---
library_name: peft
tags:
- generated_from_trainer
base_model: NousResearch/Llama-2-7b-hf
model-index:
- name: lora-out
  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: NousResearch/Llama-2-7b-hf
model_type: LlamaForCausalLM
tokenizer_type: LlamaTokenizer
is_llama_derived_model: true

load_in_8bit: true
load_in_4bit: false
strict: false

datasets:
  - path: datasets-jsonl/smut-bts-responses-881.jsonl
    ds_type: json
    type: alpaca
dataset_prepared_path:
val_set_size: 0.05
output_dir: ./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:
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: 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:
```

</details><br>

# lora-out

This model is a fine-tuned version of [NousResearch/Llama-2-7b-hf](https://huggingface.co/NousResearch/Llama-2-7b-hf) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.9196

## 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 |
|:-------------:|:-----:|:----:|:---------------:|
| 1.8373        | 0.02  | 1    | 1.8334          |
| 1.738         | 0.26  | 17   | 1.7546          |
| 1.704         | 0.51  | 34   | 1.7389          |
| 1.6762        | 0.77  | 51   | 1.7410          |
| 1.5981        | 1.02  | 68   | 1.7487          |
| 1.5593        | 1.26  | 85   | 1.7956          |
| 1.4415        | 1.51  | 102  | 1.7860          |
| 1.6098        | 1.77  | 119  | 1.8020          |
| 1.5458        | 2.02  | 136  | 1.8526          |
| 1.4358        | 2.26  | 153  | 1.8557          |
| 1.4608        | 2.51  | 170  | 1.8844          |
| 1.4465        | 2.77  | 187  | 1.8980          |
| 1.3986        | 3.02  | 204  | 1.8998          |
| 1.5333        | 3.26  | 221  | 1.9195          |
| 1.3554        | 3.51  | 238  | 1.9184          |
| 1.3287        | 3.77  | 255  | 1.9196          |


### Framework versions

- PEFT 0.8.2
- Transformers 4.38.0.dev0
- Pytorch 2.1.2+cu118
- Datasets 2.17.0
- Tokenizers 0.15.0