End of training
Browse files- README.md +22 -2
- all_results.json +21 -0
- eval_results.json +16 -0
- train_results.json +8 -0
- trainer_state.json +0 -0
README.md
CHANGED
@@ -1,13 +1,30 @@
|
|
1 |
---
|
|
|
|
|
2 |
license: apache-2.0
|
3 |
base_model: bert-base-uncased
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
7 |
- glue
|
|
|
|
|
8 |
model-index:
|
9 |
- name: out-glue-mnli
|
10 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
---
|
12 |
|
13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -15,7 +32,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
# out-glue-mnli
|
17 |
|
18 |
-
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the
|
|
|
|
|
|
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
1 |
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
license: apache-2.0
|
5 |
base_model: bert-base-uncased
|
6 |
tags:
|
7 |
- generated_from_trainer
|
8 |
datasets:
|
9 |
- glue
|
10 |
+
metrics:
|
11 |
+
- accuracy
|
12 |
model-index:
|
13 |
- name: out-glue-mnli
|
14 |
+
results:
|
15 |
+
- task:
|
16 |
+
name: Text Classification
|
17 |
+
type: text-classification
|
18 |
+
dataset:
|
19 |
+
name: GLUE MNLI
|
20 |
+
type: glue
|
21 |
+
config: mnli
|
22 |
+
split: validation_matched
|
23 |
+
args: mnli
|
24 |
+
metrics:
|
25 |
+
- name: Accuracy
|
26 |
+
type: accuracy
|
27 |
+
value: 0.8418429617575265
|
28 |
---
|
29 |
|
30 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
32 |
|
33 |
# out-glue-mnli
|
34 |
|
35 |
+
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the GLUE MNLI dataset.
|
36 |
+
It achieves the following results on the evaluation set:
|
37 |
+
- Loss: 1.0659
|
38 |
+
- Accuracy: 0.8418
|
39 |
|
40 |
## Model description
|
41 |
|
all_results.json
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 20.0,
|
3 |
+
"epoch_mm": 20.0,
|
4 |
+
"eval_accuracy": 0.8386143657666837,
|
5 |
+
"eval_accuracy_mm": 0.8418429617575265,
|
6 |
+
"eval_loss": 1.0797035694122314,
|
7 |
+
"eval_loss_mm": 1.0659372806549072,
|
8 |
+
"eval_runtime": 7.3576,
|
9 |
+
"eval_runtime_mm": 7.3181,
|
10 |
+
"eval_samples": 9815,
|
11 |
+
"eval_samples_mm": 9832,
|
12 |
+
"eval_samples_per_second": 1333.993,
|
13 |
+
"eval_samples_per_second_mm": 1343.512,
|
14 |
+
"eval_steps_per_second": 5.301,
|
15 |
+
"eval_steps_per_second_mm": 5.329,
|
16 |
+
"train_loss": 0.12400934287872191,
|
17 |
+
"train_runtime": 16044.2941,
|
18 |
+
"train_samples": 392702,
|
19 |
+
"train_samples_per_second": 489.522,
|
20 |
+
"train_steps_per_second": 2.55
|
21 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 20.0,
|
3 |
+
"epoch_mm": 20.0,
|
4 |
+
"eval_accuracy": 0.8386143657666837,
|
5 |
+
"eval_accuracy_mm": 0.8418429617575265,
|
6 |
+
"eval_loss": 1.0797035694122314,
|
7 |
+
"eval_loss_mm": 1.0659372806549072,
|
8 |
+
"eval_runtime": 7.3576,
|
9 |
+
"eval_runtime_mm": 7.3181,
|
10 |
+
"eval_samples": 9815,
|
11 |
+
"eval_samples_mm": 9832,
|
12 |
+
"eval_samples_per_second": 1333.993,
|
13 |
+
"eval_samples_per_second_mm": 1343.512,
|
14 |
+
"eval_steps_per_second": 5.301,
|
15 |
+
"eval_steps_per_second_mm": 5.329
|
16 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 20.0,
|
3 |
+
"train_loss": 0.12400934287872191,
|
4 |
+
"train_runtime": 16044.2941,
|
5 |
+
"train_samples": 392702,
|
6 |
+
"train_samples_per_second": 489.522,
|
7 |
+
"train_steps_per_second": 2.55
|
8 |
+
}
|
trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|