metadata
license: other
base_model: baffo32/decapoda-research-llama-7B-hf
tags:
- generated_from_trainer
model-index:
- name: llama-7b-absa-restaurants
results: []
llama-7b-absa-restaurants
This model is a fine-tuned version of baffo32/decapoda-research-llama-7B-hf on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0345
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: 400
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.1281 | 0.36 | 40 | 0.0380 |
| 0.0358 | 0.72 | 80 | 0.0314 |
| 0.0296 | 1.08 | 120 | 0.0263 |
| 0.0211 | 1.44 | 160 | 0.0254 |
| 0.0203 | 1.8 | 200 | 0.0236 |
| 0.0163 | 2.16 | 240 | 0.0273 |
| 0.0115 | 2.52 | 280 | 0.0276 |
| 0.0105 | 2.88 | 320 | 0.0265 |
| 0.0081 | 3.24 | 360 | 0.0306 |
| 0.0046 | 3.6 | 400 | 0.0345 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2