update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
model-index:
|
| 5 |
+
- name: DistilBERT-POWO_Scratch
|
| 6 |
+
results: []
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 10 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 11 |
+
|
| 12 |
+
# DistilBERT-POWO_Scratch
|
| 13 |
+
|
| 14 |
+
This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
|
| 15 |
+
It achieves the following results on the evaluation set:
|
| 16 |
+
- Loss: 4.9068
|
| 17 |
+
|
| 18 |
+
## Model description
|
| 19 |
+
|
| 20 |
+
More information needed
|
| 21 |
+
|
| 22 |
+
## Intended uses & limitations
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Training and evaluation data
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training procedure
|
| 31 |
+
|
| 32 |
+
### Training hyperparameters
|
| 33 |
+
|
| 34 |
+
The following hyperparameters were used during training:
|
| 35 |
+
- learning_rate: 5e-05
|
| 36 |
+
- train_batch_size: 5
|
| 37 |
+
- eval_batch_size: 16
|
| 38 |
+
- seed: 42
|
| 39 |
+
- gradient_accumulation_steps: 8
|
| 40 |
+
- total_train_batch_size: 40
|
| 41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
+
- lr_scheduler_type: linear
|
| 43 |
+
- num_epochs: 3
|
| 44 |
+
|
| 45 |
+
### Training results
|
| 46 |
+
|
| 47 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 48 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 49 |
+
| 7.104 | 0.18 | 200 | 5.9641 |
|
| 50 |
+
| 5.6973 | 0.36 | 400 | 5.5992 |
|
| 51 |
+
| 5.5464 | 0.54 | 600 | 5.4564 |
|
| 52 |
+
| 5.377 | 0.72 | 800 | 5.3606 |
|
| 53 |
+
| 5.2162 | 0.9 | 1000 | 5.2674 |
|
| 54 |
+
| 5.1499 | 1.08 | 1200 | 5.2080 |
|
| 55 |
+
| 5.1313 | 1.26 | 1400 | 5.1447 |
|
| 56 |
+
| 5.0138 | 1.44 | 1600 | 5.1041 |
|
| 57 |
+
| 4.9509 | 1.62 | 1800 | 5.0572 |
|
| 58 |
+
| 4.9598 | 1.8 | 2000 | 5.0185 |
|
| 59 |
+
| 4.9581 | 1.98 | 2200 | 5.0109 |
|
| 60 |
+
| 4.8458 | 2.16 | 2400 | 4.9608 |
|
| 61 |
+
| 4.953 | 2.34 | 2600 | 4.9482 |
|
| 62 |
+
| 4.7448 | 2.52 | 2800 | 4.9211 |
|
| 63 |
+
| 4.8574 | 2.71 | 3000 | 4.9093 |
|
| 64 |
+
| 4.8402 | 2.89 | 3200 | 4.8980 |
|
| 65 |
+
|
| 66 |
+
|
| 67 |
+
### Framework versions
|
| 68 |
+
|
| 69 |
+
- Transformers 4.25.1
|
| 70 |
+
- Pytorch 1.13.1+cu116
|
| 71 |
+
- Datasets 2.8.0
|
| 72 |
+
- Tokenizers 0.13.2
|