lBober/my-model-SaBERT-Sentimento
Browse files
README.md
CHANGED
@@ -5,20 +5,26 @@ tags:
|
|
5 |
- generated_from_trainer
|
6 |
metrics:
|
7 |
- accuracy
|
|
|
|
|
|
|
8 |
model-index:
|
9 |
-
- name:
|
10 |
results: []
|
11 |
---
|
12 |
|
13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
should probably proofread and complete it, then remove this comment. -->
|
15 |
|
16 |
-
#
|
17 |
|
18 |
This model is a fine-tuned version of [VerificadoProfesional/SaBERT-Spanish-Sentiment-Analysis](https://huggingface.co/VerificadoProfesional/SaBERT-Spanish-Sentiment-Analysis) on the None dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- Loss: 0.
|
21 |
-
- Accuracy: 0.
|
|
|
|
|
|
|
22 |
|
23 |
## Model description
|
24 |
|
@@ -37,28 +43,23 @@ More information needed
|
|
37 |
### Training hyperparameters
|
38 |
|
39 |
The following hyperparameters were used during training:
|
40 |
-
- learning_rate:
|
41 |
-
- train_batch_size:
|
42 |
-
- eval_batch_size:
|
43 |
- seed: 42
|
44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
- lr_scheduler_type: linear
|
46 |
-
- num_epochs:
|
47 |
|
48 |
### Training results
|
49 |
|
50 |
-
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
51 |
-
|
52 |
-
|
|
53 |
-
|
|
54 |
-
|
|
55 |
-
|
|
56 |
-
|
|
57 |
-
| 12.0204 | 6.0 | 438 | 5.1950 | 0.8903 |
|
58 |
-
| 7.5582 | 7.0 | 511 | 1.6250 | 0.8903 |
|
59 |
-
| 6.6289 | 8.0 | 584 | 6.2765 | 0.1097 |
|
60 |
-
| 4.6584 | 9.0 | 657 | 0.4767 | 0.8903 |
|
61 |
-
| 2.4064 | 10.0 | 730 | 0.8176 | 0.8903 |
|
62 |
|
63 |
|
64 |
### Framework versions
|
|
|
5 |
- generated_from_trainer
|
6 |
metrics:
|
7 |
- accuracy
|
8 |
+
- f1
|
9 |
+
- precision
|
10 |
+
- recall
|
11 |
model-index:
|
12 |
+
- name: my-model-SaBERT-Sentimento
|
13 |
results: []
|
14 |
---
|
15 |
|
16 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
17 |
should probably proofread and complete it, then remove this comment. -->
|
18 |
|
19 |
+
# my-model-SaBERT-Sentimento
|
20 |
|
21 |
This model is a fine-tuned version of [VerificadoProfesional/SaBERT-Spanish-Sentiment-Analysis](https://huggingface.co/VerificadoProfesional/SaBERT-Spanish-Sentiment-Analysis) on the None dataset.
|
22 |
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.2866
|
24 |
+
- Accuracy: 0.9355
|
25 |
+
- F1: 0.9362
|
26 |
+
- Precision: 0.9403
|
27 |
+
- Recall: 0.9355
|
28 |
|
29 |
## Model description
|
30 |
|
|
|
43 |
### Training hyperparameters
|
44 |
|
45 |
The following hyperparameters were used during training:
|
46 |
+
- learning_rate: 2e-05
|
47 |
+
- train_batch_size: 20
|
48 |
+
- eval_batch_size: 20
|
49 |
- seed: 42
|
50 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
- lr_scheduler_type: linear
|
52 |
+
- num_epochs: 5
|
53 |
|
54 |
### Training results
|
55 |
|
56 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|
57 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
|
58 |
+
| 0.3225 | 1.0 | 37 | 0.2158 | 0.9355 | 0.9348 | 0.9355 | 0.9355 |
|
59 |
+
| 0.1283 | 2.0 | 74 | 0.2217 | 0.9484 | 0.9472 | 0.9473 | 0.9484 |
|
60 |
+
| 0.0753 | 3.0 | 111 | 0.2598 | 0.9355 | 0.9362 | 0.9403 | 0.9355 |
|
61 |
+
| 0.0503 | 4.0 | 148 | 0.2878 | 0.9290 | 0.9309 | 0.9373 | 0.9290 |
|
62 |
+
| 0.0397 | 5.0 | 185 | 0.2866 | 0.9355 | 0.9362 | 0.9403 | 0.9355 |
|
|
|
|
|
|
|
|
|
|
|
63 |
|
64 |
|
65 |
### Framework versions
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 439436284
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2e275f39cc2b1f95c2b34b266e21de935f442ec4e5350cc1c81725692a32bd70
|
3 |
size 439436284
|
runs/May25_15-28-25_fe998d142f54/events.out.tfevents.1716650905.fe998d142f54.6359.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e23f4d2a2e0bdb89324655d7faaff1cabd7f02272334019cd7b487fd1dabc0cc
|
3 |
+
size 8824
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5112
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:888969f8ca5af3e75153d0bbfc537a39c7cbd28299cc77aaa8476b9008786ce9
|
3 |
size 5112
|