---
library_name: peft
tags:
- axolotl
- generated_from_trainer
base_model: abhinand/dr-llama-te-instruct-v0
model-index:
- name: dr-llama-te-instruct-v0-lora-ext
  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: `0.3.0`
```yaml
base_model: abhinand/dr-llama-te-instruct-v0
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: true
is_llama_derived_model: true

# huggingface repo
datasets:
  - path: abhinand/telugu_llama_instruct
    name: regional_sharegpt_gs8
    type: sharegpt.load_role
    conversation: chatml
    train_on_split: train
  
  - path: abhinand/detox-dpo-te
    name: sharegpt_gs8
    type: sharegpt.load_role
    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/dr-llama-te-instruct-v0-lora-ext
group_by_length: false

val_set_size: 0.0
sequence_len: 4096
sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 64
lora_alpha: 128
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: 0.1
lora_target_linear: true
lora_fan_in_fan_out:

output_dir: /home/dev/axolotl/saved_models/telugu-instruct-extended

gradient_accumulation_steps: 8
micro_batch_size: 4
eval_batch_size: 4
num_epochs: 1
logging_steps: 1
save_steps: 10
save_total_limit: 3

save_safetensors: false
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: 10

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: "telugu-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><br>

# dr-llama-te-instruct-v0-lora-ext

This model is a fine-tuned version of [abhinand/dr-llama-te-instruct-v0](https://huggingface.co/abhinand/dr-llama-te-instruct-v0) on the None dataset.

## 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: 0.0005
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-05
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 3
- num_epochs: 1

### Training results



### Framework versions

- PEFT 0.7.0
- Transformers 4.37.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.16.1
- Tokenizers 0.15.0