update model card README.md
Browse files
README.md
CHANGED
|
@@ -2,8 +2,6 @@
|
|
| 2 |
license: apache-2.0
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
| 5 |
-
metrics:
|
| 6 |
-
- rouge
|
| 7 |
model-index:
|
| 8 |
- name: bart-base-finetuned-xsum
|
| 9 |
results: []
|
|
@@ -16,12 +14,17 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the None dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
-
-
|
| 20 |
-
-
|
| 21 |
-
-
|
| 22 |
-
-
|
| 23 |
-
-
|
| 24 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
|
| 26 |
## Model description
|
| 27 |
|
|
@@ -41,29 +44,13 @@ More information needed
|
|
| 41 |
|
| 42 |
The following hyperparameters were used during training:
|
| 43 |
- learning_rate: 2e-05
|
| 44 |
-
- train_batch_size:
|
| 45 |
-
- eval_batch_size:
|
| 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 |
-
| 1.596 | 1.0 | 501 | 1.7802 | 10.2407 | 5.6898 | 8.8732 | 9.8768 | 20.0 |
|
| 56 |
-
| 1.6005 | 2.0 | 1002 | 1.7802 | 10.2407 | 5.6898 | 8.8732 | 9.8768 | 20.0 |
|
| 57 |
-
| 1.5976 | 3.0 | 1503 | 1.7802 | 10.2407 | 5.6898 | 8.8732 | 9.8768 | 20.0 |
|
| 58 |
-
| 1.5868 | 4.0 | 2004 | 1.7802 | 10.2407 | 5.6898 | 8.8732 | 9.8768 | 20.0 |
|
| 59 |
-
| 1.605 | 5.0 | 2505 | 1.7802 | 10.2407 | 5.6898 | 8.8732 | 9.8768 | 20.0 |
|
| 60 |
-
| 1.6027 | 6.0 | 3006 | 1.7802 | 10.2407 | 5.6898 | 8.8732 | 9.8768 | 20.0 |
|
| 61 |
-
| 1.5854 | 7.0 | 3507 | 1.7802 | 10.2407 | 5.6898 | 8.8732 | 9.8768 | 20.0 |
|
| 62 |
-
| 1.605 | 8.0 | 4008 | 1.7802 | 10.2407 | 5.6898 | 8.8732 | 9.8768 | 20.0 |
|
| 63 |
-
| 1.5957 | 9.0 | 4509 | 1.7802 | 10.2407 | 5.6898 | 8.8732 | 9.8768 | 20.0 |
|
| 64 |
-
| 1.6029 | 10.0 | 5010 | 1.7802 | 10.2407 | 5.6898 | 8.8732 | 9.8768 | 20.0 |
|
| 65 |
-
|
| 66 |
-
|
| 67 |
### Framework versions
|
| 68 |
|
| 69 |
- Transformers 4.30.2
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
|
|
|
|
|
|
| 5 |
model-index:
|
| 6 |
- name: bart-base-finetuned-xsum
|
| 7 |
results: []
|
|
|
|
| 14 |
|
| 15 |
This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the None dataset.
|
| 16 |
It achieves the following results on the evaluation set:
|
| 17 |
+
- eval_loss: 1.6558
|
| 18 |
+
- eval_rouge1: 10.116
|
| 19 |
+
- eval_rouge2: 4.6066
|
| 20 |
+
- eval_rougeL: 8.2314
|
| 21 |
+
- eval_rougeLsum: 9.4884
|
| 22 |
+
- eval_gen_len: 20.0
|
| 23 |
+
- eval_runtime: 1086.9962
|
| 24 |
+
- eval_samples_per_second: 11.385
|
| 25 |
+
- eval_steps_per_second: 0.712
|
| 26 |
+
- epoch: 2.0
|
| 27 |
+
- step: 6188
|
| 28 |
|
| 29 |
## Model description
|
| 30 |
|
|
|
|
| 44 |
|
| 45 |
The following hyperparameters were used during training:
|
| 46 |
- learning_rate: 2e-05
|
| 47 |
+
- train_batch_size: 16
|
| 48 |
+
- eval_batch_size: 16
|
| 49 |
- seed: 42
|
| 50 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 51 |
- lr_scheduler_type: linear
|
| 52 |
- num_epochs: 10
|
| 53 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 54 |
### Framework versions
|
| 55 |
|
| 56 |
- Transformers 4.30.2
|