update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
model-index:
|
6 |
+
- name: action-policy-plans-classifier
|
7 |
+
results: []
|
8 |
+
---
|
9 |
+
|
10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
11 |
+
should probably proofread and complete it, then remove this comment. -->
|
12 |
+
|
13 |
+
# action-policy-plans-classifier
|
14 |
+
|
15 |
+
This model is a fine-tuned version of [sentence-transformers/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2) on the None dataset.
|
16 |
+
It achieves the following results on the evaluation set:
|
17 |
+
- Loss: 0.6839
|
18 |
+
- Precision Micro: 0.7089
|
19 |
+
- Precision Weighted: 0.7043
|
20 |
+
- Precision Samples: 0.4047
|
21 |
+
- Recall Micro: 0.7066
|
22 |
+
- Recall Weighted: 0.7066
|
23 |
+
- Recall Samples: 0.4047
|
24 |
+
- F1-score: 0.4041
|
25 |
+
|
26 |
+
## Model description
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Intended uses & limitations
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Training and evaluation data
|
35 |
+
|
36 |
+
More information needed
|
37 |
+
|
38 |
+
## Training procedure
|
39 |
+
|
40 |
+
### Training hyperparameters
|
41 |
+
|
42 |
+
The following hyperparameters were used during training:
|
43 |
+
- learning_rate: 2.915e-05
|
44 |
+
- train_batch_size: 16
|
45 |
+
- eval_batch_size: 16
|
46 |
+
- seed: 42
|
47 |
+
- gradient_accumulation_steps: 2
|
48 |
+
- total_train_batch_size: 32
|
49 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
50 |
+
- lr_scheduler_type: linear
|
51 |
+
- lr_scheduler_warmup_steps: 300
|
52 |
+
- num_epochs: 7
|
53 |
+
|
54 |
+
### Training results
|
55 |
+
|
56 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision Micro | Precision Weighted | Precision Samples | Recall Micro | Recall Weighted | Recall Samples | F1-score |
|
57 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------------:|:------------------:|:-----------------:|:------------:|:---------------:|:--------------:|:--------:|
|
58 |
+
| 0.7333 | 1.0 | 253 | 0.5828 | 0.625 | 0.6422 | 0.4047 | 0.7098 | 0.7098 | 0.4065 | 0.4047 |
|
59 |
+
| 0.5905 | 2.0 | 506 | 0.5593 | 0.6292 | 0.6318 | 0.4437 | 0.7760 | 0.7760 | 0.4446 | 0.4434 |
|
60 |
+
| 0.4934 | 3.0 | 759 | 0.5269 | 0.6630 | 0.6637 | 0.4319 | 0.7571 | 0.7571 | 0.4347 | 0.4325 |
|
61 |
+
| 0.4018 | 4.0 | 1012 | 0.5645 | 0.6449 | 0.6479 | 0.4456 | 0.7792 | 0.7792 | 0.4465 | 0.4453 |
|
62 |
+
| 0.3235 | 5.0 | 1265 | 0.6101 | 0.6964 | 0.6929 | 0.4220 | 0.7382 | 0.7382 | 0.4229 | 0.4217 |
|
63 |
+
| 0.2638 | 6.0 | 1518 | 0.6692 | 0.6888 | 0.6841 | 0.4111 | 0.7192 | 0.7192 | 0.4120 | 0.4108 |
|
64 |
+
| 0.2197 | 7.0 | 1771 | 0.6839 | 0.7089 | 0.7043 | 0.4047 | 0.7066 | 0.7066 | 0.4047 | 0.4041 |
|
65 |
+
|
66 |
+
|
67 |
+
### Framework versions
|
68 |
+
|
69 |
+
- Transformers 4.28.0
|
70 |
+
- Pytorch 2.0.1+cu118
|
71 |
+
- Datasets 2.12.0
|
72 |
+
- Tokenizers 0.13.3
|