---
license: llama2
base_model: meta-llama/Llama-2-7b-hf
tags:
- axolotl
- generated_from_trainer
model-index:
- name: Llama-2-7b-Alpaca52k
  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/Llama-2-7b-hf
model_type: LlamaForCausalLM
tokenizer_type: LlamaTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: tatsu-lab/alpaca
    type: alpaca
    conversations: alpaca
dataset_prepared_path: last_run_prepared
val_set_size: 0.001
output_dir: ./outputs/out_llama2_alpaca
hub_model_id: flydust/Llama-2-7b-Alpaca52k

sequence_len: 4096
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 4
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 2e-5

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
flash_attn_cross_entropy: false
flash_attn_rms_norm: true
flash_attn_fuse_qkv: false
flash_attn_fuse_mlp: true

warmup_ratio: 0.03
evals_per_epoch: 3
eval_table_size:
saves_per_epoch: 1
debug:
weight_decay: 0.
fsdp:
fsdp_config:
special_tokens:

```

</details><br>

# Llama-2-7b-Alpaca52k

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: 0.9082

## 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: 2e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- total_eval_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 6
- num_epochs: 4

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 1.3641        | 0.02   | 1    | 1.5519          |
| 1.0767        | 0.34   | 17   | 0.9333          |
| 1.0938        | 0.68   | 34   | 0.9166          |
| 1.0373        | 1.02   | 51   | 0.9096          |
| 1.0149        | 1.335  | 68   | 0.9031          |
| 1.0084        | 1.675  | 85   | 0.9071          |
| 0.9582        | 2.0150 | 102  | 0.9034          |
| 0.9767        | 2.33   | 119  | 0.9066          |
| 0.964         | 2.67   | 136  | 0.9060          |
| 0.9334        | 3.01   | 153  | 0.9073          |
| 0.9254        | 3.325  | 170  | 0.9084          |
| 0.9295        | 3.665  | 187  | 0.9082          |


### Framework versions

- Transformers 4.40.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1