End of training
Browse files- README.md +18 -3
- all_results.json +6 -6
- eval_results.json +3 -3
- logs/events.out.tfevents.1677743079.serv-3317.65033.2 +3 -0
- train_results.json +3 -3
- trainer_state.json +27 -27
README.md
CHANGED
@@ -1,11 +1,26 @@
|
|
1 |
---
|
|
|
|
|
2 |
tags:
|
3 |
- generated_from_trainer
|
|
|
|
|
4 |
metrics:
|
5 |
- matthews_correlation
|
6 |
model-index:
|
7 |
- name: hBERTv2_data_aug_cola
|
8 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
9 |
---
|
10 |
|
11 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -13,9 +28,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
13 |
|
14 |
# hBERTv2_data_aug_cola
|
15 |
|
16 |
-
This model is a fine-tuned version of [gokuls/bert_12_layer_model_v2](https://huggingface.co/gokuls/bert_12_layer_model_v2) on
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Loss: 0.
|
19 |
- Matthews Correlation: 0.0
|
20 |
|
21 |
## Model description
|
|
|
1 |
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- glue
|
8 |
metrics:
|
9 |
- matthews_correlation
|
10 |
model-index:
|
11 |
- name: hBERTv2_data_aug_cola
|
12 |
+
results:
|
13 |
+
- task:
|
14 |
+
name: Text Classification
|
15 |
+
type: text-classification
|
16 |
+
dataset:
|
17 |
+
name: GLUE COLA
|
18 |
+
type: glue
|
19 |
+
args: cola
|
20 |
+
metrics:
|
21 |
+
- name: Matthews Correlation
|
22 |
+
type: matthews_correlation
|
23 |
+
value: 0.0
|
24 |
---
|
25 |
|
26 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
28 |
|
29 |
# hBERTv2_data_aug_cola
|
30 |
|
31 |
+
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 COLA dataset.
|
32 |
It achieves the following results on the evaluation set:
|
33 |
+
- Loss: 0.6181
|
34 |
- Matthews Correlation: 0.0
|
35 |
|
36 |
## Model description
|
all_results.json
CHANGED
@@ -2,13 +2,13 @@
|
|
2 |
"epoch": 8.0,
|
3 |
"eval_loss": 0.6180860996246338,
|
4 |
"eval_matthews_correlation": 0.0,
|
5 |
-
"eval_runtime": 1.
|
6 |
"eval_samples": 1043,
|
7 |
-
"eval_samples_per_second":
|
8 |
-
"eval_steps_per_second": 4.
|
9 |
"train_loss": 0.6065069872462107,
|
10 |
-
"train_runtime":
|
11 |
"train_samples": 213609,
|
12 |
-
"train_samples_per_second":
|
13 |
-
"train_steps_per_second":
|
14 |
}
|
|
|
2 |
"epoch": 8.0,
|
3 |
"eval_loss": 0.6180860996246338,
|
4 |
"eval_matthews_correlation": 0.0,
|
5 |
+
"eval_runtime": 1.2264,
|
6 |
"eval_samples": 1043,
|
7 |
+
"eval_samples_per_second": 850.44,
|
8 |
+
"eval_steps_per_second": 4.077,
|
9 |
"train_loss": 0.6065069872462107,
|
10 |
+
"train_runtime": 5969.0208,
|
11 |
"train_samples": 213609,
|
12 |
+
"train_samples_per_second": 1789.314,
|
13 |
+
"train_steps_per_second": 6.994
|
14 |
}
|
eval_results.json
CHANGED
@@ -2,8 +2,8 @@
|
|
2 |
"epoch": 8.0,
|
3 |
"eval_loss": 0.6180860996246338,
|
4 |
"eval_matthews_correlation": 0.0,
|
5 |
-
"eval_runtime": 1.
|
6 |
"eval_samples": 1043,
|
7 |
-
"eval_samples_per_second":
|
8 |
-
"eval_steps_per_second": 4.
|
9 |
}
|
|
|
2 |
"epoch": 8.0,
|
3 |
"eval_loss": 0.6180860996246338,
|
4 |
"eval_matthews_correlation": 0.0,
|
5 |
+
"eval_runtime": 1.2264,
|
6 |
"eval_samples": 1043,
|
7 |
+
"eval_samples_per_second": 850.44,
|
8 |
+
"eval_steps_per_second": 4.077
|
9 |
}
|
logs/events.out.tfevents.1677743079.serv-3317.65033.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ff44264b15daafa7b0fb471e342cf3f5d21c664c7dadb9dc8c2bc915351a26a
|
3 |
+
size 375
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 8.0,
|
3 |
"train_loss": 0.6065069872462107,
|
4 |
-
"train_runtime":
|
5 |
"train_samples": 213609,
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second":
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 8.0,
|
3 |
"train_loss": 0.6065069872462107,
|
4 |
+
"train_runtime": 5969.0208,
|
5 |
"train_samples": 213609,
|
6 |
+
"train_samples_per_second": 1789.314,
|
7 |
+
"train_steps_per_second": 6.994
|
8 |
}
|
trainer_state.json
CHANGED
@@ -17,9 +17,9 @@
|
|
17 |
"epoch": 1.0,
|
18 |
"eval_loss": 0.6237233281135559,
|
19 |
"eval_matthews_correlation": 0.0,
|
20 |
-
"eval_runtime": 1.
|
21 |
-
"eval_samples_per_second":
|
22 |
-
"eval_steps_per_second": 4.
|
23 |
"step": 835
|
24 |
},
|
25 |
{
|
@@ -32,9 +32,9 @@
|
|
32 |
"epoch": 2.0,
|
33 |
"eval_loss": 0.6185952425003052,
|
34 |
"eval_matthews_correlation": 0.0,
|
35 |
-
"eval_runtime": 1.
|
36 |
-
"eval_samples_per_second":
|
37 |
-
"eval_steps_per_second": 4.
|
38 |
"step": 1670
|
39 |
},
|
40 |
{
|
@@ -47,9 +47,9 @@
|
|
47 |
"epoch": 3.0,
|
48 |
"eval_loss": 0.6180860996246338,
|
49 |
"eval_matthews_correlation": 0.0,
|
50 |
-
"eval_runtime": 1.
|
51 |
-
"eval_samples_per_second":
|
52 |
-
"eval_steps_per_second": 4.
|
53 |
"step": 2505
|
54 |
},
|
55 |
{
|
@@ -62,9 +62,9 @@
|
|
62 |
"epoch": 4.0,
|
63 |
"eval_loss": 0.6217709183692932,
|
64 |
"eval_matthews_correlation": 0.0,
|
65 |
-
"eval_runtime": 1.
|
66 |
-
"eval_samples_per_second":
|
67 |
-
"eval_steps_per_second": 4.
|
68 |
"step": 3340
|
69 |
},
|
70 |
{
|
@@ -77,9 +77,9 @@
|
|
77 |
"epoch": 5.0,
|
78 |
"eval_loss": 0.6211623549461365,
|
79 |
"eval_matthews_correlation": 0.0,
|
80 |
-
"eval_runtime": 1.
|
81 |
-
"eval_samples_per_second":
|
82 |
-
"eval_steps_per_second": 4.
|
83 |
"step": 4175
|
84 |
},
|
85 |
{
|
@@ -92,9 +92,9 @@
|
|
92 |
"epoch": 6.0,
|
93 |
"eval_loss": 0.6185929179191589,
|
94 |
"eval_matthews_correlation": 0.0,
|
95 |
-
"eval_runtime": 1.
|
96 |
-
"eval_samples_per_second":
|
97 |
-
"eval_steps_per_second": 4.
|
98 |
"step": 5010
|
99 |
},
|
100 |
{
|
@@ -107,9 +107,9 @@
|
|
107 |
"epoch": 7.0,
|
108 |
"eval_loss": 0.618870735168457,
|
109 |
"eval_matthews_correlation": 0.0,
|
110 |
-
"eval_runtime": 1.
|
111 |
-
"eval_samples_per_second":
|
112 |
-
"eval_steps_per_second": 4.
|
113 |
"step": 5845
|
114 |
},
|
115 |
{
|
@@ -122,9 +122,9 @@
|
|
122 |
"epoch": 8.0,
|
123 |
"eval_loss": 0.6202924847602844,
|
124 |
"eval_matthews_correlation": 0.0,
|
125 |
-
"eval_runtime": 1.
|
126 |
-
"eval_samples_per_second":
|
127 |
-
"eval_steps_per_second": 4.
|
128 |
"step": 6680
|
129 |
},
|
130 |
{
|
@@ -132,9 +132,9 @@
|
|
132 |
"step": 6680,
|
133 |
"total_flos": 2.1284586608656384e+17,
|
134 |
"train_loss": 0.6065069872462107,
|
135 |
-
"train_runtime":
|
136 |
-
"train_samples_per_second":
|
137 |
-
"train_steps_per_second":
|
138 |
}
|
139 |
],
|
140 |
"max_steps": 41750,
|
|
|
17 |
"epoch": 1.0,
|
18 |
"eval_loss": 0.6237233281135559,
|
19 |
"eval_matthews_correlation": 0.0,
|
20 |
+
"eval_runtime": 1.2319,
|
21 |
+
"eval_samples_per_second": 846.646,
|
22 |
+
"eval_steps_per_second": 4.059,
|
23 |
"step": 835
|
24 |
},
|
25 |
{
|
|
|
32 |
"epoch": 2.0,
|
33 |
"eval_loss": 0.6185952425003052,
|
34 |
"eval_matthews_correlation": 0.0,
|
35 |
+
"eval_runtime": 1.2376,
|
36 |
+
"eval_samples_per_second": 842.788,
|
37 |
+
"eval_steps_per_second": 4.04,
|
38 |
"step": 1670
|
39 |
},
|
40 |
{
|
|
|
47 |
"epoch": 3.0,
|
48 |
"eval_loss": 0.6180860996246338,
|
49 |
"eval_matthews_correlation": 0.0,
|
50 |
+
"eval_runtime": 1.2346,
|
51 |
+
"eval_samples_per_second": 844.783,
|
52 |
+
"eval_steps_per_second": 4.05,
|
53 |
"step": 2505
|
54 |
},
|
55 |
{
|
|
|
62 |
"epoch": 4.0,
|
63 |
"eval_loss": 0.6217709183692932,
|
64 |
"eval_matthews_correlation": 0.0,
|
65 |
+
"eval_runtime": 1.235,
|
66 |
+
"eval_samples_per_second": 844.562,
|
67 |
+
"eval_steps_per_second": 4.049,
|
68 |
"step": 3340
|
69 |
},
|
70 |
{
|
|
|
77 |
"epoch": 5.0,
|
78 |
"eval_loss": 0.6211623549461365,
|
79 |
"eval_matthews_correlation": 0.0,
|
80 |
+
"eval_runtime": 1.2344,
|
81 |
+
"eval_samples_per_second": 844.918,
|
82 |
+
"eval_steps_per_second": 4.05,
|
83 |
"step": 4175
|
84 |
},
|
85 |
{
|
|
|
92 |
"epoch": 6.0,
|
93 |
"eval_loss": 0.6185929179191589,
|
94 |
"eval_matthews_correlation": 0.0,
|
95 |
+
"eval_runtime": 1.2333,
|
96 |
+
"eval_samples_per_second": 845.728,
|
97 |
+
"eval_steps_per_second": 4.054,
|
98 |
"step": 5010
|
99 |
},
|
100 |
{
|
|
|
107 |
"epoch": 7.0,
|
108 |
"eval_loss": 0.618870735168457,
|
109 |
"eval_matthews_correlation": 0.0,
|
110 |
+
"eval_runtime": 1.2325,
|
111 |
+
"eval_samples_per_second": 846.237,
|
112 |
+
"eval_steps_per_second": 4.057,
|
113 |
"step": 5845
|
114 |
},
|
115 |
{
|
|
|
122 |
"epoch": 8.0,
|
123 |
"eval_loss": 0.6202924847602844,
|
124 |
"eval_matthews_correlation": 0.0,
|
125 |
+
"eval_runtime": 1.2311,
|
126 |
+
"eval_samples_per_second": 847.224,
|
127 |
+
"eval_steps_per_second": 4.061,
|
128 |
"step": 6680
|
129 |
},
|
130 |
{
|
|
|
132 |
"step": 6680,
|
133 |
"total_flos": 2.1284586608656384e+17,
|
134 |
"train_loss": 0.6065069872462107,
|
135 |
+
"train_runtime": 5969.0208,
|
136 |
+
"train_samples_per_second": 1789.314,
|
137 |
+
"train_steps_per_second": 6.994
|
138 |
}
|
139 |
],
|
140 |
"max_steps": 41750,
|