metadata
library_name: peft
tags:
- generated_from_trainer
base_model: meta-llama/Llama-2-7b-hf
model-index:
- name: llama_domar
results: []
llama_domar
This model is a fine-tuned version of meta-llama/Llama-2-7b-hf on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8476
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: 0.0001
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.0253 | 0.79 | 200 | 1.0459 |
| 0.8019 | 1.59 | 400 | 0.9365 |
| 0.8056 | 2.38 | 600 | 0.8847 |
| 0.7426 | 3.18 | 800 | 0.8589 |
| 0.6669 | 3.97 | 1000 | 0.8498 |
| 0.5615 | 4.77 | 1200 | 0.8476 |
Framework versions
- PEFT 0.8.2
- Transformers 4.38.1
- Pytorch 2.2.0+cu118
- Datasets 2.17.1
- Tokenizers 0.15.2