update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- summarization
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- rouge
|
| 7 |
+
model-index:
|
| 8 |
+
- name: test
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 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 |
+
# test
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [Ameer05/tokenizer-repo](https://huggingface.co/Ameer05/tokenizer-repo) on an unknown dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 1.6109
|
| 20 |
+
- Rouge1: 54.9442
|
| 21 |
+
- Rouge2: 45.3299
|
| 22 |
+
- Rougel: 50.5219
|
| 23 |
+
- Rougelsum: 53.6475
|
| 24 |
+
|
| 25 |
+
## Model description
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Intended uses & limitations
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training and evaluation data
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Training procedure
|
| 38 |
+
|
| 39 |
+
### Training hyperparameters
|
| 40 |
+
|
| 41 |
+
The following hyperparameters were used during training:
|
| 42 |
+
- learning_rate: 5e-05
|
| 43 |
+
- train_batch_size: 8
|
| 44 |
+
- eval_batch_size: 8
|
| 45 |
+
- seed: 42
|
| 46 |
+
- gradient_accumulation_steps: 4
|
| 47 |
+
- total_train_batch_size: 32
|
| 48 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 49 |
+
- lr_scheduler_type: linear
|
| 50 |
+
- num_epochs: 10
|
| 51 |
+
- mixed_precision_training: Native AMP
|
| 52 |
+
|
| 53 |
+
### Training results
|
| 54 |
+
|
| 55 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|
| 56 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|
|
| 57 |
+
| No log | 0.91 | 5 | 2.3705 | 53.62 | 44.3835 | 49.6135 | 52.693 |
|
| 58 |
+
| No log | 1.91 | 10 | 1.9035 | 47.478 | 37.0934 | 39.7935 | 45.1881 |
|
| 59 |
+
| No log | 2.91 | 15 | 1.7990 | 54.2488 | 45.0782 | 49.8421 | 52.7564 |
|
| 60 |
+
| No log | 3.91 | 20 | 1.7125 | 55.7903 | 46.7554 | 52.2733 | 54.9389 |
|
| 61 |
+
| 2.4456 | 4.91 | 25 | 1.6421 | 52.2279 | 43.4391 | 49.6955 | 51.2915 |
|
| 62 |
+
| 2.4456 | 5.91 | 30 | 1.6102 | 55.8598 | 47.3293 | 53.1337 | 54.8596 |
|
| 63 |
+
| 2.4456 | 6.91 | 35 | 1.6164 | 53.7902 | 44.6622 | 49.5045 | 52.2304 |
|
| 64 |
+
| 2.4456 | 7.91 | 40 | 1.6015 | 51.5597 | 42.0333 | 47.9639 | 50.1154 |
|
| 65 |
+
| 1.239 | 8.91 | 45 | 1.6067 | 53.0301 | 43.7214 | 49.0227 | 51.8109 |
|
| 66 |
+
| 1.239 | 9.91 | 50 | 1.6109 | 54.9442 | 45.3299 | 50.5219 | 53.6475 |
|
| 67 |
+
|
| 68 |
+
|
| 69 |
+
### Framework versions
|
| 70 |
+
|
| 71 |
+
- Transformers 4.15.0
|
| 72 |
+
- Pytorch 1.9.1
|
| 73 |
+
- Datasets 2.0.0
|
| 74 |
+
- Tokenizers 0.10.3
|