Update README.md
Browse files
README.md
CHANGED
|
@@ -11,6 +11,8 @@ base_model: Prasadrao/xlm-roberta-large-go-emotions-v2
|
|
| 11 |
model-index:
|
| 12 |
- name: xlm-roberta-large-go-emotions-v3
|
| 13 |
results: []
|
|
|
|
|
|
|
| 14 |
---
|
| 15 |
|
| 16 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -18,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 18 |
|
| 19 |
# xlm-roberta-large-go-emotions-v3
|
| 20 |
|
| 21 |
-
This model is a fine-tuned version of [Prasadrao/xlm-roberta-large-go-emotions-v2](https://huggingface.co/Prasadrao/xlm-roberta-large-go-emotions-v2) on
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
- Loss: 0.0953
|
| 24 |
- Accuracy: 0.4534
|
|
@@ -44,8 +46,8 @@ More information needed
|
|
| 44 |
|
| 45 |
The following hyperparameters were used during training:
|
| 46 |
- learning_rate: 2e-05
|
| 47 |
-
- train_batch_size:
|
| 48 |
-
- eval_batch_size:
|
| 49 |
- seed: 42
|
| 50 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 51 |
- lr_scheduler_type: linear
|
|
@@ -64,4 +66,4 @@ The following hyperparameters were used during training:
|
|
| 64 |
- Transformers 4.37.0
|
| 65 |
- Pytorch 2.1.2
|
| 66 |
- Datasets 2.15.0
|
| 67 |
-
- Tokenizers 0.15.1
|
|
|
|
| 11 |
model-index:
|
| 12 |
- name: xlm-roberta-large-go-emotions-v3
|
| 13 |
results: []
|
| 14 |
+
datasets:
|
| 15 |
+
- go_emotions
|
| 16 |
---
|
| 17 |
|
| 18 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 20 |
|
| 21 |
# xlm-roberta-large-go-emotions-v3
|
| 22 |
|
| 23 |
+
This model is a fine-tuned version of [Prasadrao/xlm-roberta-large-go-emotions-v2](https://huggingface.co/Prasadrao/xlm-roberta-large-go-emotions-v2) on go emotion dataset.
|
| 24 |
It achieves the following results on the evaluation set:
|
| 25 |
- Loss: 0.0953
|
| 26 |
- Accuracy: 0.4534
|
|
|
|
| 46 |
|
| 47 |
The following hyperparameters were used during training:
|
| 48 |
- learning_rate: 2e-05
|
| 49 |
+
- train_batch_size: 16
|
| 50 |
+
- eval_batch_size: 16
|
| 51 |
- seed: 42
|
| 52 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 53 |
- lr_scheduler_type: linear
|
|
|
|
| 66 |
- Transformers 4.37.0
|
| 67 |
- Pytorch 2.1.2
|
| 68 |
- Datasets 2.15.0
|
| 69 |
+
- Tokenizers 0.15.1
|