|
--- |
|
license: mit |
|
base_model: microsoft/Multilingual-MiniLM-L12-H384 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: trainRanker_test_EN_EN |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# trainRanker_test_EN_EN |
|
|
|
This model is a fine-tuned version of [microsoft/Multilingual-MiniLM-L12-H384](https://huggingface.co/microsoft/Multilingual-MiniLM-L12-H384) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1997 |
|
|
|
## Model description |
|
|
|
More information needed |
|
|
|
## Intended uses & limitations |
|
|
|
More information needed |
|
|
|
## Training and evaluation data |
|
|
|
More information needed |
|
|
|
## Training procedure |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 2e-05 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 750 |
|
- training_steps: 25000 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:-----:|:---------------:| |
|
| 0.3064 | 0.04 | 2500 | 0.2716 | |
|
| 0.273 | 0.08 | 5000 | 0.2353 | |
|
| 0.2569 | 0.12 | 7500 | 0.2383 | |
|
| 0.2363 | 0.16 | 10000 | 0.2345 | |
|
| 0.2238 | 0.2 | 12500 | 0.2102 | |
|
| 0.2354 | 0.24 | 15000 | 0.2089 | |
|
| 0.2085 | 0.28 | 17500 | 0.2161 | |
|
| 0.2125 | 0.32 | 20000 | 0.1995 | |
|
| 0.217 | 0.36 | 22500 | 0.1975 | |
|
| 0.2236 | 0.4 | 25000 | 0.1997 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.15.1 |
|
|
