qwen2-ins-full-fsdp

<!-- 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"/>

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

axolotl version: 0.6.0

base_model: Qwen/Qwen2.5-7B-Instruct
trust_remote_code: true

load_in_8bit: 
load_in_4bit:
strict: false

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

sequence_len: 8192
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true


wandb_project: full-ft-qwen
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: false
tf32: false

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:
eval_steps: 100
save_steps: 100
debug:
deepspeed: deepspeed_configs/zero2.json
weight_decay: 0.05
fsdp:
fsdp_config:
special_tokens:

hub_model_id: neginashz/qwen2-ins-full-fsdp
early_stopping_patience: 3

</details><br>

qwen2-ins-full-fsdp

This model is a fine-tuned version of Qwen/Qwen2.5-7B-Instruct on the medalpaca/medical_meadow_medqa dataset. It achieves the following results on the evaluation set:

• Loss: 0.1810

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: 4
• total_train_batch_size: 4
• total_eval_batch_size: 4
• 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: 6
• num_epochs: 3

Training results

Framework versions

• Transformers 4.47.0
• Pytorch 2.5.1+cu124
• Datasets 3.1.0
• Tokenizers 0.21.0