|
--- |
|
license: llama2 |
|
base_model: meta-llama/Llama-2-7b-hf |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: sparse_llama_7b_hf2_refined_web_50p_2024-05-11 |
|
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. --> |
|
|
|
# sparse_llama_7b_hf2_refined_web_50p_2024-05-11 |
|
|
|
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: 2.2840 |
|
|
|
## 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: 1e-05 |
|
- train_batch_size: 1 |
|
- eval_batch_size: 4 |
|
- seed: 0 |
|
- distributed_type: multi-GPU |
|
- gradient_accumulation_steps: 8 |
|
- total_train_batch_size: 8 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- training_steps: 350 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 2.201 | 0.0 | 25 | 2.2172 | |
|
| 2.2379 | 0.0 | 50 | 2.2154 | |
|
| 2.1411 | 0.01 | 75 | 2.2137 | |
|
| 2.1523 | 0.01 | 100 | 2.2125 | |
|
| 2.5823 | 0.01 | 125 | 2.2103 | |
|
| 2.2672 | 0.01 | 150 | 2.2063 | |
|
| 2.3044 | 0.01 | 175 | 2.2036 | |
|
| 2.2119 | 0.02 | 200 | 2.2012 | |
|
| 2.1888 | 0.02 | 225 | 2.2004 | |
|
| 2.1592 | 0.02 | 250 | 2.1981 | |
|
| 2.2455 | 0.02 | 275 | 2.1972 | |
|
| 2.0666 | 0.02 | 300 | 2.1972 | |
|
| 2.322 | 0.03 | 325 | 2.1967 | |
|
| 2.2689 | 0.03 | 350 | 2.1946 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.36.2 |
|
- Pytorch 2.1.2+cu121 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.15.2 |
|
|
