Hugging Face's logo

neginashz
/
qwen2-ins-full-fsdp

Text Generation
Transformers
PyTorch
Safetensors
qwen2
axolotl
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
qwen2-ins-full-fsdp / README.md
neginashz's picture
neginashz
End of training
ec4f42d verified
preview code
|
raw
history blame contribute delete
3.04 kB
metadata
library_name: transformers
license: apache-2.0
base_model: Qwen/Qwen2.5-7B-Instruct
tags:
  - axolotl
  - generated_from_trainer
datasets:
  - medalpaca/medical_meadow_medqa
model-index:
  - name: qwen2-ins-full-fsdp
    results: []

Built with Axolotl

See axolotl config

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

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

Training Loss Epoch Step Validation Loss
0.0548 1.3889 100 0.1461
0.0061 2.7778 200 0.1810

Framework versions

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