|
--- |
|
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: 0.0032 |
|
|
|
## 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: 1200 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 0.089 | 0.13 | 40 | 0.0323 | |
|
| 0.0253 | 0.25 | 80 | 0.0248 | |
|
| 0.0231 | 0.38 | 120 | 0.0213 | |
|
| 0.0214 | 0.51 | 160 | 0.0194 | |
|
| 0.017 | 0.63 | 200 | 0.0153 | |
|
| 0.0162 | 0.76 | 240 | 0.0137 | |
|
| 0.0129 | 0.89 | 280 | 0.0141 | |
|
| 0.0119 | 1.01 | 320 | 0.0119 | |
|
| 0.0079 | 1.14 | 360 | 0.0109 | |
|
| 0.0072 | 1.27 | 400 | 0.0113 | |
|
| 0.0074 | 1.39 | 440 | 0.0099 | |
|
| 0.006 | 1.52 | 480 | 0.0091 | |
|
| 0.0067 | 1.65 | 520 | 0.0078 | |
|
| 0.0046 | 1.77 | 560 | 0.0091 | |
|
| 0.0055 | 1.9 | 600 | 0.0064 | |
|
| 0.0032 | 2.03 | 640 | 0.0058 | |
|
| 0.002 | 2.15 | 680 | 0.0066 | |
|
| 0.002 | 2.28 | 720 | 0.0061 | |
|
| 0.0018 | 2.41 | 760 | 0.0063 | |
|
| 0.0018 | 2.53 | 800 | 0.0057 | |
|
| 0.0021 | 2.66 | 840 | 0.0048 | |
|
| 0.0017 | 2.78 | 880 | 0.0046 | |
|
| 0.0013 | 2.91 | 920 | 0.0044 | |
|
| 0.0008 | 3.04 | 960 | 0.0036 | |
|
| 0.0005 | 3.16 | 1000 | 0.0043 | |
|
| 0.0004 | 3.29 | 1040 | 0.0042 | |
|
| 0.0004 | 3.42 | 1080 | 0.0036 | |
|
| 0.0004 | 3.54 | 1120 | 0.0039 | |
|
| 0.0003 | 3.67 | 1160 | 0.0034 | |
|
| 0.0002 | 3.8 | 1200 | 0.0032 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.38.2 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
