Masaki Eguchi
commited on
Commit
·
3363186
1
Parent(s):
041465c
update model card README.md
Browse files
README.md
CHANGED
|
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the elsevier-oa-cc-by dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
-
- Loss: 2.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
@@ -35,23 +35,39 @@ More information needed
|
|
| 35 |
### Training hyperparameters
|
| 36 |
|
| 37 |
The following hyperparameters were used during training:
|
| 38 |
-
- learning_rate:
|
| 39 |
- train_batch_size: 32
|
| 40 |
- eval_batch_size: 32
|
| 41 |
- seed: 42
|
| 42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 43 |
- lr_scheduler_type: linear
|
| 44 |
- num_epochs: 5
|
|
|
|
| 45 |
|
| 46 |
### Training results
|
| 47 |
|
| 48 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 49 |
|:-------------:|:-----:|:-----:|:---------------:|
|
| 50 |
-
| 2.
|
| 51 |
-
| 2.
|
| 52 |
-
| 2.
|
| 53 |
-
| 2.
|
| 54 |
-
| 2.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 55 |
|
| 56 |
|
| 57 |
### Framework versions
|
|
|
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the elsevier-oa-cc-by dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 2.2518
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
|
|
| 35 |
### Training hyperparameters
|
| 36 |
|
| 37 |
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 1e-06
|
| 39 |
- train_batch_size: 32
|
| 40 |
- eval_batch_size: 32
|
| 41 |
- seed: 42
|
| 42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 43 |
- lr_scheduler_type: linear
|
| 44 |
- num_epochs: 5
|
| 45 |
+
- mixed_precision_training: Native AMP
|
| 46 |
|
| 47 |
### Training results
|
| 48 |
|
| 49 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 50 |
|:-------------:|:-----:|:-----:|:---------------:|
|
| 51 |
+
| 2.4036 | 0.25 | 1025 | 2.2778 |
|
| 52 |
+
| 2.3813 | 0.5 | 2050 | 2.2568 |
|
| 53 |
+
| 2.3726 | 0.75 | 3075 | 2.2684 |
|
| 54 |
+
| 2.3832 | 1.0 | 4100 | 2.2510 |
|
| 55 |
+
| 2.3747 | 1.25 | 5125 | 2.2444 |
|
| 56 |
+
| 2.3775 | 1.5 | 6150 | 2.2536 |
|
| 57 |
+
| 2.3802 | 1.75 | 7175 | 2.2519 |
|
| 58 |
+
| 2.384 | 2.0 | 8200 | 2.2474 |
|
| 59 |
+
| 2.3828 | 2.25 | 9225 | 2.2502 |
|
| 60 |
+
| 2.3694 | 2.5 | 10250 | 2.2558 |
|
| 61 |
+
| 2.375 | 2.75 | 11275 | 2.2623 |
|
| 62 |
+
| 2.3754 | 3.0 | 12300 | 2.2484 |
|
| 63 |
+
| 2.3918 | 3.25 | 13325 | 2.2638 |
|
| 64 |
+
| 2.3763 | 3.5 | 14350 | 2.2530 |
|
| 65 |
+
| 2.368 | 3.75 | 15375 | 2.2590 |
|
| 66 |
+
| 2.3711 | 4.0 | 16400 | 2.2571 |
|
| 67 |
+
| 2.3786 | 4.25 | 17425 | 2.2528 |
|
| 68 |
+
| 2.3793 | 4.5 | 18450 | 2.2537 |
|
| 69 |
+
| 2.3756 | 4.75 | 19475 | 2.2410 |
|
| 70 |
+
| 2.3799 | 5.0 | 20500 | 2.2446 |
|
| 71 |
|
| 72 |
|
| 73 |
### Framework versions
|