---
library_name: peft
license: apache-2.0
base_model: Qwen/Qwen2.5-7B-Instruct
tags:
- axolotl
- generated_from_trainer
datasets:
- medalpaca/medical_meadow_medqa
model-index:
- name: qwen-qlora-fsdp
  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: `0.6.0`
```yaml
base_model: Qwen/Qwen2.5-7B-Instruct
trust_remote_code: true

load_in_8bit: false
load_in_4bit: true
strict: false

datasets:
  - path: medalpaca/medical_meadow_medqa
    type: alpaca
dataset_prepared_path:
val_set_size: 0.2
output_dir: ./outputs/out

sequence_len: 2048
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: qlora
lora_model_dir:
lora_r: 256
lora_alpha: 128
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: 1
micro_batch_size: 1
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00002

train_on_inputs: false
group_by_length: false
bf16: true
fp16:
tf32: 

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 10
xformers_attention:
flash_attention: true

warmup_steps:
evals_per_epoch: 4
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
  - full_shard
  - auto_wrap
fsdp_config:
  fsdp_limit_all_gathers: true
  fsdp_sync_module_states: true
  fsdp_offload_params: true
  fsdp_use_orig_params: false
  fsdp_cpu_ram_efficient_loading: true
  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
  fsdp_state_dict_type: FULL_STATE_DICT
  fsdp_sharding_strategy: FULL_SHARD
special_tokens:

hub_model_id: neginashz/qwen-lora-fsdp
```

</details><br>

# qwen-lora-fsdp

This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the medalpaca/medical_meadow_medqa dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1946

## 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: 2e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- total_train_batch_size: 2
- total_eval_batch_size: 2
- optimizer: Use adamw_torch 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: 55
- num_epochs: 3

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 0.1208        | 0.2504 | 154  | 0.1264          |
| 0.1361        | 0.5008 | 308  | 0.1208          |
| 0.1211        | 0.7512 | 462  | 0.1133          |
| 0.1154        | 1.0016 | 616  | 0.1119          |
| 0.076         | 1.2504 | 770  | 0.1208          |
| 0.0563        | 1.5008 | 924  | 0.1302          |
| 0.0493        | 1.7512 | 1078 | 0.1320          |
| 0.0678        | 2.0016 | 1232 | 0.1255          |
| 0.0091        | 2.2504 | 1386 | 0.1796          |
| 0.0216        | 2.5008 | 1540 | 0.1903          |
| 0.0105        | 2.7512 | 1694 | 0.1946          |


### Framework versions

- PEFT 0.14.0
- Transformers 4.47.0
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.21.0