update model card README.md
Browse files
README.md
CHANGED
|
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [google/pegasus-cnn_dailymail](https://huggingface.co/google/pegasus-cnn_dailymail) on the samsum dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
-
- Loss: 1.
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
@@ -43,35 +43,22 @@ The following hyperparameters were used during training:
|
|
| 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:
|
| 47 |
|
| 48 |
### Training results
|
| 49 |
|
| 50 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 51 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 52 |
| 1.6942 | 0.54 | 500 | 1.4832 |
|
| 53 |
-
| 1.
|
| 54 |
-
| 1.
|
| 55 |
-
| 1.
|
| 56 |
-
| 1.
|
| 57 |
-
| 1.2722 | 3.26 | 3000 | 1.3475 |
|
| 58 |
-
| 1.2101 | 3.8 | 3500 | 1.3395 |
|
| 59 |
-
| 1.1986 | 4.35 | 4000 | 1.3424 |
|
| 60 |
-
| 1.1821 | 4.89 | 4500 | 1.3353 |
|
| 61 |
-
| 1.1006 | 5.43 | 5000 | 1.3407 |
|
| 62 |
-
| 1.1005 | 5.98 | 5500 | 1.3356 |
|
| 63 |
-
| 1.2346 | 6.52 | 6000 | 1.3466 |
|
| 64 |
-
| 1.0769 | 7.07 | 6500 | 1.3432 |
|
| 65 |
-
| 1.0379 | 7.61 | 7000 | 1.3493 |
|
| 66 |
-
| 1.0674 | 8.15 | 7500 | 1.3514 |
|
| 67 |
-
| 1.0944 | 8.7 | 8000 | 1.3513 |
|
| 68 |
-
| 1.0151 | 9.24 | 8500 | 1.3537 |
|
| 69 |
-
| 1.0094 | 9.78 | 9000 | 1.3549 |
|
| 70 |
|
| 71 |
|
| 72 |
### Framework versions
|
| 73 |
|
| 74 |
- Transformers 4.24.0
|
| 75 |
- Pytorch 1.12.1+cu113
|
| 76 |
-
- Datasets 2.
|
| 77 |
- Tokenizers 0.13.2
|
|
|
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [google/pegasus-cnn_dailymail](https://huggingface.co/google/pegasus-cnn_dailymail) on the samsum dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 1.3587
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
|
|
| 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: 3
|
| 47 |
|
| 48 |
### Training results
|
| 49 |
|
| 50 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 51 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 52 |
| 1.6942 | 0.54 | 500 | 1.4832 |
|
| 53 |
+
| 1.4133 | 1.09 | 1000 | 1.4111 |
|
| 54 |
+
| 1.5088 | 1.63 | 1500 | 1.3778 |
|
| 55 |
+
| 1.4368 | 2.17 | 2000 | 1.3645 |
|
| 56 |
+
| 1.4041 | 2.72 | 2500 | 1.3587 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 57 |
|
| 58 |
|
| 59 |
### Framework versions
|
| 60 |
|
| 61 |
- Transformers 4.24.0
|
| 62 |
- Pytorch 1.12.1+cu113
|
| 63 |
+
- Datasets 2.7.0
|
| 64 |
- Tokenizers 0.13.2
|