update model card README.md
Browse files
README.md
CHANGED
|
@@ -4,12 +4,6 @@ tags:
|
|
| 4 |
model-index:
|
| 5 |
- name: bert-base-spanish-wwm-cased-finetuned-tweets
|
| 6 |
results: []
|
| 7 |
-
datasets:
|
| 8 |
-
- jhonparra18/petro-tweets
|
| 9 |
-
language:
|
| 10 |
-
- es
|
| 11 |
-
metrics:
|
| 12 |
-
- perplexity
|
| 13 |
---
|
| 14 |
|
| 15 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -17,9 +11,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 17 |
|
| 18 |
# bert-base-spanish-wwm-cased-finetuned-tweets
|
| 19 |
|
| 20 |
-
This model is a fine-tuned version of [dccuchile/bert-base-spanish-wwm-cased](https://huggingface.co/dccuchile/bert-base-spanish-wwm-cased) on
|
| 21 |
It achieves the following results on the evaluation set:
|
| 22 |
-
- Loss:
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
|
@@ -44,15 +38,42 @@ The following hyperparameters were used during training:
|
|
| 44 |
- seed: 42
|
| 45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
- lr_scheduler_type: linear
|
| 47 |
-
- num_epochs:
|
| 48 |
|
| 49 |
### Training results
|
| 50 |
|
| 51 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 52 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 53 |
-
|
|
| 54 |
-
|
|
| 55 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 56 |
|
| 57 |
|
| 58 |
### Framework versions
|
|
@@ -60,4 +81,4 @@ The following hyperparameters were used during training:
|
|
| 60 |
- Transformers 4.26.1
|
| 61 |
- Pytorch 1.13.1+cu116
|
| 62 |
- Datasets 2.10.1
|
| 63 |
-
- Tokenizers 0.13.2
|
|
|
|
| 4 |
model-index:
|
| 5 |
- name: bert-base-spanish-wwm-cased-finetuned-tweets
|
| 6 |
results: []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
---
|
| 8 |
|
| 9 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 11 |
|
| 12 |
# bert-base-spanish-wwm-cased-finetuned-tweets
|
| 13 |
|
| 14 |
+
This model is a fine-tuned version of [dccuchile/bert-base-spanish-wwm-cased](https://huggingface.co/dccuchile/bert-base-spanish-wwm-cased) on an unknown dataset.
|
| 15 |
It achieves the following results on the evaluation set:
|
| 16 |
+
- Loss: 2.7427
|
| 17 |
|
| 18 |
## Model description
|
| 19 |
|
|
|
|
| 38 |
- seed: 42
|
| 39 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 40 |
- lr_scheduler_type: linear
|
| 41 |
+
- num_epochs: 30
|
| 42 |
|
| 43 |
### Training results
|
| 44 |
|
| 45 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 46 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 47 |
+
| 2.7077 | 1.0 | 79 | 2.9532 |
|
| 48 |
+
| 2.6746 | 2.0 | 158 | 2.9270 |
|
| 49 |
+
| 2.64 | 3.0 | 237 | 2.8595 |
|
| 50 |
+
| 2.6593 | 4.0 | 316 | 2.8505 |
|
| 51 |
+
| 2.6419 | 5.0 | 395 | 2.8306 |
|
| 52 |
+
| 2.6556 | 6.0 | 474 | 2.8511 |
|
| 53 |
+
| 2.6474 | 7.0 | 553 | 2.7852 |
|
| 54 |
+
| 2.6399 | 8.0 | 632 | 2.8173 |
|
| 55 |
+
| 2.6516 | 9.0 | 711 | 2.7241 |
|
| 56 |
+
| 2.658 | 10.0 | 790 | 2.7709 |
|
| 57 |
+
| 2.6677 | 11.0 | 869 | 2.7407 |
|
| 58 |
+
| 2.6455 | 12.0 | 948 | 2.7636 |
|
| 59 |
+
| 2.6502 | 13.0 | 1027 | 2.7842 |
|
| 60 |
+
| 2.6235 | 14.0 | 1106 | 2.7265 |
|
| 61 |
+
| 2.6037 | 15.0 | 1185 | 2.7647 |
|
| 62 |
+
| 2.5795 | 16.0 | 1264 | 2.7656 |
|
| 63 |
+
| 2.5734 | 17.0 | 1343 | 2.7326 |
|
| 64 |
+
| 2.5643 | 18.0 | 1422 | 2.6886 |
|
| 65 |
+
| 2.5787 | 19.0 | 1501 | 2.7471 |
|
| 66 |
+
| 2.5282 | 20.0 | 1580 | 2.7318 |
|
| 67 |
+
| 2.5396 | 21.0 | 1659 | 2.7465 |
|
| 68 |
+
| 2.5328 | 22.0 | 1738 | 2.7518 |
|
| 69 |
+
| 2.5133 | 23.0 | 1817 | 2.7157 |
|
| 70 |
+
| 2.518 | 24.0 | 1896 | 2.7203 |
|
| 71 |
+
| 2.5014 | 25.0 | 1975 | 2.6893 |
|
| 72 |
+
| 2.4974 | 26.0 | 2054 | 2.6696 |
|
| 73 |
+
| 2.4754 | 27.0 | 2133 | 2.6521 |
|
| 74 |
+
| 2.4755 | 28.0 | 2212 | 2.7549 |
|
| 75 |
+
| 2.5177 | 29.0 | 2291 | 2.7126 |
|
| 76 |
+
| 2.4905 | 30.0 | 2370 | 2.6880 |
|
| 77 |
|
| 78 |
|
| 79 |
### Framework versions
|
|
|
|
| 81 |
- Transformers 4.26.1
|
| 82 |
- Pytorch 1.13.1+cu116
|
| 83 |
- Datasets 2.10.1
|
| 84 |
+
- Tokenizers 0.13.2
|