update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
model-index:
|
| 5 |
+
- name: rule_learning_margin_1mm_many_negatives_spanpred_attention
|
| 6 |
+
results: []
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 10 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 11 |
+
|
| 12 |
+
# rule_learning_margin_1mm_many_negatives_spanpred_attention
|
| 13 |
+
|
| 14 |
+
This model is a fine-tuned version of [enoriega/rule_softmatching](https://huggingface.co/enoriega/rule_softmatching) on the None dataset.
|
| 15 |
+
It achieves the following results on the evaluation set:
|
| 16 |
+
- Loss: 0.2363
|
| 17 |
+
- Margin Accuracy: 0.8921
|
| 18 |
+
|
| 19 |
+
## Model description
|
| 20 |
+
|
| 21 |
+
More information needed
|
| 22 |
+
|
| 23 |
+
## Intended uses & limitations
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Training and evaluation data
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training procedure
|
| 32 |
+
|
| 33 |
+
### Training hyperparameters
|
| 34 |
+
|
| 35 |
+
The following hyperparameters were used during training:
|
| 36 |
+
- learning_rate: 5e-05
|
| 37 |
+
- train_batch_size: 4
|
| 38 |
+
- eval_batch_size: 4
|
| 39 |
+
- seed: 42
|
| 40 |
+
- gradient_accumulation_steps: 2000
|
| 41 |
+
- total_train_batch_size: 8000
|
| 42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 43 |
+
- lr_scheduler_type: linear
|
| 44 |
+
- num_epochs: 3.0
|
| 45 |
+
- mixed_precision_training: Native AMP
|
| 46 |
+
|
| 47 |
+
### Training results
|
| 48 |
+
|
| 49 |
+
| Training Loss | Epoch | Step | Validation Loss | Margin Accuracy |
|
| 50 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------------:|
|
| 51 |
+
| 0.3814 | 0.16 | 20 | 0.3909 | 0.8317 |
|
| 52 |
+
| 0.349 | 0.32 | 40 | 0.3335 | 0.8463 |
|
| 53 |
+
| 0.3196 | 0.48 | 60 | 0.3101 | 0.8587 |
|
| 54 |
+
| 0.3083 | 0.64 | 80 | 0.3010 | 0.8645 |
|
| 55 |
+
| 0.2828 | 0.8 | 100 | 0.2871 | 0.8686 |
|
| 56 |
+
| 0.294 | 0.96 | 120 | 0.2800 | 0.8715 |
|
| 57 |
+
| 0.2711 | 1.12 | 140 | 0.2708 | 0.8741 |
|
| 58 |
+
| 0.2663 | 1.28 | 160 | 0.2671 | 0.8767 |
|
| 59 |
+
| 0.2656 | 1.44 | 180 | 0.2612 | 0.8822 |
|
| 60 |
+
| 0.2645 | 1.6 | 200 | 0.2537 | 0.8851 |
|
| 61 |
+
| 0.2625 | 1.76 | 220 | 0.2483 | 0.8878 |
|
| 62 |
+
| 0.2651 | 1.92 | 240 | 0.2471 | 0.8898 |
|
| 63 |
+
| 0.2407 | 2.08 | 260 | 0.2438 | 0.8905 |
|
| 64 |
+
| 0.2315 | 2.24 | 280 | 0.2408 | 0.8909 |
|
| 65 |
+
| 0.2461 | 2.4 | 300 | 0.2390 | 0.8918 |
|
| 66 |
+
| 0.2491 | 2.56 | 320 | 0.2390 | 0.8921 |
|
| 67 |
+
| 0.2511 | 2.72 | 340 | 0.2369 | 0.8918 |
|
| 68 |
+
| 0.2341 | 2.88 | 360 | 0.2363 | 0.8921 |
|
| 69 |
+
|
| 70 |
+
|
| 71 |
+
### Framework versions
|
| 72 |
+
|
| 73 |
+
- Transformers 4.19.2
|
| 74 |
+
- Pytorch 1.11.0
|
| 75 |
+
- Datasets 2.2.1
|
| 76 |
+
- Tokenizers 0.12.1
|