Commit
•
6471df9
1
Parent(s):
bd937e4
update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
datasets:
|
6 |
+
- arcd
|
7 |
+
model-index:
|
8 |
+
- name: rinna-roberta-qa-ar2
|
9 |
+
results: []
|
10 |
+
---
|
11 |
+
|
12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
13 |
+
should probably proofread and complete it, then remove this comment. -->
|
14 |
+
|
15 |
+
# rinna-roberta-qa-ar2
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the arcd dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 7.3167
|
20 |
+
|
21 |
+
## Model description
|
22 |
+
|
23 |
+
More information needed
|
24 |
+
|
25 |
+
## Intended uses & limitations
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Training and evaluation data
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training procedure
|
34 |
+
|
35 |
+
### Training hyperparameters
|
36 |
+
|
37 |
+
The following hyperparameters were used during training:
|
38 |
+
- learning_rate: 7e-05
|
39 |
+
- train_batch_size: 2
|
40 |
+
- eval_batch_size: 1
|
41 |
+
- seed: 42
|
42 |
+
- gradient_accumulation_steps: 16
|
43 |
+
- total_train_batch_size: 32
|
44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
+
- lr_scheduler_type: linear
|
46 |
+
- lr_scheduler_warmup_steps: 100
|
47 |
+
- num_epochs: 170
|
48 |
+
|
49 |
+
### Training results
|
50 |
+
|
51 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
52 |
+
|:-------------:|:------:|:----:|:---------------:|
|
53 |
+
| 0.3148 | 6.86 | 150 | 4.5451 |
|
54 |
+
| 0.2021 | 13.71 | 300 | 4.3560 |
|
55 |
+
| 0.1134 | 20.57 | 450 | 5.1730 |
|
56 |
+
| 0.0648 | 27.43 | 600 | 5.0504 |
|
57 |
+
| 0.0734 | 34.29 | 750 | 5.3601 |
|
58 |
+
| 0.032 | 41.14 | 900 | 5.4291 |
|
59 |
+
| 0.0171 | 48.0 | 1050 | 6.9606 |
|
60 |
+
| 0.0343 | 54.86 | 1200 | 4.9076 |
|
61 |
+
| 0.0186 | 61.71 | 1350 | 6.7967 |
|
62 |
+
| 0.0054 | 68.57 | 1500 | 6.0515 |
|
63 |
+
| 0.0118 | 75.43 | 1650 | 7.0908 |
|
64 |
+
| 0.0027 | 82.29 | 1800 | 7.5651 |
|
65 |
+
| 0.0078 | 89.14 | 1950 | 7.3787 |
|
66 |
+
| 0.0172 | 96.0 | 2100 | 7.7559 |
|
67 |
+
| 0.0077 | 102.86 | 2250 | 7.1376 |
|
68 |
+
| 0.0041 | 109.71 | 2400 | 7.3236 |
|
69 |
+
| 0.0022 | 116.57 | 2550 | 7.3134 |
|
70 |
+
| 0.0004 | 123.43 | 2700 | 7.2484 |
|
71 |
+
| 0.0018 | 130.29 | 2850 | 7.1747 |
|
72 |
+
| 0.0009 | 137.14 | 3000 | 7.4311 |
|
73 |
+
| 0.0008 | 144.0 | 3150 | 7.5083 |
|
74 |
+
| 0.0006 | 150.86 | 3300 | 7.4622 |
|
75 |
+
| 0.0002 | 157.71 | 3450 | 7.3167 |
|
76 |
+
|
77 |
+
|
78 |
+
### Framework versions
|
79 |
+
|
80 |
+
- Transformers 4.29.2
|
81 |
+
- Pytorch 2.0.1+cu118
|
82 |
+
- Datasets 2.12.0
|
83 |
+
- Tokenizers 0.13.3
|