Hugging Face's logo

ZeroAgency
/
gpt-oss-20b-multilingual-reasoning

Text Generation
Transformers
Safetensors
gpt_oss
Generated from Trainer
conversational
Model card Files
xet
Community
gpt-oss-20b-multilingual-reasoning / README.md
bethrezen's picture
bethrezen
Upload folder using huggingface_hub
4779b69 verified
preview code
|
raw
history blame contribute delete
3.4 kB
metadata
library_name: transformers
license: apache-2.0
base_model: axolotl-ai-co/gpt-oss-20b-dequantized
tags:
  - generated_from_trainer
datasets:
  - HuggingFaceH4/Multilingual-Thinking
model-index:
  - name: outputs/gpt-oss-20b/
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.12.0

# the original mxfp4 quantized model is not supported with FSDP cpu_ram_efficient_loading
# FSDP cpu_ram_efficient_loading is used to reduce the initial CPU memory usage when loading the model
base_model: axolotl-ai-co/gpt-oss-20b-dequantized

use_kernels: false

dp_shard_size: 8  # requires 2x8xH100 nodes

plugins:
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin

experimental_skip_move_to_device: true  # prevent OOM by NOT putting model to GPU before sharding

datasets:
  - path: HuggingFaceH4/Multilingual-Thinking
    type: chat_template
    field_thinking: thinking
    template_thinking_key: thinking

dataset_prepared_path: last_run_prepared
val_set_size: 0
output_dir: ./outputs/gpt-oss-20b/
#save_only_model: true

sequence_len: 4096
sample_packing: true
pad_to_sequence_len: true

wandb_project: gpt-oss-20b
wandb_name: fft-20b

gradient_accumulation_steps: 1
micro_batch_size: 4
num_epochs: 1

optimizer: adamw_torch_fused  # 8bit optimizers do not work with FSDP2 offload
lr_scheduler: constant_with_warmup
learning_rate: 2e-5
load_best_model_at_end: false

bf16: true
tf32: true

flash_attention: true
attn_implementation: kernels-community/vllm-flash-attn3

gradient_checkpointing: true
activation_offloading: true

logging_steps: 1
saves_per_epoch: 1

warmup_ratio: 0.03

special_tokens:
eot_tokens:
  - "<|end|>"

#deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json
fsdp_version: 2
fsdp_config:
  offload_params: true
  state_dict_type: SHARDED_STATE_DICT
  auto_wrap_policy: TRANSFORMER_BASED_WRAP
  transformer_layer_cls_to_wrap: GptOssDecoderLayer
  reshard_after_forward: true
  cpu_ram_efficient_loading: true

outputs/gpt-oss-20b/

This model is a fine-tuned version of axolotl-ai-co/gpt-oss-20b-dequantized on the HuggingFaceH4/Multilingual-Thinking 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: 2e-05
  • train_batch_size: 4
  • eval_batch_size: 4
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 8
  • total_train_batch_size: 32
  • total_eval_batch_size: 32
  • optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: constant_with_warmup
  • training_steps: 8

Training results

Framework versions

  • Transformers 4.55.0
  • Pytorch 2.8.0+cu128
  • Datasets 4.0.0
  • Tokenizers 0.21.4