update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
model-index:
|
| 5 |
+
- name: bert-base-uncased-pretrain-finetuned-coqa-falttened
|
| 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 |
+
# bert-base-uncased-pretrain-finetuned-coqa-falttened
|
| 13 |
+
|
| 14 |
+
This model is a fine-tuned version of [alistvt/bert-base-uncased-pretrained-mlm-coqa-stories](https://huggingface.co/alistvt/bert-base-uncased-pretrained-mlm-coqa-stories) on the None dataset.
|
| 15 |
+
It achieves the following results on the evaluation set:
|
| 16 |
+
- Loss: 2.8655
|
| 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: 16
|
| 37 |
+
- eval_batch_size: 16
|
| 38 |
+
- seed: 42
|
| 39 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 40 |
+
- lr_scheduler_type: linear
|
| 41 |
+
- num_epochs: 3
|
| 42 |
+
|
| 43 |
+
### Training results
|
| 44 |
+
|
| 45 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 46 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
| 47 |
+
| 3.2886 | 0.29 | 2000 | 3.0142 |
|
| 48 |
+
| 3.0801 | 0.59 | 4000 | 2.8347 |
|
| 49 |
+
| 2.9744 | 0.88 | 6000 | 2.7643 |
|
| 50 |
+
| 2.494 | 1.18 | 8000 | 2.7605 |
|
| 51 |
+
| 2.4417 | 1.47 | 10000 | 2.7790 |
|
| 52 |
+
| 2.4042 | 1.77 | 12000 | 2.7382 |
|
| 53 |
+
| 2.1285 | 2.06 | 14000 | 2.8588 |
|
| 54 |
+
| 2.0569 | 2.36 | 16000 | 2.8937 |
|
| 55 |
+
| 2.0794 | 2.65 | 18000 | 2.8511 |
|
| 56 |
+
| 2.0679 | 2.95 | 20000 | 2.8655 |
|
| 57 |
+
|
| 58 |
+
|
| 59 |
+
### Framework versions
|
| 60 |
+
|
| 61 |
+
- Transformers 4.15.0
|
| 62 |
+
- Pytorch 1.10.0+cu111
|
| 63 |
+
- Datasets 1.17.0
|
| 64 |
+
- Tokenizers 0.10.3
|