Commit
•
7310ca9
1
Parent(s):
d7ee898
Training in progress epoch 1
Browse files
README.md
CHANGED
@@ -15,7 +15,7 @@ probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
This model is a fine-tuned version of [PlanTL-GOB-ES/roberta-base-bne](https://huggingface.co/PlanTL-GOB-ES/roberta-base-bne) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Train Loss: 12.
|
19 |
- Validation Loss: 11.7955
|
20 |
- Train Accuracy: 0.7647
|
21 |
- Train Precision: [0. 0.76470588]
|
@@ -24,7 +24,7 @@ It achieves the following results on the evaluation set:
|
|
24 |
- Train Recall W: 0.7647
|
25 |
- Train F1: [0. 0.86666667]
|
26 |
- Train F1 W: 0.6627
|
27 |
-
- Epoch:
|
28 |
|
29 |
## Model description
|
30 |
|
@@ -43,23 +43,14 @@ More information needed
|
|
43 |
### Training hyperparameters
|
44 |
|
45 |
The following hyperparameters were used during training:
|
46 |
-
- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'WarmUp', 'config': {'initial_learning_rate': 2e-05, 'decay_schedule_fn': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps':
|
47 |
- training_precision: float32
|
48 |
|
49 |
### Training results
|
50 |
|
51 |
| Train Loss | Validation Loss | Train Accuracy | Train Precision | Train Precision W | Train Recall | Train Recall W | Train F1 | Train F1 W | Epoch |
|
52 |
|:----------:|:---------------:|:--------------:|:-----------------------:|:-----------------:|:------------:|:--------------:|:-----------------------:|:----------:|:-----:|
|
53 |
-
| 12.
|
54 |
-
| 12.2918 | 11.7955 | 0.7647 | [0. 0.76470588] | 0.5848 | [0. 1.] | 0.7647 | [0. 0.86666667] | 0.6627 | 2 |
|
55 |
-
| 12.2918 | 11.7955 | 0.7647 | [0. 0.76470588] | 0.5848 | [0. 1.] | 0.7647 | [0. 0.86666667] | 0.6627 | 3 |
|
56 |
-
| 12.2918 | 11.7955 | 0.7647 | [0. 0.76470588] | 0.5848 | [0. 1.] | 0.7647 | [0. 0.86666667] | 0.6627 | 4 |
|
57 |
-
| 12.5328 | 11.7955 | 0.7647 | [0. 0.76470588] | 0.5848 | [0. 1.] | 0.7647 | [0. 0.86666667] | 0.6627 | 5 |
|
58 |
-
| 12.0507 | 11.7955 | 0.7647 | [0. 0.76470588] | 0.5848 | [0. 1.] | 0.7647 | [0. 0.86666667] | 0.6627 | 6 |
|
59 |
-
| 12.2918 | 11.7955 | 0.7647 | [0. 0.76470588] | 0.5848 | [0. 1.] | 0.7647 | [0. 0.86666667] | 0.6627 | 7 |
|
60 |
-
| 12.0507 | 11.7955 | 0.7647 | [0. 0.76470588] | 0.5848 | [0. 1.] | 0.7647 | [0. 0.86666667] | 0.6627 | 8 |
|
61 |
-
| 12.2918 | 11.7955 | 0.7647 | [0. 0.76470588] | 0.5848 | [0. 1.] | 0.7647 | [0. 0.86666667] | 0.6627 | 9 |
|
62 |
-
| 12.5328 | 11.7955 | 0.7647 | [0. 0.76470588] | 0.5848 | [0. 1.] | 0.7647 | [0. 0.86666667] | 0.6627 | 10 |
|
63 |
|
64 |
|
65 |
### Framework versions
|
|
|
15 |
|
16 |
This model is a fine-tuned version of [PlanTL-GOB-ES/roberta-base-bne](https://huggingface.co/PlanTL-GOB-ES/roberta-base-bne) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Train Loss: 12.0507
|
19 |
- Validation Loss: 11.7955
|
20 |
- Train Accuracy: 0.7647
|
21 |
- Train Precision: [0. 0.76470588]
|
|
|
24 |
- Train Recall W: 0.7647
|
25 |
- Train F1: [0. 0.86666667]
|
26 |
- Train F1 W: 0.6627
|
27 |
+
- Epoch: 1
|
28 |
|
29 |
## Model description
|
30 |
|
|
|
43 |
### Training hyperparameters
|
44 |
|
45 |
The following hyperparameters were used during training:
|
46 |
+
- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'WarmUp', 'config': {'initial_learning_rate': 2e-05, 'decay_schedule_fn': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 35, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, '__passive_serialization__': True}, 'warmup_steps': 5, 'power': 1.0, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
|
47 |
- training_precision: float32
|
48 |
|
49 |
### Training results
|
50 |
|
51 |
| Train Loss | Validation Loss | Train Accuracy | Train Precision | Train Precision W | Train Recall | Train Recall W | Train F1 | Train F1 W | Epoch |
|
52 |
|:----------:|:---------------:|:--------------:|:-----------------------:|:-----------------:|:------------:|:--------------:|:-----------------------:|:----------:|:-----:|
|
53 |
+
| 12.0507 | 11.7955 | 0.7647 | [0. 0.76470588] | 0.5848 | [0. 1.] | 0.7647 | [0. 0.86666667] | 0.6627 | 1 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
54 |
|
55 |
|
56 |
### Framework versions
|