Model save
Browse files
README.md
CHANGED
|
@@ -4,10 +4,6 @@ license: mit
|
|
| 4 |
base_model: microsoft/deberta-v3-base
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
-
metrics:
|
| 8 |
-
- accuracy
|
| 9 |
-
- precision
|
| 10 |
-
- recall
|
| 11 |
model-index:
|
| 12 |
- name: finetuning_test
|
| 13 |
results: []
|
|
@@ -16,15 +12,10 @@ model-index:
|
|
| 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 |
# finetuning_test
|
| 20 |
|
| 21 |
This model is a fine-tuned version of [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on an unknown dataset.
|
| 22 |
-
It achieves the following results on the evaluation set:
|
| 23 |
-
- Loss: 0.6970
|
| 24 |
-
- Accuracy: 0.5
|
| 25 |
-
- F1-score: 0.6667
|
| 26 |
-
- Precision: 0.5
|
| 27 |
-
- Recall: 1.0
|
| 28 |
|
| 29 |
## Model description
|
| 30 |
|
|
@@ -44,30 +35,14 @@ More information needed
|
|
| 44 |
|
| 45 |
The following hyperparameters were used during training:
|
| 46 |
- learning_rate: 1e-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
|
| 52 |
- lr_scheduler_warmup_steps: 2
|
| 53 |
- num_epochs: 1
|
| 54 |
|
| 55 |
-
### Training results
|
| 56 |
-
|
| 57 |
-
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1-score | Precision | Recall |
|
| 58 |
-
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:---------:|:------:|
|
| 59 |
-
| 0.7485 | 0.1 | 1 | 0.6990 | 0.5 | 0.6667 | 0.5 | 1.0 |
|
| 60 |
-
| 0.6785 | 0.2 | 2 | 0.6984 | 0.5 | 0.6667 | 0.5 | 1.0 |
|
| 61 |
-
| 0.6803 | 0.3 | 3 | 0.6982 | 0.5 | 0.6667 | 0.5 | 1.0 |
|
| 62 |
-
| 0.6517 | 0.4 | 4 | 0.6983 | 0.5 | 0.6667 | 0.5 | 1.0 |
|
| 63 |
-
| 0.7254 | 0.5 | 5 | 0.6980 | 0.5 | 0.6667 | 0.5 | 1.0 |
|
| 64 |
-
| 0.6979 | 0.6 | 6 | 0.6978 | 0.5 | 0.6667 | 0.5 | 1.0 |
|
| 65 |
-
| 0.7064 | 0.7 | 7 | 0.6975 | 0.5 | 0.6667 | 0.5 | 1.0 |
|
| 66 |
-
| 0.6709 | 0.8 | 8 | 0.6973 | 0.5 | 0.6667 | 0.5 | 1.0 |
|
| 67 |
-
| 0.7092 | 0.9 | 9 | 0.6971 | 0.5 | 0.6667 | 0.5 | 1.0 |
|
| 68 |
-
| 0.6975 | 1.0 | 10 | 0.6970 | 0.5 | 0.6667 | 0.5 | 1.0 |
|
| 69 |
-
|
| 70 |
-
|
| 71 |
### Framework versions
|
| 72 |
|
| 73 |
- Transformers 4.44.2
|
|
|
|
| 4 |
base_model: microsoft/deberta-v3-base
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
model-index:
|
| 8 |
- name: finetuning_test
|
| 9 |
results: []
|
|
|
|
| 12 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
|
| 15 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/abson-/twitter_sentiment_small/runs/reuhw38z)
|
| 16 |
# finetuning_test
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on an unknown dataset.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
|
|
| 35 |
|
| 36 |
The following hyperparameters were used during training:
|
| 37 |
- learning_rate: 1e-05
|
| 38 |
+
- train_batch_size: 16
|
| 39 |
+
- eval_batch_size: 16
|
| 40 |
- seed: 42
|
| 41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
- lr_scheduler_type: linear
|
| 43 |
- lr_scheduler_warmup_steps: 2
|
| 44 |
- num_epochs: 1
|
| 45 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 46 |
### Framework versions
|
| 47 |
|
| 48 |
- Transformers 4.44.2
|