update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,91 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- glue
|
| 7 |
+
metrics:
|
| 8 |
+
- accuracy
|
| 9 |
+
model-index:
|
| 10 |
+
- name: distilbert_sst2_finetuned
|
| 11 |
+
results:
|
| 12 |
+
- task:
|
| 13 |
+
name: Text Classification
|
| 14 |
+
type: text-classification
|
| 15 |
+
dataset:
|
| 16 |
+
name: glue
|
| 17 |
+
type: glue
|
| 18 |
+
config: sst2
|
| 19 |
+
split: validation
|
| 20 |
+
args: sst2
|
| 21 |
+
metrics:
|
| 22 |
+
- name: Accuracy
|
| 23 |
+
type: accuracy
|
| 24 |
+
value: 0.875
|
| 25 |
+
---
|
| 26 |
+
|
| 27 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 28 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 29 |
+
|
| 30 |
+
# distilbert_sst2_finetuned
|
| 31 |
+
|
| 32 |
+
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the glue dataset.
|
| 33 |
+
It achieves the following results on the evaluation set:
|
| 34 |
+
- Loss: 0.2831
|
| 35 |
+
- Accuracy: 0.875
|
| 36 |
+
|
| 37 |
+
## Model description
|
| 38 |
+
|
| 39 |
+
More information needed
|
| 40 |
+
|
| 41 |
+
## Intended uses & limitations
|
| 42 |
+
|
| 43 |
+
More information needed
|
| 44 |
+
|
| 45 |
+
## Training and evaluation data
|
| 46 |
+
|
| 47 |
+
More information needed
|
| 48 |
+
|
| 49 |
+
## Training procedure
|
| 50 |
+
|
| 51 |
+
### Training hyperparameters
|
| 52 |
+
|
| 53 |
+
The following hyperparameters were used during training:
|
| 54 |
+
- learning_rate: 1e-06
|
| 55 |
+
- train_batch_size: 32
|
| 56 |
+
- eval_batch_size: 32
|
| 57 |
+
- seed: 42
|
| 58 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 59 |
+
- lr_scheduler_type: linear
|
| 60 |
+
- lr_scheduler_warmup_steps: 1000
|
| 61 |
+
- num_epochs: 4
|
| 62 |
+
- mixed_precision_training: Native AMP
|
| 63 |
+
|
| 64 |
+
### Training results
|
| 65 |
+
|
| 66 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 67 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 68 |
+
| 0.6883 | 0.24 | 500 | 0.6768 | 0.5115 |
|
| 69 |
+
| 0.5422 | 0.48 | 1000 | 0.4060 | 0.8200 |
|
| 70 |
+
| 0.3479 | 0.71 | 1500 | 0.3533 | 0.8452 |
|
| 71 |
+
| 0.3217 | 0.95 | 2000 | 0.3343 | 0.8567 |
|
| 72 |
+
| 0.2967 | 1.19 | 2500 | 0.3200 | 0.8635 |
|
| 73 |
+
| 0.2857 | 1.43 | 3000 | 0.3110 | 0.8624 |
|
| 74 |
+
| 0.2723 | 1.66 | 3500 | 0.3010 | 0.8670 |
|
| 75 |
+
| 0.2744 | 1.9 | 4000 | 0.2896 | 0.8727 |
|
| 76 |
+
| 0.2594 | 2.14 | 4500 | 0.2897 | 0.8716 |
|
| 77 |
+
| 0.2574 | 2.38 | 5000 | 0.2845 | 0.8761 |
|
| 78 |
+
| 0.2484 | 2.61 | 5500 | 0.2869 | 0.8739 |
|
| 79 |
+
| 0.2464 | 2.85 | 6000 | 0.2842 | 0.8761 |
|
| 80 |
+
| 0.2451 | 3.09 | 6500 | 0.2820 | 0.8773 |
|
| 81 |
+
| 0.2504 | 3.33 | 7000 | 0.2805 | 0.8784 |
|
| 82 |
+
| 0.236 | 3.56 | 7500 | 0.2833 | 0.875 |
|
| 83 |
+
| 0.2366 | 3.8 | 8000 | 0.2831 | 0.875 |
|
| 84 |
+
|
| 85 |
+
|
| 86 |
+
### Framework versions
|
| 87 |
+
|
| 88 |
+
- Transformers 4.27.4
|
| 89 |
+
- Pytorch 1.13.1+cu116
|
| 90 |
+
- Datasets 2.11.0
|
| 91 |
+
- Tokenizers 0.13.2
|