End of training
Browse files
README.md
CHANGED
|
@@ -3,6 +3,9 @@ license: mit
|
|
| 3 |
base_model: facebook/mbart-large-50
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
|
|
|
|
|
|
|
|
|
| 6 |
model-index:
|
| 7 |
- name: mBART-TextSimp-LT-BatchSize4-lr1e-4
|
| 8 |
results: []
|
|
@@ -14,6 +17,13 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
# mBART-TextSimp-LT-BatchSize4-lr1e-4
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [facebook/mbart-large-50](https://huggingface.co/facebook/mbart-large-50) on the None dataset.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
|
| 18 |
## Model description
|
| 19 |
|
|
@@ -41,13 +51,20 @@ The following hyperparameters were used during training:
|
|
| 41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
- lr_scheduler_type: linear
|
| 43 |
- lr_scheduler_warmup_steps: 500
|
| 44 |
-
- num_epochs:
|
| 45 |
|
| 46 |
### Training results
|
| 47 |
|
| 48 |
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Sacrebleu | Gen Len |
|
| 49 |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
|
| 50 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 51 |
|
| 52 |
|
| 53 |
### Framework versions
|
|
|
|
| 3 |
base_model: facebook/mbart-large-50
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- rouge
|
| 8 |
+
- sacrebleu
|
| 9 |
model-index:
|
| 10 |
- name: mBART-TextSimp-LT-BatchSize4-lr1e-4
|
| 11 |
results: []
|
|
|
|
| 17 |
# mBART-TextSimp-LT-BatchSize4-lr1e-4
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [facebook/mbart-large-50](https://huggingface.co/facebook/mbart-large-50) on the None dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.0962
|
| 22 |
+
- Rouge1: 0.76
|
| 23 |
+
- Rouge2: 0.6246
|
| 24 |
+
- Rougel: 0.7508
|
| 25 |
+
- Sacrebleu: 53.9078
|
| 26 |
+
- Gen Len: 32.9976
|
| 27 |
|
| 28 |
## Model description
|
| 29 |
|
|
|
|
| 51 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 52 |
- lr_scheduler_type: linear
|
| 53 |
- lr_scheduler_warmup_steps: 500
|
| 54 |
+
- num_epochs: 8
|
| 55 |
|
| 56 |
### Training results
|
| 57 |
|
| 58 |
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Sacrebleu | Gen Len |
|
| 59 |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
|
| 60 |
+
| 0.0639 | 1.0 | 418 | 0.0779 | 0.7012 | 0.5432 | 0.6904 | 43.0798 | 32.9976 |
|
| 61 |
+
| 0.0653 | 2.0 | 836 | 0.0732 | 0.7197 | 0.5593 | 0.7091 | 44.8483 | 32.9976 |
|
| 62 |
+
| 0.0327 | 3.0 | 1254 | 0.0726 | 0.7319 | 0.5787 | 0.7206 | 47.842 | 32.9976 |
|
| 63 |
+
| 0.0168 | 4.0 | 1672 | 0.0782 | 0.7466 | 0.6031 | 0.7371 | 50.9225 | 32.9976 |
|
| 64 |
+
| 0.013 | 5.0 | 2090 | 0.0804 | 0.7507 | 0.6077 | 0.7409 | 51.8293 | 32.9976 |
|
| 65 |
+
| 0.0032 | 6.0 | 2508 | 0.0846 | 0.7606 | 0.6237 | 0.7507 | 53.5224 | 32.9976 |
|
| 66 |
+
| 0.0012 | 7.0 | 2926 | 0.0911 | 0.7597 | 0.6263 | 0.751 | 54.0182 | 32.9976 |
|
| 67 |
+
| 0.0012 | 8.0 | 3344 | 0.0962 | 0.76 | 0.6246 | 0.7508 | 53.9078 | 32.9976 |
|
| 68 |
|
| 69 |
|
| 70 |
### Framework versions
|