Commit
•
4c634ba
1
Parent(s):
4fcb886
update model card README.md
Browse files
README.md
CHANGED
@@ -17,9 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
|
18 |
This model is a fine-tuned version of [xlm-roberta-large](https://huggingface.co/xlm-roberta-large) on the None dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- Loss: 0.
|
21 |
-
- Accuracy: 0.
|
22 |
-
- F1: 0.
|
23 |
|
24 |
## Model description
|
25 |
|
@@ -39,10 +39,10 @@ More information needed
|
|
39 |
|
40 |
The following hyperparameters were used during training:
|
41 |
- learning_rate: 1e-05
|
42 |
-
- train_batch_size:
|
43 |
-
- eval_batch_size:
|
44 |
- seed: 42
|
45 |
-
- gradient_accumulation_steps:
|
46 |
- total_train_batch_size: 128
|
47 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
48 |
- lr_scheduler_type: linear
|
@@ -50,24 +50,21 @@ The following hyperparameters were used during training:
|
|
50 |
|
51 |
### Training results
|
52 |
|
53 |
-
| Training Loss | Epoch | Step |
|
54 |
-
|
55 |
-
| 0.
|
56 |
-
| 0.
|
57 |
-
| 0.
|
58 |
-
| 0.
|
59 |
-
| 0.
|
60 |
-
| 0.
|
61 |
-
| 0.
|
62 |
-
| 0.
|
63 |
-
| 0.2261 | 4.5 | 14166 | 0.4859 | 0.8562 | 0.8570 |
|
64 |
-
| 0.2215 | 5.0 | 15740 | 0.4728 | 0.8592 | 0.8599 |
|
65 |
-
| 0.1874 | 5.5 | 17314 | 0.5146 | 0.8579 | 0.8583 |
|
66 |
|
67 |
|
68 |
### Framework versions
|
69 |
|
70 |
- Transformers 4.26.1
|
71 |
-
- Pytorch
|
72 |
- Datasets 2.2.0
|
73 |
-
- Tokenizers 0.13.
|
|
|
17 |
|
18 |
This model is a fine-tuned version of [xlm-roberta-large](https://huggingface.co/xlm-roberta-large) on the None dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.4158
|
21 |
+
- Accuracy: 0.8600
|
22 |
+
- F1: 0.8612
|
23 |
|
24 |
## Model description
|
25 |
|
|
|
39 |
|
40 |
The following hyperparameters were used during training:
|
41 |
- learning_rate: 1e-05
|
42 |
+
- train_batch_size: 16
|
43 |
+
- eval_batch_size: 16
|
44 |
- seed: 42
|
45 |
+
- gradient_accumulation_steps: 8
|
46 |
- total_train_batch_size: 128
|
47 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
48 |
- lr_scheduler_type: linear
|
|
|
50 |
|
51 |
### Training results
|
52 |
|
53 |
+
| Training Loss | Epoch | Step | Accuracy | F1 | Validation Loss |
|
54 |
+
|:-------------:|:-----:|:-----:|:--------:|:------:|:---------------:|
|
55 |
+
| 0.4647 | 0.5 | 1613 | 0.8396 | 0.8403 | 0.4262 |
|
56 |
+
| 0.4437 | 1.0 | 3226 | 0.8511 | 0.8522 | 0.4042 |
|
57 |
+
| 0.3956 | 1.5 | 4839 | 0.3783 | 0.8604 | 0.8602 |
|
58 |
+
| 0.3639 | 2.0 | 6452 | 0.3913 | 0.8592 | 0.8600 |
|
59 |
+
| 0.323 | 2.5 | 8065 | 0.3783 | 0.8657 | 0.8659 |
|
60 |
+
| 0.3186 | 3.0 | 9678 | 0.3850 | 0.8626 | 0.8625 |
|
61 |
+
| 0.2485 | 3.5 | 11291 | 0.4326 | 0.8597 | 0.8592 |
|
62 |
+
| 0.2509 | 4.0 | 12904 | 0.4158 | 0.8600 | 0.8612 |
|
|
|
|
|
|
|
63 |
|
64 |
|
65 |
### Framework versions
|
66 |
|
67 |
- Transformers 4.26.1
|
68 |
+
- Pytorch 2.0.1+cu117
|
69 |
- Datasets 2.2.0
|
70 |
+
- Tokenizers 0.13.3
|