metadata
library_name: transformers
license: mit
base_model: aparajitha/mbart-sci-ms-tr
tags:
- generated_from_trainer
model-index:
- name: mbart-sci-ms-tr-hi
results: []
mbart-sci-ms-tr-hi
This model is a fine-tuned version of aparajitha/mbart-sci-ms-tr on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.3624
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: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.4977 | 1.0 | 1092 | 2.3430 |
| 2.099 | 2.0 | 2184 | 2.2412 |
| 1.8193 | 3.0 | 3276 | 2.2304 |
| 1.5883 | 4.0 | 4368 | 2.2644 |
| 1.4088 | 5.0 | 5460 | 2.3011 |
| 1.2952 | 6.0 | 6552 | 2.3624 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1