|
--- |
|
license: other |
|
base_model: baffo32/decapoda-research-llama-7B-hf |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: llama-7b-absa-MT-restaurants |
|
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. --> |
|
|
|
# llama-7b-absa-MT-restaurants |
|
|
|
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: 0.0061 |
|
|
|
## 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: 2 |
|
- training_steps: 600 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 0.0939 | 0.13 | 40 | 0.0302 | |
|
| 0.0258 | 0.25 | 80 | 0.0237 | |
|
| 0.0223 | 0.38 | 120 | 0.0208 | |
|
| 0.0198 | 0.51 | 160 | 0.0182 | |
|
| 0.0159 | 0.63 | 200 | 0.0163 | |
|
| 0.0158 | 0.76 | 240 | 0.0137 | |
|
| 0.0125 | 0.89 | 280 | 0.0126 | |
|
| 0.0118 | 1.01 | 320 | 0.0111 | |
|
| 0.0078 | 1.14 | 360 | 0.0098 | |
|
| 0.0059 | 1.27 | 400 | 0.0095 | |
|
| 0.006 | 1.39 | 440 | 0.0091 | |
|
| 0.0052 | 1.52 | 480 | 0.0078 | |
|
| 0.0059 | 1.65 | 520 | 0.0068 | |
|
| 0.0045 | 1.77 | 560 | 0.0066 | |
|
| 0.0044 | 1.9 | 600 | 0.0061 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.38.2 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
