|
--- |
|
license: other |
|
base_model: baffo32/decapoda-research-llama-7B-hf |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: olinaweights |
|
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. --> |
|
|
|
# olinaweights |
|
|
|
This model is a fine-tuned version of [baffo32/decapoda-research-llama-7B-hf](https://huggingface.co/baffo32/decapoda-research-llama-7B-hf) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0104 |
|
|
|
## 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: 0.0003 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 32 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 40 |
|
- training_steps: 1000 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| No log | 0.01 | 100 | 0.1012 | |
|
| No log | 0.03 | 200 | 0.0426 | |
|
| 0.1403 | 0.04 | 300 | 0.0455 | |
|
| 0.1403 | 0.05 | 400 | 0.0258 | |
|
| 0.0307 | 0.07 | 500 | 0.0227 | |
|
| 0.0307 | 0.08 | 600 | 0.0200 | |
|
| 0.0307 | 0.09 | 700 | 0.0164 | |
|
| 0.019 | 0.11 | 800 | 0.0126 | |
|
| 0.019 | 0.12 | 900 | 0.0117 | |
|
| 0.0115 | 0.13 | 1000 | 0.0104 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.0 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.14.6 |
|
- Tokenizers 0.14.1 |
|
|