update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- rouge
|
| 7 |
+
model-index:
|
| 8 |
+
- name: led-base-16384-finetune-xsum
|
| 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 |
+
# led-base-16384-finetune-xsum
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [allenai/led-base-16384](https://huggingface.co/allenai/led-base-16384) on the None dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 2.5945
|
| 20 |
+
- Rouge1: 33.044
|
| 21 |
+
- Rouge2: 10.1279
|
| 22 |
+
- Rougel: 26.0726
|
| 23 |
+
- Rougelsum: 26.1473
|
| 24 |
+
- Gen Len: 19.88
|
| 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: 2e-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: 10
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|
| 54 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
|
| 55 |
+
| No log | 1.0 | 125 | 2.0340 | 33.5205 | 11.6068 | 27.034 | 27.1108 | 19.4 |
|
| 56 |
+
| No log | 2.0 | 250 | 2.0703 | 33.4026 | 11.5155 | 26.8554 | 26.9315 | 19.52 |
|
| 57 |
+
| No log | 3.0 | 375 | 2.1928 | 31.8924 | 11.2046 | 25.5199 | 25.4997 | 19.86 |
|
| 58 |
+
| 1.4951 | 4.0 | 500 | 2.2934 | 32.8838 | 11.2708 | 26.4849 | 26.5854 | 19.78 |
|
| 59 |
+
| 1.4951 | 5.0 | 625 | 2.3796 | 32.3596 | 11.1823 | 25.8718 | 25.9102 | 19.92 |
|
| 60 |
+
| 1.4951 | 6.0 | 750 | 2.4533 | 32.3313 | 11.008 | 25.9119 | 25.9228 | 19.89 |
|
| 61 |
+
| 1.4951 | 7.0 | 875 | 2.5151 | 31.6539 | 9.9426 | 25.1465 | 25.265 | 19.89 |
|
| 62 |
+
| 0.4719 | 8.0 | 1000 | 2.5631 | 32.2152 | 10.4829 | 25.808 | 25.9387 | 19.79 |
|
| 63 |
+
| 0.4719 | 9.0 | 1125 | 2.5777 | 31.8661 | 9.6903 | 25.7577 | 25.7874 | 19.89 |
|
| 64 |
+
| 0.4719 | 10.0 | 1250 | 2.5945 | 33.044 | 10.1279 | 26.0726 | 26.1473 | 19.88 |
|
| 65 |
+
|
| 66 |
+
|
| 67 |
+
### Framework versions
|
| 68 |
+
|
| 69 |
+
- Transformers 4.30.2
|
| 70 |
+
- Pytorch 2.0.1+cu118
|
| 71 |
+
- Datasets 2.13.1
|
| 72 |
+
- Tokenizers 0.13.3
|