metadata
license: mit
base_model: microsoft/Multilingual-MiniLM-L12-H384
tags:
- generated_from_trainer
model-index:
- name: trainRanker_AR_VI_non_top
results: []
trainRanker_AR_VI_non_top
This model is a fine-tuned version of microsoft/Multilingual-MiniLM-L12-H384 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5773
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 |
|---|---|---|---|
| 0.5486 | 0.04 | 2500 | 0.5773 |
| 0.5484 | 0.08 | 5000 | 0.5773 |
| 0.5444 | 0.12 | 7500 | 0.5773 |
| 0.5465 | 0.16 | 10000 | 0.5773 |
| 0.5499 | 0.2 | 12500 | 0.5773 |
| 0.5485 | 0.24 | 15000 | 0.5773 |
| 0.5406 | 0.28 | 17500 | 0.5773 |
| 0.5472 | 0.32 | 20000 | 0.5773 |
| 0.5413 | 0.36 | 22500 | 0.5773 |
| 0.5428 | 0.4 | 25000 | 0.5773 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1