Hugging Face's logo

nicoboss
/
DeepSeek-R1-Distill-Qwen-7B-Uncensored

PEFT
Safetensors
qwen2
Generated from Trainer
Model card Files Community
1
DeepSeek-R1-Distill-Qwen-7B-Uncensored / README.md
nicoboss's picture
nicoboss
Create README.md
bc49d5a verified
preview code
|
raw
history blame
3.31 kB
metadata
library_name: peft
tags:
  - generated_from_trainer
datasets:
  - Guilherme34/uncensor
base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
model-index:
  - name: outputs/out/DeepSeek-R1-Distill-Qwen-7B-Uncensored
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.6.0

base_model: /cpool/DeepSeek-R1-Distill-Qwen-7B

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: Guilherme34/uncensor
    type: chat_template
    chat_template: llama3
    field_messages: messages
    message_field_role: role
    message_field_content: content
    roles:
      system:
        - system
      user:
        - user
      assistant:
        - assistant
dataset_prepared_path: last_run_prepared
val_set_size: 0.0
output_dir: ./outputs/out/DeepSeek-R1-Distill-Qwen-7B-Uncensored
save_safetensors: true

sequence_len: 4096
sample_packing: false
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:

gradient_accumulation_steps: 4
micro_batch_size: 1
num_epochs: 4
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.0002

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

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: true
logging_steps: 1
flash_attention: true

warmup_steps: 10
evals_per_epoch: 1
eval_table_size: 20
eval_max_new_tokens: 128
saves_per_epoch: 1
save_total_limit: 20
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:

outputs/out/DeepSeek-R1-Distill-Qwen-7B-Uncensored

This model was trained from scratch on the Guilherme34/uncensor 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: 0.0002
  • train_batch_size: 1
  • eval_batch_size: 1
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 2
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 8
  • total_eval_batch_size: 2
  • optimizer: Use OptimizerNames.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: 10
  • num_epochs: 4

Training results

Framework versions

  • PEFT 0.14.0
  • Transformers 4.47.1
  • Pytorch 2.5.1+cu124
  • Datasets 3.2.0
  • Tokenizers 0.21.0