october-sd
commited on
Commit
•
8a18812
1
Parent(s):
fb1ed9c
Training complete
Browse files
README.md
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
---
|
2 |
license: mit
|
3 |
-
base_model:
|
4 |
tags:
|
5 |
- summarization
|
6 |
- generated_from_trainer
|
@@ -14,9 +14,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
14 |
|
15 |
# mbart-large-50-finetuned-mr-sum
|
16 |
|
17 |
-
This model is a fine-tuned version of [
|
18 |
It achieves the following results on the evaluation set:
|
19 |
-
- Loss: 1.
|
20 |
|
21 |
## Model description
|
22 |
|
@@ -41,6 +41,7 @@ The following hyperparameters were used during training:
|
|
41 |
- seed: 42
|
42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
- lr_scheduler_type: linear
|
|
|
44 |
- num_epochs: 2
|
45 |
- mixed_precision_training: Native AMP
|
46 |
|
@@ -48,8 +49,8 @@ The following hyperparameters were used during training:
|
|
48 |
|
49 |
| Training Loss | Epoch | Step | Validation Loss |
|
50 |
|:-------------:|:-----:|:----:|:---------------:|
|
51 |
-
|
|
52 |
-
| 1.
|
53 |
|
54 |
|
55 |
### Framework versions
|
|
|
1 |
---
|
2 |
license: mit
|
3 |
+
base_model: october-sd/mbart-large-50-finetuned-mr-sum
|
4 |
tags:
|
5 |
- summarization
|
6 |
- generated_from_trainer
|
|
|
14 |
|
15 |
# mbart-large-50-finetuned-mr-sum
|
16 |
|
17 |
+
This model is a fine-tuned version of [october-sd/mbart-large-50-finetuned-mr-sum](https://huggingface.co/october-sd/mbart-large-50-finetuned-mr-sum) on the None dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 1.9896
|
20 |
|
21 |
## Model description
|
22 |
|
|
|
41 |
- seed: 42
|
42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
- lr_scheduler_type: linear
|
44 |
+
- lr_scheduler_warmup_steps: 100
|
45 |
- num_epochs: 2
|
46 |
- mixed_precision_training: Native AMP
|
47 |
|
|
|
49 |
|
50 |
| Training Loss | Epoch | Step | Validation Loss |
|
51 |
|:-------------:|:-----:|:----:|:---------------:|
|
52 |
+
| 1.5989 | 1.0 | 3605 | 1.9562 |
|
53 |
+
| 1.1384 | 2.0 | 7210 | 1.9896 |
|
54 |
|
55 |
|
56 |
### Framework versions
|