Text Classification
Transformers
PyTorch
bert
Generated from Trainer
Eval Results (legacy)
text-embeddings-inference
Instructions to use santis2/bert-base-uncased-glue-mrpc with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use santis2/bert-base-uncased-glue-mrpc with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="santis2/bert-base-uncased-glue-mrpc")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("santis2/bert-base-uncased-glue-mrpc") model = AutoModelForSequenceClassification.from_pretrained("santis2/bert-base-uncased-glue-mrpc", device_map="auto") - Notebooks
- Google Colab
- Kaggle
End of training
Browse files- README.md +7 -17
- pytorch_model.bin +1 -1
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -23,10 +23,10 @@ model-index:
|
|
| 23 |
metrics:
|
| 24 |
- name: Accuracy
|
| 25 |
type: accuracy
|
| 26 |
-
value: 0.
|
| 27 |
- name: F1
|
| 28 |
type: f1
|
| 29 |
-
value: 0.
|
| 30 |
---
|
| 31 |
|
| 32 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -36,9 +36,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 36 |
|
| 37 |
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the glue dataset.
|
| 38 |
It achieves the following results on the evaluation set:
|
| 39 |
-
- Loss:
|
| 40 |
-
- Accuracy: 0.
|
| 41 |
-
- F1: 0.
|
| 42 |
|
| 43 |
## Model description
|
| 44 |
|
|
@@ -63,23 +63,13 @@ The following hyperparameters were used during training:
|
|
| 63 |
- seed: 42
|
| 64 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 65 |
- lr_scheduler_type: linear
|
| 66 |
-
- num_epochs:
|
| 67 |
|
| 68 |
### Training results
|
| 69 |
|
| 70 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|
| 71 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
|
| 72 |
-
| 0.
|
| 73 |
-
| 0.2577 | 1.74 | 200 | 0.4251 | 0.8554 | 0.8981 |
|
| 74 |
-
| 0.1418 | 2.61 | 300 | 0.4819 | 0.8529 | 0.8936 |
|
| 75 |
-
| 0.0821 | 3.48 | 400 | 0.7154 | 0.8505 | 0.8913 |
|
| 76 |
-
| 0.0511 | 4.35 | 500 | 0.9418 | 0.8505 | 0.8950 |
|
| 77 |
-
| 0.0362 | 5.22 | 600 | 0.9225 | 0.8333 | 0.8803 |
|
| 78 |
-
| 0.0287 | 6.09 | 700 | 0.9822 | 0.8309 | 0.8816 |
|
| 79 |
-
| 0.0088 | 6.96 | 800 | 1.0204 | 0.8358 | 0.8851 |
|
| 80 |
-
| 0.0041 | 7.83 | 900 | 1.0580 | 0.8407 | 0.8873 |
|
| 81 |
-
| 0.0013 | 8.7 | 1000 | 1.1243 | 0.8407 | 0.8896 |
|
| 82 |
-
| 0.0027 | 9.57 | 1100 | 1.1675 | 0.8382 | 0.8885 |
|
| 83 |
|
| 84 |
|
| 85 |
### Framework versions
|
|
|
|
| 23 |
metrics:
|
| 24 |
- name: Accuracy
|
| 25 |
type: accuracy
|
| 26 |
+
value: 0.8333333333333334
|
| 27 |
- name: F1
|
| 28 |
type: f1
|
| 29 |
+
value: 0.8870431893687708
|
| 30 |
---
|
| 31 |
|
| 32 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 36 |
|
| 37 |
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the glue dataset.
|
| 38 |
It achieves the following results on the evaluation set:
|
| 39 |
+
- Loss: 0.3979
|
| 40 |
+
- Accuracy: 0.8333
|
| 41 |
+
- F1: 0.8870
|
| 42 |
|
| 43 |
## Model description
|
| 44 |
|
|
|
|
| 63 |
- seed: 42
|
| 64 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 65 |
- lr_scheduler_type: linear
|
| 66 |
+
- num_epochs: 1
|
| 67 |
|
| 68 |
### Training results
|
| 69 |
|
| 70 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|
| 71 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
|
| 72 |
+
| 0.5454 | 0.87 | 100 | 0.3979 | 0.8333 | 0.8870 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 73 |
|
| 74 |
|
| 75 |
### Framework versions
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 438003505
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b93749f5bd8bde37740fc18bdba3175e16c210e583e519543b77c4c15368c774
|
| 3 |
size 438003505
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4027
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a0f6833f0ff771c5920234adb1f28015321b3e3eb10de78a0f55393b1c4d2223
|
| 3 |
size 4027
|