update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- accuracy
|
| 7 |
+
- f1
|
| 8 |
+
model-index:
|
| 9 |
+
- name: tiny-mlm-wikitext-target-rotten_tomatoes
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# tiny-mlm-wikitext-target-rotten_tomatoes
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [muhtasham/tiny-mlm-wikitext](https://huggingface.co/muhtasham/tiny-mlm-wikitext) on the None dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.8868
|
| 21 |
+
- Accuracy: 0.7533
|
| 22 |
+
- F1: 0.7528
|
| 23 |
+
|
| 24 |
+
## Model description
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Intended uses & limitations
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training and evaluation data
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training procedure
|
| 37 |
+
|
| 38 |
+
### Training hyperparameters
|
| 39 |
+
|
| 40 |
+
The following hyperparameters were used during training:
|
| 41 |
+
- learning_rate: 3e-05
|
| 42 |
+
- train_batch_size: 32
|
| 43 |
+
- eval_batch_size: 32
|
| 44 |
+
- seed: 42
|
| 45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
+
- lr_scheduler_type: constant
|
| 47 |
+
- training_steps: 5000
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|
| 52 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
|
| 53 |
+
| 0.6236 | 1.87 | 500 | 0.5413 | 0.7289 | 0.7285 |
|
| 54 |
+
| 0.4892 | 3.75 | 1000 | 0.5137 | 0.7448 | 0.7435 |
|
| 55 |
+
| 0.4112 | 5.62 | 1500 | 0.5224 | 0.7636 | 0.7629 |
|
| 56 |
+
| 0.3454 | 7.49 | 2000 | 0.5365 | 0.7627 | 0.7624 |
|
| 57 |
+
| 0.2899 | 9.36 | 2500 | 0.5962 | 0.7655 | 0.7651 |
|
| 58 |
+
| 0.2447 | 11.24 | 3000 | 0.6489 | 0.7561 | 0.7554 |
|
| 59 |
+
| 0.2025 | 13.11 | 3500 | 0.6943 | 0.7692 | 0.7688 |
|
| 60 |
+
| 0.1671 | 14.98 | 4000 | 0.7455 | 0.7627 | 0.7621 |
|
| 61 |
+
| 0.1418 | 16.85 | 4500 | 0.7962 | 0.7608 | 0.7600 |
|
| 62 |
+
| 0.1239 | 18.73 | 5000 | 0.8868 | 0.7533 | 0.7528 |
|
| 63 |
+
|
| 64 |
+
|
| 65 |
+
### Framework versions
|
| 66 |
+
|
| 67 |
+
- Transformers 4.26.0.dev0
|
| 68 |
+
- Pytorch 1.13.0+cu116
|
| 69 |
+
- Datasets 2.8.1.dev0
|
| 70 |
+
- Tokenizers 0.13.2
|