---
library_name: peft
tags:
- generated_from_trainer
base_model: 152334H/miqu-1-70b-sf
model-index:
- name: qlora-hermes
  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: 152334H/miqu-1-70b-sf
model_type: LlamaForCausalLM
tokenizer_type: LlamaTokenizer
is_llama_derived_model: true

load_in_8bit: false
load_in_4bit: true
strict: false

datasets:
  - path: teknium/OpenHermes-2.5
    type: sharegpt
    conversation: chatml
dataset_prepared_path: hermes-prepped
val_set_size: 0
output_dir: ./qlora-hermes

adapter: qlora
lora_model_dir:

sequence_len: 4096
sample_packing: true
pad_to_sequence_len: true

lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_target_modules:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: huggingface
wandb_entity: 152334h
wandb_watch:
wandb_name: hermes2-miqu
wandb_log_model:

gradient_accumulation_steps: 16
micro_batch_size: 2
num_epochs: 3
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 0.0001

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
eval_table_size:
eval_sample_packing: false
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.05
fsdp:
fsdp_config:


save_safetensors: true
resize_token_embeddings_to_32x: true
lora_modules_to_save:
  - embed_tokens
  - lm_head
special_tokens:
  eos_token: "<|im_end|>"
tokens:
  - "<|im_start|>"
  - "<|im_end|>"

```

</details><br>

# qlora-hermes

This model is a fine-tuned version of [152334H/miqu-1-70b-sf](https://huggingface.co/152334H/miqu-1-70b-sf) 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: 0.0001
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- num_devices: 6
- gradient_accumulation_steps: 16
- total_train_batch_size: 192
- total_eval_batch_size: 12
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 10
- num_epochs: 3

### Training results



### Framework versions

- PEFT 0.8.2
- Transformers 4.38.0.dev0
- Pytorch 2.2.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0