Text Classification
Transformers
TensorBoard
Safetensors
bert
glue
rte
max_length_128
dropout_0.4
Generated from Trainer
text-embeddings-inference
Instructions to use ipeksnmz/bert-base-uncased-finetuned-rte-run_3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ipeksnmz/bert-base-uncased-finetuned-rte-run_3 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="ipeksnmz/bert-base-uncased-finetuned-rte-run_3")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("ipeksnmz/bert-base-uncased-finetuned-rte-run_3") model = AutoModelForSequenceClassification.from_pretrained("ipeksnmz/bert-base-uncased-finetuned-rte-run_3", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Best model with accuracy 0.6787
Browse files
README.md
CHANGED
|
@@ -22,8 +22,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 22 |
|
| 23 |
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
|
| 24 |
It achieves the following results on the evaluation set:
|
| 25 |
-
- Loss:
|
| 26 |
-
- Accuracy: 0.
|
| 27 |
|
| 28 |
## Model description
|
| 29 |
|
|
@@ -54,16 +54,16 @@ The following hyperparameters were used during training:
|
|
| 54 |
|
| 55 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 56 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 57 |
-
| No log | 1.0 | 78 | 0.
|
| 58 |
-
| No log | 2.0 | 156 | 0.
|
| 59 |
-
| No log | 3.0 | 234 | 0.
|
| 60 |
-
| No log | 4.0 | 312 | 0.
|
| 61 |
-
| No log | 5.0 | 390 | 1.
|
| 62 |
-
| No log | 6.0 | 468 | 1.
|
| 63 |
-
| 0.
|
| 64 |
-
| 0.
|
| 65 |
-
| 0.
|
| 66 |
-
| 0.
|
| 67 |
|
| 68 |
|
| 69 |
### Framework versions
|
|
|
|
| 22 |
|
| 23 |
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
|
| 24 |
It achieves the following results on the evaluation set:
|
| 25 |
+
- Loss: 0.6286
|
| 26 |
+
- Accuracy: 0.6787
|
| 27 |
|
| 28 |
## Model description
|
| 29 |
|
|
|
|
| 54 |
|
| 55 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 56 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 57 |
+
| No log | 1.0 | 78 | 0.6671 | 0.6101 |
|
| 58 |
+
| No log | 2.0 | 156 | 0.6286 | 0.6787 |
|
| 59 |
+
| No log | 3.0 | 234 | 0.7819 | 0.6282 |
|
| 60 |
+
| No log | 4.0 | 312 | 0.9900 | 0.6354 |
|
| 61 |
+
| No log | 5.0 | 390 | 1.2262 | 0.6426 |
|
| 62 |
+
| No log | 6.0 | 468 | 1.3365 | 0.6462 |
|
| 63 |
+
| 0.3699 | 7.0 | 546 | 1.7402 | 0.6426 |
|
| 64 |
+
| 0.3699 | 8.0 | 624 | 1.8381 | 0.6426 |
|
| 65 |
+
| 0.3699 | 9.0 | 702 | 1.8395 | 0.6462 |
|
| 66 |
+
| 0.3699 | 10.0 | 780 | 1.9266 | 0.6354 |
|
| 67 |
|
| 68 |
|
| 69 |
### Framework versions
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 437958648
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:86e72da919dbfbf2ebdc835eef4d9b4216180cd3b656ea54c13c89ee68164aab
|
| 3 |
size 437958648
|
runs/Apr07_19-56-35_578d22db0b7b/events.out.tfevents.1744056048.578d22db0b7b.632.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d0f48cd2ca7f7e5b3ff38758714c67274827f65c77bc871fca50f8a065f1fa05
|
| 3 |
+
size 411
|