README.md

---
license: llama3
library_name: peft
tags:
- generated_from_trainer
base_model: meta-llama/Meta-Llama-3-8B-Instruct
model-index:
- name: llama-3-8b-claudstruct-v2
  results: []
datasets:
- Norquinal/claude_multi_instruct_30k
language:
- en
---

<!-- 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: `0.4.1`
```yaml
base_model: meta-llama/Meta-Llama-3-8B-Instruct
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer  # PreTrainedTokenizerFast

load_in_8bit: false
load_in_4bit: true
strict: false

chat_template: llama3
datasets:
  - path: Norquinal/claude_multi_instruct_30k
    type: alpaca
dataset_prepared_path: last_run_prepared
val_set_size: 0.05
output_dir: ./outputs/llama-3-8b-claudstruct-v2/

adapter: qlora
lora_model_dir:

sequence_len: 512
sample_packing: false
pad_to_sequence_len: true

lora_r: 8
lora_alpha: 16
lora_dropout: 0.05
lora_target_modules:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 16
num_epochs: 1
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00001

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

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 10
evals_per_epoch: 4
eval_table_size:
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
  - full_shard
  - auto_wrap
fsdp_config:
  fsdp_limit_all_gathers: true
  fsdp_sync_module_states: true
  fsdp_offload_params: true
  fsdp_use_orig_params: false
  fsdp_cpu_ram_efficient_loading: true
  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
  fsdp_transformer_layer_cls_to_wrap: LlamaDecoderLayer
  fsdp_state_dict_type: FULL_STATE_DICT
  fsdp_sharding_strategy: FULL_SHARD
special_tokens:
  pad_token: <|end_of_text|>

```

</details><br>

# llama-3-8b-claudstruct-v2

This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the [Norquinal/claude_multi_instruct_30k](https://huggingface.co/datasets/Norquinal/claude_multi_instruct_30k) dataset.
It achieves the following results on the evaluation set:
- Loss: 1.6839

## 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: 16
- eval_batch_size: 16
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- total_train_batch_size: 32
- total_eval_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 10
- num_epochs: 1

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 2.0639        | 0.0015 | 1    | 2.0395          |
| 1.7905        | 0.2507 | 171  | 1.7402          |
| 1.8968        | 0.5015 | 342  | 1.6960          |
| 1.6319        | 0.7522 | 513  | 1.6839          |


### Framework versions

- PEFT 0.11.1
- Transformers 4.41.1
- Pytorch 2.3.0
- Datasets 2.19.1
- Tokenizers 0.19.1