bunbohue's picture
Model save
ff229a9 verified
---
base_model: meta-llama/Llama-2-7b-hf
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: zero-shot-prompting-llama-2-7b_readsum_Ver2
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. -->
# zero-shot-prompting-llama-2-7b_readsum_Ver2
This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.6961
## 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
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.6231 | 0.21 | 300 | 1.7653 |
| 1.4252 | 0.41 | 600 | 1.7429 |
| 1.3652 | 0.62 | 900 | 1.7273 |
| 1.4877 | 0.82 | 1200 | 1.7188 |
| 1.8531 | 1.03 | 1500 | 1.7113 |
| 1.6964 | 1.23 | 1800 | 1.7061 |
| 1.6873 | 1.44 | 2100 | 1.7011 |
| 1.7671 | 1.65 | 2400 | 1.6985 |
| 1.7008 | 1.85 | 2700 | 1.6961 |
### Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0