21iridescent
commited on
Commit
•
65a957f
1
Parent(s):
74159f0
update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: cc-by-nc-sa-4.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
metrics:
|
6 |
+
- precision
|
7 |
+
- recall
|
8 |
+
model-index:
|
9 |
+
- name: output
|
10 |
+
results: []
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
# output
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [Babelscape/rebel-large](https://huggingface.co/Babelscape/rebel-large) on an unknown dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.3052
|
21 |
+
- Precision: 0.9444
|
22 |
+
- Recall: 0.9444
|
23 |
+
- F1-measure: 0.9444
|
24 |
+
|
25 |
+
## Model description
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Intended uses & limitations
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training and evaluation data
|
34 |
+
|
35 |
+
More information needed
|
36 |
+
|
37 |
+
## Training procedure
|
38 |
+
|
39 |
+
### Training hyperparameters
|
40 |
+
|
41 |
+
The following hyperparameters were used during training:
|
42 |
+
- learning_rate: 1e-05
|
43 |
+
- train_batch_size: 8
|
44 |
+
- eval_batch_size: 16
|
45 |
+
- seed: 42
|
46 |
+
- gradient_accumulation_steps: 4
|
47 |
+
- total_train_batch_size: 32
|
48 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
49 |
+
- lr_scheduler_type: linear
|
50 |
+
- num_epochs: 3
|
51 |
+
|
52 |
+
### Training results
|
53 |
+
|
54 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1-measure |
|
55 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:----------:|
|
56 |
+
| No log | 1.0 | 210 | 0.3113 | 0.9167 | 0.9167 | 0.9167 |
|
57 |
+
| No log | 2.0 | 420 | 0.3027 | 0.9444 | 0.9444 | 0.9444 |
|
58 |
+
| 0.3652 | 3.0 | 630 | 0.3052 | 0.9444 | 0.9444 | 0.9444 |
|
59 |
+
|
60 |
+
|
61 |
+
### Framework versions
|
62 |
+
|
63 |
+
- Transformers 4.21.1
|
64 |
+
- Pytorch 1.9.0+cu111
|
65 |
+
- Datasets 2.4.0
|
66 |
+
- Tokenizers 0.12.1
|