Dan Semin
commited on
Commit
•
868d4fa
1
Parent(s):
7456baa
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: 0.
|
36 |
-
- Accuracy: 0.
|
37 |
|
38 |
## Model description
|
39 |
|
@@ -53,8 +53,8 @@ More information needed
|
|
53 |
|
54 |
The following hyperparameters were used during training:
|
55 |
- learning_rate: 1.5e-05
|
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
|
@@ -65,16 +65,16 @@ The following hyperparameters were used during training:
|
|
65 |
|
66 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
67 |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
68 |
-
| 1.
|
69 |
-
| 0.
|
70 |
-
| 0.
|
71 |
-
| 0.
|
72 |
-
| 0.
|
73 |
-
| 0.
|
74 |
-
| 0.
|
75 |
-
| 0.
|
76 |
-
| 0.
|
77 |
-
| 0.
|
78 |
|
79 |
|
80 |
### Framework versions
|
|
|
22 |
metrics:
|
23 |
- name: Accuracy
|
24 |
type: accuracy
|
25 |
+
value: 0.6514056224899598
|
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: 0.8516
|
36 |
+
- Accuracy: 0.6514
|
37 |
|
38 |
## Model description
|
39 |
|
|
|
53 |
|
54 |
The following hyperparameters were used during training:
|
55 |
- learning_rate: 1.5e-05
|
56 |
+
- train_batch_size: 128
|
57 |
+
- eval_batch_size: 128
|
58 |
- seed: 42
|
59 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
60 |
- lr_scheduler_type: linear
|
|
|
65 |
|
66 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
67 |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
68 |
+
| 1.0129 | 1.0 | 3068 | 0.8285 | 0.6357 |
|
69 |
+
| 0.9628 | 2.0 | 6136 | 0.8120 | 0.6470 |
|
70 |
+
| 0.9407 | 3.0 | 9204 | 0.7934 | 0.6643 |
|
71 |
+
| 0.9205 | 4.0 | 12272 | 0.7802 | 0.6546 |
|
72 |
+
| 0.9001 | 5.0 | 15340 | 0.7820 | 0.6594 |
|
73 |
+
| 0.8791 | 6.0 | 18408 | 0.8046 | 0.6502 |
|
74 |
+
| 0.8593 | 7.0 | 21476 | 0.7950 | 0.6627 |
|
75 |
+
| 0.8404 | 8.0 | 24544 | 0.8231 | 0.6514 |
|
76 |
+
| 0.8242 | 9.0 | 27612 | 0.8376 | 0.6558 |
|
77 |
+
| 0.8118 | 10.0 | 30680 | 0.8516 | 0.6514 |
|
78 |
|
79 |
|
80 |
### Framework versions
|