Update README.md
Browse files
README.md
CHANGED
|
@@ -19,7 +19,7 @@ model_index:
|
|
| 19 |
metric:
|
| 20 |
name: Accuracy
|
| 21 |
type: accuracy
|
| 22 |
-
value: 0.
|
| 23 |
---
|
| 24 |
|
| 25 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -30,21 +30,20 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 30 |
This model is a fine-tuned version of [distilbert-base-cased](https://huggingface.co/distilbert-base-cased) on the tamilmixsentiment dataset.
|
| 31 |
It achieves the following results on the evaluation set:
|
| 32 |
- Loss: 1.0230
|
| 33 |
-
- Accuracy: 0.
|
| 34 |
|
| 35 |
-
##
|
| 36 |
-
|
| 37 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 38 |
|
| 39 |
## Intended uses & limitations
|
| 40 |
|
| 41 |
-
|
| 42 |
-
|
| 43 |
-
## Training and evaluation data
|
| 44 |
-
|
| 45 |
-
More information needed
|
| 46 |
-
|
| 47 |
-
## Training procedure
|
| 48 |
|
| 49 |
### Training hyperparameters
|
| 50 |
|
|
@@ -52,7 +51,7 @@ The following hyperparameters were used during training:
|
|
| 52 |
- learning_rate: 5e-05
|
| 53 |
- train_batch_size: 8
|
| 54 |
- eval_batch_size: 8
|
| 55 |
-
- seed:
|
| 56 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 57 |
- lr_scheduler_type: linear
|
| 58 |
- num_epochs: 3.0
|
|
|
|
| 19 |
metric:
|
| 20 |
name: Accuracy
|
| 21 |
type: accuracy
|
| 22 |
+
value: 0.663
|
| 23 |
---
|
| 24 |
|
| 25 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 30 |
This model is a fine-tuned version of [distilbert-base-cased](https://huggingface.co/distilbert-base-cased) on the tamilmixsentiment dataset.
|
| 31 |
It achieves the following results on the evaluation set:
|
| 32 |
- Loss: 1.0230
|
| 33 |
+
- Accuracy: 0.663
|
| 34 |
|
| 35 |
+
## Dataset Information
|
| 36 |
+
text: Tamil-English code-mixed comment.
|
| 37 |
+
label: list of the possible sentiments
|
| 38 |
+
LABEL_0: "Positive",
|
| 39 |
+
LABEL_1: "Negative",
|
| 40 |
+
LABEL_2: "Mixed_feelings",
|
| 41 |
+
LABEL_3: "unknown_state",
|
| 42 |
+
LABEL_4: "not-Tamil"
|
| 43 |
|
| 44 |
## Intended uses & limitations
|
| 45 |
|
| 46 |
+
This model was just created for doing classification task on tamilmixsentiment dataset
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 47 |
|
| 48 |
### Training hyperparameters
|
| 49 |
|
|
|
|
| 51 |
- learning_rate: 5e-05
|
| 52 |
- train_batch_size: 8
|
| 53 |
- eval_batch_size: 8
|
| 54 |
+
- seed: 0
|
| 55 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 56 |
- lr_scheduler_type: linear
|
| 57 |
- num_epochs: 3.0
|