End of training
Browse files
README.md
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
-
base_model: bert-base-uncased
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
metrics:
|
|
@@ -15,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# bert-base-uncased-finetuned-swag
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
-
- Loss:
|
| 21 |
-
- Accuracy: 0.
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
@@ -43,15 +43,52 @@ The following hyperparameters were used during training:
|
|
| 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 |
-
| No log | 1.0 | 150 | 1.
|
| 53 |
-
| No log | 2.0 | 300 | 1.
|
| 54 |
-
| No log | 3.0 | 450 | 1.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 55 |
|
| 56 |
|
| 57 |
### Framework versions
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
+
base_model: Yama/bert-base-uncased-finetuned-swag
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
metrics:
|
|
|
|
| 15 |
|
| 16 |
# bert-base-uncased-finetuned-swag
|
| 17 |
|
| 18 |
+
This model is a fine-tuned version of [Yama/bert-base-uncased-finetuned-swag](https://huggingface.co/Yama/bert-base-uncased-finetuned-swag) on an unknown dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.0061
|
| 21 |
+
- Accuracy: 0.9958
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 43 |
- seed: 42
|
| 44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
- lr_scheduler_type: linear
|
| 46 |
+
- num_epochs: 40
|
| 47 |
|
| 48 |
### Training results
|
| 49 |
|
| 50 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 51 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 52 |
+
| No log | 1.0 | 150 | 1.3780 | 0.3592 |
|
| 53 |
+
| No log | 2.0 | 300 | 1.3234 | 0.4383 |
|
| 54 |
+
| No log | 3.0 | 450 | 1.3158 | 0.4992 |
|
| 55 |
+
| 1.3577 | 4.0 | 600 | 1.1356 | 0.5792 |
|
| 56 |
+
| 1.3577 | 5.0 | 750 | 0.7939 | 0.7217 |
|
| 57 |
+
| 1.3577 | 6.0 | 900 | 0.6167 | 0.7958 |
|
| 58 |
+
| 1.0479 | 7.0 | 1050 | 0.4737 | 0.8467 |
|
| 59 |
+
| 1.0479 | 8.0 | 1200 | 0.3424 | 0.8867 |
|
| 60 |
+
| 1.0479 | 9.0 | 1350 | 0.2448 | 0.9142 |
|
| 61 |
+
| 0.5968 | 10.0 | 1500 | 0.2117 | 0.9158 |
|
| 62 |
+
| 0.5968 | 11.0 | 1650 | 0.1589 | 0.9467 |
|
| 63 |
+
| 0.5968 | 12.0 | 1800 | 0.1420 | 0.9492 |
|
| 64 |
+
| 0.5968 | 13.0 | 1950 | 0.0970 | 0.9675 |
|
| 65 |
+
| 0.3341 | 14.0 | 2100 | 0.1014 | 0.9725 |
|
| 66 |
+
| 0.3341 | 15.0 | 2250 | 0.0678 | 0.9742 |
|
| 67 |
+
| 0.3341 | 16.0 | 2400 | 0.0624 | 0.9825 |
|
| 68 |
+
| 0.1802 | 17.0 | 2550 | 0.0407 | 0.9783 |
|
| 69 |
+
| 0.1802 | 18.0 | 2700 | 0.0501 | 0.9858 |
|
| 70 |
+
| 0.1802 | 19.0 | 2850 | 0.0341 | 0.9867 |
|
| 71 |
+
| 0.1213 | 20.0 | 3000 | 0.0284 | 0.9883 |
|
| 72 |
+
| 0.1213 | 21.0 | 3150 | 0.0398 | 0.9883 |
|
| 73 |
+
| 0.1213 | 22.0 | 3300 | 0.0290 | 0.9908 |
|
| 74 |
+
| 0.1213 | 23.0 | 3450 | 0.0211 | 0.9908 |
|
| 75 |
+
| 0.0758 | 24.0 | 3600 | 0.0179 | 0.9908 |
|
| 76 |
+
| 0.0758 | 25.0 | 3750 | 0.0151 | 0.9917 |
|
| 77 |
+
| 0.0758 | 26.0 | 3900 | 0.0154 | 0.9933 |
|
| 78 |
+
| 0.0464 | 27.0 | 4050 | 0.0216 | 0.9942 |
|
| 79 |
+
| 0.0464 | 28.0 | 4200 | 0.0124 | 0.9942 |
|
| 80 |
+
| 0.0464 | 29.0 | 4350 | 0.0122 | 0.9942 |
|
| 81 |
+
| 0.0306 | 30.0 | 4500 | 0.0103 | 0.9942 |
|
| 82 |
+
| 0.0306 | 31.0 | 4650 | 0.0094 | 0.9942 |
|
| 83 |
+
| 0.0306 | 32.0 | 4800 | 0.0083 | 0.9942 |
|
| 84 |
+
| 0.0306 | 33.0 | 4950 | 0.0079 | 0.9958 |
|
| 85 |
+
| 0.0201 | 34.0 | 5100 | 0.0079 | 0.9950 |
|
| 86 |
+
| 0.0201 | 35.0 | 5250 | 0.0069 | 0.9958 |
|
| 87 |
+
| 0.0201 | 36.0 | 5400 | 0.0069 | 0.9950 |
|
| 88 |
+
| 0.0205 | 37.0 | 5550 | 0.0060 | 0.9967 |
|
| 89 |
+
| 0.0205 | 38.0 | 5700 | 0.0060 | 0.9958 |
|
| 90 |
+
| 0.0205 | 39.0 | 5850 | 0.0061 | 0.9958 |
|
| 91 |
+
| 0.0102 | 40.0 | 6000 | 0.0061 | 0.9958 |
|
| 92 |
|
| 93 |
|
| 94 |
### Framework versions
|
runs/Nov08_11-57-14_0e352fe6bd0e/events.out.tfevents.1699444645.0e352fe6bd0e.31473.3
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7c23b35c1f2e5d77fdb2658f7e4f1162a7b9bc03b0ca63c6a5a9c8c7fcbb92cf
|
| 3 |
+
size 19462
|