End of training
Browse files
README.md
ADDED
@@ -0,0 +1,98 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
datasets:
|
6 |
+
- xglue
|
7 |
+
metrics:
|
8 |
+
- accuracy
|
9 |
+
model-index:
|
10 |
+
- name: xlm-v-base-finetuned-xglue-xnli
|
11 |
+
results:
|
12 |
+
- task:
|
13 |
+
name: Text Classification
|
14 |
+
type: text-classification
|
15 |
+
dataset:
|
16 |
+
name: xglue
|
17 |
+
type: xglue
|
18 |
+
config: xnli
|
19 |
+
split: validation.en+validation.ar+validation.bg+validation.de+validation.el+validation.es+validation.fr+validation.hi+validation.ru+validation.sw+validation.th+validation.tr+validation.ur+validation.vi+validation.zh
|
20 |
+
args: xnli
|
21 |
+
metrics:
|
22 |
+
- name: Accuracy
|
23 |
+
type: accuracy
|
24 |
+
value: 0.7402677376171352
|
25 |
+
---
|
26 |
+
|
27 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
28 |
+
should probably proofread and complete it, then remove this comment. -->
|
29 |
+
|
30 |
+
# xlm-v-base-finetuned-xglue-xnli
|
31 |
+
|
32 |
+
This model is a fine-tuned version of [stefan-it/xlm-v-base](https://huggingface.co/stefan-it/xlm-v-base) on the xglue dataset.
|
33 |
+
It achieves the following results on the evaluation set:
|
34 |
+
- Loss: 0.6511
|
35 |
+
- Accuracy: 0.7403
|
36 |
+
|
37 |
+
## Model description
|
38 |
+
|
39 |
+
More information needed
|
40 |
+
|
41 |
+
## Intended uses & limitations
|
42 |
+
|
43 |
+
More information needed
|
44 |
+
|
45 |
+
## Training and evaluation data
|
46 |
+
|
47 |
+
More information needed
|
48 |
+
|
49 |
+
## Training procedure
|
50 |
+
|
51 |
+
### Training hyperparameters
|
52 |
+
|
53 |
+
The following hyperparameters were used during training:
|
54 |
+
- learning_rate: 2e-05
|
55 |
+
- train_batch_size: 32
|
56 |
+
- eval_batch_size: 32
|
57 |
+
- seed: 42
|
58 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
59 |
+
- lr_scheduler_type: linear
|
60 |
+
- num_epochs: 2
|
61 |
+
- mixed_precision_training: Native AMP
|
62 |
+
|
63 |
+
### Training results
|
64 |
+
|
65 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
66 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
67 |
+
| 1.0994 | 0.08 | 1000 | 1.0966 | 0.3697 |
|
68 |
+
| 1.0221 | 0.16 | 2000 | 1.0765 | 0.4560 |
|
69 |
+
| 0.8437 | 0.24 | 3000 | 0.8472 | 0.6179 |
|
70 |
+
| 0.6997 | 0.33 | 4000 | 0.7650 | 0.6804 |
|
71 |
+
| 0.6304 | 0.41 | 5000 | 0.7227 | 0.7007 |
|
72 |
+
| 0.5972 | 0.49 | 6000 | 0.7430 | 0.6977 |
|
73 |
+
| 0.5886 | 0.57 | 7000 | 0.7365 | 0.7066 |
|
74 |
+
| 0.5585 | 0.65 | 8000 | 0.6819 | 0.7223 |
|
75 |
+
| 0.5464 | 0.73 | 9000 | 0.7222 | 0.7046 |
|
76 |
+
| 0.5289 | 0.81 | 10000 | 0.7290 | 0.7054 |
|
77 |
+
| 0.5298 | 0.9 | 11000 | 0.6824 | 0.7221 |
|
78 |
+
| 0.5241 | 0.98 | 12000 | 0.6650 | 0.7268 |
|
79 |
+
| 0.4806 | 1.06 | 13000 | 0.6861 | 0.7308 |
|
80 |
+
| 0.4715 | 1.14 | 14000 | 0.6619 | 0.7304 |
|
81 |
+
| 0.4645 | 1.22 | 15000 | 0.6656 | 0.7284 |
|
82 |
+
| 0.4443 | 1.3 | 16000 | 0.7026 | 0.7270 |
|
83 |
+
| 0.4582 | 1.39 | 17000 | 0.7055 | 0.7225 |
|
84 |
+
| 0.4456 | 1.47 | 18000 | 0.6592 | 0.7361 |
|
85 |
+
| 0.44 | 1.55 | 19000 | 0.6816 | 0.7329 |
|
86 |
+
| 0.4419 | 1.63 | 20000 | 0.6772 | 0.7357 |
|
87 |
+
| 0.4403 | 1.71 | 21000 | 0.6745 | 0.7319 |
|
88 |
+
| 0.4348 | 1.79 | 22000 | 0.6678 | 0.7338 |
|
89 |
+
| 0.4355 | 1.87 | 23000 | 0.6614 | 0.7365 |
|
90 |
+
| 0.4295 | 1.96 | 24000 | 0.6511 | 0.7403 |
|
91 |
+
|
92 |
+
|
93 |
+
### Framework versions
|
94 |
+
|
95 |
+
- Transformers 4.26.0
|
96 |
+
- Pytorch 1.13.1+cu116
|
97 |
+
- Datasets 2.9.0
|
98 |
+
- Tokenizers 0.13.2
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3114055349
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:42d43d53752368c709cfd4685ca7556222a042610a622a4ef40865507dbfe8f0
|
3 |
size 3114055349
|
runs/Feb07_22-07-48_2b9c2c1d21e4/events.out.tfevents.1675807680.2b9c2c1d21e4.26684.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4c12e1a32ed60c0fae5aa0eeea1896497f2307171499b1d6746845801aaa5263
|
3 |
+
size 19963
|