update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- summarization
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- rouge
|
| 8 |
+
model-index:
|
| 9 |
+
- name: BARTkrame-abstract
|
| 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 |
+
# BARTkrame-abstract
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [moussaKam/mbarthez](https://huggingface.co/moussaKam/mbarthez) on the None dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 2.1454
|
| 21 |
+
- Rouge1: 0.2588
|
| 22 |
+
- Rouge2: 0.1200
|
| 23 |
+
- Rougel: 0.2261
|
| 24 |
+
- Rougelsum: 0.2272
|
| 25 |
+
|
| 26 |
+
## Model description
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Intended uses & limitations
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training and evaluation data
|
| 35 |
+
|
| 36 |
+
More information needed
|
| 37 |
+
|
| 38 |
+
## Training procedure
|
| 39 |
+
|
| 40 |
+
### Training hyperparameters
|
| 41 |
+
|
| 42 |
+
The following hyperparameters were used during training:
|
| 43 |
+
- learning_rate: 5.6e-05
|
| 44 |
+
- train_batch_size: 4
|
| 45 |
+
- eval_batch_size: 4
|
| 46 |
+
- seed: 42
|
| 47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
+
- lr_scheduler_type: linear
|
| 49 |
+
- num_epochs: 8
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|
| 54 |
+
|:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|:------:|:---------:|
|
| 55 |
+
| 1.9038 | 1.0 | 1250 | 1.5561 | 0.2519 | 0.1229 | 0.2178 | 0.2222 |
|
| 56 |
+
| 1.2571 | 2.0 | 2500 | 1.5738 | 0.2610 | 0.1292 | 0.2236 | 0.2271 |
|
| 57 |
+
| 0.8214 | 3.0 | 3750 | 1.6332 | 0.2529 | 0.1203 | 0.2170 | 0.2198 |
|
| 58 |
+
| 0.5215 | 4.0 | 5000 | 1.8092 | 0.2397 | 0.1025 | 0.2051 | 0.2067 |
|
| 59 |
+
| 0.3168 | 5.0 | 6250 | 1.9376 | 0.2655 | 0.1324 | 0.2305 | 0.2329 |
|
| 60 |
+
| 0.1879 | 6.0 | 7500 | 2.0258 | 0.2618 | 0.1267 | 0.2282 | 0.2298 |
|
| 61 |
+
| 0.1142 | 7.0 | 8750 | 2.1103 | 0.2615 | 0.1278 | 0.2282 | 0.2300 |
|
| 62 |
+
| 0.0725 | 8.0 | 10000 | 2.1454 | 0.2588 | 0.1200 | 0.2261 | 0.2272 |
|
| 63 |
+
|
| 64 |
+
|
| 65 |
+
### Framework versions
|
| 66 |
+
|
| 67 |
+
- Transformers 4.23.1
|
| 68 |
+
- Pytorch 1.12.1+cu113
|
| 69 |
+
- Datasets 2.6.1
|
| 70 |
+
- Tokenizers 0.13.1
|