metadata
license: llama2
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: codellama/CodeLlama-7b-hf
model-index:
- name: zero-shot-prompting-codellama-2-7b_readsum
results: []
zero-shot-prompting-codellama-2-7b_readsum
This model is a fine-tuned version of codellama/CodeLlama-7b-hf on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.5760
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: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.5059 | 0.21 | 300 | 1.6446 |
| 1.3069 | 0.41 | 600 | 1.6194 |
| 1.2804 | 0.62 | 900 | 1.6057 |
| 1.415 | 0.82 | 1200 | 1.5966 |
| 1.7712 | 1.03 | 1500 | 1.5898 |
| 1.604 | 1.23 | 1800 | 1.5847 |
| 1.5464 | 1.44 | 2100 | 1.5806 |
| 1.6766 | 1.65 | 2400 | 1.5779 |
| 1.5547 | 1.85 | 2700 | 1.5760 |
Framework versions
- PEFT 0.7.1
- Transformers 4.37.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0