---
license: llama3
library_name: peft
tags:
- axolotl
- generated_from_trainer
base_model: meta-llama/Meta-Llama-3-8B
model-index:
- name: llama-3-8b_dolly_lora
  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. -->

[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
<details><summary>See axolotl config</summary>

axolotl version: `0.4.0`
```yaml
base_model: meta-llama/Meta-Llama-3-8B
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: true
load_in_4bit: false
strict: false

datasets:
  - path: kareemamrr/databricks-dolly-15k-alpaca
    type: alpaca
dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/lora-out

sequence_len: 4096
sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: llama-3-8b-dolly-axolotl
wandb_entity: kamr54

hub_model_id: kareemamrr/llama-3-8b_dolly_lora

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 4
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.0002

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 10
evals_per_epoch: 4
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
   pad_token: <|end_of_text|>

```

</details><br>

# llama-3-8b_dolly_lora

This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.5906

## 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: 0.0002
- 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: cosine
- lr_scheduler_warmup_steps: 10
- num_epochs: 4

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 1.6347        | 0.0114 | 1    | 1.6104          |
| 1.5831        | 0.2507 | 22   | 1.5513          |
| 1.6087        | 0.5014 | 44   | 1.5421          |
| 1.3508        | 0.7521 | 66   | 1.5383          |
| 1.4055        | 1.0028 | 88   | 1.5344          |
| 1.45          | 1.2279 | 110  | 1.5376          |
| 1.3131        | 1.4786 | 132  | 1.5385          |
| 1.1921        | 1.7293 | 154  | 1.5384          |
| 1.4415        | 1.9801 | 176  | 1.5387          |
| 1.3818        | 2.2051 | 198  | 1.5586          |
| 1.3292        | 2.4558 | 220  | 1.5662          |
| 1.4667        | 2.7066 | 242  | 1.5664          |
| 1.3002        | 2.9573 | 264  | 1.5660          |
| 1.3682        | 3.1852 | 286  | 1.5878          |
| 1.2825        | 3.4359 | 308  | 1.5901          |
| 1.3347        | 3.6866 | 330  | 1.5906          |


### Framework versions

- PEFT 0.10.0
- Transformers 4.40.2
- Pytorch 2.1.2+cu118
- Datasets 2.19.1
- Tokenizers 0.19.1