Dan Semin
commited on
Commit
•
257c48b
1
Parent(s):
8424a3d
update model card README.md
Browse files
README.md
CHANGED
@@ -22,7 +22,7 @@ model-index:
|
|
22 |
metrics:
|
23 |
- name: Accuracy
|
24 |
type: accuracy
|
25 |
-
value: 0.
|
26 |
---
|
27 |
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
32 |
|
33 |
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the xnli dataset.
|
34 |
It achieves the following results on the evaluation set:
|
35 |
-
- Loss:
|
36 |
-
- Accuracy: 0.
|
37 |
|
38 |
## Model description
|
39 |
|
@@ -52,29 +52,29 @@ More information needed
|
|
52 |
### Training hyperparameters
|
53 |
|
54 |
The following hyperparameters were used during training:
|
55 |
-
- learning_rate:
|
56 |
-
- train_batch_size:
|
57 |
-
- eval_batch_size:
|
58 |
- seed: 42
|
59 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
60 |
- lr_scheduler_type: linear
|
61 |
-
- lr_scheduler_warmup_steps:
|
62 |
- num_epochs: 10
|
63 |
|
64 |
### Training results
|
65 |
|
66 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
67 |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
68 |
-
| 1.
|
69 |
-
|
|
70 |
-
|
|
71 |
-
|
|
72 |
-
|
|
73 |
-
|
|
74 |
-
|
|
75 |
-
|
|
76 |
-
|
|
77 |
-
|
|
78 |
|
79 |
|
80 |
### Framework versions
|
|
|
22 |
metrics:
|
23 |
- name: Accuracy
|
24 |
type: accuracy
|
25 |
+
value: 0.6526104417670683
|
26 |
---
|
27 |
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
32 |
|
33 |
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the xnli dataset.
|
34 |
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 0.8165
|
36 |
+
- Accuracy: 0.6526
|
37 |
|
38 |
## Model description
|
39 |
|
|
|
52 |
### Training hyperparameters
|
53 |
|
54 |
The following hyperparameters were used during training:
|
55 |
+
- learning_rate: 1.5e-05
|
56 |
+
- train_batch_size: 192
|
57 |
+
- eval_batch_size: 192
|
58 |
- seed: 42
|
59 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
60 |
- lr_scheduler_type: linear
|
61 |
+
- lr_scheduler_warmup_steps: 1000
|
62 |
- num_epochs: 10
|
63 |
|
64 |
### Training results
|
65 |
|
66 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
67 |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
68 |
+
| 1.0253 | 1.0 | 2046 | 0.8330 | 0.6382 |
|
69 |
+
| 0.9659 | 2.0 | 4092 | 0.8105 | 0.6530 |
|
70 |
+
| 0.9445 | 3.0 | 6138 | 0.7978 | 0.6558 |
|
71 |
+
| 0.9254 | 4.0 | 8184 | 0.7791 | 0.6594 |
|
72 |
+
| 0.9075 | 5.0 | 10230 | 0.7792 | 0.6614 |
|
73 |
+
| 0.8892 | 6.0 | 12276 | 0.7812 | 0.6554 |
|
74 |
+
| 0.8728 | 7.0 | 14322 | 0.7762 | 0.6538 |
|
75 |
+
| 0.8565 | 8.0 | 16368 | 0.8019 | 0.6494 |
|
76 |
+
| 0.8427 | 9.0 | 18414 | 0.8067 | 0.6558 |
|
77 |
+
| 0.8332 | 10.0 | 20460 | 0.8165 | 0.6526 |
|
78 |
|
79 |
|
80 |
### Framework versions
|