update model card README.md
Browse files
README.md
CHANGED
|
@@ -3,8 +3,6 @@ license: apache-2.0
|
|
| 3 |
base_model: google/electra-base-discriminator
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
-
metrics:
|
| 7 |
-
- accuracy
|
| 8 |
model-index:
|
| 9 |
- name: electra_multiple_choice
|
| 10 |
results: []
|
|
@@ -16,9 +14,6 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
# electra_multiple_choice
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [google/electra-base-discriminator](https://huggingface.co/google/electra-base-discriminator) on the None dataset.
|
| 19 |
-
It achieves the following results on the evaluation set:
|
| 20 |
-
- Loss: 0.1882
|
| 21 |
-
- Accuracy: 0.97
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
@@ -43,40 +38,10 @@ 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 |
-
| 1.4562 | 1.0 | 1725 | 1.2637 | 0.46 |
|
| 53 |
-
| 1.2814 | 2.0 | 3450 | 1.0774 | 0.55 |
|
| 54 |
-
| 1.1775 | 3.0 | 5175 | 0.9072 | 0.675 |
|
| 55 |
-
| 1.069 | 4.0 | 6900 | 0.7319 | 0.72 |
|
| 56 |
-
| 0.9674 | 5.0 | 8625 | 0.6151 | 0.78 |
|
| 57 |
-
| 0.8679 | 6.0 | 10350 | 0.5140 | 0.825 |
|
| 58 |
-
| 0.7673 | 7.0 | 12075 | 0.4306 | 0.84 |
|
| 59 |
-
| 0.6849 | 8.0 | 13800 | 0.3721 | 0.87 |
|
| 60 |
-
| 0.6147 | 9.0 | 15525 | 0.3286 | 0.885 |
|
| 61 |
-
| 0.5522 | 10.0 | 17250 | 0.2913 | 0.895 |
|
| 62 |
-
| 0.4936 | 11.0 | 18975 | 0.2785 | 0.915 |
|
| 63 |
-
| 0.4532 | 12.0 | 20700 | 0.2467 | 0.91 |
|
| 64 |
-
| 0.4107 | 13.0 | 22425 | 0.2226 | 0.93 |
|
| 65 |
-
| 0.3825 | 14.0 | 24150 | 0.2073 | 0.945 |
|
| 66 |
-
| 0.3492 | 15.0 | 25875 | 0.2027 | 0.93 |
|
| 67 |
-
| 0.3189 | 16.0 | 27600 | 0.2269 | 0.925 |
|
| 68 |
-
| 0.2977 | 17.0 | 29325 | 0.2412 | 0.93 |
|
| 69 |
-
| 0.2817 | 18.0 | 31050 | 0.1913 | 0.935 |
|
| 70 |
-
| 0.266 | 19.0 | 32775 | 0.1517 | 0.94 |
|
| 71 |
-
| 0.2437 | 20.0 | 34500 | 0.2012 | 0.935 |
|
| 72 |
-
| 0.234 | 21.0 | 36225 | 0.1600 | 0.935 |
|
| 73 |
-
| 0.2195 | 22.0 | 37950 | 0.1688 | 0.955 |
|
| 74 |
-
| 0.2002 | 23.0 | 39675 | 0.1347 | 0.955 |
|
| 75 |
-
| 0.1987 | 24.0 | 41400 | 0.1976 | 0.95 |
|
| 76 |
-
| 0.1858 | 25.0 | 43125 | 0.1568 | 0.955 |
|
| 77 |
-
| 0.1784 | 26.0 | 44850 | 0.1453 | 0.955 |
|
| 78 |
-
| 0.169 | 27.0 | 46575 | 0.1547 | 0.955 |
|
| 79 |
-
| 0.1597 | 28.0 | 48300 | 0.1882 | 0.97 |
|
| 80 |
|
| 81 |
|
| 82 |
### Framework versions
|
|
|
|
| 3 |
base_model: google/electra-base-discriminator
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
|
|
|
|
|
|
| 6 |
model-index:
|
| 7 |
- name: electra_multiple_choice
|
| 8 |
results: []
|
|
|
|
| 14 |
# electra_multiple_choice
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [google/electra-base-discriminator](https://huggingface.co/google/electra-base-discriminator) on the None dataset.
|
|
|
|
|
|
|
|
|
|
| 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: 3
|
| 42 |
|
| 43 |
### Training results
|
| 44 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 45 |
|
| 46 |
|
| 47 |
### Framework versions
|