damianoimola
commited on
Commit
•
88f0203
1
Parent(s):
e305a44
Model save
Browse files
README.md
CHANGED
@@ -9,18 +9,18 @@ metrics:
|
|
9 |
- f1
|
10 |
- accuracy
|
11 |
model-index:
|
12 |
-
- name:
|
13 |
results: []
|
14 |
---
|
15 |
|
16 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
17 |
should probably proofread and complete it, then remove this comment. -->
|
18 |
|
19 |
-
#
|
20 |
|
21 |
This model is a fine-tuned version of [FacebookAI/roberta-base](https://huggingface.co/FacebookAI/roberta-base) on the None dataset.
|
22 |
It achieves the following results on the evaluation set:
|
23 |
-
- Loss: 2.
|
24 |
- Precision: 0.1154
|
25 |
- Recall: 0.3333
|
26 |
- F1: 0.1715
|
@@ -50,14 +50,13 @@ The following hyperparameters were used during training:
|
|
50 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
- lr_scheduler_type: linear
|
52 |
- lr_scheduler_warmup_steps: 500
|
53 |
-
- num_epochs:
|
54 |
|
55 |
### Training results
|
56 |
|
57 |
-
| Training Loss | Epoch | Step
|
58 |
-
|
59 |
-
|
|
60 |
-
| 1.6815 | 2.0 | 167012 | 2.8181 | 0.1150 | 0.3333 | 0.1710 | 0.3451 |
|
61 |
|
62 |
|
63 |
### Framework versions
|
|
|
9 |
- f1
|
10 |
- accuracy
|
11 |
model-index:
|
12 |
+
- name: mnlp_adversarial
|
13 |
results: []
|
14 |
---
|
15 |
|
16 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
17 |
should probably proofread and complete it, then remove this comment. -->
|
18 |
|
19 |
+
# mnlp_adversarial
|
20 |
|
21 |
This model is a fine-tuned version of [FacebookAI/roberta-base](https://huggingface.co/FacebookAI/roberta-base) on the None dataset.
|
22 |
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 2.8943
|
24 |
- Precision: 0.1154
|
25 |
- Recall: 0.3333
|
26 |
- F1: 0.1715
|
|
|
50 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
- lr_scheduler_type: linear
|
52 |
- lr_scheduler_warmup_steps: 500
|
53 |
+
- num_epochs: 1
|
54 |
|
55 |
### Training results
|
56 |
|
57 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
58 |
+
|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
59 |
+
| 2.0428 | 1.0 | 87097 | 2.8943 | 0.1154 | 0.3333 | 0.1715 | 0.3463 |
|
|
|
60 |
|
61 |
|
62 |
### Framework versions
|