|
--- |
|
license: other |
|
tags: |
|
- generated_from_trainer |
|
base_model: facebook/opt-1.3b |
|
model-index: |
|
- name: opt_2.7b_wiki_ce |
|
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. --> |
|
|
|
# opt_2.7b_wiki_ce |
|
|
|
This model is a fine-tuned version of [facebook/opt-1.3b](https://huggingface.co/facebook/opt-1.3b) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.4190 |
|
|
|
## 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 |
|
- gradient_accumulation_steps: 2 |
|
- total_train_batch_size: 8 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 500 |
|
- num_epochs: 1 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 2.6033 | 0.4354 | 500 | 2.4562 | |
|
| 2.5267 | 0.8707 | 1000 | 2.4247 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.40.2 |
|
- Pytorch 2.2.2 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |
|
|
