---
license: mit
library_name: peft
tags: []
base_model: Josephgflowers/TinyLlama-Cinder-1.3B-Test.2
model-index:
- name: TinyLLaMA-1.3B-Alpaca
  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: Josephgflowers/TinyLlama-Cinder-1.3B-Test.2
model_type: LlamaForCausalLM
tokenizer_type: LlamaTokenizer

load_in_8bit: true
load_in_4bit: false
strict: false

datasets:
  - path: mahiatlinux/merged_alpaca-1k
    type: alpaca
dataset_prepared_path:
val_set_size: 0.05
output_dir: ./lora-out

sequence_len: 2048
sample_packing: false
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 16
lora_alpha: 8
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: 2
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

warmup_steps: 10
evals_per_epoch: 4
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:

```

</details><br>

# TinyLLaMA-1.3B-Alpaca

This model is a fine-tuned version of [Josephgflowers/TinyLlama-Cinder-1.3B-Test.2](https://huggingface.co/Josephgflowers/TinyLlama-Cinder-1.3B-Test.2) on the Alpaca dataset.
It achieves the following results on the evaluation set:
- Loss: 1.4912

## 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: 2

### Training results

ARC_e: 57.53
Hellaswag: 0.5629

### Framework versions

- PEFT 0.9.1.dev0
- Transformers 4.39.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.17.0
- Tokenizers 0.15.0