Update README.md
Browse files
README.md
CHANGED
@@ -1,5 +1,4 @@
|
|
1 |
---
|
2 |
-
license: apache-2.0
|
3 |
tags:
|
4 |
- generated_from_trainer
|
5 |
model-index:
|
@@ -12,7 +11,16 @@ should probably proofread and complete it, then remove this comment. -->
|
|
12 |
|
13 |
# BERT-FINETUNE-MBTI-LM-BERT-FINETUNE-MBTI-LM-JointBERT-Warmup-from-LM
|
14 |
|
15 |
-
This model is a fine-tuned version of [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
16 |
|
17 |
## Model description
|
18 |
|
@@ -39,9 +47,18 @@ The following hyperparameters were used during training:
|
|
39 |
- lr_scheduler_type: linear
|
40 |
- num_epochs: 3
|
41 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
42 |
### Framework versions
|
43 |
|
44 |
- Transformers 4.21.2
|
45 |
- Pytorch 1.12.1
|
46 |
- Datasets 2.4.0
|
47 |
-
- Tokenizers 0.12.1
|
|
|
1 |
---
|
|
|
2 |
tags:
|
3 |
- generated_from_trainer
|
4 |
model-index:
|
|
|
11 |
|
12 |
# BERT-FINETUNE-MBTI-LM-BERT-FINETUNE-MBTI-LM-JointBERT-Warmup-from-LM
|
13 |
|
14 |
+
This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
|
15 |
+
It achieves the following results on the evaluation set:
|
16 |
+
- Loss: 4.7966
|
17 |
+
- Cls loss: 1.4255
|
18 |
+
- Lm loss: 4.4398
|
19 |
+
- Cls Accuracy: 0.6380
|
20 |
+
- Cls F1: 0.6319
|
21 |
+
- Cls Precision: 0.6416
|
22 |
+
- Cls Recall: 0.6380
|
23 |
+
- Perplexity: 84.76
|
24 |
|
25 |
## Model description
|
26 |
|
|
|
47 |
- lr_scheduler_type: linear
|
48 |
- num_epochs: 3
|
49 |
|
50 |
+
### Training results
|
51 |
+
|
52 |
+
| Training Loss | Epoch | Step | Validation Loss | Cls loss | Lm loss | Cls Accuracy | Cls F1 | Cls Precision | Cls Recall | Perplexity |
|
53 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:-------:|:------------:|:------:|:-------------:|:----------:|:----------:|
|
54 |
+
| 5.3087 | 1.0 | 3470 | 4.9005 | 1.4109 | 4.5474 | 0.6075 | 0.5981 | 0.6132 | 0.6075 | 94.39 |
|
55 |
+
| 4.8274 | 2.0 | 6940 | 4.7987 | 1.3448 | 4.4621 | 0.6242 | 0.6193 | 0.6381 | 0.6242 | 86.67 |
|
56 |
+
| 4.6472 | 3.0 | 10410 | 4.7966 | 1.4255 | 4.4398 | 0.6380 | 0.6319 | 0.6416 | 0.6380 | 84.76 |
|
57 |
+
|
58 |
+
|
59 |
### Framework versions
|
60 |
|
61 |
- Transformers 4.21.2
|
62 |
- Pytorch 1.12.1
|
63 |
- Datasets 2.4.0
|
64 |
+
- Tokenizers 0.12.1
|