Commit
·
aa6b10c
1
Parent(s):
0b13c1f
End of training
Browse files- README.md +10 -0
- generation_config.json +1 -0
README.md
CHANGED
|
@@ -14,6 +14,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
# my_awesome_opus_books_model
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [facebook/bart-large](https://huggingface.co/facebook/bart-large) on an unknown dataset.
|
|
|
|
|
|
|
| 17 |
|
| 18 |
## Model description
|
| 19 |
|
|
@@ -40,6 +42,14 @@ The following hyperparameters were used during training:
|
|
| 40 |
- lr_scheduler_type: linear
|
| 41 |
- num_epochs: 2
|
| 42 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 43 |
### Framework versions
|
| 44 |
|
| 45 |
- Transformers 4.33.3
|
|
|
|
| 14 |
# my_awesome_opus_books_model
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [facebook/bart-large](https://huggingface.co/facebook/bart-large) on an unknown dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 0.2390
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
|
|
| 42 |
- lr_scheduler_type: linear
|
| 43 |
- num_epochs: 2
|
| 44 |
|
| 45 |
+
### Training results
|
| 46 |
+
|
| 47 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 48 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 49 |
+
| 0.0423 | 1.0 | 2000 | 0.3021 |
|
| 50 |
+
| 0.0265 | 2.0 | 4000 | 0.2390 |
|
| 51 |
+
|
| 52 |
+
|
| 53 |
### Framework versions
|
| 54 |
|
| 55 |
- Transformers 4.33.3
|
generation_config.json
CHANGED
|
@@ -1,4 +1,5 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"bos_token_id": 0,
|
| 3 |
"decoder_start_token_id": 2,
|
| 4 |
"early_stopping": true,
|
|
|
|
| 1 |
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
"bos_token_id": 0,
|
| 4 |
"decoder_start_token_id": 2,
|
| 5 |
"early_stopping": true,
|