mt5-tr-sci-ms-hi / README.md
aparajitha's picture
aparajitha/mt5-tr-sci-ms-hi
0062794 verified
|
raw
history blame
1.57 kB
---
library_name: transformers
base_model: aparajitha/mt5-tr-sci-ms
tags:
- generated_from_trainer
model-index:
- name: mt5-tr-sci-ms-hi
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. -->
# mt5-tr-sci-ms-hi
This model is a fine-tuned version of [aparajitha/mt5-tr-sci-ms](https://huggingface.co/aparajitha/mt5-tr-sci-ms) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 2.1572
## 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 |
|:-------------:|:-----:|:----:|:---------------:|
| 2.5594 | 1.0 | 1092 | 2.3215 |
| 2.4126 | 2.0 | 2184 | 2.2380 |
| 2.3427 | 3.0 | 3276 | 2.1977 |
| 2.295 | 4.0 | 4368 | 2.1661 |
| 2.2531 | 5.0 | 5460 | 2.1589 |
| 2.2396 | 6.0 | 6552 | 2.1572 |
### Framework versions
- Transformers 4.44.2
- Pytorch 2.3.1.post300
- Datasets 2.19.1
- Tokenizers 0.19.1