update model card README.md
Browse files
README.md
CHANGED
@@ -18,20 +18,20 @@ model-index:
|
|
18 |
dataset:
|
19 |
name: amazon_reviews_multi
|
20 |
type: amazon_reviews_multi
|
21 |
-
args:
|
22 |
metrics:
|
23 |
- name: Accuracy
|
24 |
type: accuracy
|
25 |
-
value: 0.
|
26 |
- name: F1
|
27 |
type: f1
|
28 |
-
value: 0.
|
29 |
- name: Precision
|
30 |
type: precision
|
31 |
-
value: 0.
|
32 |
- name: Recall
|
33 |
type: recall
|
34 |
-
value: 0.
|
35 |
---
|
36 |
|
37 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -41,11 +41,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
41 |
|
42 |
This model is a fine-tuned version of [google/electra-small-discriminator](https://huggingface.co/google/electra-small-discriminator) on the amazon_reviews_multi dataset.
|
43 |
It achieves the following results on the evaluation set:
|
44 |
-
- Loss: 1.
|
45 |
-
- Accuracy: 0.
|
46 |
-
- F1: 0.
|
47 |
-
- Precision: 0.
|
48 |
-
- Recall: 0.
|
49 |
|
50 |
## Model description
|
51 |
|
@@ -70,18 +70,16 @@ The following hyperparameters were used during training:
|
|
70 |
- seed: 42
|
71 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
72 |
- lr_scheduler_type: linear
|
73 |
-
- num_epochs:
|
74 |
- mixed_precision_training: Native AMP
|
75 |
|
76 |
### Training results
|
77 |
|
78 |
-
| Training Loss | Epoch | Step
|
79 |
-
|
80 |
-
| 1.
|
81 |
-
| 1.
|
82 |
-
| 0.
|
83 |
-
| 0.9279 | 4.0 | 10000 | 1.0973 | 0.5308 | 0.5329 | 0.5371 | 0.5308 |
|
84 |
-
| 0.8812 | 5.0 | 12500 | 1.1142 | 0.5332 | 0.5334 | 0.5339 | 0.5332 |
|
85 |
|
86 |
|
87 |
### Framework versions
|
|
|
18 |
dataset:
|
19 |
name: amazon_reviews_multi
|
20 |
type: amazon_reviews_multi
|
21 |
+
args: en
|
22 |
metrics:
|
23 |
- name: Accuracy
|
24 |
type: accuracy
|
25 |
+
value: 0.5504
|
26 |
- name: F1
|
27 |
type: f1
|
28 |
+
value: 0.5457527808330634
|
29 |
- name: Precision
|
30 |
type: precision
|
31 |
+
value: 0.5428695841337288
|
32 |
- name: Recall
|
33 |
type: recall
|
34 |
+
value: 0.5504
|
35 |
---
|
36 |
|
37 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
41 |
|
42 |
This model is a fine-tuned version of [google/electra-small-discriminator](https://huggingface.co/google/electra-small-discriminator) on the amazon_reviews_multi dataset.
|
43 |
It achieves the following results on the evaluation set:
|
44 |
+
- Loss: 1.0560
|
45 |
+
- Accuracy: 0.5504
|
46 |
+
- F1: 0.5458
|
47 |
+
- Precision: 0.5429
|
48 |
+
- Recall: 0.5504
|
49 |
|
50 |
## Model description
|
51 |
|
|
|
70 |
- seed: 42
|
71 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
72 |
- lr_scheduler_type: linear
|
73 |
+
- num_epochs: 3
|
74 |
- mixed_precision_training: Native AMP
|
75 |
|
76 |
### Training results
|
77 |
|
78 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|
79 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
|
80 |
+
| 1.2172 | 1.0 | 1000 | 1.1014 | 0.5216 | 0.4902 | 0.4954 | 0.5216 |
|
81 |
+
| 1.0027 | 2.0 | 2000 | 1.0388 | 0.549 | 0.5471 | 0.5494 | 0.549 |
|
82 |
+
| 0.9035 | 3.0 | 3000 | 1.0560 | 0.5504 | 0.5458 | 0.5429 | 0.5504 |
|
|
|
|
|
83 |
|
84 |
|
85 |
### Framework versions
|