---
library_name: peft
license: apache-2.0
base_model: openlm-research/open_llama_3b_v2
tags:
- generated_from_trainer
model-index:
- name: outputs/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/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
<details><summary>See axolotl config</summary>

axolotl version: `0.5.0`
```yaml
base_model: openlm-research/open_llama_3b_v2
model_type: LlamaForCausalLM
tokenizer_type: LlamaTokenizer
load_in_8bit: true
load_in_4bit: false
strict: false
push_dataset_to_hub:
datasets:
  - path: vicgalle/alpaca-gpt4
    type: alpaca
dataset_prepared_path:
val_set_size: 0.02
adapter: lora
lora_model_dir:
sequence_len: 1024
sample_packing: true
lora_r: 8
lora_alpha: 16
lora_dropout: 0.0
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_fan_in_fan_out:
wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
output_dir: ./outputs/lora-out
gradient_accumulation_steps: 1
micro_batch_size: 2
num_epochs: 4
optimizer: adamw_bnb_8bit
torchdistx_path:
lr_scheduler: cosine
learning_rate: 0.0002
train_on_inputs: false
group_by_length: false
bf16: false
fp16: true
tf32: false
gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
gptq_groupsize:
s2_attention:
gptq_model_v1:
warmup_steps: 20
evals_per_epoch: 4
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.1
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<s>"
  eos_token: "</s>"
  unk_token: "<unk>"

```

</details><br>

# outputs/lora-out

This model is a fine-tuned version of [openlm-research/open_llama_3b_v2](https://huggingface.co/openlm-research/open_llama_3b_v2) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.1770

## 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
- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 20
- num_epochs: 4
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step  | Validation Loss |
|:-------------:|:------:|:-----:|:---------------:|
| 1.1997        | 0.0002 | 1     | 1.3698          |
| 1.1468        | 0.25   | 1404  | 1.1159          |
| 1.2207        | 0.5    | 2808  | 1.1072          |
| 0.9448        | 0.75   | 4212  | 1.0982          |
| 1.0709        | 1.0    | 5616  | 1.0931          |
| 0.9592        | 1.2498 | 7020  | 1.1051          |
| 1.1133        | 1.4998 | 8424  | 1.1058          |
| 0.884         | 1.7498 | 9828  | 1.1018          |
| 0.9117        | 1.9998 | 11232 | 1.0963          |
| 0.9594        | 2.2496 | 12636 | 1.1336          |
| 0.9034        | 2.4996 | 14040 | 1.1338          |
| 0.6645        | 2.7496 | 15444 | 1.1326          |
| 0.8913        | 2.9996 | 16848 | 1.1309          |
| 0.9476        | 3.2495 | 18252 | 1.1752          |
| 0.9015        | 3.4995 | 19656 | 1.1762          |
| 0.6284        | 3.7495 | 21060 | 1.1768          |
| 0.7522        | 3.9995 | 22464 | 1.1770          |


### Framework versions

- PEFT 0.13.2
- Transformers 4.46.1
- Pytorch 2.3.1+cu121
- Datasets 3.0.1
- Tokenizers 0.20.3