update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: ainize/bart-base-cnn
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: bart-samsum
|
| 8 |
+
results: []
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
# bart-samsum
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [ainize/bart-base-cnn](https://huggingface.co/ainize/bart-base-cnn) on an unknown dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 1.4587
|
| 19 |
+
|
| 20 |
+
## Model description
|
| 21 |
+
|
| 22 |
+
More information needed
|
| 23 |
+
|
| 24 |
+
## Intended uses & limitations
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Training and evaluation data
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training procedure
|
| 33 |
+
|
| 34 |
+
### Training hyperparameters
|
| 35 |
+
|
| 36 |
+
The following hyperparameters were used during training:
|
| 37 |
+
- learning_rate: 5e-05
|
| 38 |
+
- train_batch_size: 1
|
| 39 |
+
- eval_batch_size: 1
|
| 40 |
+
- seed: 42
|
| 41 |
+
- gradient_accumulation_steps: 16
|
| 42 |
+
- total_train_batch_size: 16
|
| 43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
+
- lr_scheduler_type: linear
|
| 45 |
+
- lr_scheduler_warmup_steps: 500
|
| 46 |
+
- num_epochs: 15
|
| 47 |
+
|
| 48 |
+
### Training results
|
| 49 |
+
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 51 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
| 52 |
+
| 1.2901 | 0.64 | 500 | 1.2203 |
|
| 53 |
+
| 1.2057 | 1.28 | 1000 | 1.1384 |
|
| 54 |
+
| 1.1364 | 1.93 | 1500 | 1.1225 |
|
| 55 |
+
| 0.9711 | 2.57 | 2000 | 1.1362 |
|
| 56 |
+
| 0.786 | 3.21 | 2500 | 1.1461 |
|
| 57 |
+
| 0.818 | 3.85 | 3000 | 1.1298 |
|
| 58 |
+
| 0.7135 | 4.49 | 3500 | 1.1666 |
|
| 59 |
+
| 0.6222 | 5.14 | 4000 | 1.2114 |
|
| 60 |
+
| 0.64 | 5.78 | 4500 | 1.2103 |
|
| 61 |
+
| 0.5272 | 6.42 | 5000 | 1.2571 |
|
| 62 |
+
| 0.5057 | 7.06 | 5500 | 1.2963 |
|
| 63 |
+
| 0.4917 | 7.7 | 6000 | 1.2937 |
|
| 64 |
+
| 0.4291 | 8.35 | 6500 | 1.3286 |
|
| 65 |
+
| 0.4171 | 8.99 | 7000 | 1.3125 |
|
| 66 |
+
| 0.418 | 9.63 | 7500 | 1.3516 |
|
| 67 |
+
| 0.3576 | 10.27 | 8000 | 1.3778 |
|
| 68 |
+
| 0.3736 | 10.91 | 8500 | 1.3847 |
|
| 69 |
+
| 0.3443 | 11.56 | 9000 | 1.4215 |
|
| 70 |
+
| 0.2952 | 12.2 | 9500 | 1.4324 |
|
| 71 |
+
| 0.3236 | 12.84 | 10000 | 1.4355 |
|
| 72 |
+
| 0.2978 | 13.48 | 10500 | 1.4473 |
|
| 73 |
+
| 0.2828 | 14.13 | 11000 | 1.4557 |
|
| 74 |
+
| 0.304 | 14.77 | 11500 | 1.4587 |
|
| 75 |
+
|
| 76 |
+
|
| 77 |
+
### Framework versions
|
| 78 |
+
|
| 79 |
+
- Transformers 4.31.0
|
| 80 |
+
- Pytorch 2.0.1+cu118
|
| 81 |
+
- Datasets 2.13.0
|
| 82 |
+
- Tokenizers 0.13.3
|