metadata
library_name: transformers
license: mit
base_model: HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1
tags:
- generated_from_trainer
model-index:
- name: wb-climate-regression-kalm
results: []
wb-climate-regression-kalm
This model is a fine-tuned version of HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0273
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: 1e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.0499 | 1.0 | 754 | 0.0386 |
| 0.0304 | 2.0 | 1508 | 0.0330 |
| 0.0188 | 3.0 | 2262 | 0.0293 |
| 0.0119 | 4.0 | 3016 | 0.0295 |
| 0.0069 | 5.0 | 3770 | 0.0299 |
| 0.0039 | 6.0 | 4524 | 0.0279 |
| 0.0025 | 7.0 | 5278 | 0.0273 |
| 0.0015 | 8.0 | 6032 | 0.0275 |
| 0.0007 | 9.0 | 6786 | 0.0275 |
| 0.0003 | 10.0 | 7540 | 0.0273 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.20.3