metadata
license: other
base_model: baffo32/decapoda-research-llama-7B-hf
tags:
- generated_from_trainer
model-index:
- name: llama-7b-absa-MT-laptops
results: []
llama-7b-absa-MT-laptops
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: 0.0071
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 |
|---|---|---|---|
| 0.0856 | 0.13 | 40 | 0.0248 |
| 0.021 | 0.25 | 80 | 0.0197 |
| 0.0232 | 0.38 | 120 | 0.0167 |
| 0.016 | 0.51 | 160 | 0.0147 |
| 0.0145 | 0.63 | 200 | 0.0121 |
| 0.0127 | 0.76 | 240 | 0.0110 |
| 0.0126 | 0.89 | 280 | 0.0096 |
| 0.009 | 1.01 | 320 | 0.0085 |
| 0.0055 | 1.14 | 360 | 0.0076 |
| 0.005 | 1.26 | 400 | 0.0071 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2