4 +1,6 @@
|
|
1 |
---
|
|
|
|
|
2 |
tags:
|
3 |
- generated_from_trainer
|
4 |
datasets:
|
@@ -13,7 +15,7 @@ model-index:
|
|
13 |
name: Text Classification
|
14 |
type: text-classification
|
15 |
dataset:
|
16 |
-
name:
|
17 |
type: glue
|
18 |
config: mrpc
|
19 |
split: validation
|
@@ -21,10 +23,10 @@ model-index:
|
|
21 |
metrics:
|
22 |
- name: Accuracy
|
23 |
type: accuracy
|
24 |
-
value: 0.
|
25 |
- name: F1
|
26 |
type: f1
|
27 |
-
value: 0.
|
28 |
---
|
29 |
|
30 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -32,12 +34,12 @@ should probably proofread and complete it, then remove this comment. -->
|
|
32 |
|
33 |
# hBERTv1_mrpc
|
34 |
|
35 |
-
This model is a fine-tuned version of [gokuls/bert_12_layer_model_v1](https://huggingface.co/gokuls/bert_12_layer_model_v1) on the
|
36 |
It achieves the following results on the evaluation set:
|
37 |
-
- Loss: 0.
|
38 |
-
- Accuracy: 0.
|
39 |
-
- F1: 0.
|
40 |
-
- Combined Score: 0.
|
41 |
|
42 |
## Model description
|
43 |
|
|
|
1 |
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
|
|
15 |
name: Text Classification
|
16 |
type: text-classification
|
17 |
dataset:
|
18 |
+
name: GLUE MRPC
|
19 |
type: glue
|
20 |
config: mrpc
|
21 |
split: validation
|
|
|
23 |
metrics:
|
24 |
- name: Accuracy
|
25 |
type: accuracy
|
26 |
+
value: 0.6862745098039216
|
27 |
- name: F1
|
28 |
type: f1
|
29 |
+
value: 0.7999999999999999
|
30 |
---
|
31 |
|
32 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
34 |
|
35 |
# hBERTv1_mrpc
|
36 |
|
37 |
+
This model is a fine-tuned version of [gokuls/bert_12_layer_model_v1](https://huggingface.co/gokuls/bert_12_layer_model_v1) on the GLUE MRPC dataset.
|
38 |
It achieves the following results on the evaluation set:
|
39 |
+
- Loss: 0.6051
|
40 |
+
- Accuracy: 0.6863
|
41 |
+
- F1: 0.8000
|
42 |
+
- Combined Score: 0.7431
|
43 |
|
44 |
## Model description
|
45 |
|
all_results.json
CHANGED
@@ -4,13 +4,13 @@
|
|
4 |
"eval_combined_score": 0.7431372549019608,
|
5 |
"eval_f1": 0.7999999999999999,
|
6 |
"eval_loss": 0.6050820350646973,
|
7 |
-
"eval_runtime": 0.
|
8 |
"eval_samples": 408,
|
9 |
-
"eval_samples_per_second":
|
10 |
-
"eval_steps_per_second": 3.
|
11 |
-
"train_loss": 0.
|
12 |
-
"train_runtime":
|
13 |
"train_samples": 3668,
|
14 |
-
"train_samples_per_second":
|
15 |
-
"train_steps_per_second":
|
16 |
}
|
|
|
4 |
"eval_combined_score": 0.7431372549019608,
|
5 |
"eval_f1": 0.7999999999999999,
|
6 |
"eval_loss": 0.6050820350646973,
|
7 |
+
"eval_runtime": 0.5364,
|
8 |
"eval_samples": 408,
|
9 |
+
"eval_samples_per_second": 760.588,
|
10 |
+
"eval_steps_per_second": 3.728,
|
11 |
+
"train_loss": 0.4964691546228197,
|
12 |
+
"train_runtime": 282.764,
|
13 |
"train_samples": 3668,
|
14 |
+
"train_samples_per_second": 648.597,
|
15 |
+
"train_steps_per_second": 2.652
|
16 |
}
|
eval_results.json
CHANGED
@@ -4,8 +4,8 @@
|
|
4 |
"eval_combined_score": 0.7431372549019608,
|
5 |
"eval_f1": 0.7999999999999999,
|
6 |
"eval_loss": 0.6050820350646973,
|
7 |
-
"eval_runtime": 0.
|
8 |
"eval_samples": 408,
|
9 |
-
"eval_samples_per_second":
|
10 |
-
"eval_steps_per_second": 3.
|
11 |
}
|
|
|
4 |
"eval_combined_score": 0.7431372549019608,
|
5 |
"eval_f1": 0.7999999999999999,
|
6 |
"eval_loss": 0.6050820350646973,
|
7 |
+
"eval_runtime": 0.5364,
|
8 |
"eval_samples": 408,
|
9 |
+
"eval_samples_per_second": 760.588,
|
10 |
+
"eval_steps_per_second": 3.728
|
11 |
}
|
logs/events.out.tfevents.1677737995.serv-9223.249682.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2f50ea8f611c8ea2600b186a8a0f9dace58aea64fa20b2be9baacf4404f4d569
|
3 |
+
size 467
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 12.0,
|
3 |
-
"train_loss": 0.
|
4 |
-
"train_runtime":
|
5 |
"train_samples": 3668,
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second":
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 12.0,
|
3 |
+
"train_loss": 0.4964691546228197,
|
4 |
+
"train_runtime": 282.764,
|
5 |
"train_samples": 3668,
|
6 |
+
"train_samples_per_second": 648.597,
|
7 |
+
"train_steps_per_second": 2.652
|
8 |
}
|
trainer_state.json
CHANGED
@@ -19,9 +19,9 @@
|
|
19 |
"eval_combined_score": 0.7480253018237863,
|
20 |
"eval_f1": 0.8122270742358079,
|
21 |
"eval_loss": 0.6242610216140747,
|
22 |
-
"eval_runtime": 0.
|
23 |
-
"eval_samples_per_second":
|
24 |
-
"eval_steps_per_second": 3.
|
25 |
"step": 15
|
26 |
},
|
27 |
{
|
@@ -36,9 +36,9 @@
|
|
36 |
"eval_combined_score": 0.7563543936092956,
|
37 |
"eval_f1": 0.8117283950617284,
|
38 |
"eval_loss": 0.6174396872520447,
|
39 |
-
"eval_runtime": 0.
|
40 |
-
"eval_samples_per_second":
|
41 |
-
"eval_steps_per_second": 3.
|
42 |
"step": 30
|
43 |
},
|
44 |
{
|
@@ -53,9 +53,9 @@
|
|
53 |
"eval_combined_score": 0.7571301247771836,
|
54 |
"eval_f1": 0.8181818181818181,
|
55 |
"eval_loss": 0.6089469194412231,
|
56 |
-
"eval_runtime": 0.
|
57 |
-
"eval_samples_per_second":
|
58 |
-
"eval_steps_per_second": 3.
|
59 |
"step": 45
|
60 |
},
|
61 |
{
|
@@ -70,9 +70,9 @@
|
|
70 |
"eval_combined_score": 0.7508428629183632,
|
71 |
"eval_f1": 0.8129602356406479,
|
72 |
"eval_loss": 0.606163740158081,
|
73 |
-
"eval_runtime": 0.
|
74 |
-
"eval_samples_per_second":
|
75 |
-
"eval_steps_per_second": 3.
|
76 |
"step": 60
|
77 |
},
|
78 |
{
|
@@ -87,9 +87,9 @@
|
|
87 |
"eval_combined_score": 0.739911448450348,
|
88 |
"eval_f1": 0.7935483870967743,
|
89 |
"eval_loss": 0.6104128956794739,
|
90 |
-
"eval_runtime": 0.
|
91 |
-
"eval_samples_per_second":
|
92 |
-
"eval_steps_per_second": 3.
|
93 |
"step": 75
|
94 |
},
|
95 |
{
|
@@ -104,9 +104,9 @@
|
|
104 |
"eval_combined_score": 0.7633269720101782,
|
105 |
"eval_f1": 0.818320610687023,
|
106 |
"eval_loss": 0.6184039115905762,
|
107 |
-
"eval_runtime": 0.
|
108 |
-
"eval_samples_per_second":
|
109 |
-
"eval_steps_per_second": 3.
|
110 |
"step": 90
|
111 |
},
|
112 |
{
|
@@ -121,9 +121,9 @@
|
|
121 |
"eval_combined_score": 0.7431372549019608,
|
122 |
"eval_f1": 0.7999999999999999,
|
123 |
"eval_loss": 0.6050820350646973,
|
124 |
-
"eval_runtime": 0.
|
125 |
-
"eval_samples_per_second":
|
126 |
-
"eval_steps_per_second": 3.
|
127 |
"step": 105
|
128 |
},
|
129 |
{
|
@@ -138,9 +138,9 @@
|
|
138 |
"eval_combined_score": 0.7477645971225257,
|
139 |
"eval_f1": 0.8019017432646594,
|
140 |
"eval_loss": 0.6560007929801941,
|
141 |
-
"eval_runtime": 0.
|
142 |
-
"eval_samples_per_second":
|
143 |
-
"eval_steps_per_second": 3.
|
144 |
"step": 120
|
145 |
},
|
146 |
{
|
@@ -155,9 +155,9 @@
|
|
155 |
"eval_combined_score": 0.7282749937269242,
|
156 |
"eval_f1": 0.7678244972577698,
|
157 |
"eval_loss": 0.6672889590263367,
|
158 |
-
"eval_runtime": 0.
|
159 |
-
"eval_samples_per_second":
|
160 |
-
"eval_steps_per_second": 3.
|
161 |
"step": 135
|
162 |
},
|
163 |
{
|
@@ -172,9 +172,9 @@
|
|
172 |
"eval_combined_score": 0.7382192221150756,
|
173 |
"eval_f1": 0.7901639344262296,
|
174 |
"eval_loss": 0.8091686367988586,
|
175 |
-
"eval_runtime": 0.
|
176 |
-
"eval_samples_per_second":
|
177 |
-
"eval_steps_per_second": 3.
|
178 |
"step": 150
|
179 |
},
|
180 |
{
|
@@ -189,9 +189,9 @@
|
|
189 |
"eval_combined_score": 0.741110712577714,
|
190 |
"eval_f1": 0.7934959349593496,
|
191 |
"eval_loss": 0.9342193603515625,
|
192 |
-
"eval_runtime": 0.
|
193 |
-
"eval_samples_per_second":
|
194 |
-
"eval_steps_per_second": 3.
|
195 |
"step": 165
|
196 |
},
|
197 |
{
|
@@ -206,19 +206,19 @@
|
|
206 |
"eval_combined_score": 0.7324041246379707,
|
207 |
"eval_f1": 0.7809847198641766,
|
208 |
"eval_loss": 0.9707943201065063,
|
209 |
-
"eval_runtime": 0.
|
210 |
-
"eval_samples_per_second":
|
211 |
-
"eval_steps_per_second": 3.
|
212 |
"step": 180
|
213 |
},
|
214 |
{
|
215 |
"epoch": 12.0,
|
216 |
"step": 180,
|
217 |
"total_flos": 5559706315653120.0,
|
218 |
-
"train_loss": 0.
|
219 |
-
"train_runtime":
|
220 |
-
"train_samples_per_second":
|
221 |
-
"train_steps_per_second":
|
222 |
}
|
223 |
],
|
224 |
"max_steps": 750,
|
|
|
19 |
"eval_combined_score": 0.7480253018237863,
|
20 |
"eval_f1": 0.8122270742358079,
|
21 |
"eval_loss": 0.6242610216140747,
|
22 |
+
"eval_runtime": 0.5234,
|
23 |
+
"eval_samples_per_second": 779.55,
|
24 |
+
"eval_steps_per_second": 3.821,
|
25 |
"step": 15
|
26 |
},
|
27 |
{
|
|
|
36 |
"eval_combined_score": 0.7563543936092956,
|
37 |
"eval_f1": 0.8117283950617284,
|
38 |
"eval_loss": 0.6174396872520447,
|
39 |
+
"eval_runtime": 0.5245,
|
40 |
+
"eval_samples_per_second": 777.948,
|
41 |
+
"eval_steps_per_second": 3.813,
|
42 |
"step": 30
|
43 |
},
|
44 |
{
|
|
|
53 |
"eval_combined_score": 0.7571301247771836,
|
54 |
"eval_f1": 0.8181818181818181,
|
55 |
"eval_loss": 0.6089469194412231,
|
56 |
+
"eval_runtime": 0.5219,
|
57 |
+
"eval_samples_per_second": 781.803,
|
58 |
+
"eval_steps_per_second": 3.832,
|
59 |
"step": 45
|
60 |
},
|
61 |
{
|
|
|
70 |
"eval_combined_score": 0.7508428629183632,
|
71 |
"eval_f1": 0.8129602356406479,
|
72 |
"eval_loss": 0.606163740158081,
|
73 |
+
"eval_runtime": 0.5254,
|
74 |
+
"eval_samples_per_second": 776.564,
|
75 |
+
"eval_steps_per_second": 3.807,
|
76 |
"step": 60
|
77 |
},
|
78 |
{
|
|
|
87 |
"eval_combined_score": 0.739911448450348,
|
88 |
"eval_f1": 0.7935483870967743,
|
89 |
"eval_loss": 0.6104128956794739,
|
90 |
+
"eval_runtime": 0.5226,
|
91 |
+
"eval_samples_per_second": 780.687,
|
92 |
+
"eval_steps_per_second": 3.827,
|
93 |
"step": 75
|
94 |
},
|
95 |
{
|
|
|
104 |
"eval_combined_score": 0.7633269720101782,
|
105 |
"eval_f1": 0.818320610687023,
|
106 |
"eval_loss": 0.6184039115905762,
|
107 |
+
"eval_runtime": 0.5242,
|
108 |
+
"eval_samples_per_second": 778.365,
|
109 |
+
"eval_steps_per_second": 3.816,
|
110 |
"step": 90
|
111 |
},
|
112 |
{
|
|
|
121 |
"eval_combined_score": 0.7431372549019608,
|
122 |
"eval_f1": 0.7999999999999999,
|
123 |
"eval_loss": 0.6050820350646973,
|
124 |
+
"eval_runtime": 0.5657,
|
125 |
+
"eval_samples_per_second": 721.186,
|
126 |
+
"eval_steps_per_second": 3.535,
|
127 |
"step": 105
|
128 |
},
|
129 |
{
|
|
|
138 |
"eval_combined_score": 0.7477645971225257,
|
139 |
"eval_f1": 0.8019017432646594,
|
140 |
"eval_loss": 0.6560007929801941,
|
141 |
+
"eval_runtime": 0.5247,
|
142 |
+
"eval_samples_per_second": 777.645,
|
143 |
+
"eval_steps_per_second": 3.812,
|
144 |
"step": 120
|
145 |
},
|
146 |
{
|
|
|
155 |
"eval_combined_score": 0.7282749937269242,
|
156 |
"eval_f1": 0.7678244972577698,
|
157 |
"eval_loss": 0.6672889590263367,
|
158 |
+
"eval_runtime": 0.5245,
|
159 |
+
"eval_samples_per_second": 777.879,
|
160 |
+
"eval_steps_per_second": 3.813,
|
161 |
"step": 135
|
162 |
},
|
163 |
{
|
|
|
172 |
"eval_combined_score": 0.7382192221150756,
|
173 |
"eval_f1": 0.7901639344262296,
|
174 |
"eval_loss": 0.8091686367988586,
|
175 |
+
"eval_runtime": 0.5259,
|
176 |
+
"eval_samples_per_second": 775.813,
|
177 |
+
"eval_steps_per_second": 3.803,
|
178 |
"step": 150
|
179 |
},
|
180 |
{
|
|
|
189 |
"eval_combined_score": 0.741110712577714,
|
190 |
"eval_f1": 0.7934959349593496,
|
191 |
"eval_loss": 0.9342193603515625,
|
192 |
+
"eval_runtime": 0.5247,
|
193 |
+
"eval_samples_per_second": 777.527,
|
194 |
+
"eval_steps_per_second": 3.811,
|
195 |
"step": 165
|
196 |
},
|
197 |
{
|
|
|
206 |
"eval_combined_score": 0.7324041246379707,
|
207 |
"eval_f1": 0.7809847198641766,
|
208 |
"eval_loss": 0.9707943201065063,
|
209 |
+
"eval_runtime": 0.5231,
|
210 |
+
"eval_samples_per_second": 779.911,
|
211 |
+
"eval_steps_per_second": 3.823,
|
212 |
"step": 180
|
213 |
},
|
214 |
{
|
215 |
"epoch": 12.0,
|
216 |
"step": 180,
|
217 |
"total_flos": 5559706315653120.0,
|
218 |
+
"train_loss": 0.4964691546228197,
|
219 |
+
"train_runtime": 282.764,
|
220 |
+
"train_samples_per_second": 648.597,
|
221 |
+
"train_steps_per_second": 2.652
|
222 |
}
|
223 |
],
|
224 |
"max_steps": 750,
|