|
--- |
|
license: other |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: opt-iml-max-1.3b-lora-s-t3000-v300-v2 |
|
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-iml-max-1.3b-lora-s-t3000-v300-v2 |
|
|
|
This model is a fine-tuned version of [facebook/opt-iml-max-1.3b](https://huggingface.co./facebook/opt-iml-max-1.3b) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.0578 |
|
|
|
## 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: 0.0002 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 8 |
|
- total_train_batch_size: 64 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 10 |
|
- num_epochs: 2 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 2.3525 | 0.43 | 20 | 2.1918 | |
|
| 2.1991 | 0.85 | 40 | 2.0734 | |
|
| 2.1575 | 1.28 | 60 | 2.0636 | |
|
| 2.1974 | 1.71 | 80 | 2.0578 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.28.0.dev0 |
|
- Pytorch 1.13.1+cu116 |
|
- Datasets 2.11.0 |
|
- Tokenizers 0.13.2 |
|
|
