---
license: apache-2.0
datasets:
- teknium/OpenHermes-2.5
- abhinand/ultrachat_200k_sharegpt
language:
- en
---

# TinyLLaMA OpenHermes2.5 [Work in Progress] (Quantized)

This a finetune of TinyLLaMA base model finetuned on [OpenHermes 2.5](https://huggingface.co/datasets/teknium/OpenHermes-2.5) and [UltraChat 200k](https://huggingface.co/datasets/abhinand/ultrachat_200k_sharegpt) for a single epoch. 

Training was generously supported by [Jarvislabs.ai](https://jarvislabs.ai/).

If you appreciate this work and would like to support its continued development, consider [buying me a coffee](https://www.buymeacoffee.com/abhinand.b). Your support is invaluable and greatly appreciated.

[!["Buy Me A Coffee"](https://www.buymeacoffee.com/assets/img/custom_images/orange_img.png)](https://www.buymeacoffee.com/abhinand.b)

<details><summary>See axolotl config</summary>

axolotl version: `0.4.0`
```yaml
base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: true
is_llama_derived_model: true

# huggingface repo
datasets:
  - path: teknium/OpenHermes-2.5
    type: sharegpt
    conversation: chatml
    train_on_split: train

  - path: abhinand/ultrachat_200k_sharegpt
    type: sharegpt
    conversation: chatml
    train_on_split: train

load_in_4bit: false
load_in_8bit: false
bf16: true # require >=ampere
chat_template: chatml

dataset_prepared_path: last_run_prepared_path
hub_model_id: abhinand/TinyLlama-1.1B-OpenHermes-2.5-Chat-v1.0
group_by_length: false

val_set_size: 0.0
sequence_len: 2048
sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 32
lora_alpha: 16
lora_target_modules:
  - q_proj
  - v_proj
  - k_proj
  - o_proj
  - gate_proj
  - down_proj
  - up_proj
lora_modules_to_save:
  - embed_tokens
  - lm_head
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:

output_dir: /home/tiny-llama/trained_models

gradient_accumulation_steps: 2
micro_batch_size: 32
eval_batch_size: 32
num_epochs: 1
logging_steps: 1
save_steps: 50
save_total_limit: 3

save_safetensors: true
gradient_checkpointing: true

lr_scheduler: cosine
optimizer: "adamw_bnb_8bit"
adam_beta2: 0.95
adam_epsilon: 0.00001
weight_decay: 0.1
learning_rate: 0.0005
max_grad_norm: 1.0
warmup_ratio: 0.05
# warmup_steps: 100

flash_attention: true

# Resume from a specific checkpoint dir
resume_from_checkpoint:
# If resume_from_checkpoint isn't set and you simply want it to start where it left off.
# Be careful with this being turned on between different models.
# auto_resume_from_checkpoints: true

# wandb configuration if you're using it
# Make sure your `WANDB_API_KEY` environment variable is set (recommended) or you login to wandb with `wandb login`.
wandb_mode: # "offline" to save run metadata locally and not sync to the server, "disabled" to turn off wandb
wandb_project: "tiny-llama-sft"
wandb_name:
wandb_run_id:

special_tokens:
  bos_token: "<s>"
  eos_token: "</s>"
  unk_token: "<unk>"
tokens: # these are delimiters
  - "<|im_start|>"
  - "<|im_end|>"

```

</details>

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 0.0005
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-05
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 476
- num_epochs: 1

### Framework versions

- PEFT 0.8.2
- Transformers 4.38.0.dev0
- Pytorch 2.0.1
- Datasets 2.16.1
- Tokenizers 0.15.0