Commit
·
599b891
1
Parent(s):
7f3172e
update model card README.md
Browse files
README.md
CHANGED
|
@@ -2,9 +2,24 @@
|
|
| 2 |
license: mit
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
model-index:
|
| 6 |
- name: deberta_amazon_reviews_v1
|
| 7 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
---
|
| 9 |
|
| 10 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -12,7 +27,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 12 |
|
| 13 |
# deberta_amazon_reviews_v1
|
| 14 |
|
| 15 |
-
This model is a fine-tuned version of [
|
|
|
|
|
|
|
|
|
|
| 16 |
|
| 17 |
## Model description
|
| 18 |
|
|
@@ -40,6 +58,22 @@ The following hyperparameters were used during training:
|
|
| 40 |
- lr_scheduler_warmup_steps: 200
|
| 41 |
- num_epochs: 2
|
| 42 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 43 |
### Framework versions
|
| 44 |
|
| 45 |
- Transformers 4.17.0
|
|
|
|
| 2 |
license: mit
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- amazon_reviews_multi
|
| 7 |
+
metrics:
|
| 8 |
+
- accuracy
|
| 9 |
model-index:
|
| 10 |
- name: deberta_amazon_reviews_v1
|
| 11 |
+
results:
|
| 12 |
+
- task:
|
| 13 |
+
name: Text Classification
|
| 14 |
+
type: text-classification
|
| 15 |
+
dataset:
|
| 16 |
+
name: amazon_reviews_multi
|
| 17 |
+
type: amazon_reviews_multi
|
| 18 |
+
args: en
|
| 19 |
+
metrics:
|
| 20 |
+
- name: Accuracy
|
| 21 |
+
type: accuracy
|
| 22 |
+
value: 0.6184
|
| 23 |
---
|
| 24 |
|
| 25 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 27 |
|
| 28 |
# deberta_amazon_reviews_v1
|
| 29 |
|
| 30 |
+
This model is a fine-tuned version of [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on the amazon_reviews_multi dataset.
|
| 31 |
+
It achieves the following results on the evaluation set:
|
| 32 |
+
- Loss: 0.9076
|
| 33 |
+
- Accuracy: 0.6184
|
| 34 |
|
| 35 |
## Model description
|
| 36 |
|
|
|
|
| 58 |
- lr_scheduler_warmup_steps: 200
|
| 59 |
- num_epochs: 2
|
| 60 |
|
| 61 |
+
### Training results
|
| 62 |
+
|
| 63 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 64 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
| 65 |
+
| 0.9312 | 0.2 | 5000 | 0.9796 | 0.5856 |
|
| 66 |
+
| 0.9316 | 0.4 | 10000 | 0.9336 | 0.5974 |
|
| 67 |
+
| 0.9076 | 0.6 | 15000 | 0.9171 | 0.6026 |
|
| 68 |
+
| 0.9024 | 0.8 | 20000 | 0.9194 | 0.6046 |
|
| 69 |
+
| 0.8794 | 1.0 | 25000 | 0.9109 | 0.6084 |
|
| 70 |
+
| 0.8067 | 1.2 | 30000 | 0.9339 | 0.6092 |
|
| 71 |
+
| 0.8268 | 1.4 | 35000 | 0.9073 | 0.6162 |
|
| 72 |
+
| 0.8205 | 1.6 | 40000 | 0.9042 | 0.6158 |
|
| 73 |
+
| 0.795 | 1.8 | 45000 | 0.9189 | 0.6168 |
|
| 74 |
+
| 0.7836 | 2.0 | 50000 | 0.9076 | 0.6184 |
|
| 75 |
+
|
| 76 |
+
|
| 77 |
### Framework versions
|
| 78 |
|
| 79 |
- Transformers 4.17.0
|